Year: 2025
Type: article
Abstract: Artificial Intelligence (AI) has seen rapid evolution over the past decade, significantly impacting various sectors, particularly healthcare. One of its most transformative applications is in medical imaging, where AI models have shown promise in detecting and classifying diseases from X-rays, MRIs, and CT scans. However, challenges such as limited expert availability, diagnostic delays, and interpretability issues persist, especially in low-resource settings. To address these gaps, this study proposes a cloud-deployable diagnostic support system that integrates deep learning-based image analysis with Google’s Gemini large language model (LLM) to provide accurate, explainable medical image interpretations. The system, built using Streamlit, allows users to upload medical images, receive visual heatmaps and textual diagnostic summaries, and download complete reports. Experimental evaluation using annotated datasets demonstrates high accuracy in anomaly detection and strong alignment with expert diagnoses, highlighting the tool’s potential as a decision-support aid for clinicians.
Authors: Rini Sharon, Dr. Puneeth G J
Institution: Visvesvaraya Technological University
Language: English
Subfield: Health Informatics
Field: Medicine
Domain: Health Sciences
Open Access status: diamond
OpenAlex ID: W4414444172