GastroMalign: Vision Transformer-Based Framework for Early Detection and Malignancy-Risk Stratification for High-Risk Gastrointestinal Lesions
: GastroMalign delivers an interpretable, progression-aware AI framework for GI lesion risk stratification that outperforms existing CNN- and transformer-based models. Clinically, GastroMalign is intended as an adjunct decision-support tool during endoscopic review to standardize lesion risk stratification (benign to malignant spectrum), support management decisions (biopsy vs. resection vs. surveillance), and reduce operator-dependent variability by pairing ordinal risk outputs with interpretable visual explanations.
Authors
- Gautam Maddineni (ORCID: https://orcid.org/0009-0007-9492-2733)
- Sri Harsha Boppana
- Pradeep Yarra (ORCID: https://orcid.org/0000-0003-4239-5808)
- Medha Sharath (ORCID: https://orcid.org/0000-0002-5151-1615)
- Raja Chandra Chakinala (ORCID: https://orcid.org/0000-0002-8547-2917)
- C. David Mintz (ORCID: https://orcid.org/0000-0001-9278-4380)
- Sachin Sravan Kumar Komati
- Aditya Chandrashekar
Institutions
- Creighton University (US)
- Johns Hopkins University (US)
- The University of Texas at San Antonio Health Science Center (US)
- Florida International University (US)
- SUNY Upstate Medical University (US)
- Johns Hopkins Medicine (US)
- Nassau University Medical Center (US)
- Guthrie Robert Packer Hospital (US)
- Bangalore Medical College and Research Institute (IN)
Publication Details
- Journal
- Journal of Clinical Medicine
- Published
- 2026-04-02
- DOI
- https://doi.org/10.3390/jcm15072701
- Primary Topic
- Colorectal Cancer Screening and Detection
- Type
- article
- Field-Weighted Citation Impact
- 0.00