Resha Tejpaul
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Resha Tejpaul has a total of 115 co-authors. Here are the top co-authors by number of shared publications:
- Christopher J. Weight
Department of Urology, Integrated Surgical Institute, Cleveland Clinic, Cleveland, OH 44195, USA
7 shared publications - Nicholas Heller
Department of Urology Cleveland Clinic Cleveland OH USA
6 shared publications - Joel E. Rosenberg
University of Minnesota Medical School; University of Minnesota; Minneapolis Minnesota USA
4 shared publications - Sean McSweeney
Department of Urology, Glickman Urological and Kidney Institute, Cleveland Clinic Foundation, Cleveland, OH, USA
4 shared publications - Edward Walczak
Department of Urology, University of Minnesota, Minneapolis, MN, United States
3 shared publications - Jack Rickman
Department of Urology, University of Minnesota, Minneapolis, MN, United States
3 shared publications
Latest Publications
- Open Access
- 30 May 2025
- Published by Public Library of Science (PLoS) in PLOS ONE
- Vol. 20 (5) , e0323240
Preoperative kidney tumor risk estimation with AI: From logistic regression to transformer
We consider the problem of renal mass risk classification to support doctors in adjuvant treatment decisions following nephrectomy. Recommendation of adjuvant therapy based on the mass appearance poses two major challenges: first, morphologic patterns may sometimes overlap across subtypes of varying risks. Second, interobserver variability is large. These complexities encourage the use of computational models as accurate noninvasive tools to find relevant relationships between individual perioperative renal mass characteristics and patient risk. In addition, recent evidence highlights the importance of clinical context as a promising direction to inform treatment decisions post-nephrectomy. In this work, we aim to identify relevant clinical markers that can be predictive of renal cancer prognosis. As a starting point, we perform a clinical feature ablation study by training a logistic regression baseline model to predict renal cancer patients’ eligibility for adjuvant therapy. The training dataset consisted of medical records of 300 individuals with renal tumors who underwent partial or radical nephrectomy between 2011 and 2020. In addition, we evaluate the same task using a transformer-based model pretrained on a much larger dataset of over 300,000 clinical records of individuals from the UK Biobank. Our findings demonstrate the pretrained model’s efficacy in knowledge transfer across different populations, with radiographic data from preoperative cross-sectional imaging playing an important role in informing renal risk and treatment decisions.
- 30 May 2025
- Published by Public Library of Science (PLoS) in PLOS ONE
- Vol. 20 (5) , e0323240
Open AccessPreoperative kidney tumor risk estimation with AI: From logistic regression to transformer
We consider the problem of renal mass risk classification to support doctors in adjuvant treatment decisions following nephrectomy. Recommendation of adjuvant therapy based on the mass appearance poses two major challenges: first, morphologic patterns may sometimes overlap across subtypes of varying risks. Second, interobserver variability is large. These complexities encourage the use of computational models as accurate noninvasive tools to find relevant relationships between individual perioperative renal mass characteristics and patient risk. In addition, recent evidence highlights the importance of clinical context as a promising direction to inform treatment decisions post-nephrectomy. In this work, we aim to identify relevant clinical markers that can be predictive of renal cancer prognosis. As a starting point, we perform a clinical feature ablation study by training a logistic regression baseline model to predict renal cancer patients’ eligibility for adjuvant therapy. The training dataset consisted of medical records of 300 individuals with renal tumors who underwent partial or radical nephrectomy between 2011 and 2020. In addition, we evaluate the same task using a transformer-based model pretrained on a much larger dataset of over 300,000 clinical records of individuals from the UK Biobank. Our findings demonstrate the pretrained model’s efficacy in knowledge transfer across different populations, with radiographic data from preoperative cross-sectional imaging playing an important role in informing renal risk and treatment decisions.
