MRI for image-guided procedures -
MRI is especially helpful for imaging the brain. To utilize MRI technology during surgery, doctors use special imaging systems and operating rooms, including:. At certain points in your operation, the surgeon may request imaging with iMRI. When and how often the surgeon creates images during surgery depends on your procedure and your condition.
Doctors use iMRI to assist in surgery to treat:. Surgeons use iMRI to assist in procedures that treat a variety of brain tumors. Surgery is often the first step to treat a tumor that can be removed without causing neurological damage.
Some tumors have a clearly defined shape and can be removed easily. In addition, surgeons use iMRI to place deep brain stimulators to treat epilepsy, essential tremor, dystonia and Parkinson's disease.
iMRI is also used to assist in surgery for some brain conditions, such as a bulge in a blood vessel aneurysm and tangled blood vessels arteriovenous malformation as well as mental health disorders.
During these procedures, iMRI allows surgeons to monitor brain activity; check for bleeding, clots and other complications; prevent damage to surrounding tissue; and protect brain function.
This helps with earlier intervention to address complications and may reduce the need for additional operations. For cancer surgery, iMRI helps surgeons ensure that the entire tumor has been removed. Surgeons use iMRI to create real-time brain images. At certain points during an operation, the surgeon may want to see certain images of the brain.
MRI uses a magnetic field and radio waves to create detailed brain images. To use MRI technology during surgery, doctors may bring a portable iMRI machine into the operating room to create images.
They may also keep the iMRI machine in a room near the operating room so surgeons can easily move you there for imaging during the procedure. iMRI cannot be used in patients with most pacemakers, cochlear implants, and metal joints or certain implants.
Intraoperative magnetic resonance imaging iMRI care at Mayo Clinic. Mayo Clinic does not endorse companies or products. Advertising revenue supports our not-for-profit mission. Check out these best-sellers and special offers on books and newsletters from Mayo Clinic Press.
This content does not have an English version. This content does not have an Arabic version. Overview Intraoperative magnetic resonance imaging iMRI is a procedure that creates images of the brain during surgery.
By Mayo Clinic Staff. Request an appointment. Show references Dietrich J, et al. Clinical manifestation, diagnosis, and initial surgical management of high-grade gliomas. Accessed Nov. Winn RH, ed. Youmans and Winn Neurological Surgery.
Elsevier; Van Gompel J expert opinion. Mayo Clinic. December 6, Rogers CM, et al. Intraoperative MRI for brain tumors. Journal of Neuro-Oncology. Brain and spinal cord tumors: Hope through research. National Institute of Neurological Disorders and Stroke.
Accessed Dec. Brown DA, et al. Cranial tumor surgical outcomes at a high-volume academic referral center. Mayo Clinic Proceedings. However, even if the patient has a known allergy to gadolinium, it may be possible to use it after appropriate pre-medication.
For more information on allergic reactions to gadolinium contrast, please consult the ACR Manual on Contrast Media. Tell the technologist or radiologist if you have any serious health problems or recent surgeries. Some conditions, such as severe kidney disease, may mean that you cannot safely receive gadolinium.
You may need a blood test to confirm your kidneys are functioning normally. Women should always tell their doctor and technologist if they are pregnant. MRI has been used since the s with no reports of any ill effects on pregnant women or their unborn babies.
However, the baby will be in a strong magnetic field. Therefore, pregnant women should not have an MRI in the first trimester unless the benefit of the exam clearly outweighs any potential risks.
Pregnant women should not receive gadolinium contrast unless absolutely necessary. See the MRI Safety During Pregnancy page for more information about pregnancy and MRI. Prior to a needle biopsy, tell your doctor about all the medications you take, including herbal supplements.
List any allergies, especially to anesthesia. Your doctor may advise you to stop taking aspirin, blood thinners, or certain herbal supplements three to five days before your procedure. This will help decrease your risk of bleeding. There are other important guidelines for patients to follow prior to undergoing MR imaging.
For a list of these and a review of all preparations that should be made prior to MR imaging, please see MRI of the Breast. The traditional MRI unit is a large cylinder-shaped tube surrounded by a circular magnet. You will lie on a table that slides into a tunnel towards the center of the magnet.
Some MRI units, called short-bore systems , are designed so that the magnet does not completely surround you. Some newer MRI machines have a larger diameter bore, which can be more comfortable for larger patients or those with claustrophobia.
They are especially helpful for examining larger patients or those with claustrophobia. Open MRI units can provide high quality images for many types of exams. Open MRI may not be used for certain exams.
For more information, consult your radiologist. Most MRI-guided breast biopsies are currently performed in closed MRI systems with a specially modified exam table.
This moveable examination table allows your breasts to hang freely into cushioned openings, which contain wire coils that send and receive radio waves to help create the MR images.
This procedure may use other sterile equipment, including syringes, sponges, forceps, scalpels and a specimen cup or microscope slide. Unlike x-ray and computed tomography CT exams, MRI does not use radiation.
Instead, radio waves re-align hydrogen atoms that naturally exist within the body. This does not cause any chemical changes in the tissues. As the hydrogen atoms return to their usual alignment, they emit different amounts of energy depending on the type of tissue they are in.
The scanner captures this energy and creates a picture using this information. In most MRI units, the magnetic field is produced by passing an electric current through wire coils. Other coils are inside the machine and, in some cases, are placed around the part of the body being imaged.
These coils send and receive radio waves, producing signals that are detected by the machine. The electric current does not come into contact with the patient.
A computer processes the signals and creates a series of images, each of which shows a thin slice of the body. The radiologist can study these images from different angles. MRI is often able to tell the difference between diseased tissue and normal tissue better than x-ray, CT, and ultrasound.
Using MRI guidance to calculate the position of the abnormal tissue and to verify the placement of the needle, the radiologist inserts the biopsy needle through the skin, advances it into the lesion and removes tissue samples.
If a surgical biopsy is being performed, MRI may be used to guide a wire into the mass to help the surgeon locate the area for excision. Image-guided, minimally invasive procedures such as MR-guided breast biopsies are most often performed by a specially trained breast radiologist.
In most cases, you will lie face down on a moveable exam table. The doctor will position the affected breast into an opening in the table.
A nurse or technologist will insert an intravenous IV line into a vein in your hand or arm and the contrast material gadolinium will be given intravenously.
Your breast will be gently compressed between two compression plates similar to those used in a diagnostic MRI exam , one of which is marked with a grid structure. Using computer software, the radiologist measures the position of the lesion with respect to the grid and calculates the position and depth of the needle placement.
The doctor will inject a local anesthetic into the skin and more deeply into the breast to numb it. The doctor will make a very small nick in the skin at the site where they will insert the biopsy needle.
The radiologist then inserts the needle, advances it to the location of the abnormality and MR imaging is performed to verify its position. Depending on the type of MRI unit being used, you may remain in place or be moved out of the center or bore of the MRI scanner.
The doctor removes tissue samples using a vacuum-assisted device VAD. Vacuum pressure pulls tissue from the breast through the needle into the sampling chamber. Without withdrawing and reinserting the needle, it rotates positions and collects additional samples.
