About

Inderbir S. Gill is a professor involved in research at the Keck School of Medicine of USC. The specific research focus, background, and key contributions of Professor Gill are not detailed in the provided page text.

Research topics

• Medicine
• Computer Science
• Internal medicine
• Artificial Intelligence
• Medical physics
• Machine Learning
• Radiology
• Urology
• Data science
• Surgery
• Environmental health

Selected publications

• Image Imputation with conditional generative adversarial networks captures clinically relevant imaging features on computed tomography

  PLOS Digital Health · 2025-08-13

  articleOpen accessCorresponding

  Kidney cancer is among the top 10 most common malignancies in adults, and is commonly evaluated with four-phase computed tomography (CT) imaging. However, the presence of missing or corrupted images remains a significant problem in medical imaging that impairs the detection, diagnosis, and treatment planning of kidney cancer. Deep learning approaches through conditional generative adversarial networks (cGANs) have recently shown technical promise in the task of imputing missing imaging data from these four-phase studies. In this study, we explored the clinical utility of these imputed images. We utilized a cGAN trained on 333 patients, with the task of the cGAN being to impute the image of any phase given the other three phases. We tested the clinical utility on the imputed images of the 37 patients in the test set by manually extracting 21 clinically relevant imaging features and comparing them to their ground truth counterpart. All 13 categorical clinical features had greater than 85% agreement rate between true images and their imputed counterparts. This high accuracy is maintained when stratifying across imaging phases. Imputed images also show good agreement with true images in select radiomic features including mean intensity and enhancement. Imputed images possess the features characteristic of benign or malignant diagnosis at an equivalent rate to true images. In conclusion, imputed images from cGANs have large potential for clinical use due to their ability to retain clinically relevant qualitative and quantitative features.

  PublisherDOI

• Supplementary Table 1 from <i>SETD2</i> Deficiency Confers Sensitivity to Dual Inhibition of DNA Methylation and PARP in Kidney Cancer

  2025-12-17

  articleOpen access

  <p>Supplementary Table 1</p>

  PublisherDOI

• Oncologic Outcomes of Template Versus Radioguided Salvage Lymph Node Dissection for Node-only Recurrent Prostate Cancer on Prostate-specific Membrane Antigen Positron Emission Tomography Scan: Results from a Multi-institutional Collaboration

  European Urology Focus · 2025-08-19 · 3 citations

  article
  PublisherDOI

• Awareness and use of generative AI-powered tools: results of one-year follow-up prospective cross-sectional global survey

  Minerva Urology and Nephrology · 2025-04-15 · 6 citations

  article

  BACKGROUND: Generative AI (GenAI) frameworks, such as generative pre-trained transformer (GPTs) and large language models (LLMs), promise to transform clinical and research practices. Informed human opinion is key to guiding appropriate technological development and task refinement. Detailed data on how GPTs/LLMs powered-Chatbots usage, perceived risks and benefits among physicians has evolved over time and their impact on clinical and academic activities remain unclear. The aim of this study is to assess how the use of GPTs/LLMs chatbots by professionals working in urology has changed over time in the setting of academic and clinical activities. METHODS: , 2023) and re-deployment of the survey 12 months after chi square and t-test were used to compare categorical and continuous variables. RESULTS: A total of 129 participants completed the second survey. Eighty-six percent of participants reported having used any GPTs/LLMs chatbot for academic tasks, a significant increase from the previous survey (52.4%; P<0.001). When asked if they were using GPTs/LLMs chatbots more in academic settings compared to one year prior, 70.1% of participants answered affirmatively. Participants, when asked about the use of GPT/LLMs in particular clinical tasks after one year, reported less frequent use for deciding treatment options (18.6% vs. 31.0%; P=0.03) and patient follow-up care (10.1% vs. 21.4%; P=0.02). When participants were asked if they were using LLM chatbots more in clinical settings compared to one year before, 35.6% answered affirmatively. CONCLUSIONS: GPTs/LLMs have a consolidated role in academic tasks, with increasing usage, while some resistance to their use in clinical practice remains. These results are relevant for driving the human-centered development of GenAI technology.