- Open Access
- 4 January 2022
- Published by Frontiers Media SA in Frontiers in Digital Health
- Vol. 3, 797607
Automatic Segmentation of Kidneys and Kidney Tumors: The KiTS19 International Challenge
Purpose: Clinicians rely on imaging features to calculate complexity of renal masses based on validated scoring systems. These scoring methods are labor-intensive and are subjected to interobserver variability. Artificial intelligence has been increasingly utilized by the medical community to solve such issues. However, developing reliable algorithms is usually time-consuming and costly. We created an international community-driven competition (KiTS19) to develop and identify the best system for automatic segmentation of kidneys and kidney tumors in contrast CT and report the results.Methods: A training and test set of CT scans that was manually annotated by trained individuals were generated from consecutive patients undergoing renal surgery for whom demographic, clinical and outcome data were available. The KiTS19 Challenge was a machine learning competition hosted on grand-challenge.org in conjunction with an international conference. Teams were given 3 months to develop their algorithm using a full-annotated training set of images and an unannotated test set was released for 2 weeks from which average Sørensen-Dice coefficient between kidney and tumor regions were calculated across all 90 test cases.Results: There were 100 valid submissions that were based on deep neural networks but there were differences in pre-processing strategies, architectural details, and training procedures. The winning team scored a 0.974 kidney Dice and a 0.851 tumor Dice resulting in 0.912 composite score. Automatic segmentation of the kidney by the participating teams performed comparably to expert manual segmentation but was less reliable when segmenting the tumor.Conclusion: Rapid advancement in automated semantic segmentation of kidney lesions is possible with relatively high accuracy when the data is released publicly, and participation is incentivized. We hope that our findings will encourage further research that would enable the potential of adopting AI into the medical field.
- 4 January 2022
- Published by Frontiers Media SA in Frontiers in Digital Health
- Vol. 3, 797607
Open AccessAutomatic Segmentation of Kidneys and Kidney Tumors: The KiTS19 International Challenge
Purpose: Clinicians rely on imaging features to calculate complexity of renal masses based on validated scoring systems. These scoring methods are labor-intensive and are subjected to interobserver variability. Artificial intelligence has been increasingly utilized by the medical community to solve such issues. However, developing reliable algorithms is usually time-consuming and costly. We created an international community-driven competition (KiTS19) to develop and identify the best system for automatic segmentation of kidneys and kidney tumors in contrast CT and report the results.Methods: A training and test set of CT scans that was manually annotated by trained individuals were generated from consecutive patients undergoing renal surgery for whom demographic, clinical and outcome data were available. The KiTS19 Challenge was a machine learning competition hosted on grand-challenge.org in conjunction with an international conference. Teams were given 3 months to develop their algorithm using a full-annotated training set of images and an unannotated test set was released for 2 weeks from which average Sørensen-Dice coefficient between kidney and tumor regions were calculated across all 90 test cases.Results: There were 100 valid submissions that were based on deep neural networks but there were differences in pre-processing strategies, architectural details, and training procedures. The winning team scored a 0.974 kidney Dice and a 0.851 tumor Dice resulting in 0.912 composite score. Automatic segmentation of the kidney by the participating teams performed comparably to expert manual segmentation but was less reliable when segmenting the tumor.Conclusion: Rapid advancement in automated semantic segmentation of kidney lesions is possible with relatively high accuracy when the data is released publicly, and participation is incentivized. We hope that our findings will encourage further research that would enable the potential of adopting AI into the medical field.
- Open Access
- 30 December 2021
- Published by Wolters Kluwer Health in Journal of Urology
- Vol. 207 (5) , 1105-1115
Computer-Generated R.E.N.A.L. Nephrometry Scores Yield Comparable Predictive Results to Those of Human-Expert Scores in Predicting Oncologic and Perioperative Outcomes
Purpose:To automate R.E.N.A.L. nephrometry scoring of preoperative computed tomography (CT) scans and create an artificial intelligence generated score (AI-Score). Subsequently, to evaluate its abi...
- 30 December 2021
- Published by Wolters Kluwer Health in Journal of Urology
- Vol. 207 (5) , 1105-1115
Open AccessComputer-Generated R.E.N.A.L. Nephrometry Scores Yield Comparable Predictive Results to Those of Human-Expert Scores in Predicting Oncologic and Perioperative Outcomes
Purpose:To automate R.E.N.A.L. nephrometry scoring of preoperative computed tomography (CT) scans and create an artificial intelligence generated score (AI-Score). Subsequently, to evaluate its abi...
