About

Professor Vidya Arole is not mentioned in the provided page text. The page primarily details the team members, including faculty, research scientists, graduate researchers, and undergraduate researchers associated with the AI4Path Ohio State research group. The only faculty member explicitly described is Khalid Niazi, PhD, who is an Associate Professor of Pathology at The Ohio State University and the Principal Investigator of the Computational Pathology Lab, focusing on integrating artificial intelligence into medical research and clinical practice. No specific biography or research focus for Vidya Arole is provided in the text.

Research topics

• Medicine
• Biology
• Pathology
• Computer Science
• Internal medicine
• Immunology
• Computer vision
• Radiology
• Cancer research

Selected publications

• Real-world utility of Histotype Px colorectal as a prognostic and potentially predictive biomarker.

  Journal of Clinical Oncology · 2026-01-10

  article1st authorCorresponding

  215 Background: The decision to offer adjuvant chemotherapy (ACT) for patients with high-risk stage II and stage III colon cancer is fraught with challenges as most patients do not benefit from potentially toxic therapy. Histotype Px Colorectal stratifies patients into distinct risk groups by combining staging parameters with the DoMore v1 marker, a novel artificial intelligence-based digital biomarker that analyzes routine H&E-stained FFPE whole-slide images. The purpose of this study was to externally validate its prognostic performance and investigate its potential to predict adjuvant chemotherapy (ACT) benefit. Methods: This was a retrospective analysis of patients diagnosed with pathological stage II/III colon adenocarcinoma treated at Ohio State University in 2011-2024. Clinical parameters and outcome data were extracted from patient records. Blinded to clinical outcomes, anonymized digitized slides were analyzed by Histotype Px. Logrank test and Cox proportional hazards regression were used to analyze cancer-specific death (CSD). The multivariable models included age, sex, pN stage, pT stage, number of lymph nodes sampled, tumor perforation, lymphovascular invasion, perineural invasion, MSI status, and receipt of ACT. Competing risk analysis was used to calculate CSD rates. Results: Baseline characteristics of the 503 eligible patients included median age of 63 years (22-97), 54% male, 55% stage III, 61% right-sided tumors and 23% MSI, with 51% of patients receiving ACT and a median follow-up of 44 months. The DoMore v1 marker was statistically significant in both univariable (p<0.0001) and multivariable analysis with the clinicopathological markers (p=0.0010). Among the 298 patients in the Histotype Px low-risk group, 41.3% received ACT and their 5-year CSD rate was 6.1% (2.2%-12.8%) compared to 5.9% (2.7%-10.9%) for those that did not receive ACT. For the 123 Histotype Px intermediate-risk patients, 58.5% received ACT with a 5-year CSD rate of 17.5% (8.3%-29.5%) compared to 15.7% (6.2%-29.2%) without ACT. For the 81 Histotype Px high-risk patients, 76.5% received ACT with a 5-year CSD rate of 42.3% (21.9%-61.5%) compared to 58.3% (30.8%-78.1%) without ACT. In multivariable analyses, ACT benefit was observed in the high-risk group (HR 0.17, 95% CI 0.06-0.47; p=0.0007) but neither in the intermediate-risk (p=0.84) nor low-risk (p=0.16) group. Conclusions: Histotype Px Colorectal was able to improve risk stratification and showed promise as a predictive biomarker for ACT benefit in patients with stage II/III colon adenocarcinoma. Current standard-of-care ACT might not be sufficient for Histotype Px high-risk patients, while ACT might not be beneficial for Histotype Px low-risk patients.

  PublisherDOI

• <scp>AI</scp> for pathologists: a universal lymph node metastasis detection app that enhances efficiency while preserving diagnostic accuracy

  The Journal of Pathology Clinical Research · 2026-01-01

  articleOpen access

  Increasing workload combined with the shortage of pathologists is the leading cause of diagnostic errors and delays. Nonetheless, in clinical practice, pathologists often spend hours on tedious tasks such as counting mitoses and searching for lymph node micro-metastasis, which may yield unreliable results. The advent of digital pathology and the development of artificial intelligence (AI) applications (app) for image analysis have opened new possibilities for improving the efficiency and accuracy of pathologists. However, the perceived black box nature of AI has led to skepticism among many pathologists about its diagnostic capabilities, resulting in a lack of trust in AI. In addition, it is a common belief that AI applications should be limited to the areas they were trained in, which has significantly limited their generalizability. Given the homogeneous cell population of lymph nodes and overlapping of tumor morphology across different organs, we hypothesized that a lymph node metastasis detection application trained on a few organs could potentially recognize metastasis from multiple organs. We used the commercially available Visiopharm app (AI tool), initially trained on lymph node metastases from breast and colon cancer, to detect metastasis of 12 distinct types of cancer from 15 organ systems based on the analysis of 172 slides (all with corresponding immunohistochemical staining confirmation). Furthermore, by using the annotation map generated by the app as a guide, pathologists were also able to reduce the time spent searching for metastasis substantially (from 54.7 to 42.1 s per slide on average) without compromising diagnostic accuracy. With pathologists serving as the trusted gatekeepers and the development of more sophisticated image analysis applications, the use of AI can help to address the shortage of pathologists, enhance their performance and eventually improve patient care.