Typically, the doctor will collect eight to 10 samples of tissue from around the lesion. If a surgical biopsy is to be performed, the doctor will insert a wire into the suspicious area as a guide for the surgeon.
The doctor may place a small marker at the biopsy site so they can locate it in the future if necessary. Once the biopsy is complete, the doctor or nurse will apply pressure to stop any bleeding. They will cover the opening in the skin with a dressing. No sutures are needed.
You will be awake during your biopsy and should have little discomfort. Many women report little pain and no scarring on the breast. However, certain patients, including those with dense breast tissue or abnormalities near the chest wall or behind the nipple, may be more sensitive during the procedure.
Some women find that the major discomfort of the procedure is from lying on their stomach for the length of the procedure. Strategically placed cushions can ease this discomfort. When you receive the local anesthetic to numb the skin, you will feel a pin prick from the needle followed by a mild stinging sensation from the local anesthetic.
You will likely feel some pressure when the doctor inserts the biopsy needle and during tissue sampling. This is normal.
As tissue samples are taken, you may hear clicks or buzzing sounds from the sampling instrument. These are normal. If you experience swelling and bruising following your biopsy, your doctor may tell you to take an over-the-counter pain reliever and to use a cold pack.
Temporary bruising is normal. Call your doctor if you experience excessive swelling, bleeding, drainage, redness, or heat in the breast.
If a marker is left inside the breast to mark the location of the biopsied lesion, it will cause no pain, disfigurement, or harm. Biopsy markers are MRI compatible and will not cause metal detectors to alarm.
Avoid strenuous activity for at least 24 hours after the biopsy. Your doctor will outline more detailed post-procedure care instructions for you. A pathologist examines the removed specimen and makes a final diagnosis. Depending on the facility, the radiologist or your referring physician will share the results with you.
The radiologist will also evaluate the results of the biopsy to make sure that the pathology and image findings explain one another. In some instances, even if cancer is not diagnosed, surgical removal of the entire biopsy site and imaging abnormality may be recommended if the pathology does not match the imaging findings.
You may need a follow-up exam. If so, your doctor will explain why. Sometimes a follow-up exam further evaluates a potential issue with more views or a special imaging technique. It may also see if there has been any change in an issue over time.
Follow-up exams are often the best way to see if treatment is working or if a problem needs attention. MRI-guided tissue sampling is limited by the position of the abnormality in the breast. Breast lesions located in the extreme posterior region of the breast or small abnormalities can be difficult or impossible to accurately target using MR.
Breast biopsy procedures will occasionally miss a lesion or underestimate the extent of disease present. If the diagnosis remains uncertain after a technically successful procedure, surgical biopsy will usually be necessary.
The MR-guided breast biopsy method cannot be used unless the mass can be seen on an MRI exam. Calcifications within a cancerous nodule are not seen on Breast MRI. Therefore, it may be difficult to accurately target small lesions during MR-guided breast biopsy. The widespread use of this technique is limited by its high cost, availability, and length of the procedure.
MR-guided biopsy should not be considered if the lesion can be seen on mammography or on ultrasound , where the biopsy can be performed more easily with less patient discomfort. In those cases, stereotactic biopsy or ultrasound-guided biopsy are the more appropriate methods of tissue sampling.
Imaging Center Imaging Center Toggle mobile sub-nav. Back to Imaging Center. About Us. Imaging History. Procedurds to Expect. Breast Imaging. Procedires MRI for image-guided procedures Details: spie. Wagner Antioxidant protection against diseases Best Student Paper MRI for image-guided procedures Sponsored Exercise MIPS and SPIE. Join us fot we recognize colleagues of i,age-guided medical imaging community who have been selected. Wagner Award finalists for conferences, and Computer-Aided Diagnosis Best Paper Award Image-Guided Procedures, Robotic Interventions, and Modeling student paper and Young Scientist Award. Conference attendees are invited to attend the SPIE Medical Imaging poster session on Monday evening.MRI for image-guided procedures -
org Hours: Monday - Friday am - pm. Learn More About PRISM ». To schedule an appointment, please call: Types of Procedures Conditions Treated. Share on Facebook. Notice: Users may be experiencing issues with displaying some pages on stanfordhealthcare.
We are working closely with our technical teams to resolve the issue as quickly as possible. Thank you for your patience. Billing Insurance Medical Records Support Groups Help Paying Your Bill COVID Resource Center. Locations and Parking Visitor Policy Hospital Check-in Video Visits International Patients Contact Us.
View the changes to our visitor policy » View information for Guest Services ». New to MyHealth? Manage Your Care From Anywhere. ALREADY HAVE AN ACCESS CODE? Activate Account. DON'T HAVE AN ACCESS CODE? Create a New Account.
NEED MORE DETAILS? MyHealth for Mobile Get the iPhone MyHealth app » Get the Android MyHealth app ». WELCOME BACK. Forgot Username or Password? Minimally Invasive MRI-Guided Interventional Care.
Leaders in Minimally Invasive MRI-Guided Interventional Care Our radiologists in the Minimally Invasive MR Interventional Center MIMRIC lead the way in using magnetic resonance imaging MRI for targeted, personalized treatment of a wide variety of conditions. Find a Doctor.
Make An Appointment. Nationally recognized expertise in radiology, with a dedicated team of specialists trained in using MRI to diagnose conditions and precisely guide treatment procedures. Advanced, minimally invasive test and treatment approaches , including MRI-guided biopsy, MRI-guided high-intensity focused ultrasound HIFU , and MRI-guided cryoablation, to provide expert care for a wide range of conditions.
Preventive screening and thorough evaluations for your health, comfort, and peace of mind. Extensive support services such as pain management, patient and caregiver support groups, and physical therapy to help you have the best quality of life possible. Access to Clinical Trials for innovative treatments developed by our doctors in the Minimally Invasive MR Interventional Center MIMRIC addressing various conditions.
Focal Therapy For Prostate Cancer Gives Patient Full Recovery, Fewer Side Effects. Play Video MRI-guided Ultrasound For Prostate Cancer Gives Patient Full Recovery. What is Minimally Invasive MRI-Guided Interventional Care. Conditions Treated. Types of Procedures.
About Minimally Invasive MRI-Guided Interventional Care Minimally invasive MRI-guided interventional care makes use of the detailed images of the body anatomy captured by magnetic resonance imaging MRI to deliver precision care to patients, with reduced risk and quicker recovery times as compared to conventional surgery.
Referrals For provider MIMRIC Referral for Consultation, please complete the Requisition Referral for Consultation Form , and patient self-referral for MIMRIC Referral for Consultation, use the Self-Referral for Consultation Form.
Unlike other imaging modalities, ultrasound tomography in medicine is computationally bounded. Its future advancement is discussed from the perspective of ever-increasing computational power and Moore's Law. Session 1: Robotic Assistance.
Session Chairs: Kristy K. Brock , The Univ. of Texas M. Anderson Cancer Ctr. United States , David M. Kwartowitz , Grand Canyon Univ. Probe positioning for robot-assisted intraoperative ultrasound imaging using deep reinforcement learning.