- 1 October 2021
- Published by Elsevier in Journal of Pediatric Urology
- Vol. 17 (5) , 736.e1-736.e6
Referral patterns for undescended testis: A 7 year comparative analysis of primary care providers
- 1 October 2021
- Published by Elsevier in Journal of Pediatric Urology
- Vol. 17 (5) , 736.e1-736.e6
Referral patterns for undescended testis: A 7 year comparative analysis of primary care providers
- Top Cited Papers
- 2 October 2020
- Published by Elsevier in Medical Image Analysis
- Vol. 67, 101821
The state of the art in kidney and kidney tumor segmentation in contrast-enhanced CT imaging: Results of the KiTS19 challenge
- 2 October 2020
- Published by Elsevier in Medical Image Analysis
- Vol. 67, 101821
Top Cited PapersThe state of the art in kidney and kidney tumor segmentation in contrast-enhanced CT imaging: Results of the KiTS19 challenge
- 1 October 2020
- Published by SAGE Publications in Journal of Endourology
- Vol. 34 (10) , 1041-1048
Public Perceptions of Artificial Intelligence and Robotics in Medicine
Objective: To understand better the public perception and comprehension of medical technology such as artificial intelligence (AI) and robotic surgery. In addition to this, to identify sensitivity to their use to ensure acceptability and quality of counseling. Subjects and Methods: A survey was conducted on a convenience sample of visitors to the MN Minnesota State Fair ( n = 264). Participants were randomized to receive one of two similar surveys. In the first, a diagnosis was made by a physician and in the second by an AI application to compare confidence in human and computer-based diagnosis. Results: The median age of participants was 45 (interquartile range 28–59), 58% were female ( n = 154) vs 42% male ( n = 110), 69% had completed at least a bachelor's degree, 88% were Caucasian ( n = 233) vs 12% ethnic minorities ( n = 31) and were from 12 states, mostly from the Upper Midwest. Participants had nearly equal trust in AI vs physician diagnoses. However, they were significantly more likely to trust an AI diagnosis of cancer over a doctor's diagnosis when responding to the version of the survey that suggested that an AI could make medical diagnoses ( p = 9.32e-06). Though 55% of respondents ( n = 145) reported that they were uncomfortable with automated robotic surgery, the majority of the individuals surveyed (88%) mistakenly believed that partially autonomous surgery was already happening. Almost all (94%, n = 249) stated that they would be willing to pay for a review of medical imaging by an AI if available. Conclusion: Most participants express confidence in AI providing medical diagnoses, sometimes even over human physicians. Participants generally express concern with surgical AI, but they mistakenly believe that it is already being performed. As AI applications increase in medical practice, health care providers should be cognizant of the potential amount of misinformation and sensitivity that patients have to how such technology is represented.
- 1 October 2020
- Published by SAGE Publications in Journal of Endourology
- Vol. 34 (10) , 1041-1048
Public Perceptions of Artificial Intelligence and Robotics in Medicine
Objective: To understand better the public perception and comprehension of medical technology such as artificial intelligence (AI) and robotic surgery. In addition to this, to identify sensitivity to their use to ensure acceptability and quality of counseling. Subjects and Methods: A survey was conducted on a convenience sample of visitors to the MN Minnesota State Fair ( n = 264). Participants were randomized to receive one of two similar surveys. In the first, a diagnosis was made by a physician and in the second by an AI application to compare confidence in human and computer-based diagnosis. Results: The median age of participants was 45 (interquartile range 28–59), 58% were female ( n = 154) vs 42% male ( n = 110), 69% had completed at least a bachelor's degree, 88% were Caucasian ( n = 233) vs 12% ethnic minorities ( n = 31) and were from 12 states, mostly from the Upper Midwest. Participants had nearly equal trust in AI vs physician diagnoses. However, they were significantly more likely to trust an AI diagnosis of cancer over a doctor's diagnosis when responding to the version of the survey that suggested that an AI could make medical diagnoses ( p = 9.32e-06). Though 55% of respondents ( n = 145) reported that they were uncomfortable with automated robotic surgery, the majority of the individuals surveyed (88%) mistakenly believed that partially autonomous surgery was already happening. Almost all (94%, n = 249) stated that they would be willing to pay for a review of medical imaging by an AI if available. Conclusion: Most participants express confidence in AI providing medical diagnoses, sometimes even over human physicians. Participants generally express concern with surgical AI, but they mistakenly believe that it is already being performed. As AI applications increase in medical practice, health care providers should be cognizant of the potential amount of misinformation and sensitivity that patients have to how such technology is represented.
