Marc Niethammer, PhD
Professor in Computer Science and Engineering
University of California, San Diego (UCSD)

�ٲ��ٱ�:��Thursday, April 16, 2026
Location: LightHall 202
�վ�����:��11:45 am for lunch,12:00 pm start

Title:
Practical machine learning approaches for medical image registration

Abstract:
Image registration, the process of establishing spatial correspondences between images, is a key task in medical image computing. For example, to facilitate analyses in a common atlas spatial coordinate system or to track changes over time in radiation treatment planning. Image registration approaches have been extensively developed over the previous decades with a shift to approaches based on deep learning over the last decade. However, while modern deep learning registration approaches allow for highly accurate and fast registrations many existing approaches are task-specific. Hence, these approaches require extensive retraining or fine tuning for a new registration task. This talk will provide an overview of approaches to obtain deep registration networks that generalize across image types and registration tasks. It will also discuss some recent work on building deep registration models with desirable equivariance properties as a further step towards registration models that work well in practice and that behave somewhat more predictably.

Bio:
Marc Niethammer is a professor in Computer Science and Engineering with a joint appointment in Neurological Surgery at the University of California, San Diego (UCSD). He holds the Halıcıoğlu Endowed Chair in Health AI and leads the Biomedical Image Analysis Group. Before joining UCSD, he was a Professor of Computer Science at the University of North Carolina at Chapel Hill (UNC) from 2008 to 2024. Dr. Niethammer was the program chair for the International Conference on Information Processing in Medical Imaging (IPMI, 2017) and is an Executive Editor of MELBA, the Journal for Machine Learning for Biomedical Imaging. Dr. Niethammer’s work focuses on methods for statistical shape analysis, image segmentation, image registration, machine learning, and related applications.

Joseph S. Neimat, MD, MS
Professor and Chair
University of Louisville Neurosurgery

�ٲ��ٱ�:��Thursday, April 2, 2026
Location: LightHall 202
�վ�����:��11:45 am for lunch,12:00 pm start

Title:
Functional Neurosurgery: ��A Historical Testing Ground for Surgical Engineering

Summary:
The discipline of functional neurosurgery has been fundamentally shaped by engineering innovations that empowered the surgical advancement of the field. From its genesis, spurred by the creation of stereotactic frames, to its ongoing transformation through spinal and deep brain stimulation, the field continues to evolve alongside rapid technological breakthroughs.����The speaker is an engineering luddite who was embraced by the ��ͷ�� Initiative in Surgery and Engineering (VISE), and has subsequently had his career shaped by such collaborative partnerships.����Dr Neimat looks forward to returning to VISE to share his perspectives on how these synergies continue to define the future of the specialty.

Bio:
Joseph Neimat grew up in the Washington DC area. He studied at Dartmouth College and Duke University. Dr. Neimat performed his residency in Neurosurgery at Massachusetts General Hospital, and a fellowship in Neuromodulation surgery at the University of Toronto.

Dr Neimat served as Director of Epilepsy and was a founding member of the Institute for Surgery and Engineering at ��ͷ�� University. In 2016 Dr. Neimat transitioned to the University of Louisville where he serves as Chairman of Neurological Surgery.�� His clinical interests include the surgical treatment of movement disorders, the treatment of epilepsy, novel therapies for disorders of mood and behavior, and the multi-modality treatment of complex pain.

Dr. Neimat additionally runs a collaborative research lab exploring cognitive and emotional processing in cortical and subcortical structures. The lab uses the opportunity of DBS and epilepsy surgeries, to evaluate the response of neuronal ensembles to novel stimuli that task cognitive and emotional processing.

Dr. Neimat has served on the Board of Directors for the American and World Societies for Stereotactic and Functional Neurosurgery (ASSFN and WSSFN). He is a Past – President of the ASSFN.

