AIM-HI Lab

Advancing urologic care through cutting-edge AI, medical imaging, and computer vision at Cleveland Clinic

Scroll

About AIM-HI Lab

The AIM-HI Lab (Artificial Intelligence in Medicine and Health Imaging) at Cleveland Clinic's Department of Urology is dedicated to developing and applying artificial intelligence solutions to improve the lives of those affected by urologic diseases. We use advanced computing approaches to enhance diagnosis, treatment planning, and patient outcomes.

By combining cutting-edge AI technologies with clinical and translational research expertise, we aim to enhance the precision and efficiency of urologic care while maintaining the highest standards of patient safety and data privacy. Learn more about our AI research projects and recent publications in medical imaging and artificial intelligence.

AIM-HI Lab Leadership Team

Dr. Christopher Weight - AIM-HI Lab Clinical Director and Cancer Lead at Cleveland Clinic Urology

Christopher Weight, MD

Clinical Director-Cancer Lead

Director of the AIM-HI Lab, focusing on AI applications in kidney cancer care and surgical planning.

Jack Weaver, MD

Pediatric Lead

Specializing in AI applications for pediatric kidney care and genetic disease management.

Glenn Werneburg, MD

Drug Discovery Lead

Leading research in AI applications for urinary disorders and antibiotic resistance prediction.

Dr. Jihad Kaouk - Chairman of Cleveland Clinic Department of Urology and Director of Robotic Surgery

Jihad Kaouk, MD

Chairman of Dept of Urology

Director of the Center for Robotic and Image-Guided Surgery and Vice-Chair of Enterprise Surgical Operations, pioneering innovations in robotic and minimally invasive urologic surgery.

Nicholas Heller, PhD

Computing Lead

Research associate at Cleveland Clinic department of urology, specializing in medical image computing and AI applications.

AIM-HI Lab Research: AI in Medical Imaging and Urology

AIM-HI Lab Publications: AI Research in Medical Imaging

AI Age Discrepancy: A Novel Parameter for Frailty Assessment in Kidney Tumor Patients

AI Age Discrepancy research visualization showing machine learning analysis of kidney tumor CT scans for frailty assessment

Seshadri, R., Siva, J., Bartholomew, A., Goebel, C., Wallerstein-King, G., Morato, B. L., Heller, N., Scovell, J., Campbell, R., Wood, A., Ozery-Flato, M., Barros, V., Gabrani, M., Rosen-Zvi, M., Tejpaul, R., Ramesh, V., Papanikolopoulos, N., Regmi, S., Ward, R., Abouassaly, R., Campbell, S. C., Remer, E., & Weight, C.

arXiv preprint arXiv:2407.00438 (2024)

This paper introduces AI Age Discrepancy, a novel metric derived from machine learning analysis of preoperative abdominal CT scans, as a potential indicator of frailty and postoperative risk in kidney cancer patients. This retrospective study of 599 patients from the 2023 Kidney Tumor Segmentation (KiTS) challenge dataset found that a higher AI Age Discrepancy is significantly associated with longer hospital stays and lower overall survival rates, independent of established factors.

The KiTS21 Challenge: Automatic segmentation of kidneys, renal tumors, and renal cysts in corticomedullary-phase CT

KiTS21 Challenge kidney tumor segmentation visualization showing AI algorithms for automatic kidney and tumor detection in CT scans

Heller, N., Isensee, F., Trofimova, D., Tejpaul, R., Zhao, Z., Chen, H., Wang, L., Golts, A., Khapun, D., Shats, D., Shoshan, Y., Gilboa-Solomon, F., George, Y., Yang, X., Zhang, J., Zhang, J., Xia, Y., Wu, M., Liu, Z., Walczak, E., McSweeney, S., Vasdev, R., Hornung, C., Solaiman, R., Schoephoerster, J., Abernathy, B., Wu, D., Abdulkadir, S., Byun, B., Spriggs, J., Struyk, G., Austin, A., Simpson, B., Hagstrom, M., Virnig, S., French, J., Venkatesh, N., Chan, S., Moore, K., Jacobsen, A., Austin, S., Austin, M., Regmi, S., Papanikolopoulos, N., & Weight, C.

arXiv preprint arXiv:2307.01984 (2023)

This paper presents the challenge report for the 2021 Kidney and Kidney Tumor Segmentation Challenge (KiTS21) held in conjunction with the 2021 international conference on Medical Image Computing and Computer Assisted Interventions (MICCAI). KiTS21 is a sequel to its first edition in 2019, featuring innovations in challenge design and a larger dataset. The challenge used a novel annotation method with three separate annotations for each region of interest, performed in a fully transparent setting using a web-based annotation tool. The test set was collected from an outside institution, challenging participants to develop methods that generalize well to new populations. The top-performing teams achieved significant improvements over the 2019 state of the art, approaching human-level performance.

Computer Generated R.E.N.A.L. Nephrometry Scores Yield Comparable Predictive Results to that of Human-Expert Scores in Predicting Oncologic and Perioperative Outcomes

Computer Generated R.E.N.A.L. Nephrometry Score visualization showing AI-powered kidney tumor complexity assessment using deep learning

N. Heller, R. Tejpaul, F. Isensee, T. Benidir, M. Hofmann, P. Blake, Z. Rengal, K. Moore, N. Sathianathene, A. Kalapara, J. Rosenberg, S. Peterson, E. Walczak, A. Kutikov, R.G. Uzzo, D.A. Palacios, E.M. Remer, S.C. Campbell, N. Papanikolopoulos, C.J. Weight

The Journal of Urology, Volume 207, Issue 5, May 2022 (pp. 1105–1115)

Leveraging deep learning for semantic segmentation of kidney CT scans (n = 300), this work automatically computes R.E.N.A.L. nephrometry scores ("AI-Scores") and compares them to human-expert ("H-Scores"). AI-Scores showed substantial concordance with H-Scores (Lin's ρ = 0.59) and proved equally predictive of malignancy, high tumor grade/stage, and key perioperative metrics (e.g., surgical approach, estimated blood loss). By removing manual scoring variability and saving clinician time, the AI-based system aims to facilitate broader adoption of standardized nephrometry in renal tumor care.

Public Perceptions of Artificial Intelligence and Robotics in Medicine

Public Perceptions of AI in Medicine research visualization showing survey results on patient trust in artificial intelligence and robotic surgery

Bethany Stai, Nick Heller, Sean McSweeney, Jack Rickman, Paul Blake, Ranveer Vasdev, Zach Edgerton, Resha Tejpaul, Matt Peterson, Joel Rosenberg, Arveen Kalapara, Subodh Regmi, Nikolaos Papanikolopoulos, Christopher Weight

Journal of Endourology, Volume 34, Number 10, October 2020 (pp. 1041–1048)

This survey-based study (n = 264) assessed how laypersons perceive AI and robotic surgery in oncologic care. Although most participants expressed similar trust in physician vs. AI‐based diagnoses, they were significantly more likely to trust AI for cancer detection when primed to believe AI can diagnose. Additionally, 88% mistakenly thought partial autonomy in robotic surgery already exists, and over half reported discomfort with robotic procedures—highlighting the need for clear patient counseling as AI/robotic tools become more prevalent.

Contact AIM-HI Lab

AIM-HI Lab - Artificial Intelligence in Medicine and Health Imaging

Department of Urology

Cleveland Clinic

9500 Euclid Avenue

Cleveland, Ohio 44195

Email: hellern@ccf.org

For research collaborations, media inquiries, or questions about our AI research in medical imaging and urology, please contact our team.