Macular disease is one of the important causes of blindness, manual screening is prone to misdiagnosis, and automatic diagnosis based on deep learning helps early detection and treatment. A classification and detection algorithm for macular lesions based on improved YOLOv5 was proposed. To solve the problem of insufficient fusion of fine features in macular lesions images, a weighted bidirectional feature pyramid network replaced the PANet feature fusion module of YOLOv5 neck to achieve efficient multi-scale feature fusion to obtain better-detailed features of macular lesions. To solve the problem of poor detection ability of small target lesions, the SK attention mechanism was introduced into the model to enhance the capture of regional features of macular lesions by adjusting the receptive field adaptively. Comparative experiments show that the proposed algorithm can improve the detection accuracy of small targets from 91.9% to 94.2%, and the average accuracy of the whole class from 93.4% to 96.6%. Moreover, under the same conditions, the algorithm performs better than other target detection network models.
CHENBinbin, LOULixia, YEJuan. Eye diseases burden in China in the past 30 years[J]. Journal of Zhejiang University (Medical Sciences), 2021, 50(4): 420-428. (in Chinese)
[3]
韩璐.基于深度学习的视网膜病变分类与检测任务研究[D]. 哈尔滨: 哈尔滨工程大学, 2022.
[4]
周鹏.基于深度学习的眼底疾病诊断研究[D]. 南京: 南京航空航天大学, 2020.
[5]
LEES C, BAUGHMANM D, LEEY A. Deep learning is effective for classifying normal versus age-related macular degeneration OCT images[J]. Ophthalmology Retina, 2017, 1(4): 322-327.
[6]
BHADRAR, KARS. Retinal disease classification from optical coherence tomographical scans using multilayered convolution neural network[C]//2020 IEEE Applied Signal Processing Conference (ASPCON), IEEE, 2020: 212-216.
YANGWenyi, CHENWen, ZHOULan, et al. An improved convolutional neural network model for macular diseases classification[J]. Journal of China West Normal University (Natural Science), 2023, 44(3): 318-325. (in Chinese)
[9]
KARRIS P K, CHAKRABORTYD, CHATTERJEEJ. Transfer learning based classification of optical coherence tomography images with diabetic macular edema and dry age-related macular degeneration[J]. Biomedical Optics Express, 2017, 8(2): 579-592.
KAROLINAP. Vehicle detection and masking in UAV images using YOLO to improve photogrammetric products[J]. Reports on Geodesy and Geoinformatics, 2022, 114(1): 15-23.
[13]
SHEPINGZ, DINGRONGS, SHUHUANW, et al. DF-SSD: an improved SSD object detection algorithm based on DenseNet and feature fusion[J].IEEE Access, 2020, 8: 24344-24357.
[14]
ZHUX, LÜS, WANGX, et al. TPH-YOLOv5: Improved YOLOv5 based on transformer prediction head for object detection on drone-captured scenarios[C]//Proceedings of the IEEE/CVF International Conference on Computer Vision, 2021: 2778-2788.
[15]
WANGK, LIEWJ H, ZOUY, et al. Panet: Few-shot image semantic segmentation with prototype alignment[C]//Proceedings of the IEEE/CVF International Conference on Computer Vision, 2019: 9197-9206.
XUMingsheng, ZHUJunhui, GANJiaxin, et al. Steel surface defect detection algorithm based on YOLOv5[J]. Radio Engineering, 2024, 54(2): 351-359. (in Chinese)
[18]
TANM, PANGR, LEQ V. Efficientdet: scalable and efficient object detection[C]//Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2020: 10781-10790.
[19]
LIX, WANGW, HUX, et al. Selective kernel networks[C]//Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2019: 510-519.
XIAOWeiying, WANGJian, LIWenshun. Research on YOLOv5 lightweight algorithm for pine tree strain identification[J]. Forest Engineering, 2023, 39(4): 126-133. (in Chinese)