Jason Kerkmans, JD
Founder and Executive Vice President, Strategic Development
MINDSET Integrated Co

�ٲ��ٱ�:��Thursday, March 26, 2026
NEW ���dz����پ��Dz�:��MCN CC-2209
�վ�����:��12:30 pm for lunch,12:40 pm start

Title:
From Data to Verdict: How the US Litigation System Advances, Tests, and Distorts Neuroimaging Science
Abstract:
Advanced neuroimaging is increasingly entering courtrooms, creating a parallel translational pathway that complements traditional academic publication and the regulatory approval process. Whereas scientific acceptance emphasizes peer review and replication, and regulatory clearance through the U.S. The Food and Drug Administration focuses on population-level safety and efficacy, legal admissibility centers on methodological reliability and individualized application. This talk examines how litigation functions as a real-world validation ecosystem for neuroimaging data analysis. On the translational side, legal cases fund comprehensive evaluations that are often independent of clinical reimbursement constraints. This exposes advanced analytic tools to patients who might not otherwise access them and subjects them to varying levels of transparency through adversarial scrutiny. The legal process also introduces structured bias, strategic challenges, and the risk of misinterpretation under high-stakes conditions. By analyzing how evidence operates across low-value personal injury claims to high-value medical malpractice litigation, this presentation illustrates how legal deployment can refine documentation standards, improve reproducibility, and expose gaps and misuse of regulatory cleared processes. Ultimately, engaging thoughtfully with litigation environments can advance the development of robust, interpretable, and patient-centered neuroimaging algorithms that might otherwise take decades to reach the general population, while also acknowledging the structural risks inherent in adversarial systems.

Bio:

Jason Kerkmans, JD, founded to identify complex and reliable neuroscience and integrate it into the legal system. His actionable expertise in the admissibility of scientific and expert evidence has been utilized in dozens of admissibility responses he helped author. He has also worked on briefings for the United States Supreme Court, the New Mexico Legislature, and numerous federal, military, and state filings. Jason has presented on science and the law at domestic and international conferences and has taught Scientific Evidence at the University of New Mexico School of Law.

Charles F. Caskey, Ph.D.
Professor of Radiology and Biomedical Engineering
��ͷ�� University Medical Center

�ٲ��ٱ�:��Thursday, February 26, 2026
NEW Location: Light Hall 214
�վ�����:��11:45 am for lunch,12:00 start

Title:
How to Tickle the Brain Without Touching It

Abstract:
Focused ultrasound (FUS) offers a rare combination in neuroscience: the ability to deliver millimeter-scale, noninvasive energy to deep brain structures with exquisite spatial precision. When paired with MRI, FUS becomes a fully image-guided neuromodulation platform capable of accurate targeting, real‑time monitoring, and whole-brain functional readout through fMRI. This talk will highlight collaborative efforts across ��ͷ�� to engineer and validate this platform in preclinical models and move it along the translational pipeline to humans.

Recent advances include optical tracking to minimize targeting error, multi-element FUS arrays enabling rapid beam steering and multi-site stimulation, and MR acoustic radiation force imaging (MR‑ARFI) for robust visualization of the acoustic focus. These tools have enabled reliable modulation of both cortical and deep nuclei and have revealed network-level mechanisms of action. Functional studies show that low-intensity FUS can selectively suppress thalamic responses to tactile and nociceptive input, disrupt thalamocortical information flow, and reconfigure distributed brain networks. Comprehensive safety assessments combining MR thermometry, acoustic pressure simulations, and histology demonstrate safe operating windows suitable for translation.

Together, these engineering and preclinical advances are driving MRI‑guided FUS toward clinical neuromodulation studies, including early applications in essential tremor and post-stroke pain. By integrating imaging, modeling, and therapeutic ultrasound, this work lays the groundwork for precise, noninvasive brain stimulation approaches that extend the reach of both neuroscience and medicine.

