Interpretable Gallbladder Ultrasound Diagnosis: A Lightweight Web-Mobile Software Platform with Real-Time XAI
Fuyad Hasan Bhoyan, Prashanta Sarker, Parsia Noor Ethila, Md. Emon Hossain, Md Kaviul Hossain, Md Humaion Kabir Mehedi
TL;DR
The study presents a lightweight, interpretable AI solution for gallbladder ultrasound diagnosis by integrating MobResTaNet into a web-mobile platform that delivers real-time predictions across ten classes with XAI visualizations. Using two public datasets, it achieves up to $99.85\%$ accuracy with only $2.24M$ parameters, and provides Grad-CAM, SHAP, and LIME explanations to support clinical trust. The system emphasizes accessibility, reproducibility via Docker, and potential integration into PACS/RIS, aiming to standardize triage and enable point-of-care decision support. While not yet certified as a medical device, the approach demonstrates significant practical impact for radiology training, clinical research, and scalable deployment in diverse healthcare settings, with ongoing work to improve generalization and workflow integration.
Abstract
Early and accurate detection of gallbladder diseases is crucial, yet ultrasound interpretation is challenging. To address this, an AI-driven diagnostic software integrates our hybrid deep learning model MobResTaNet to classify ten categories, nine gallbladder disease types and normal directly from ultrasound images. The system delivers interpretable, real-time predictions via Explainable AI (XAI) visualizations, supporting transparent clinical decision-making. It achieves up to 99.85% accuracy with only 2.24M parameters. Deployed as web and mobile applications using HTML, CSS, JavaScript, Bootstrap, and Flutter, the software provides efficient, accessible, and trustworthy diagnostic support at the point of care