  PublisherDOI

• Radiogenomic correlation of hypoxia-related biomarkers in clear cell renal cell carcinoma

  Journal of Cancer Research and Clinical Oncology · 2025-06-11 · 3 citations

  articleOpen access

  PURPOSE: This study aimed to evaluate radiomic models' ability to predict hypoxia-related biomarker expression in clear cell renal cell carcinoma (ccRCC). METHODS: Clinical and molecular data from 190 patients were extracted from The Cancer Genome Atlas-Kidney Renal Clear Cell Carcinoma dataset, and corresponding CT imaging data were manually segmented from The Cancer Imaging Archive. A panel of 2,824 radiomic features was analyzed, and robust, high-interscanner-reproducibility features were selected. Gene expression data for 13 hypoxia-related biomarkers were stratified by tumor grade (1/2 vs. 3/4) and stage (I/II vs. III/IV) and analyzed using Wilcoxon rank sum test. Machine learning modeling was conducted using the High-Performance Random Forest (RF) procedure in SAS Enterprise Miner 15.1, with significance at P < 0.05. RESULTS: Descriptive univariate analysis revealed significantly lower expression of several biomarkers in high-grade and late-stage tumors, with KLF6 showing the most notable decrease. The RF model effectively predicted the expression of KLF6, ETS1, and BCL2, as well as PLOD2 and PPARGC1A underexpression. Stratified performance assessment showed improved predictive ability for RORA, BCL2, and KLF6 in high-grade tumors and for ETS1 across grades, with no significant performance difference across grade or stage. CONCLUSION: The RF model demonstrated modest but significant associations between texture metrics derived from clinical CT scans, such as GLDM and GLCM, and key hypoxia-related biomarkers including KLF6, BCL2, ETS1, and PLOD2. These findings suggest that radiomic analysis could support ccRCC risk stratification and personalized treatment planning by providing non-invasive insights into tumor biology.

  PublisherOA PDFDOI

• Readability Optimization of Layperson Summaries in Urological Oncology Clinical Trials: Outcomes from the BRIDGE-AI 8 Study

  Preprints.org · 2025-10-11

  preprintOpen access

  Accessible health information is essential to promote patient engagement and informed participation in clinical research. Brief summaries on ClinicalTrials.gov are indented for lay people, however are often written at a reading level that is too advanced for the public. This study evaluated the performance of a Generative Artificial Intelligence (GAI) powered tool - Pub2Post-, in producing readable and complete layperson brief summaries for urologic oncology clinical trials. Twenty actively recruiting clinical trials on prostate, bladder, kidney, and testis cancers were retrieved from ClinicalTrials.gov. For each, a GAI-generated summary was produced and compared with its publicly available counterpart. Readability indices, grade-level indicators, and text metrics were analyzed alongside content inclusion across eight structural domains. GAI-generated summaries demonstrated markedly improved readability (mean FRES 73.3 ± 3.5 vs. 17.0 ± 13.1; p &amp;amp;lt; 0.0001), aligning with the recommended middle-school reading level, and achieved 100% inclusion of guideline-defined content elements. GAI summaries exhibited simpler syntax and reduced lexical complexity, supporting improved comprehension. These findings suggest that GAI tools such as Pub2Post can generate patient-facing summaries that are both accessible and comprehensive.

  PublisherOA PDFDOI

• Enhancing Readability of Lay Abstracts and Summaries for Urologic Oncology Literature Using Generative Artificial Intelligence: BRIDGE-AI 6 Randomized Controlled Trial