Bio:
Charles F. Caskey, Ph.D.��is a Professor of Radiology and��Biomedical Engineering at ��ͷ�� University Medical Center, where he leads the Laboratory for Acoustic Therapy and Imaging at the ��ͷ�� University Institute of Imaging Science. He has worked in ultrasound research since 2004 and completed his Ph.D. in��Biomedical Engineering at the University of California, Davis, studying the��biophysical mechanisms of microbubble‑enhanced drug delivery under Dr. Katherine Ferrara. His subsequent work advanced MR‑guided focused ultrasound neuromodulation technologies, and in 2018 he received the Fred Lizzi Early Career Award from the International Society for Therapeutic Ultrasound.��

Dr. Caskey’s laboratory develops ultrasound technologies for neuromodulation, drug delivery, and functional imaging, integrating ultrasound with MRI, electrophysiology, and molecular imaging. He leads multiple projects aimed at first‑in‑human neuromodulation systems, mechanistic foundations of focused ultrasound stimulation, and next‑generation transcranial therapeutic strategies. His work emphasizes advancing ultrasound technologies toward clinical translation, along with precision targeting, and multimodal approaches to noninvasive modulation of brain circuits, supported by extensive interdisciplinary collaborations within and beyond ��ͷ��.

W. Hong Yeo, PhD
G.P. “Bud” Peterson and Valerie H. Peterson Endowed Professor
Woodruff School of Mechanical Engineering
and the Coulter Department of Biomedical Engineering
Georgia Tech

�ٲ��ٱ�:��Thursday, February 12, 2026
NEW Location: Light Hall 202
�վ�����:��11:45 am for lunch,12:00 start
Title:
Soft Wearable Intelligent Bioelectronics for Health Monitoring

Abstract:
In this presentation, Dr. Yeo will discuss the fundamental scientific principles behind integrated nanomembrane biosensors and bioelectronics, with a focus on their groundbreaking applications in wearable configurations. He will address the limitations and challenges of current biomedical systems used for health monitoring, such as issues with comfort, accuracy, and long-term stability. To respond to these challenges, Dr. Yeo will present a series of innovative solutions utilizing soft sensors and integrated electronics, which allow for flexible, skin-like devices tailored for real-world use. Specifically, he will highlight novel strategies for designing and fabricating advanced systems through materials engineering, state-of-the-art printing-based nanomanufacturing, and the integration of hard-soft system packaging technologies for optimal durability and performance. Additionally, Dr. Yeo will provide compelling examples from both in vitro and in vivo studies to illustrate the novelty, reliability, and effectiveness of these soft intelligent bioelectronics. He will emphasize their significant advantages over existing technologies, such as enabling real-time, continuous health monitoring, portable healthcare solutions, quantitative disease diagnosis, and connected therapeutics facilitated by advanced human-machine interfaces. The talk will conclude with a discussion of future directions and broader impacts for personalized healthcare.

Bio:
Dr. Yeo holds the title of G.P. “Bud” Peterson and Valerie H. Peterson Endowed Professor in the Woodruff School of Mechanical Engineering and the Coulter Department of Biomedical Engineering at Georgia Tech. He is also the director of the Wearable Intelligent Systems and Healthcare Center, the NSF Research Traineeship Program in Sustainable Development of Smart Medical Devices, and the KIAT-Georgia Tech Semiconductor Electronics Center. Dr. Yeo’s research focuses on understanding the fundamentals of soft materials, deformable mechanics, interfacial physics, manufacturing, and the integration of hard and soft materials for the development of soft biomedical systems. He earned his Ph.D. in mechanical engineering and genome sciences from the University of Washington in Seattle and subsequently worked as a postdoctoral research fellow at the University of Illinois at Urbana-Champaign. With over 190 peer-reviewed publications, Dr. Yeo has contributed to many prestigious journals, including Nature Materials, Nature Machine Intelligence, Nature Communications, and Science Advances. He is an Associate Editor of Biosensors and Bioelectronics and has received numerous awards, including the Professorship from the Institute Jean Lamour at the Université de Lorraine in France, the Lucy G. Moses Lectureship Award at the Mount Sinai School of Medicine, the NIH Trailblazer Young Investigator Award, the IEEE Outstanding Engineer Award, the Emory School of Medicine Research Award, and the Imlay Innovation Award. Dr. Yeo is also the founder of two startup companies: Huxley Medical, Inc. and WisMedical, Inc.