Author s : Yicheng Hu, Yixuan Huang, Anthony Song, Craig K. Jones, Wojciech Zbijewski, Johns Hopkins Univ. United States ; Jeffrey H. Siewerdsen, Johns Hopkins Univ. United States , The Univ. United States ; Burcu Basar, Patrick A. Helm, Medtronic, Inc. United States ; Ali Uneri, Johns Hopkins Univ.
This work presents a new approach that leverages deep reinforcement learning to automate probe positioning during intraoperative ultrasound imaging.
A dueling deep Q-network is applied and evaluated for kidney imaging. The agent was trained on images resliced from CT images, with a novel reward function that used image features. A surgical navigation framework for image-guided transoral robotic surgery.
Author s : Yuan Shi, Michael A. Kokko, Thayer School of Engineering at Dartmouth United States ; Joseph A. Paydarfar, Dartmouth-Hitchcock Medical Ctr. United States ; Ryan J.
Halter, Thayer School of Engineering at Dartmouth United States. In , there will be an estimated 66, new cases diagnosed with approximately 15, deaths in the United States2. Minimally-invasive transoral robotic surgery TORS is an effective approach for head and neck cancer management with demonstrated excellent oncologic and functional outcomes and low surgical morbidity3—5.
However, the lack of haptic feedback in TORS poses increased risks of positive surgical margins in select areas and neurovascular complications6—9. Proposing that surgical navigation with image guidance has the potential to compensate for the sensory deficit, we have previously demonstrated the feasibility of intra-operative imaging10 and robotic instrument tracking11 in TORS.
This paper describes the development of a surgical navigation framework utilizing intra-operative imaging and instrument tracking and its integration with the da Vinci Surgical System. MRI-compatible robot for intracerebral hemorrhage evacuation: sheep brain phantom study.
Author s : Sarah C. Nanziri, The George Washington Univ. United States ; Van Khanh Lam, Pavel Yarmolenko, Children's National Hospital United States ; Lucas Hintz, The George Washington Univ.
United States ; Gang Li, Children's National Hospital United States ; Hadi Fooladi Talari, Children's National Health System United States ; Kevin Cleary, Children's National Hospital United States ; Anthony L. Gunderman, Yue Chen, Georgia Institute of Technology United States ; Dimitri Sigounas, The George Washington Univ.
However, these approaches are still disruptive to surrounding normal brain tissue and do not allow for the near-total evacuation of a hemorrhage. In this MRI-guided study, we assessed an MRI-Compatible robotic aspiration device in a sheep brain phantom.
The robot was advanced into the clot and aspiration was performed with real-time intraoperative MR imaging. SAMSNeRF: segment anything model SAM guided dynamic surgical scene reconstruction by neural radiance field NeRF.
Author s : Ange Lou, Yamin Li, Xing Yao, Yike Zhang, Jack H. Noble, Vanderbilt Univ. However, previous approaches, mainly relying on depth estimation, have limited effectiveness in reconstructing surgical scenes with moving surgical tools.
To address this limitation and provide accurate 3D position prediction for surgical tools in all frames, we propose a novel approach called SAMSNeRF that combines Segment Anything Model SAM and Neural Radiance Field NeRF techniques. Our approach generates accurate segmentation masks of surgical tools using SAM, which guides the refinement of the dynamic surgical scene reconstruction by NeRF.
Our experimental results on public endoscopy surgical videos demonstrate that our approach successfully reconstructs high-fidelity dynamic surgical scenes and accurately reflects the spatial information of surgical tools. Our proposed approach can significantly enhance surgical navigation and automation by providing surgeons with accurate 3D position information of surgical tools during surgery.
Session 2: Moving Targets. Session Chairs: Elvis C. Chen , Robarts Research Institute Canada , David R.
Holmes , Mayo Clinic United States. Physical replication and validation of mathematical mitral valve models. Author s : Patrick K. Carnahan, Charles C. Yuan, John Moore, Western Univ. Canada ; Gianluigi Bisleri, Univ. of Toronto Canada ; Daniel Bainbridge, London Health Sciences Ctr.
Canada ; Terry M. Peters, Elvis C. Chen, Western Univ. Currently, heart simulator technologies are used which rely on patient-specific data to create valve replicas. Alternatively, mathematical models of the mitral valve have been developed for computational applications. Mathematical models to date have not been replicated as dynamic, physical valve models and validated in a heart simulator system.
We propose a new parametric representation of the mitral valve based on a combination of valve models from prior literature, combining both accurate leaflet shape, and annular geometry. A physical silicone replica of the model is created and validated in a pulse duplicator. Using a transesophageal echocardiography probe with color Doppler imaging, we demonstrate that our combined model replicates healthy valve behaviour, showing no regurgitation at realistic pressure gradients across the valve.
Design of coronary artery phantom using polyvinyl alcohol cryogel for optical coherence tomography imaging in Kawasaki Disease. Author s : Matilde Pazzaglia, Atefeh Abdolmanafi, Gerardo Tibamoso Pedraza, Ecole de Technologie Supérieure Canada ; Nagib Dahdah, Div.
of Pediatric Cardiology, CHU Sainte-Justine Canada , Ctr. de Recherche du CHU Sainte-Justine Canada ; Luc Duong, Ecole de Technologie Supérieure Canada. Intravascular Optical Coherence Tomography IV-OCT offers vital coronary artery imaging guidance to cardiologists, but its operation demands skilled expertise and adherence to intricate protocols.
Our study introduces a novel approach utilizing polyvinyl alcohol cryogel PVA-c to fabricate patient-specific coronary OCT phantoms.
These phantoms closely mimic human tissue, serving as valuable tools for training cardiologists and deepening understanding of the OCT image formation process. By designing 3D molds based on real OCT arterial images, we create PVA-c phantoms that capture the morphological characteristics and visual features of diseased coronary arteries.
Our findings indicate that these phantoms effectively emulate the structures and appearances observed in OCT, closely resembling human tissue. Motion-compensated OCT imaging of laryngeal tissue. Author s : Sarah Latus, Marica Kulas, Johanna Sprenger, Technische Univ.
Hamburg-Harburg Germany ; Debayan Bhattacharya, Technische Univ. Hamburg-Harburg Germany , Universitätsklinikum Hamburg-Eppendorf Germany ; Philippe Christophe Breda, Lukas Wittig, Universitätsklinikum Hamburg-Eppendorf Germany ; Tim Eixmann, Gereon Hüttmann, Medizinisches Laserzentrum Lübeck GmbH Germany ; Lennart Maack, Technische Univ.
Hamburg-Harburg Germany ; Dennis Eggert, Christian Betz, Universitätsklinikum Hamburg-Eppendorf Germany ; Alexander Schlaefer, Technische Univ. Hamburg-Harburg Germany. In clinical practice, white light endoscopy of the laryngeal region is typically followed by biopsy under general anesthesia.
Optical coherence tomography OCT has been proposed to study sub-surface tissue layers at high resolution. However, accessing the region of interest requires miniature OCT probes that can be inserted in the working channel of a laryngoscope. Typically, such probes generate single column depth images which are difficult to interpret.
