About

Anil Parwani, MD, PhD, MBA, is a professor at The Ohio State University, where he is involved in clinical and research activities within the Department of Pathology. His work focuses on applying artificial intelligence (AI) to address complex challenges in pathology and related medical fields, including oncology, urology, nephrology, and radiology. He is part of the AI4Path initiative at Ohio State, leading efforts to develop customized AI-driven solutions to advance clinical and research applications in medicine. Dr. Parwani's background includes extensive experience in applying AI to medical challenges, and he is actively involved in mentoring graduate students pursuing degrees in biomedical engineering and biomedical sciences. His research aims to explore the potential of AI to improve healthcare outcomes, and he collaborates with clinicians, researchers, and students to integrate AI into clinical practice and research. His contributions are centered on leveraging innovative AI techniques to enhance diagnostic and prognostic capabilities in pathology.

Research topics

• Medicine
• Computer Science
• Pathology
• Biology
• Artificial Intelligence
• Internal medicine
• Medical physics
• Radiology
• Data science
• Computer vision
• Medical emergency
• Business
• Risk analysis (engineering)
• Finance
• Family medicine
• World Wide Web
• Cancer research
• Multimedia
• Process management
• Immunology
• Medical education

Selected publications

• Inferring Clinically Relevant Molecular Subtypes of Pancreatic Cancer from Routine Histopathology Using Deep Learning

  medRxiv · 2026-01-08 · 1 citations

  articleOpen access

  Abstract Background and aims Molecular subtyping of pancreatic ductal adenocarcinoma (PDAC) into basal-like and classical has established prognostic and predictive value. However, its use in clinical practice is limited by cost, turnaround time, and tissue requirements, thereby restricting its application in the management of PDAC. We introduce PanSubNet (PANcreatic SUBtyping NETwork), an interpretable deep learning framework that predicts therapy-relevant molecular subtypes directly from standard hematoxylin and eosin (H&E)-stained whole-slide images. Methods PanSubNet was developed using data from 1 , 055 patients across two multi-institutional cohorts (PANCAN, n=846; TCGA, n=209) with paired histology and RNA sequencing data. Ground-truth labels were derived using the validated Moffitt 50-gene signature refined by GATA6 expression. The model employs dual-scale architecture that fuses cellular-level morphology with tissue-level architecture, leveraging attention mechanisms for multi-scale representation learning and transparent feature attribution. Results On internal validation within PANCAN using five-fold cross-validation, PanSubNet achieved mean area under the receiver operating characteristic curve (AUC) of 88.5% in high-confidence cases, with balanced sensitivity and specificity. External validation on the independent TCGA cohort without fine-tuning demonstrated robust generalizability (AUC 84.0% ). PanSubNet preserved and, in metastatic disease, strengthened prognostic stratification compared to RNA-seq–based labels. Prediction uncertainty linked to intermediate transcriptional states, not classification noise. Model predictions are aligned with established transcriptomic programs, differentiation markers, and DNA damage repair signatures. Conclusions By enabling rapid, cost-effective molecular stratification from routine H&E-stained slides, PanSubNet offers a clinically deployable and interpretable tool for genetic subtyping. We are gathering data from two institutions to validate and assess real-world performance, supporting integration into digital pathology workflows and advancing precision oncology for PDAC.

  PublisherOA PDFDOI

• Applications and challenges of utilizing digital pathology and AI-enabled workflows in clinical trials

  Journal of Pathology Informatics · 2026-01-01 · 4 citations

  articleOpen accessSenior author

  This is a comprehensive review on current utilization and challenges of digital pathology adoption in clinical trials and aims to provide a broad view on its impact on pathology review processes in clinical trials. It provides an overview of current pathology review practices in clinical trials and unique advantages digital pathology adoption can offer. The key areas including existing workflows, use case scenarios in different disease areas in clinical trials, including but not limited to patient identification and pre-screening, and regulatory aspects have been described with relevance. In addition, the review delves into the integration of genomics, AI, image analysis, radiology, and advanced computational pathology, to propose measures to enhance clinical trial outcomes. The current regulatory landscape around digital pathology adoption and potential future advancements in this field are also discussed as appropriate.

  PublisherDOI

• 1016 SOX17 Expression in Germ Cell Tumors

  Laboratory Investigation · 2026-03-01

  article
  PublisherDOI

• Transforming breast cancer care: the critical role of digital pathology and artificial intelligence in biomarker testing and risk stratification

  Expert Review of Molecular Diagnostics · 2026-01-02

  article
  PublisherDOI

• Digital twin manifesto for the pathology laboratory

  Diagnostic Pathology · 2025-07-17

  articleOpen access

  This manuscript presents a manifesto developed by a multifaceted board of stakeholders aimed at guiding the implementation of Digital Twin (DT) technology in pathology laboratories. DTs, already transformative in other sectors, hold substantial promise for enhancing operational efficiency, diagnostic accuracy, and quality of care in pathology. We provide a comparative analysis of traditional versus DT-enhanced workflows across critical steps including accessioning, grossing, processing, embedding, cutting, staining, scanning, diagnosis, and archiving. The framework highlights measurable gains such as up to 90% reduction in labeling errors, 20-30% improvements in slide quality, and 30-50% reductions in diagnostic turnaround time. Alongside these benefits, we address key implementation challenges including upfront infrastructure costs, workforce adaptation, and data security concerns. A practical, phased deployment strategy is proposed-centered on LIS integration, IoT sensors, AI modules, and robust data governance. Estimated setup costs for a medium-sized laboratory range between USD 100,000 and USD 200,000, with a phased rollout timeline of 12-24 months. Supporting technologies like robotic process automation (RPA), collaborative robotics, and edge computing are also discussed as enablers of successful DT adoption. The manifesto closes by identifying critical research gaps, including the need for longitudinal studies evaluating DTs' clinical and economic impacts, integration within existing hospital IT systems, and ethical implications of AI-assisted diagnostics. Through this collective vision, we provide a realistic and actionable roadmap to drive the transition toward predictive, efficient, and digitally optimized pathology laboratories.