Marcia K. O’Malley, PhD
Thomas Michael Panos Family Professor of Mechanical Engineering, Computer Science, Electrical and Computer Engineering, and Bioengineering
Rice University

�ٲ��ٱ�:��Thursday, January 29, 2026
NEW Location: Light Hall 214
�վ�����:��11:45 am for lunch,12:00 start

Title:
Guiding with touch: Objective assessment and haptic cueing to improve surgical performance on virtual and robotic platforms

Abstract:
Recent advances in simulation and robotic surgery have changed the way surgeons are trained in terms of their ability to gain experience without risk to patients. However, the feedback surgical trainees receive during training is still delayed, subjective, and qualitative, which does not provide the maximum support for rapid acquisition of motor skill. In this talk, I will describe our research on identifying objective and quantitative metrics that capture surgical skill in the endovascular domain. Specifically, we have shown that low-level properties of movements (e.g., smoothness) made in the performance of several motor tasks—including surgery in both virtual and robotic environments—are highly correlated with high-level performance outcomes, such as expert evaluations in surgical environments. I will also describe our progress in transforming these performance metrics to haptic representations that are provided in real-time to a trainee. We have shown that the provision of real-time haptic feedback during training of complex motor tasks can alter trainee strategies and learning curves. We hypothesize that we can enhance surgical performance and training by providing performance feedback based on these same motion-based metrics that quantify movement quality and strategies rather than task outcomes. This approach allows trainees to receive feedback that is immediate and quantitative, which should amplify human capabilities and result in improved performance in difficult-to-train motor domains such as surgery.

Bio:

Dr. Marcia K. O’Malley is the Thomas Michael Panos Family Professor of Mechanical Engineering, Computer Science, Electrical and Computer Engineering, and Bioengineering at Rice University, where she serves as Chair of the Department of Mechanical Engineering in the George R. Brown School of Engineering and Computing. She directs the Mechatronics and Haptic Interfaces (MAHI) Lab and holds adjunct appointments in Physical Medicine and Rehabilitation at Baylor College of Medicine and the University of Texas Medical School at Houston. Dr. O’Malley earned her B.S. in Mechanical Engineering from Purdue University and her M.S. and Ph.D. in Mechanical Engineering from ��ͷ�� University. Her research advances physical human-robot interaction, haptic feedback, and wearable robotic and exoskeleton systems for rehabilitation and assistive applications. She has pioneered strategies for motor adaptation and skill acquisition through psychophysical studies and shared control, enabling technologies that restore movement coordination after neurological injury and enhance training of complex motor skills in virtual environments. At Rice, she has twice received the George R. Brown Award for Superior Teaching, and was honored with the Faculty Award for Excellence in Research, Teaching, and Service. Dr. O’Malley is a Fellow of ASME, IEEE, AIMBE, and IAMBE, and her contributions have been recognized with the ONR Young Investigator Award, NSF CAREER Award, and the Grand Nagamori Award.

Daniel Gonzales, PhD
Assistant Professor, Biomedical Engineering
��ͷ�� University

�ٲ��ٱ�:��Thursday, November 13, 2025
���dz����پ��Dz�:��SVC 5326
�վ�����:��11:45 am for lunch,12:00 start

Talk Title:

Flexible brain implants for stable recordings across species

�������ٰ�������:��

Neurophysiological recordings have traditionally relied on rigid substrates such as silicon, steel, and tungsten. These materials mismatch the mechanical properties of soft brain tissue, reducing recording stability and leading to signal degradation over time. Moreover, the opacity of these conventional substrates limits integration with powerful optical techniques for imaging and manipulating neural circuits. I will present our group’s recent advances in flexible, transparent neural interfaces that provide chronic, stable, and optically compatible access to neuronal populations. In non-human primates, our flexible electrode arrays yield reliable population-level recordings during complex cognitive behaviors, demonstrating improved stability compared to conventional rigid arrays. In rodents, we achieve months-long chronic recordings using flexible implants. By combining this electrical access with an optical window, we achieve simultaneous optical interrogation of neuronal dynamics. Together, these results highlight a path toward durable, multimodal interfaces for long-term investigation of neural circuits across species.

