@inproceedings{c82059f2552046caae2522db2117534b,
title = "Efficient Vocal Cord Lesion Recognition by Combing Yolov7 and Attention Module",
abstract = "Currently, vocal cord lesion diagnosis of laryngoscopic images mainly relies on physicians' expertise and clinical experience. This greatly increases the work pressure of physicians and has limited efficiency. To solve the above problems, this study aims to construct a deep network structure named VCLR-Net based on the improved YOLOv7 to achieve the detection and recognition of vocal cord lesions. First, Convolutional Block Attention Modules (CBAM) are added to the HEAD network to improve the focus of color and spatial features on lesions. Next, the Alpha Intersection over Union loss (AlphaIOU) loss function is used to improve the robustness of the lesion recognition model. In the experimental results, the proposed VCLR-Net network achieves mAP and F1 of 0.762 and 0.748 in the image dataset. The network enables accurate lesion recognition for a large number of laryngoscopic images.",
keywords = "attention module, deep learning, improved yolov7, laryngoscope image, lesion detection",
author = "Yanda Wu and Yuqing He and Dongyan Huang and Yang Liu and Jingxuan Zhu and Hengli Zhang",
note = "Publisher Copyright: {\textcopyright} 2023 SPIE. All rights reserved.; 2023 Applied Optics and Photonics China: Optical Sensing, Imaging, and Display Technology and Applications; and Biomedical Optics, AOPC 2023 ; Conference date: 25-07-2023 Through 27-07-2023",
year = "2023",
doi = "10.1117/12.3007662",
language = "English",
series = "Proceedings of SPIE - The International Society for Optical Engineering",
publisher = "SPIE",
editor = "Yadong Jiang and Xiaoyong Wang and Dong Liu and Bin Xue and Yongtian Wang and Liangcai Cao and Qiong-Hua Wang and Chao-Yang Lu",
booktitle = "AOPC 2023",
address = "United States",
}