We propose a novel approach using endoscopic images to spatially align these images. Given the natural tissue motion and movements of the laryngoscope, resulting OCT images show a three-dimensional representation of sub-surface structures, which is simpler to interpret.
We present a motion tracking method and assess the precision of spatial alignment. Furthermore, we demonstrate the in-vivo application, illustrating the benefit of spatially meaningful alignment of OCT images to study laryngeal tissue. Motion artifact classification for quality assessment of cochlear implant postoperative CT images.
Author s : Yubo Fan, Han Liu, Jack H. Noble, Benoit M. Dawant, Vanderbilt Univ. Postoperative images with adequate image quality are required to allow the EA to be reliably and precisely localized.
However, these images sometimes are affected by motion artifacts which can make the localization task unreliable or even fail.
Thus, flagging these low-quality images prior to the subsequent clinical use is important. To address the challenges of subjective annotations and class imbalance, several techniques a new loss term, an oversampling strategy, and motion artifact simulation are used during training.
Results demonstrate the proposed method has the potential to reduce time and efforts on image quality assessment that is traditionally by visual inspection.
Self-supervised monocular depth and ego-motion estimation for CT-bronchoscopy fusion. Author s : Qi Chang, William E. Higgins, The Pennsylvania State Univ. However, integrating these data sources is challenging due to the difficulty in obtaining depth and camera pose from bronchoscopic videos.
Generative adversarial networks GANs help by transforming CT endoluminal views into synthesized bronchoscopic frames, aligning them with CT-derived depth maps for training.
However, this domain transformation method lacks the use of sequential frame knowledge, such as photometric consistency, and cannot predict camera ego-motion.
Addressing this limitation, a self-supervised training strategy is used for the Monodepth2 architecture, incorporating domain transformation and photometric consistency.
This enhances depth and ego-motion prediction in bronchoscopic frames. Test data results show accurate predictions and reference scaling factors derived from these tests facilitate real-world applications.
Session 3: Tracking and Localization. Session Chairs: Ziv R. Yaniv , National Institute of Allergy and Infectious Diseases United States , Eric J.
Seibel , Univ. of Washington United States. Image guidance system for breast conserving surgery with integrated stereo camera monitoring and deformable correction.
Author s : Morgan J. Ringel, Winona L. Richey, Vanderbilt Univ. United States ; Jon S. Heiselman, Memorial Sloan-Kettering Cancer Ctr.
United States ; Alexander W. Stabile, Vanderbilt Univ. United States ; Ingrid M. Meszoely, Vanderbilt Univ. Medical Ctr. United States ; Michael I. Miga, Vanderbilt Univ. This work proposes an image guidance system for breast conserving surgery that combines stereo camera soft tissue monitoring with nonrigid registration for deformation correction.
A series of breast phantom deformation experiments were performed to demonstrate system capabilities, and validation studies with human volunteers are ongoing. Overall, this system may allow for better navigation and tumor localization during breast conserving surgeries.
Guiding endovascular catheters using electromagnetic tracking and path-based registration for brain aneurysm treatment. Author s : Fangjie Li, Huilin Xu, Shanelle D. Cao, Jinchi Wei, Dante Rhodes, Johns Hopkins Univ. Siewerdsen, The Univ. United States , Johns Hopkins Univ.
United States ; Luis F. Gonzalez, The Johns Hopkins Univ. School of Medicine United States ; Ali Uneri, Johns Hopkins Univ. A custom catheter instrument was designed and constructed to integrate a 5 single EM coil sensor at its tip. The tracked sensor was used in 1 dynamically reconstructing the instrument shape as it is advanced or retracted within the vessels; 2 visualizing the tip direction to guide it through vessel bifurcations; and 3 registering its path to vessel centerlines to provide image overlay.
Experimental studies demonstrate sufficient accuracy 4. An augmented reality and high-speed optical tracking system for laparoscopic surgery. Author s : Nati Nawawithan, Jeff Young, Patric Bettati, Armand P. Rathgeb, Kelden T.
Pruitt, Jordan Frimpter, Henry Kim, Jonathan Yu, Davis Driver, Amanuel Shiferaw, Aditi Chaudhari, The Univ. of Texas at Dallas United States ; Brett A.
Johnson, Jeffrey Gahan, The Univ. of Texas Southwestern Medical Ctr. at Dallas United States ; James Yu, The Univ. at Dallas United States , The Univ. of Texas at Dallas United States ; Baowei Fei, The Univ. of Texas at Dallas United States , The Univ.
at Dallas United States. Our proposed solution applies an augmented reality AR based system to overlay pre-operative images acquired from magnetic resonance imaging MRI onto the target organ providing the location of subsurface lesions and a proposed surgical guidance path in real-time. An infrared motion tracking camera system was employed to obtain real-time position data of the phantom model and surgical instruments.
To perform hologram registration, fiducial markers were used to track and map virtual coordinates to the real -world. Phantom models of each organ were constructed to test the reliability of the AR system. Our results show a registration root-mean-square error of 2. Preliminary assessment of a convolutional neural network for localization of a radioactive source with a hand-held gamma detector.
Author s : Sydney Wilson, Western Univ. Canada , Robarts Research Institute Canada ; David W. Holdsworth, Robarts Research Institute Canada , Western Univ.
Unfortunately, precise localization of radiolabeled lesions during radioguided surgery is not always possible, especially when using a high-energy radiotracer. This research investigates the use of deep learning algorithms to improve the resolution of lesion detection in a hand-held gamma probe.
Preliminary results demonstrate that a neural network achieves up to a fold improvement in resolution compared to existing clinically available gamma probes for detection of high-energy radionuclides. These results show promise for efficiently guiding a surgeon towards the lesion of interest and thus improving the surgical accuracy.
Towards optimal camera positioning for navigated surgery applications based on RGBD data. Author s : Philipp Gehrmann, Tom L.
Koller, Jan Klein, Fraunhofer-Institut für Digitale Medizin MEVIS Germany. However, OTS face challenges due to line-of-sight issues caused by occluded or contaminated markers.
To overcome these limitations, this paper proposes a novel approach using real surgery data to simulate occlusion and evaluate instrument visibility based on the idea to develop a markerless system with multiple RGBD-cameras, AI-based techniques, and optical-geometrical postprocessing for precise instrument tracking.
The simulation introduces the "task occlusion score" TOS to measure average instrument occlusion. Results indicate that optimal camera placement for visibility is above the situs, contrary to traditional setups. This simulation enhances the usability of navigated surgery, offering potential for marker-based systems with different marker geometries, and further possibilities for optimizing tracking accuracy using multiple cameras.
Posters - Monday. Surgical site-specific ensemble model for surgical procedure segmentation. Author s : Kai Chen, Sreeram Kamabattula, Kiran Bhattacharyya, Intuitive Surgical, Inc.
However, it is unknown how well these models generalize across various surgical techniques practiced at different institutions.
In this paper, we examined the possibility of using surgical site information for a more tailored, better-performing model on surgical procedure segmentation. Specifically, we developed an ensemble model consisting of site-specific models, meaning each individual model was trained on videos from a specific surgical site.