Short Bio:

Daniel Gonzales is an Assistant Professor of Biomedical Engineering and a member of the ��ͷ�� Brain Institute and VINSE. His lab develops advanced brain interfaces to study the neural computations underlying learning and cognition. Before joining ��ͷ��, Daniel trained at Rice University, where he received his PhD in Applied Physics, and at Purdue University, where he performed his postdoctoral work. His work has been recognized by the Howard Hughes Medical Institute, Burroughs Wellcome Fund, and National Science Foundation.

Hao Li, PhD
Research Assistant Professor
Department of Computer Science
��ͷ�� University

�ٲ��ٱ�:��Thursday, November 6, 2025
���dz����پ��Dz�:��SVC 5326
�վ�����:��11:45 am for lunch,12:00 start

Title:
From Data-driven to Data-centric Medical Image Segmentation

Abstract:

Recent advances in deep learning have significantly advanced medical image segmentation, evolving from data-driven to data-centric paradigms. This transition highlights the growing importance of data quality in achieving reliable and efficient segmentation. Data-driven strategies focus on enhancing neural network (NN) architectures and loss functions using existing datasets, whereas data-centric methods emphasize improving data quality, consistency, and diversity to strengthen model performance and generalizability. This talk covers both perspectives. On the data-driven side, state-of-the-art neural networks are developed for robust segmentation with supervised learning across diverse medical applications, enabling the effective extraction of clinically relevant biomarkers. On the data-centric side, domain shifts are addressed through unsupervised domain adaptation and test-time adaptation to improve data harmonization across institutions, scanners, and patient populations. Incorporating expert knowledge further enhances interpretability and reliability under heterogeneous supervision, while uncertainty-guided semi-supervised learning tackles the common challenge of limited data availability to achieve more accurate and generalizable segmentation performance. Evaluations across diverse imaging modalities, including multi-center MRI, CT, ultrasound, and endoscopic datasets, demonstrate that deep learning–based segmentation methods achieve strong performance, particularly when efforts focus on improving data fidelity and consistency. This transition from data-driven to data-centric medical image segmentation establishes a sustainable direction for developing generalizable, trustworthy, and clinically deployable algorithms by aligning methodological innovation with the realities of real-world medical data.

Bio:
Dr. Hao Li��is a Research Assistant Professor in the Department of Computer Science at ��ͷ�� University. His research focuses broadly on algorithmic development for medical image analysis across both medical image computing and computer-aided intervention. He develops methods in multi-modal learning, unsupervised domain adaptation, and uncertainty-guided semi-supervised learning. with��applications to segmentation, registration, and detection across various imaging modalities such as MRI, CT, ultrasound and endoscopy in both 2D and 3D domains. His research aims to build robust and efficient solutions for real-world clinical and surgical applications, advancing disease assessment, diagnostic decision support, preoperative analysis, and real-time image-guided procedures.

��

James S. Duncan, PhD
Ebenezer K. Hunt Professor of Biomedical Engineering,
Professor of Radiology & Biomedical Engineering, Electrical Engineering and Statistics & Data Science
Yale University

�ٲ��ٱ�:��Thursday, October 16, 2025
���dz����پ��Dz�:��SVC 5326
�վ�����:��11:45 am for lunch,12:00 start

Title:
Neuroimage Analysis in Autism: from Model-Based Estimation to Data-driven Learning

