Person: Tenenholtz, Neil Arturo
Loading...
Email Address
AA Acceptance Date
Birth Date
Research Projects
Organizational Units
Job Title
Last Name
Tenenholtz
First Name
Neil Arturo
Name
Tenenholtz, Neil Arturo
5 results
Search Results
Now showing 1 - 5 of 5
Publication Fast Surgical Simulation to Improve Mitral Valve Repair(2014-06-06) Tenenholtz, Neil Arturo; Howe, Robert D.; Pfister, Hanspeter; del Nido, PedroMitral valve repair, the preferred method of treating mitral regurgitation, is a demanding surgical procedure consisting of the resection and approximation of valve tissue. Operating on an arrested heart, the clinician is forced to predict closed valve shape and the effect of surgical modifications. The valve's complex morphology makes this a difficult task, and as a result, the procedure is underperformed by less experienced surgeons in lieu of the simpler, less effective valve replacement.Publication Patient-Specific Mitral Leaflet Segmentation from 4D Ultrasound(Springer, 2011) Tenenholtz, Neil Arturo; Perrin, Douglas; Marx, Gerald; Del Nido, Pedro; Schneider, Robert J.; Howe, RobertSegmenting the mitral valve during closure and throughout a cardiac cycle from four dimensional ultrasound (4DUS) is important for creation and validation of mechanical models and for improved visualization and understanding of mitral valve behavior. Current methods of segmenting the valve from 4DUS either require extensive user interaction and initialization, do not maintain the valve geometry across a cardiac cycle, or are incapable of producing a detailed coaptation line and surface. We present a method of segmenting the mitral valve annulus and leaflets from 4DUS such that a detailed, patient-specific annulus and leaflets are tracked throughout mitral valve closure, resulting in a detailed coaptation region. The method requires only the selection of two frames from a sequence indicating the start and end of valve closure and a single point near a closed valve. The annulus and leaflets are first found through direct segmentation in the appropriate frames and then by tracking the known geometry to the remaining frames. We compared the automatically segmented meshes to expert manual tracings for both a normal and diseased mitral valve, and found an average difference of 0.59 ± 0.49mm, which is on the order of the spatial resolution of the ultrasound volumes (0.5–1.0mm/voxel).Publication On the design of an interactive, patient-specific surgical simulator for mitral valve repair(IEEE, 2011) Tenenholtz, Neil Arturo; Hammer, Peter; Schneider, Robert J.; Vasilyev, Nikolay; Howe, RobertSurgical repair of the mitral valve is a difficult procedure that is often avoided in favor of less effective valve replacement because of the associated technical challenges facing non-expert surgeons. In the interest of increasing the rate of valve repair, an accurate, interactive surgical simulator for mitral valve repair was developed. With a haptic interface, users can interact with a mechanical model during simulation to aid in the development of a surgical plan and then virtually implement the procedure to assess its efficacy. Sub-millimeter accuracy was achieved in a validation study, and the system was successfully used by a cardiac surgeon to repair three virtual pathological valves.Publication Fast Interactive Simulations of Mitral Valve Repair(2012) Tenenholtz, Neil Arturo; Hammer, Peter; Howe, RobertPublication Tag-LLM: Repurposing General-Purpose LLMs for Specialized Domains(JMLR, 2024-07-21) Shen, Junhong; Alvarez Melis, David; Tenenholtz, Neil Arturo; Hall, James Brian; Fusi, NicoloLarge Language Models (LLMs) have demonstrated remarkable proficiency in understanding and generating natural language. However, their capabilities wane in highly specialized domains underrepresented in the pretraining corpus, such as physical and biomedical sciences. This work explores how to repurpose general LLMs into effective task solvers for specialized domains. We introduce a novel, model-agnostic framework for learning custom input tags, which are parameterized as continuous vectors appended to the LLM’s embedding layer, to condition the LLM. We design two types of input tags: domain tags are used to delimit specialized representations (e.g., chemical formulas) and provide domain-relevant context; function tags are used to represent specific functions (e.g., predicting molecular properties) and compress function-solving instructions. We develop a three-stage protocol to learn these tags using auxiliary data and domain knowledge. By explicitly disentangling task domains from task functions, our method enables zero-shot generalization to unseen problems through diverse combinations of the input tags. It also boosts LLM’s performance in various specialized domains, such as predicting protein or chemical properties and modeling drug-target interactions, outperforming expert models tailored to these tasks.