We showed that the site-specific ensemble model consistently outperforms the state-of-the-art site-agnostic model. Furthermore, by examining the representation of video-frames in the latent space, we corroborated our findings with similarity metrics comparing videos within and across sites.
Lastly, we proposed model deployment strategies to manage the introduction of videos from a new site or sites with insufficient data. Enabling rapid and high-quality 3D scene reconstruction in cystoscopy through neural radiance fields. Author s : Pengcheng Chen, Nicole M. Gunderson, Andrew Lewis, Jason R.
Speich, Michael P. Porter, Eric J. Seibel, Univ. By creating 3D models of the bladder, physicians can quickly assess conditions such as bladder cancer and monitor patients over time. However, existing 3D reconstruction methods face challenges like texture loss and slow computation.
In this study, we achieved dynamic cystoscopy scene reconstruction using Neural Radiance Fields NeRF. NeRF restores scenes with limited views and features, overcoming texture loss issues. We employed Instant-NGP to accelerate NeRF computation using hash encoding, significantly reducing computation time.
Compared to SfM, NeRF exhibits stronger resistance to interference, making it a promising method in endoscopy. NeRF has the potential to provide rapid and comprehensive recording for remote diagnosis of bladder abnormalities in future robotic-assisted flexible cystoscopy.
Using attention-based convolutional auto-encoders for catheter path reconstruction in ultrasound images. Author s : Shreyasi Mandal, Indian Institute of Technology Kanpur India ; Srinjoy Bhuiya, Univ.
of Alberta Canada ; Elodie Lugez, Toronto Metropolitan Univ. The proposed method incorporates a lightweight spatial attention-based convolutional neural network to accurately segment volumetric ultrasound images in near real-time and a 3D catheter path reconstruction algorithm.
Using automated data augmentation, structured dropout, and batch normalization techniques, the model training pipeline was designed to be robust to various issues, including overfitting and limited annotated data.
This 3D path-tracking pipeline has the potential to significantly improve the accuracy and efficiency of high-dose-rate prostate brachytherapy. TensorRT-based surgical instrument detection assessment for deep learning on edge computing.
Author s : Abdelkrim Belhaoua, Tom R. Kimpe, Barco N. Deep Learning has had a major impact on a range of surgical procedures, such as optimizing workflow, surgical training, intraoperative assistance, patient safety, and efficiency. However, it also requires high computational and memory resources.
There has been a lot of research into optimizing deep learning models to balance performance and accuracy under limited resources. Techniques like post-training quantization can significantly reduce model size and latency. In this paper, we explore TensorRT-based techniques with Yolo-based instrument detection technique on edge devices to achieve real-time inference without compromising accuracy under limited compute.
This paper gives a review looking at how deep learning and edge computing intersect and how to optimize deep learning for edge devices with limited resources. Automatic procedure planning for radial-probe endobronchial ultrasound.
Author s : Austin Kao, William E. The physician performs bronchoscopy and then employs radial-probe endobronchial ultrasound RP-EBUS to examine and biopsy suspect lesions. Physician skill, however, plays a significant part in the success of these procedures.
This has driven the introduction of image-guided bronchoscopy systems. Unfortunately, such systems do not provide guidance on how to use RP-EBUS. Our recently proposed image-guided bronchoscopy system does offer guidance for both the bronchoscope and RP-EBUS.
Unfortunately, the system relies on a time-consuming, error-prone, manual approach to generate device maneuvers. We propose an automatic approach for creating a creating a complete set of device maneuvers for both the bronchoscope and the R-EBUS probe.
Results show that planning the device maneuvers, which previously took on the order of 5 minutes or more per ROI, is reduced to under one second. Toward requirement-based performance in data-driven image analysis algorithms for robotic applications. Author s : Yuri F. Hudak, Timo J. Oude Vrielink, Fons van der Sommen, Technische Univ.
Eindhoven Netherlands. Current evaluation metrics for segmentation algorithm performance lack specificity to individual use cases and may not adequately assess the accuracy of 2D segmentation in context.
In this preliminary work, we propose a novel evaluation approach that incorporates use case-specific evaluation metrics, focusing particularly on the spatial congruence and mass center accuracy of the nodule segmentation in the context of robot-assisted image-guided interventions.
By promoting the adoption of use case-specific metrics, we aim to improve the performance of segmentation algorithms, and ultimately, the outcome of critical healthcare procedures. An assistive photo capture system for pre- and post-operative analysis of facial reconstructive surgeries.
Author s : Wenzhangzhi Guo, Yanlin Huang, Joel C. Davies, Univ. of Toronto Canada ; Vito Forte, The Hospital for Sick Children Canada ; Eitan Grinspun, Univ. of Toronto Canada ; Lueder A. Kahrs, Univ. of Toronto Mississauga Canada. However, current guidelines only focus on hardware and lighting setup.
Thus, most pre- and post-operative images are taken from different perspectives. This makes them not suitable for quantitative analysis such as comparing with simulation results, as it is very difficult to compare paths and distances in two face photos taken from vastly different perspectives.
To address this issue, we propose an application to ensure the pre- and post-operative images are taken from the same perspective.
We build a mobile application where we first record the face pose of the pre-operative image. When taking the post-operative image, we compare the face pose of the current frame with the pre-operative pose and only take a photo when the difference is below a threshold.
We performed a comparison of taking post-operative images with the proposed application and the phone camera on six head models. Source-detector trajectory optimization for customized CBCT FOV extension using simulated annealing algorithm. Author s : Hannah Jungreuthmayer, Medizinische Univ.
Wien Austria , Univ. Wien Austria , ACMIT GmbH Austria ; S. Ragib Shahriar Islam, ACMIT GmbH Austria ; Ander Biguri, Univ.
of Cambridge United Kingdom ; Gernot Kronreif, ACMIT GmbH Austria ; Wolfgang Birkfellner, Medizinische Univ. Wien Austria ; Sepideh Hatamikia, Danube Private Univ.
GmbH Austria , ACMIT GmbH Austria. Extended Field of View FOV CBCT is of great clinical importance for many medical applications, especially for cases where the Volume of Interest VOI is outside the standard FOV.
In this study, we investigate FOV extension by optimizing customized source-detector CBCT trajectories using Simulated Annealing SA algorithm, a heuristic search optimization algorithm.
The SA algorithm explores different elliptical trajectories within a given parameter space, attempting to optimize image quality in a given VOI.
Kinematic constraints e. Our experimental results have shown that our proposed customized trajectories can lead to an extended FOV and enable improved visualization of anatomical structures in extreme positions while taking into account the available kinematic constraints.
Simulation study of minimally invasive surgical scenes and their effect on hand-held stereovision driven level-wise registration techniques. Author s : Ryan B. Duke, Xiaoyao Fan, William R.
Warner, Thayer School of Engineering at Dartmouth United States ; Linton T. Evans, Dartmouth-Hitchcock Medical Ctr. United States , Geisel School of Medicine, Dartmouth College United States ; Songbai Ji, Thayer School of Engineering at Dartmouth United States , Worchester Polytechnic Institute United States ; Sohail K.
