Abstract
Inflammatory bowel disease (IBD) requires frequent imaging-based assessment, yet interpretation of modalities such as wireless capsule endoscopy (WCE) and intestinal ultrasound remains heavily dependent on specialist expertise. Vision-Language Models (VLMs) demonstrate significant potential in multimodal medical image analysis, but their clinical adoption is hindered by their insufficient domain-specific reasoning, susceptibility to hallucination, scarcity of high quality training data in fine-grained diagnostics and limited interpretability. We introduce ARISE (Adaptive Agentic Reasoning with Image-grounded Self-Evaluation), an autonomous planning framework that models few-shot medical image understanding as a sequential agentic workflow. ARISE structures agent execution into a transparent 5-stage workflow: hypothesis generation, image-grounded evidence summarization, evidence-conditioned refinement, symbolic verification, and final diagnosis. We apply ARISE to IBD assessment across two independent patient cohorts: wireless capsule endoscopy (WCE) images for Crohn's disease and B-mode ultrasound data for ulcerative colitis. ARISE consistently improves diagnostic performance over baseline VLMs while exposing where reasoning succeeds or fails, providing a more interpretable basis for clinical decision support and realistic deployment.
Keywords
Subject
Publication details
- Journal
- Not available
- Open access
- Green open access
Cite this article
APA 7
Banerjee, P., Shah, A., Wu, J., Rahman, M. M., Mohanty, S., Kurada, S., & Wachs, J. P. (2026). ARISE: Adaptive Agentic Reasoning with Image-grounded Self-Evaluation for Interpretable IBD Assessment. https://omanscience.com/en/articles/arise-adaptive-agentic-reasoning-with-image-grounded-self-evaluation-for-interpretable-ibd-assessment
MLA 9
Banerjee, Pronoma, et al. "ARISE: Adaptive Agentic Reasoning with Image-grounded Self-Evaluation for Interpretable IBD Assessment." https://omanscience.com/en/articles/arise-adaptive-agentic-reasoning-with-image-grounded-self-evaluation-for-interpretable-ibd-assessment.
Chicago (author–date)
Banerjee, Pronoma, Anuva Shah, Jason Wu, Md. Masudur Rahman, Sanjay Mohanty, Satya Kurada, and Juan P. Wachs. 2026. "ARISE: Adaptive Agentic Reasoning with Image-grounded Self-Evaluation for Interpretable IBD Assessment." https://omanscience.com/en/articles/arise-adaptive-agentic-reasoning-with-image-grounded-self-evaluation-for-interpretable-ibd-assessment.
Harvard
Banerjee, P., Shah, A., Wu, J., Rahman, M. M., Mohanty, S., Kurada, S. and Wachs, J. P. (2026) 'ARISE: Adaptive Agentic Reasoning with Image-grounded Self-Evaluation for Interpretable IBD Assessment', Available at: https://omanscience.com/en/articles/arise-adaptive-agentic-reasoning-with-image-grounded-self-evaluation-for-interpretable-ibd-assessment.
Vancouver
Banerjee P, Shah A, Wu J, Rahman MM, Mohanty S, Kurada S, et al. ARISE: Adaptive Agentic Reasoning with Image-grounded Self-Evaluation for Interpretable IBD Assessment. https://omanscience.com/en/articles/arise-adaptive-agentic-reasoning-with-image-grounded-self-evaluation-for-interpretable-ibd-assessment
IEEE
P. Banerjee, A. Shah, J. Wu, M. M. Rahman, S. Mohanty, S. Kurada, and J. P. Wachs, "ARISE: Adaptive Agentic Reasoning with Image-grounded Self-Evaluation for Interpretable IBD Assessment," https://omanscience.com/en/articles/arise-adaptive-agentic-reasoning-with-image-grounded-self-evaluation-for-interpretable-ibd-assessment.