Work

An Efficient Method for Lung Lesions Classification Using Automatic Vascularization Evaluation on Color Doppler Ultrasound

Year: 2025

Type: article

Abstract: Lung cancer still represents one of the main causes of cancer-related mortality, highlighting the necessity for precise, effective, and minimally intrusive diagnostic methods. This research presents an innovative approach to classifying lung lesions using Doppler ultrasound imagery combined with a feed-forward neural network (FNN). This study integrates Doppler mode ultrasound vascularization features—blood vessel area, tortuosity index, and orientation—into an FNN to classify lung lesions as benign or malignant. A dataset of 565 Doppler ultrasound pictures was extended using augmentation techniques to enhance robustness, yielding a training dataset of 3390 images. The FNN architecture was trained utilizing the Levenberg–Marquardt algorithm, achieving a classification accuracy of 98%, demonstrating its potential as a diagnostic aid. The results indicate that integrating all three vascularization factors significantly improves diagnosis accuracy compared with individual modules. This method offers a non-invasive and cost-effective complementary tool to conventional techniques such as CT scans, with the potential to improve early detection and treatment planning for lung cancer patients.

Source: Applied Sciences

DOI: 10.3390/app15052851

Authors: Roxana Rusu-Both, Adrian Satmari, Romeo-Ioan Chira, Alexandra Chira, Camelia Avram

Institutions: Technical University of Cluj-Napoca, Iuliu Hațieganu University of Medicine and Pharmacy, Spitalul Clinic Județean de Urgență Cluj-Napoca

Language: English

Topic: AI in cancer detection

Subfield: Artificial Intelligence

Field: Computer Science

Domain: Physical Sciences

SDG: Good health and well-being

Open Access status: gold

Estimated APC paid: $2,896