Mirza, Keith D. Paulsen, Thayer School of Engineering at Dartmouth United States , Dartmouth-Hitchcock Medical Ctr. United States , Geisel School of Medicine, Dartmouth College United States. The surgical scene in these procedures is constantly changing during surgery due to intervertebral motion.
Hand-held stereovision systems can be used to drive a deformation model to generate an updated CT using intraoperative data, however they require a large spine exposure for robust data collection. This study uses simulated narrow exposures to test the robustness of the deformation model.
The 3 HHS datasets were manually segmented in the following ways: out to the transverse process, out to the facet joints, and out to the lamina. The mean values for L2 norms for the transverse process segmentation data, facet segmentation data, and lamina segmentation are 2.
Towards an augmented reality system supporting nail implantation for tibial fractures. Author s : Nora Dimitrova, Armin Teubert, Reutlingen Univ. Germany ; Tim Klopfer, Anna Manawapat-Klopfer, Orthopädisch Chirurgie Bayreuth Germany ; Thomas Notheisen, Heiko Baumgartner, Christoph Emanuel Gonser, BG Klinik Tübingen Germany ; Ramy Zeineldin, Oliver Burgert, Reutlingen Univ.
Successful segmentation of bone and metal, even in cases with artifacts, is demonstrated. Integration into clinical workflows could enhance surgical outcomes and safety by reducing radiation exposure and intervention time.
Evaluating unsupervised optical flow for keypoint tracking in laparoscopic videos. Author s : Bruno Silva, Life and Health Sciences Research Institute, Univ. Torres, Pedro Morais, 2Ai —School of Technology Portugal , LASI — Associate Laboratory of Intelligent Systems Portugal ; Lukas R.
Vilaça, 2Ai —School of Technology Portugal , LASI — Associate Laboratory of Intelligent Systems Portugal. This assessment could provide insight into the applicability of ARFlow and similar architectures for this particular application, as well as their strengths and limitations.
Our results corroborate some of the findings reported by Jonschkowski et al. However, certain components demonstrate a distinct behavior, possibly indicating underlying issues, namely intrinsic to the application, that impact overall performance and which may have to be addressed in the context of soft-tissue trackers.
These results point to potential bottlenecks and areas where future work may target on. Segmentation of spinal computed tomography to produce biomechanically accurate patient-specific surgical models. Author s : Kaelyn Button, David C. Zaretksy, Univ.
at Buffalo United States , Canon Stroke and Vascular Research Ctr. United States ; Kasey Pfleging, Megan Malueg, Marissa Kruk, Jeffrey Mullin, Univ.
at Buffalo United States ; Ciprian N. Ionita, Univ. Traditional cadavers, limited by scarcity and cost, may not fully meet specific anatomical needs.
Patient-tailored 3D-printed spine models offer a promising alternative. This study, leveraging medical image segmentation, CAD, and advanced 3D printing techniques, explores the potential of patient-specific 3D-printed spine models.
Non-invasive imaging of exposed nerves in vivo with near-infrared hyperspectral laparoscopic devices. Author s : Ryodai Fukushima, Tokyo Univ.
of Science Japan ; Toshihiro Takamatsu, National Cancer Ctr. Japan ; Konosuke Sato, Kyohei Okubo, Masakazu Umezawa, Tokyo Univ. of Science Japan ; Nobuhiro Takeshita, Hiro Hasegawa, National Cancer Ctr. Japan ; Hideo Yokota, RIKEN Ctr. for Advanced Photonics Japan ; Kohei Soga, Hiroshi Takemura, Tokyo Univ.
of Science Japan. However, because a typical laparoscope can only receive visible light, there is a risk of accidentally damaging nerves that are similar in color to other tissues.
To solve this problem, near-infrared NIR light approximately , nm is considered to be effective because of its feature; component analysis based on the molecular vibrations specific to biomolecules.
Previously, we have developed NIR multispectral imaging MSI laparoscopy, which acquires NIR spectrum at 14 wavelengths with a band-pass filter. However, since the wavelength is limited, the optimal wavelength for identification cannot be studied.
In this study, we developed the world's first laparoscopic device capable of NIR hyperspectral imaging HSI with an increased number of wavelengths. Furthermore, NIR-HSI was conducted in a living pig, and the machine-learning was demonstrated to identify nerves and other tissues; accuracy was 0.
Eye tracking for tele-robotic surgery: a comparative evaluation of head-worn solutions. Author s : Regine Büter, Roger D. Soberanis-Mukul, Paola Ruiz Puentes, Johns Hopkins Univ. United States ; Ahmed Ghazi, The Johns Hopkins Medical Institutions United States ; Jie Ying Wu, Vanderbilt Univ. United States ; Mathias Unberath, Johns Hopkins Univ.
Current eye-tracking solutions face challenges in tele-robotic surgery due to close-range interactions, leading to extreme angles of the pupil and occlusion. A matched-user study was performed to compare the effectiveness of the Tobii Pro 3 Glasses and the Pupil Labs Core with regards to the stability of the estimated gaze and pupil diameter.
Results show, that both systems perform similarly in both regards without an outdated calibration. Large MRI specimen submersion phantom design. Author s : Haley E. Stoner, Keith D. Paulsen, Sohail K.
Mirza, Xiaoyao Fan, Ryan B. Duke, William R. Warner, Thayer School of Engineering at Dartmouth United States. This study defines a large MRI phantom design for specimen submersion to verify and quantify artifact generation from robotic system components as well as provide a better visualization platform for robotic performance during preliminary testing and evaluation.
The main topics of focus for the phantom design are fluid selection, phantom shape, phantom containment material, and 3D printed artifact measurement evaluation grids. After image equalization from the acquired MRI images, the image uniformity was determined through the ACR method while the SNR and CNR values were calculated in Fiji.
The results illustrated the preferred environmental constraints according to the main topics: food grade mineral oil, cylindrical, motion artifact interference, and PETG 3D printed grid. Quantification of changes in regional diaphragmatic motion and shape due to surgery via free-breathing dynamic MRI in pediatric patients with thoracic insufficiency syndrome.
Author s : Mahdie Hosseini, Shiva Shaghaghi, You K. Hao, Yubing Tong, Yusuf Akhtar, Mostafa Al-Noury, Caiyun Wu, Univ. of Pennsylvania United States ; Oscar H. Mayer, Joseph M.
McDonough, Patrick J. Cahill, Jason B. Anari, The Children's Hospital of Philadelphia United States ; Drew A.
Torigian, Jayaram K. Udupa, Univ. of Pennsylvania United States. Despite minimal changes in diaphragm shape, we observed significant improvement in diaphragm motion after surgery, indicating a positive impact on diaphragmatic function. This promising approach offers comprehensive insights into TIS patient management, potentially leading to improved treatment planning and patient outcomes.
Providing automatic formative feedback along surgical skill assessment. Author s : Gaspard Tonetti, Grenoble INP, Univ. Grenoble Alpes France , VetAgro Sup France , CNRS France ; Cecilie Våpenstad, SINTEF Norway , Norwegian Univ.
of Science and Technology Norway ; Nabil Zemiti, Univ. de Montpellier France , Lab. d'Informatique de Robotique et de Microelectronique de Montpellier France ; Sandrine Voros, INSERM France. Using a simple deep learning method and descriptive motion features, we developed an automatic method to assess technical surgical skills.
