Fine-grained Abnormality Detection and Natural Language Description of Medical CT Images Using Large Language Models
Journal Title: International Journal of Innovative Research in Computer Science and Technology - Year 2025, Vol 13, Issue 1
Abstract
Medical report generation demands accurate abnormality detection and precise description generation from CT images. While large language models have shown promising results in natural language processing tasks, their application in medical imaging analysis faces challenges due to the complexity of fine-grained feature detection and the requirement for domain-specific knowledge. This paper presents a novel framework integrating large language models with specialized medical image processing techniques for fine-grained abnormality detection and natural language description generation. Our approach incorporates a multi-modal knowledge enhancement module and a hierarchical attention mechanism to bridge the gap between visual understanding and textual description. The framework employs an adapter-based architecture for efficient domain adaptation and introduces a medical knowledge-enhanced loss function to improve description accuracy. Experimental results on three public datasets demonstrate the effectiveness of our approach, achieving 94.6% detection accuracy and a BLEU-4 score of 0.421 for description generation, surpassing current state-of-the-art methods. The system shows particular strength in handling subtle abnormalities, with a 91.2% average precision in fine-grained detection tasks. Comprehensive ablation studies validate the contribution of each component, while qualitative analysis demonstrates the clinical relevance of generated descriptions. The proposed framework represents a significant advancement in automated medical image analysis, offering potential benefits for clinical workflow optimization and diagnostic support.
Authors and Affiliations
Zhongwen Zhou , Siwei Xia , Mengying Shu , Hong Zhou
Keywords
Related Articles
- EP ID EP753591
- DOI 10.55524/ijircst.2024.12.6.8
- Views 12
- Downloads 0
Unlocking Athletic Potential The Athle-E-Team Software Solution
The "Athle-E-Team" project is an innovative collaborative sports platform designed to revolutionize the way athletes connect and engage in sports within their local communities. With a focus on enhancing the overall spor...
Experimental Investigation of Three Phase Flow (Liquid-Gas-Solid) In Horizontal Pipe
The study of three phase flow in horizontal and vertical pipe are important phenomena in oil and gas industry due to extracting process involve liquid, solid and gas phase. The effect of the particle amount, the discharg...
Quality Assessment of Ground Water in Kashmir
The current research examines the quality of ground water in Kashmir (J&K), India, for human consumption and other purposes. For water quality testing, a total of six sampling sites in the research region were chosen. Pa...
Security in Smart Home Development: A Review
A clever home or structure is a modern house or construction with special organized wiring that enables residents to control or program a variety of automatic household electrical devices remotely with a single order. Tr...
Maximum Power Point Tracking Algorithms Under Partial Shading Condition
High and rising fuel consumption has occurred in past times. resulted in enormous growth in renewable energy generation and consumption. As economies Photovoltaic (PV) solar is becoming more popular as the world's intere...