International Conference on Computer and Knowledge Engineering

Home / 14th International Conference on Computer and Knowledge Engineering

YOLOatt-Med: YOLO-Based Attention Mechanism for Medical Image Classification

Authors :

Fatemeh Naserizadeh¹ Erfan Akbarnezhad Sany² Parsa Sinichi³ Seyyed Abed Hosseini⁴

1- Faculty of Electrical and Computer Engineering, Malek Ashtar University of Technology, Tehran, Iran 2- Faculty of Computer Engineering, Quchan University of Technology, Quchan, Iran 3- Faculty of Computer Engineering, Quchan University of Technology, Quchan, Iran 4- Department of Electrical Engineering, Mashhad Branch, Islamic Azad University, Mashhad, Iran

Keywords :

Diagnosis،YOLOv8،Convolutional Block Attention Module،Classification،Lung cancer

Abstract :

Early and accurate diagnosis of respiratory diseases can significantly reduce mortality rates. This study presents a novel approach for classifying respiratory diseases from medical images using computer vision. The method integrates YOLOv8 (you only look once version 8), a powerful object detection model, with the convolutional block attention module (CBAM) to enhance feature extraction and improve classification accuracy. The proposed model was evaluated on two datasets: chest computed tomography (CT) scans for lung cancer classification and chest X-rays for pneumonia classification. The results demonstrate that the CBAM-YOLOv8 model outperforms existing state-of-the-art methods. This improvement highlights the effectiveness of the proposed method in focusing on critical image features for accurate disease classification.