Our method outperforms the state-of-the-art technique for robotic minimally invasive surgery skills assessment and is also suitable for non-robotic laparoscopic training. As opposed to most methods that classify students in broad skill level categories, we focused on predicting the ratings of specific surgical technical skills.
Therefore students can know where to direct their training efforts. Surface-based volumetric image reconstruction for image-guided procedures using a data-driven framework.
Author s : Chih-Wei Chang, Shaoyan Pan, The Winship Cancer Institute of Emory Univ. United States ; Zhen Tian, The Univ. of Chicago United States ; Tonghe Wang, Memorial Sloan-Kettering Cancer Ctr. United States ; Marian Axente, Joseph Shelton, The Winship Cancer Institute of Emory Univ.
United States ; Tian Liu, Mount Sinai Medical Ctr. United States ; Justin Roper, Xiaofeng Yang, The Winship Cancer Institute of Emory Univ. This study includes computed tomography CT image sets from 50 patients.
Compared to the ground truth CT, the synthetic images result in the evaluation metric values of This approach provides a data integration solution that can potentially enable real-time imaging, which is free of radiation-induced risk and could be applied to image-guided medical procedures. Multimodality image fusion for intraoperative guidance in transcatheter structural heart disease procedures.
Author s : Sihong He, Siu-Chun M. Ho, McGovern Medical School, The Univ. of Texas Health Science Ctr. at Houston United States ; Andrew Kuhls-Gilcrist, Todd Erpelding, Canon Medical Systems USA, Inc. United States ; Richard Smalling, Memorial Hermann Heart and Vascular Institute United States , McGovern Medical School, The Univ.
at Houston United States. Mentally integrating the information from these images can be challenging during procedures and can take up time and increase radiation exposure.
This study used the free Unity graphics engine and tailored LabVIEW and Python algorithms, along with deep learning, to merge echocardiography, CT-derived 3D heart models, and fiber optic shape sensing data with fluoroscopic imaging.
Tests were performed on a patient specific ballistic gel heart model. This is the first attempt at fusing the above four imaging modalities together and can pave the way for more advanced guidance techniques in the future.
Risk prediction of stereotactic-body-radiotherapy-induced vertebral compression fracture using multi-modal deep learning network. Author s : Seoyoung Lee, Hyoyi Kim, KAIST Korea, Republic of ; Haeyoung Kim, SAMSUNG Medical Ctr.
Korea, Republic of ; Seungryong Cho, KAIST Korea, Republic of. In this study, we propose a multi-modal deep network for risk prediction of VCF after SBRT that uses clinical records, CT images, and radiotherapy factors altogether without explicit feature extraction.
The retrospective study was conducted on a cohort of patients who received SBRT for spinal bone metastasis. A 1-D feature vector was generated from clinical information. We cropped a 3-D patch of the lesion area from pretreatment CT images and planning dose images. We designed a three-branch multi-modal deep learning network.
From the k-fold validation and ablation study, our proposed multi-modal network showed the best performance with an area under the curve AUC of 0.
Smart line detection and histogram-based approach to robust freehand ultrasound calibration. Author s : William R. Warner, Xiaoyao Fan, Ryan B.
Duke, Kristen L. Chen, Chengpei Li, Haley E. Stoner, Thayer School of Engineering at Dartmouth United States ; Kirthi S. Bellamkonda, Linton T. Evans, Richard J. Powell, Dartmouth-Hitchcock Medical Ctr. United States ; Sohail K.
Paulsen, Thayer School of Engineering at Dartmouth United States. Accurate spatial calibration is essential to enable iUS navigation. Utilizing sterilizable ultrasound probes introduces new calibration challenges that can be solved by a robust, efficient and user independent calibration technique to be performed sterilely at the time of surgery in the sterile field.
This study investigates the effect of pose variation on the accuracy of a plane-based ultrasound calibration technique through analysis of a comprehensive dataset.
The location of the tracked tool attached to the probe is decoupled into 6 degrees of freedom and monitored during data acquisition. An intelligent line detection algorithm is deployed to US video feed during acquisition. The range of the degrees of freedom of the data set are iteratively reduced to study its effect on the spatial calibration accuracy.
Analysis of reducing the translation and rotation range increased both TRE and standard deviation emphasizing the need for increasing pose variation during calibration data acquisition to ensure high calibration accuracy This work facilitates a larger development toward sterile time-of-surgery calibration.
Adaptive octree cube refinement depending on grasping position for deformable organ models. Author s : Rintaro Miyazaki, Yuichiro Hayashi, Masahiro Oda, Kensaku Mori, Nagoya Univ.
Surgical simulation is one of the most promising ways for surgical training. Laparoscopic surgery simulators are already in practical use and have been evaluated for their effectiveness.
To realize a high-quality simulator, it is important to efficiently process organ deformation models. In this study, we extend adaptive mesh refinement and apply it to an octree cube structure. Refinement of the structure is performed based on the grasping position.
This approach improves the resolution of the octree around the grasping position. In addition, it makes it easier to detect interference between the grasp model and the high-resolution grid of the octree. Simulation results showed there were cubes before and cubes after refinement, and the FPS decreased from Exploring optical flow inclusion into nnU-Net framework for surgical instrument segmentation.
Author s : Marcos Fernández-Rodríguez, Life and Health Sciences Research Institute, Univ. do Minho Portugal , School of Medicine, Univ. do Minho Portugal ; Bruno Silva, Sandro Queirós, Life and Health Sciences Research Institute, Univ. do Minho Portugal ; Helena R.
Torres, Applied Artificial Intelligence Laboratory Portugal ; Bruno Oliveira, Life and Health Sciences Research Institute, Univ. do Minho Portugal ; Pedro Morais, Applied Artificial Intelligence Laboratory, Instituto Politécnico do Cávado e do Ave Portugal ; Lukas R.
KG Germany ; Jorge Correia-Pinto, Life and Health Sciences Research Institute Portugal , School of Medicine Portugal ; Estevão Lima, Life and Health Sciences Research Institute, Univ.
do Minho Portugal ; João L. Vilaça, Applied Artificial Intelligence Laboratory, Instituto Politécnico do Cávado e do Ave Portugal. The dynamic setting of laparoscopic surgery still makes it hard to obtain a precise segmentation.
The nnU-Net framework, excelled in semantic segmentation analyzing single frames without temporal information. Optical flow OF estimates motion and represent it in a single frame, containing temporal information. Meanwhile, in surgeries, instruments often show the most movement.
Novel method to improve feature extraction in MR for model-based image updating in image-guided neurosurgery.
Author s : Kristen L. Chen, Chengpei Li, Xiaoyao Fan, Scott Davis, Thayer School of Engineering at Dartmouth United States ; Linton T. United States ; Keith D. United States , Norris Cotton Cancer Ctr. Image-guided systems incorporate this spatial information to provide real-time information on where surgical instruments are located with respect to preoperative imaging.