Abstract:
Functional magnetic resonance imaging (fMRI) has been shown to be helpful for the study of��autism spectrum disorders (ASD). This talk will describe the evolution of efforts in this area��within our group that carry promise for producing objective biomarkers for ASD, as well as predicting patient response to a behavioral therapy known as Pivotal Response Treatment��(PRT), using task-based fMRI. Such biomarkers would provide an important step for better understanding the underlying pathophysiology of ASD that could help with objective and personalized diagnosis, provide new targets for development of new treatments, and provide a way to monitor patient progress.��Initially��a robust, group-wise unified Bayesian framework to detect both hyper and hypo-active communities from connectivity maps will be described. Next, more recent work will be presented that has focused on deriving ASD biomarkers from individual subject’s time-series data, based on the classification of��individual subjects (into ASD or typical control) and identifying spatially-specific key regions using graph convolutional neural networks and ablation analysis of regions. In addition, a strategy based on recurrent neural networks (using long-short-term memories or LSTMs) will be presented that predicts��patient response to PRT behavioral therapy from baseline��imaging while incorporating subject-specific phenotypic information for network initialization. Finally, initial efforts on the use of a spatiotemporal transformer strategy for classification and early work on the use of effective connectivity based on whole brain dynamic causal modeling as an alternative or an adjunct to functional connectivity for classification and biomarker analysis will be discussed.

James S. Duncan��is the Ebenezer K. Hunt Professor of Biomedical Engineering and a Professor of Radiology & Biomedical Engineering, Electrical Engineering and Statistics & Data Science at Yale University. Dr. Duncan received his B.S.E.E. with honors from Lafayette College, his M.S. ��degree from the University of California, Los Angeles��and his Ph.D. ��in Electrical Engineering from the University of Southern California.������He is currently the Chair of the Department of Biomedical Engineering. Dr. Duncan’s research efforts have been in the areas of computer vision, image processing, and medical imaging, with an emphasis on biomedical image analysis and image-based machine learning. He has published over 300 peer-reviewed articles and has been the principal investigator on a number of peer-reviewed grants from both the National Institutes of Health and the National Science Foundation over the past 35 years. He is a Life Fellow of the Institute of Electrical and Electronic Engineers (IEEE), and a Fellow of the American Institute for Medical and Biological Engineering (AIMBE) and of the Medical Image Computing and Computer Assisted Intervention (MICCAI) Society. In 2014 he was elected to the Connecticut Academy of Science & Engineering. He has served as co-Editor-in-Chief of Medical Image Analysis,��Associate Editor of IEEE Transactions on Medical Imaging, and on the Editorial Board of the Proceedings of the IEEE. He is a past President of the MICCAI Society. In 2012, he was elected to the Council of Distinguished Investigators, Academy of Radiology Research and in 2017 received the “Enduring Impact Award” from the MICCAI Society. ��He served as General Co-Chair of the 2023 MICCAI meeting in Vancouver, Canada.

Angela Crudele, MD
Assistant Professor of Neurology
��ͷ�� University Medical Center

Date: Thursday, October 2, 2025
Location: SVC 5326
Time: 11:45 am for lunch, 12:00 start

Title:
“The Thalamus in Epilepsy: A New Target in Neuromodulation”
Abstract:
Treatment of drug-resistant idiopathic generalized epilepsy (IGE) remains a critical unmet need, with patients facing more limited options than their counterparts with focal epilepsy. Novel pharmacologic trials disproportionately emphasize focal epilepsies, and currently available neuromodulatory devices are FDA-approved exclusively for focal onset disease. Moreover, patients with drug-resistant IGE are not candidates for potentially curative resective surgical approaches, further constraining the therapeutic landscape. In recent years, direct thalamic stimulation has emerged as a promising strategy for addressing this therapeutic gap. This talk will highlight the neurobiological rationale for thalamic targeting in IGE, recent investigational efforts, including work performed in part at ��ͷ��, to expand treatment availability, and the ongoing limitations of these advances in achieving seizure control. This research underscores a transformative potential for neuromodulation to redefine therapeutic opportunities in IGE.
Bio:
Angela Crudele, MD is an Assistant Professor of Neurology at ��ͷ�� University Medical Center in Nashville, TN. She joined the faculty of VUMC in 2019 as an epileptologist. She is the Clinical��Director of Epilepsy Surgery and leads the program’s fellow education in stereographic EEG. Dr. Crudele is also active in the area of��medical education within the ��ͷ�� School of Medicine, leading the Brain, Behavior, and Movement course for the first-year��medical students.��She teaches about neuromodulation regularly on a national level and has been involved in multiple clinical trials in neuromodulation.