  PublisherOA PDFDOI

• Clinical validation of Histotype Px Colorectal in patients in a U.S. colon cancer cohort.

  Journal of Clinical Oncology · 2024-06-01 · 3 citations

  article1st authorCorresponding

  3622 Background: According to current guidelines, most patients with high-risk stage II and stage III colon cancer should receive adjuvant chemotherapy (ACT). However, risk determination is controversial and most patients do not benefit from ACT. Histotype Px Colorectal is a novel artificial intelligence-based biomarker validated for R0 stage II-III colorectal adenocarcinoma that analyzes digitized routine H&amp;E-stained FFPE tumor resections. Combined with clinical parameters, patients are stratified into distinct low, intermediate, and high-risk groups. This pilot study seeks to validate the applicability of Histotype Px Colorectal in an independent cohort from the United States. Methods: This was a retrospective analysis of patients diagnosed with pathological stage II-III colon adenocarcinoma at Ohio State University from 2016-2020. Anonymized slides were collected and digitized using the Aperio AT2 scanner. Clinical parameters and outcome data were extracted from patient records. Histotype Px Colorectal biomarker was blindly applied to each scan and subsequently linked to clinical outcomes. Statistical analysis was performed using Cox proportional hazards regression analysis. The pre-specified primary outcome was cancer-specific survival with a secondary outcome of time-to-recurrence. Results: Baseline characteristics of the 159 eligible patients included median age of 63 years (range 22-91), 52% female, 52% stage III, 64% right-sided tumors, and 31% MSI. 18% of stage II and 70% of stage III patients received ACT, respectively, with FOLFOX in 61%. Median follow-up for all patients was 54.2 months. For stage II patients, 21% were classified as intermediate-risk and 79% as low-risk. Only 6 (8%) of the 76 stage II patients had a cancer-related death with 3 of those patients classified as intermediate-risk. For stage III patients, 26% were classified as high-risk, 22% as intermediate-risk, and 52% as low-risk. 18 (22%) of the 83 stage III patients had a cancer-related death with 14 of those patients classified as high or intermediate-risk. Overall, Histotype Px Colorectal was a significant predictor of cancer-specific survival with HR=7.80 (95% CI 2.96-20.56, p&lt;0.001) for high vs. low-risk patients and 2.81 (95% CI 0.98-8.04, p=0.05) for intermediate vs. low-risk patients. In addition, it was found to be a significant predictor for time-to-recurrence with HR=7.59 (3.56-16.20, p&lt;0.001) for high vs. low-risk patients and 2.67 (1.20-5.96, p=0.02) for intermediate vs. low-risk patients. Conclusions: The findings from this study highlight the potential utility of this innovative biomarker in guiding clinical decisions regarding ACT. Further research involving a larger and more diverse patient cohort and subsequent clinical studies are planned to solidify these initial findings and to enable personalized treatment strategies based on individual risk assessments.

  PublisherDOI

• Comparing Accuracy of Helicobacter pylori Identification Using Traditional Hematoxylin and Eosin–Stained Glass Slides With Digital Whole Slide Imaging

  Laboratory Investigation · 2023 · 3 citations

  • Computer Science
  • Medicine
  • Pathology

  With advancements in the field of digital pathology, there has been a growing need to compare the diagnostic abilities of pathologists using digitized whole slide images against those when using traditional hematoxylin and eosin (H&E)-stained glass slides for primary diagnosis. One of the most common specimens received in pathology practices is an endoscopic gastric biopsy with a request to rule out Helicobacter pylori (H. pylori) infection. The current standard of care is the identification of the organisms on H&E-stained slides. Immunohistochemical or histochemical stains are used selectively. However, due to their small size (2-4 μm in length by 0.5-1 μm in width), visualization of the organisms can present a diagnostic challenge. The goal of the study was to compare the ability of pathologists to identify H. pylori on H&E slides using a digital platform against the gold standard of H&E glass slides using routine light microscopy. Diagnostic accuracy rates using glass slides vs digital slides were 81% vs 72% (P = .0142) based on H&E slides alone. When H. pylori immunohistochemical slides were provided, the diagnostic accuracy was significantly improved to comparable rates (96% glass vs 99% digital, P = 0.2199). Furthermore, differences in practice settings (academic/subspecialized vs community/general) and the duration of sign-out experience did not significantly impact the accuracy of detecting H. pylori on digital slides. We concluded that digital whole slide images, although amenable in different practice settings and teaching environments, does present some shortcomings in accuracy and precision, especially in certain circumstances and thus is not yet fully capable of completely replacing glass slide review for identification of H. pylori. We specifically recommend reviewing glass slides and/or performing ancillary stains, especially when there is a discrepancy between the degree of inflammation and the presence of microorganisms on digital images.