- 20 May 2020
- Published by American Society of Clinical Oncology (ASCO) in Journal of Clinical Oncology
- Vol. 38 (15_suppl) , 5074
CT-based radiomic classifier of primary renal tumors to distinguish between metastatic and non-metastatic disease.
5074 Background: Existing clinicopathological tools are unable to accurately identify renal cell carcinoma (RCC) patients who will develop metastases after surgery. As a result, it is unclear how long and how often to follow-up patients post-operatively. Tumor macropathology, as assayed by CT scanning, represents the sum product of tumor biology and microenvironment. We hypothesized that quantitative tumor features extracted from CT scans (termed radiomics) could discriminate between metastatic and non-metastatic RCCs. Methods: This retrospective study incorporated three cohorts of clear-cell RCC patients (n = 279, from TCGA, CPTAC and KiTS19 datasets) treated with nephrectomy. The study cohort was sub-divided into metastatic (n = 54, M1 at diagnosis or recurrence after surgery), high metastatic risk/HMR (n = 85, N1, T3-4, T2G3/4, T1G4) or low metastatic risk/LMR (n = 140, absence of these features) subsets. 3D primary tumor segmentation of arterial contrast CT scans was performed by trained investigators. Features were extracted using pyRadiomics 2.2.0 (n = 839) with gray value and voxel size normalization. For random forest (RF) model training, the cohort was randomly split into training (75%) and validation (25%) sets. Results: Multidimensional clustering of radiomic features by t-SNE analysis showed that metastatic and HMR tumors predominantly cluster together, while LMR tumors cluster separately. Consistent with this, there were no differentially regulated radiomic features (DR-features) between HMR and metastatic tumors. In contrast, we identified 26 DR-features (adjusted p-value < 0.05) between presumed-metastatic (n = 139, HMR and metastatic tumors) and LMR tumors, which were then used as input to a RF binary classifier. In the training set, the trained classifier discriminated between presumed-metastatic and LMR tumors with bootstrapped AUC = 0.81. In the validation set, the classifier discriminated subsets with AUC = 0.80. Conclusions: High-risk and metastatic tumors have similar radiomic properties, suggesting common biology driving metastasis in RCC. We propose a novel radiomic classifier that accurately distinguishes between presumed-metastatic and low-risk tumors. Further work will assess whether this tool can identify patients with micrometastatic disease at diagnosis, who may benefit from adjuvant therapy or closer, long-term surveillance.
- 20 May 2020
- Published by American Society of Clinical Oncology (ASCO) in Journal of Clinical Oncology
- Vol. 38 (15_suppl) , 5074
CT-based radiomic classifier of primary renal tumors to distinguish between metastatic and non-metastatic disease.
5074 Background: Existing clinicopathological tools are unable to accurately identify renal cell carcinoma (RCC) patients who will develop metastases after surgery. As a result, it is unclear how long and how often to follow-up patients post-operatively. Tumor macropathology, as assayed by CT scanning, represents the sum product of tumor biology and microenvironment. We hypothesized that quantitative tumor features extracted from CT scans (termed radiomics) could discriminate between metastatic and non-metastatic RCCs. Methods: This retrospective study incorporated three cohorts of clear-cell RCC patients (n = 279, from TCGA, CPTAC and KiTS19 datasets) treated with nephrectomy. The study cohort was sub-divided into metastatic (n = 54, M1 at diagnosis or recurrence after surgery), high metastatic risk/HMR (n = 85, N1, T3-4, T2G3/4, T1G4) or low metastatic risk/LMR (n = 140, absence of these features) subsets. 3D primary tumor segmentation of arterial contrast CT scans was performed by trained investigators. Features were extracted using pyRadiomics 2.2.0 (n = 839) with gray value and voxel size normalization. For random forest (RF) model training, the cohort was randomly split into training (75%) and validation (25%) sets. Results: Multidimensional clustering of radiomic features by t-SNE analysis showed that metastatic and HMR tumors predominantly cluster together, while LMR tumors cluster separately. Consistent with this, there were no differentially regulated radiomic features (DR-features) between HMR and metastatic tumors. In contrast, we identified 26 DR-features (adjusted p-value < 0.05) between presumed-metastatic (n = 139, HMR and metastatic tumors) and LMR tumors, which were then used as input to a RF binary classifier. In the training set, the trained classifier discriminated between presumed-metastatic and LMR tumors with bootstrapped AUC = 0.81. In the validation set, the classifier discriminated subsets with AUC = 0.80. Conclusions: High-risk and metastatic tumors have similar radiomic properties, suggesting common biology driving metastasis in RCC. We propose a novel radiomic classifier that accurately distinguishes between presumed-metastatic and low-risk tumors. Further work will assess whether this tool can identify patients with micrometastatic disease at diagnosis, who may benefit from adjuvant therapy or closer, long-term surveillance.