  PublisherOA PDFDOI

• Incidence, Clinicopathologic Features, and Follow-Up Results of human epidermal growth factor receptor-2–Ultralow Breast Carcinoma

  Modern Pathology · 2025-04-22 · 6 citations

  article
  PublisherDOI

• Conditional Reprogramming: A Living Biomarker and Phenotypic Screening Drug Platform for Urological Cancer

  2025-07-14

  book-chapter

  Patient-derived and clinically relevant models including patient-derived xenografts (PDX), organoids, and conditional reprogramming (CR) of cell cultures efficiently generate numerous models and are being used in both basic and translational cancer biology. We describe our own CR technology supported by several NCI funds in translational potential of urological cancer. Specifically, CR can be used to generate clinically relevant patient-derived cell models for both bladder cancer (BC) and prostate cancer. These clinically relevant cells may be used for selection or prediction of treatment and drug discovery. In addition to cell models derived from tumor tissue specimens, we can also generate urine cancer cells from bladder cancer patients, providing a non-invasive, living biomarker for predicting patient responses and serving as a phenotypic drug screening platform.

  PublisherDOI

• Artificial intelligence entering the pathology arena in oncology: current applications and future perspectives

  Annals of Oncology · 2025-04-29 · 56 citations

  reviewOpen access

  BACKGROUND: Artificial intelligence (AI) is rapidly transforming the fields of pathology and oncology, offering novel opportunities for advancing diagnosis, prognosis, and treatment of cancer. METHODS: Through a systematic review-based approach, the representatives from the European Society for Medical Oncology (ESMO) Precision Oncology Working Group (POWG) and international experts identified studies in pathology and oncology that applied AI-based algorithms for tumour diagnosis, molecular biomarker detection, and cancer prognosis assessment. These findings were synthesised to provide a comprehensive overview of current AI applications and future directions in cancer pathology. RESULTS: The integration of AI tools in digital pathology is markedly improving the accuracy and efficiency of image analysis, allowing for automated tumour detection and classification, identification of prognostic molecular biomarkers, and prediction of treatment response and patient outcomes. Several barriers for the adoption of AI in clinical workflows, such as data availability, explainability, and regulatory considerations, still persist. There are currently no prognostic or predictive AI-based biomarkers supported by level IA or IB evidence. The ongoing advancements in AI algorithms, particularly foundation models, generalist models and transformer-based deep learning, offer immense promise for the future of cancer research and care. AI is also facilitating the integration of multi-omics data, leading to more precise patient stratification and personalised treatment strategies. CONCLUSIONS: The application of AI in pathology is poised to not only enhance the accuracy and efficiency of cancer diagnosis and prognosis but also facilitate the development of personalised treatment strategies. Although barriers to implementation remain, ongoing research and development in this field coupled with addressing ethical and regulatory considerations will likely lead to a future where AI plays an integral role in cancer management and precision medicine. The continued evolution and adoption of AI in pathology and oncology are anticipated to reshape the landscape of cancer care, heralding a new era of precision medicine and improved patient outcomes.

  PublisherOA PDFDOI

• 166 Incidence, Clinicopathological Features and HER2 FISH Results of HER2 ultra-low Breast Carcinomas

  Laboratory Investigation · 2025-03-01

  article
  PublisherDOI

• 828 Clinical Utility of Tumor-Detect AI algorithm for Detection of Prostate Cancer on Transurethral Resection Specimens

  Laboratory Investigation · 2025-03-01

  articleOpen access
  PublisherOA PDFDOI

Recent grants

• The Cooperative Human Tissue Network Midwestern Division (CHTN MWD)

  NIH · $6.1M · 2019–2029

Frequent coauthors

• Rajiv Dhir

  Shadyside Hospital

  495 shared

• Waqas Amin

  Southwest University of Science and Technology

  217 shared

• Jcm Ho

  University of Hong Kong

  212 shared

• Maria E. Arcila

  Memorial Sloan Kettering Cancer Center

  200 shared

• L Mock

  Central Connecticut State University

  200 shared

• W Jamil

  The University of Texas MD Anderson Cancer Center

  200 shared

• H. L. McLeod

  University of Bristol

  200 shared

• Rajyalakshmi Luthra

  200 shared

Labs

• AI4PathPI

  From Pixels to Prognosis: AI in Action!

Education

• Ph.D., Virology

  Ohio State University

  1993

• M.D.

  Case Western Reserve University

  1999

• Other, Anatomical and Clinical Pathology

  Johns Hopkins Hospital

  2003

• Other, Urological Pathology

  Johns Hopkins Hospital

  2004

• Other

  University of Pittsburgh

  2013

Awards & honors

• Donald A. Senhauser Chair, Department of Pathology, The Ohio…