  PublisherOA PDFDOI

• Multiple Cutaneous Solitary Circumscribed Neuroma in a Patient with Neurofibromatosis Type 2: An “Incidentaloma” or New Association?

  International Journal of Surgical Pathology · 2022-09-21 · 1 citations

  article1st authorCorresponding

  Solitary circumscribed neuroma formerly known as palisaded encapsulated neuroma is a rare, benign neural tumor that usually presents as a painless firm nodule or papule on the face and within oral cavity, although they can occur elsewhere on the body. No association with neurofibromatosis has been reported in the literature. Herein, we report, a previously unreported unique association of neurofibromatosis type 2 (NF-2) with multiple cutaneous solitary circumscribed neuromas in a 24-year-old female. A 24-year-old female with history of NF-2 presented with two slow-growing soft-to-firm papules on the chin and forehead that had been gradually increasing in size over a period of 5 years. The papule on the chin was increasingly tender to palpation. Histologic sections demonstrated a dermal based almost encapsulated, smoothly contoured tumefactive mass composed of spindle cell proliferation with neuroid structures and foci of palisaded growth (resembling schwannoma) and intralesional cleft like spaces. By immunohistochemistry, the lesional cells were strongly and diffusely positive for S-100 and SOX10 with multifocal neurofilament expression while the "capsule" was diffusely reactive for epithelial membrane antigen. The overall features were considered prototypic for solitary circumscribed neuroma. The patient is 18-months post-surgical resection with no evidence of recurrence. In summary, we report for the first time a case of multiple solitary circumscribed neuromas in a patient with known NF2. We highlight pertinent diagnostic clues relevant to surgical pathologist to facilitate recognition (as this tumor is often mistaken for schwannoma or neurofibroma). The clinical behavior is excellent and surgical resection is considered curative.

  PublisherDOI

• Evaluating Mismatch Repair Status to Screen Clinical Advanced Breast Carcinomas for Immunotherapy: Experience From a Large Academic Institution

  Clinical Breast Cancer · 2022-01-22 · 2 citations

  article1st authorCorresponding
  PublisherDOI

• M2 tumor-associated macrophages play important role in predicting response to neoadjuvant chemotherapy in triple-negative breast carcinoma

  Breast Cancer Research and Treatment · 2021 · 24 citations

  1st authorCorresponding
  • Medicine
  • Cancer research
  • Pathology
  PublisherDOI

• Abstracts from USCAP 2021: Breast Pathology (66-147)

  Modern Pathology · 2021 · 4 citations

  • Pathology
  • Medicine
  • Biology
  PublisherOA PDFDOI

• Author Correction: A modular cGAN classification framework: Application to colorectal tumor detection

  Scientific Reports · 2020-02-06

  erratumOpen access

  An amendment to this paper has been published and can be accessed via a link at the top of the paper.

  PublisherOA PDFDOI

• Segmentation of follicles from CD8-stained slides of follicular lymphoma using deep learning

  2019-03-18 · 6 citations

  article

  Follicular Lymphoma (FL) is the second most common subtype of lymphoma in the Western World. It is a low-grade lymphoma arising from Germinal Centre (GC) B cells. The neoplasm predominantly consists of back-to-back arrangement of nodules or follicles of transformed GC B cells with the replacement of lymph node architecture and loss of normal cortex and medullary differentiation, which is preserved in non-neoplastic or reactive lymph node. There is a growing interest in studying different cell subsets inside and on the periphery of the follicles to direct curative therapies and minimize treatment-related complications. To facilitate this analysis, we develop an automated method for follicle detection from images of CD8 stained histopathological slides. The proposed method is trained on eight whole digital slides. The method is inspired by U-net to segment follicles from the whole slide images. The results on an independent dataset resulted in an average Dice similarity coefficient of 85.6% when compared to an expert pathologist’s annotations. We expect that the method will play a considerable role for comparing the ratios of different subsets of cells inside and at the periphery of the follicles.

  PublisherDOI

Frequent coauthors

• Tiansheng Shen

  The Ohio State University

  36 shared

• Vishakha Pardeshi

  Detroit Medical Center

  35 shared

• Hiro Nitta

  Roche (United States)

  35 shared

• Dhananjay Chitale

  Henry Ford Hospital

  35 shared

• Ghassan Allo

  University Hospital Cologne

  35 shared

• Phillip Williams

  35 shared

• Anil V. Parwani

  The Ohio State University

  30 shared

• Lai Wei

  Ministry of Education of the People's Republic of China

  26 shared

Labs

• Computational Pathology LabPI

Education

• M.D., Pathology

  Topiwala National Medical College

  2014

• M.D., Pathology

  BJ Government Medical College

  2014

• Other, Anatomic and Clinical Pathology

  BJGMC, Pune, India

  2011

• Other

  KEM Hospital, Mumbai, India

  2015

• Other

  The Ohio State University

  2023

• Other, Anatomic and Clinical Pathology

  The Ohio State University

  2019

• Other

  Wexner Medical Center, The Ohio State University

  2017