  JCO Clinical Cancer Informatics · 2025-09-01 · 3 citations

  article

  PURPOSE To evaluate a generative artificial intelligence (GAI) framework for creating readable lay abstracts and summaries (LASs) of urologic oncology research, while maintaining accuracy, completeness, and clarity, for the purpose of assessing their comprehension and perception among patients and caregivers. METHODS Forty original abstracts (OAs) on prostate, bladder, kidney, and testis cancers from leading journals were selected. LASs were generated using a free GAI tool, with three versions per abstract for consistency. Readability was compared with OAs using validated metrics. Two independent reviewers assessed accuracy, completeness, and clarity and identified AI hallucinations. A pilot study was conducted with 277 patients and caregivers randomly assigned to receive either OAs or LASs and complete comprehension and perception assessments. RESULTS Mean GAI-generated LAS generation time was &lt;10 seconds. Across 600 sections generated, readability and quality metrics were consistent ( P &gt; .05). Quality scores ranged from 85% to 100%, with hallucinations in 1% of sections. The best test showed significantly better readability (68.9 v 25.3; P &lt; .001), grade level, and text metrics compared with the OA. Methods sections had slightly lower accuracy (85% v 100%; P = .03) and trifecta achievement (82.5% v 100%; P = .01), but other sections retained high quality (≥92.5%; P &gt; .05). GAI-generated LAS recipients scored significantly better in comprehension and most perception-based questions ( P &lt; .001) with LAS being the only consistently significant predictor ( P &lt; .001). CONCLUSION GAI-generated LASs for urologic oncology research are highly readable and generally preserve the quality of the OAs. Patients and caregivers demonstrated improved comprehension and more favorable perceptions of LASs compared with OAs. Human oversight remains essential to ensure the accurate, complete, and clear representations of the original research.

  PublisherDOI

• The Current State of Artificial Intelligence for Benign Prostatic Hyperplasia

  European Urology Focus · 2025-07-25 · 1 citations

  review
  PublisherDOI

• GUSL: A Novel and Efficient Machine Learning Model for Prostate Segmentation on MRI

  ArXiv.org · 2025-06-30

  preprintOpen access

  Prostate and zonal segmentation is a crucial step for clinical diagnosis of prostate cancer (PCa). Computer-aided diagnosis tools for prostate segmentation are based on the deep learning (DL) paradigm. However, deep neural networks are perceived as "black-box" solutions by physicians, thus making them less practical for deployment in the clinical setting. In this paper, we introduce a feed-forward machine learning model, named Green U-shaped Learning (GUSL), suitable for medical image segmentation without backpropagation. GUSL introduces a multi-layer regression scheme for coarse-to-fine segmentation. Its feature extraction is based on a linear model, which enables seamless interpretability during feature extraction. Also, GUSL introduces a mechanism for attention on the prostate boundaries, which is an error-prone region, by employing regression to refine the predictions through residue correction. In addition, a two-step pipeline approach is used to mitigate the class imbalance, an issue inherent in medical imaging problems. After conducting experiments on two publicly available datasets and one private dataset, in both prostate gland and zonal segmentation tasks, GUSL achieves state-of-the-art performance among other DL-based models. Notably, GUSL features a very energy-efficient pipeline, since it has a model size several times smaller and less complexity than the rest of the solutions. In all datasets, GUSL achieved a Dice Similarity Coefficient (DSC) performance greater than $0.9$ for gland segmentation. Considering also its lightweight model size and transparency in feature extraction, it offers a competitive and practical package for medical imaging applications.

  PublisherOA PDFDOI

• Supplementary Table 2 from &lt;i&gt;SETD2&lt;/i&gt; Deficiency Confers Sensitivity to Dual Inhibition of DNA Methylation and PARP in Kidney Cancer

  2025-12-17

  articleOpen access

  &lt;p&gt;Supplementary Table 2&lt;/p&gt;

  PublisherDOI

Recent grants

• Using DNA methylation markers to improve the predictive accuracy and utility of needle biopsiesfor determining prostate cancer aggressiveness

  NIH · $395k · 2016–2019

• Diagnosing clinically-significant prostate cancer in African American men: Systematic random versus MR-image-fusion guided biopsy

  NIH · $596k · 2016–2020

• Diagnosing clinically-significant prostate cancer in African American men: Systematic random versus MR-image-fusion guided biopsy

  NIH · $1.5M · 2016–2022

Frequent coauthors

• Mihir Desai

  University of Southern California

  561 shared

• Osamu Ukimura

  257 shared

• André Luís de Castro Abreu

  257 shared

• Giovanni Cacciamani

  University of Southern California

  251 shared

• Jihad Kaouk

  Cleveland Clinic

  231 shared

• Monish Aron

  University of Southern California

  228 shared

• Monish Aron

  University of Southern California

  201 shared

• André Berger

  182 shared

Education

• M.D., Urology

  University of Alberta

  1987

• Other, Urology

  University of California, Los Angeles

  1991

• Other, Urology

  University of California, San Francisco

  1992

• Ph.D., Biochemistry

  University of Alberta

  1983

• B.S., Biochemistry

  University of Alberta

  1979