The accuracy of these systems become degraded due to intraoperative brain shift. To account for brain shift, we previously developed an image-guidance updating framework that incorporates brain shift information acquired from registering intraoperative stereovision iSV surface with the pMR surface to create an updated magnetic resonance image uMR.
To register the iSV surface and the pMR surface, the two surfaces must have some matching features that can be used for registration. To capture features falling outside of the brain volume, we have developed a method to improve feature extraction, which involves performing a selective dilation in the region of the stereovision surface.
The goal of this method is to capture useful features that can be use to improve image registration. In-silico CT lung phantom generated from finite-element mesh. United States ; Bradford J. Smith, Univ. United States ; Rahim R. Rizi, Univ. Image registration through the use of dynamic imaging has emerged as a powerful tool to assess the kinematic and deformation behavior of lung parenchyma during respiration.
However, the difficulty in validating the results provided by image registration has limited its use in clinical settings. To overcome this barrier, we developed a method to convert an FE mesh of the lung to a phantom CT image. Through the generation of the phantom image, we were able to isolate the geometry of the lung and large airways.
A series of high-quality phantom images generated from the FE mesh deformed through in-silico experiments simulating the respiratory cycle will allow for the validation and evaluation of image-registration algorithms.
The method presented in this study will serve as an essential step towards the implementation of dynamic imaging and image registration in clinical settings to assess regional deformation in patients as a diagnostic and risk-stratification tool.
Comprehensive examination of personalized microwave ablation: exploring the effects of blood perfusion rate and metabolic heat on treatment responses. Author s : Amirreza Heshmat, Caleb S.
O'Connor, Jun Hong, Jessica Albuquerque Marques Silva, Iwan Paolucci, Aaron K. Jones, Bruno C. Odisio, Kristy K. Brock, The Univ. The Penne bioheat equation explains heat distribution in tissues, including factors like blood perfusion rate BPR and metabolic heat MH. We employed 3D patient-specific models and sensitivity analysis to examine how BPR and MH affect MWA results.
Numerical simulations using a triaxial antenna and 65 Watts power on tumors demonstrated that lower BPR led to less damage and complete tumor destruction.
Models without MH had less liver damage. The study highlights the importance of tailored ablation parameters for personalized treatments, revealing the impact of BPR and MH on MWA outcomes.
Comparative analysis of non-rigid registration techniques for liver surface registration. Author s : Bipasha Kundu, Zixin Yang, Richard Simon, Cristian A. Linte, Rochester Institute of Technology United States. To address limited access to liver registration methods, we compare the robustness of three open-source optimization-based nonrigid registration methods and one data-driven method to a reduced visibility ratio reduced partial views of the surface and an increasing deformation level mean displacement , reported as the root mean square error RMSE between the pre- and intra-operative liver surface meshed following registration.
The Gaussian Mixture Model-Finite Element Model GMM-FEM method consistently yields a lower post-registration error than the other three tested methods in the presence of both reduced visibility ratio and increased intra-operative surface displacement, therefore offering a potentially promising solution for pre- to intra-operative nonrigid liver surface registration.
Auditory nerve fiber localization using a weakly supervised non-rigid registration U-Net. Author s : Hannah G. Mason, Ziteng Liu, Jack H. CIs induce hearing sensation by stimulating auditory nerve fibers ANFs using an electrode array that is surgically implanted into the cochlea.
After the device is implanted, an audiologist programs the CI processor to optimize hearing performance. Without knowing which ANFs are being stimulated by each electrode, audiologists must rely solely on patient performance to inform programming adjustments. Patient-specific neural stimulation modeling has been proposed to assist audiologists, but requires accurate localization of ANFs.
In this paper, we propose an automatic neural-network-based method for atlas-based localization of the ANFs. Our results show that our method is able to produce smooth ANF predictions that are more realistic than those produced by a previously proposed semi-manual localization method.
Accurate and realistic ANF localizations are critical for constructing patient-specific ANF stimulation models for model guided CI programming. A comparison of onboard and offboard user interfaces for handheld robots. Author s : Ethan Wilke, Jesse F. d'Almeida, Jason Shrand, Tayfun Ertop, Nicholas L.
Kavoussi, Amy Reed, Duke Herrell, Robert J. Webster, Vanderbilt Univ. Several research groups have shown that robots can be made so small and light that they can become hand-held tools.
This hand-held paradigm enables robots to fit much more seamlessly into existing clinical workflows. In this paper, we compare an onboard user interface approach against the traditional offboard approach.
In the latter, the surgeon positions the robot, and a support arm holds it in place while the surgeon operates the manipulators using the offboard surgeon console.
The surgeon can move back and forth between the robot and the console as often as desired. Three experiments were conducted, and results show that the onboard interface enables statistically significantly faster performance in a point-touching task performed in a virtual reality environment.
Author s : Connor Mitchell, Robarts Research Institute Canada ; Shuwei Xing, Robarts Research Institute Canada , Western Univ.
Canada ; Derek W. Cool, London Health Sciences Ctr. Canada , Robarts Research Institute Canada ; David Tessier, Robarts Research Institute Canada ; Aaron Fenster, Robarts Research Institute Canada , Western Univ.
For this procedure, the radiologist must compare the pre-operative with the post-operative CT to determine the presence of residual tumors. Distinguishing between malignant and benign kidney tumors poses a significant challenge. To automate this tumor coverage evaluation step and assist the radiologist in identifying kidney tumors, we proposed a coarse-to-fine U-Net-based model to segment kidneys and masses.
We used the TotalSegmentator tool to obtain an approximate segmentation and region of interest of the kidneys, which was inputted into our 3D segmentation network trained using the nnUNet library to fully segment the kidneys and masses within them.
Our model achieved an aggregated DICE score of 0. Our results indicate the model will be useful for tumour identification and evaluation. Automating creation of high-fidelity holographic hand animations for surgical skills training using mixed reality headsets.
Author s : Regina W. Leung, Ge Shi, Western Univ. Canada ; Christina A. Using this methodology, we successfully developed a 3D holographic animation of one-handed knot ties used in surgery. With regards to the quality of the produced animation, our qualitative pilot study demonstrated comparable successful learning of knot-ties from the holographic animation to in-person demonstration.
Furthermore, participants found learning knot-ties from the holographic animation to be easier, more effective, were more confident in mastery of the skill in comparison to in-person demonstration, and also found the animation comparable to real hands showing promise for application in surgical skills training applications.
A robust system for capture and archival of high-definition stereoendoscopic video. Author s : Michael A. Kokko, Ryan J.
The Image Guided MRI for image-guided procedures Program IGTP is combining advances in imaging and therapeutic technology to procecures minimally MRI for image-guided procedures surgical Low-carb and portion control interventional techniques. Procedrues program represents a multidisciplinary clinical and image-guied effort and has developed several novel therapies. The IGTP is supported by the Center for Innovative Minimally Invasive Therapy CIMIT which is funded by the Department of Defense DOD. The use of medical imaging for guidance of therapy is not a new concept. Since the discovery of x-rays, various imaging methods have been used to localize normal anatomical structures and pathologic lesions, as well as to locate instruments.
0 thoughts on “MRI for image-guided procedures”