- Open Access
Public Perceptions of Artificial Intelligence and Robotics in Medicine
Objective: To understand better the public perception and comprehension with medical technology such as artificial intelligence and robotic surgery. Additionally, to identify sensitivity to, and comfort with, the use of AI and robotics in medicine a in order to ensure acceptability and quality of counseling and to guide future development. Subjects and Methods: A survey was conducted on a convenience sample of visitors to the Minnesota State Fair (n = 264). The survey investigated participant beliefs on the capabilities of AI and robotics in medicine and their comfort with such technology. Participants were randomized to receive one of two similar surveys. In the first a diagnosis was made by a physician and in the second by an AI application in order to compare confidence in human and computer-based diagnosis. Results: The median age of participants was 45 (IQR 28-59), 58% were female (n=154) vs. 42% male (n=110), 69% had completed at least a bachelor’s degree, 88% were Caucasian (n=233) vs. 12% ethnic minorities (n=31) and were from 12 states in the US with most from the Upper Midwest. Participants had nearly equal trust in AI vs. physician diagnoses, however, they were significantly more likely to trust an AI diagnosis of cancer over a doctor’s diagnosis when responding to the version of the survey that suggested an AI could make medical diagnosis (p = 9.32e-06). Though 55% of respondents (n=145) reported they were uncomfortable with automated robotic surgery the majority of the individuals surveyed (88%) mistakenly believed that partially autonomous surgery was already being performed. Almost all (94%) stated they would be willing to pay for an AI to review their medical imaging, if available. Conclusion: Most participants express confidence in AI providing medical diagnoses, sometimes even over human physicians. Participants generally expressed concern with surgical AI, but mistakenly believe it is already happening. As AI applications make their way into medical practice, health care providers should be cognizant of patient misconceptions and the sensitivity that patients have to how such technology is represented.
Open AccessPublic Perceptions of Artificial Intelligence and Robotics in Medicine
Objective: To understand better the public perception and comprehension with medical technology such as artificial intelligence and robotic surgery. Additionally, to identify sensitivity to, and comfort with, the use of AI and robotics in medicine a in order to ensure acceptability and quality of counseling and to guide future development. Subjects and Methods: A survey was conducted on a convenience sample of visitors to the Minnesota State Fair (n = 264). The survey investigated participant beliefs on the capabilities of AI and robotics in medicine and their comfort with such technology. Participants were randomized to receive one of two similar surveys. In the first a diagnosis was made by a physician and in the second by an AI application in order to compare confidence in human and computer-based diagnosis. Results: The median age of participants was 45 (IQR 28-59), 58% were female (n=154) vs. 42% male (n=110), 69% had completed at least a bachelor’s degree, 88% were Caucasian (n=233) vs. 12% ethnic minorities (n=31) and were from 12 states in the US with most from the Upper Midwest. Participants had nearly equal trust in AI vs. physician diagnoses, however, they were significantly more likely to trust an AI diagnosis of cancer over a doctor’s diagnosis when responding to the version of the survey that suggested an AI could make medical diagnosis (p = 9.32e-06). Though 55% of respondents (n=145) reported they were uncomfortable with automated robotic surgery the majority of the individuals surveyed (88%) mistakenly believed that partially autonomous surgery was already being performed. Almost all (94%) stated they would be willing to pay for an AI to review their medical imaging, if available. Conclusion: Most participants express confidence in AI providing medical diagnoses, sometimes even over human physicians. Participants generally expressed concern with surgical AI, but mistakenly believe it is already happening. As AI applications make their way into medical practice, health care providers should be cognizant of patient misconceptions and the sensitivity that patients have to how such technology is represented.