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 26
- Downloads 0
Literature Survey for IoT Based Smart Home Automation: A Comparative Analysis
Since a few years, smart devices have become an integral part of our daily lives. As a result, on smart devices, offering facilities and security is becoming more important. The goal of this article is to create a home a...
A Study on Prevention of Soil Erosion in Hilly Region Using Jute Footrub Mats
Topsoil erosion is the most common issues in today’s world related to soil distresses. Soil erosion can cause contamination of drinking water, disturbs ecosystem of lakes and other water bodies and can cause landslides p...
Cloud Learning For Virtual Campus
Taking in mind the growing Cloud Computing technology in every field including education and it’s becoming an adoptable technology for many of the organizations with its dynamic scalability and usage of virtualized resou...
A Novel Solution to the Synchronization Problem of CAN
One of the main problems in synchronous digital system design is synchronization of different clocks in the system. Obviously, this problem is always present in CAN bus related equipment. The problem is more acute in CAN...
Effects of Lifting Straps on Biomechanics of Deadlift- A Case Study
The objective of the present study was to evaluate muscle activities while performing deadlift with or without lifting straps. Ultimately, the finding from the present study was intended to be used for the use of lifting...