BCL-YOLO: A YOLO-Based Model for Medical Image Detection
DOI:
https://doi.org/10.65455/j2rdvd27关键词:
Medical Imaging Detections, BSA, BEA, LDConv摘要
Medical image detection requires accurate localization of subtle lesions while maintaining efficient inference. Methods:We propose BCL-YOLO, a YOLOv8-based detector that integrates the BC2fB attention module,the C2fIRB inverted-residual module, LDSPPF with linear deformable convolution, and the Multi-InterpIoU loss. Results: On the Br35H brain-tumour MRI dataset, BCL-YOLO achieved 97.2% mAP@0.5 and 74.6% mAP@0.5:0.95, improving mAP@0.5 by 3.4 percentage points over YOLOv8. Ablation and comparative experiments confirmed the contribution of each component and showed competitive precision, recall, efficiency, and cross-dataset robustness on ChestX-Det10. Conclusions:BCL-YOLO improves medical lesion detection by combining attention-guided feature extraction, multi-scale fusion, and efficient bounding-box regression.
参考
[1]GUO C, HE Y, LIU H. Research progress on applications of artificial intelligence in musculoskeletal medical imaging. Chinese Journal of Medical Ultrasound (Electronic Edition), 2025, 22(3): 266.
[2]CHEN H, CHEN S. Application and prospects of keypoint detection technologies in medical imaging. Software Engineering and Applications, 2025, 14: 38. DOI: https://doi.org/10.12677/sea.2025.141005
[3]WANG N, LIN S, QI F, et al. Anomaly detection in medical images based on self-supervised learning. Journal of Computer-Aided Design and Computer Graphics, 2025, 37(3): 474-483. DOI: https://doi.org/10.3724/SP.J.1089.2023-00339
[4]ZHANG S, ZHAO T, QI F, et al. An intelligent biomedical image classification algorithm based on wavelet transform. Advances in Applied Mathematics, 2025, 14: 16. DOI: https://doi.org/10.12677/aam.2025.143088
[5]HUANG S, ZHANG S. A medical image segmentation method using hierarchical fusion and multi-scale attention. Modeling and Simulation, 2025, 14: 887. DOI: https://doi.org/10.12677/mos.2025.145442
[6]WU X, LIU L, CHEN J, et al. Application of an artificial-intelligence-assisted cataract diagnosis system in community screening. Chinese Journal of Ophthalmology, 2021.
[7]LIN C, CHEN M. A diversified evaluation of classroom teaching effectiveness based on computer vision. Intelligent Computer and Applications, 2025, 15(4): 125-131.
[8]HUANG Y, CHEN H, XU S. Causes and detection methods of appearance defects in fair-faced concrete. Guangdong Building Materials, 2025, 41(7): 96-100.
[9]WANG S, ZHANG H, LIU Q, et al. The role of a pinhole mirror in predicting visual acuity before cataract surgery. Ophthalmology, 2025, 14(1): 43-47.
[10]GUO S, ZHANG W, DONG Y. Intelligent detection of pulmonary medical images based on DenseNet. Journal of Harbin University of Commerce (Natural Sciences), 2023, 39(2): 164-168.
[11]HUANG D. Research on keypoint detection in orthopedic images based on self-supervised learning. Changchun: Jilin University, 2024.
[12]REIS D, KUPEC J, HONG J, et al. Real-time flying object detection with YOLOv8[Z/OL]. arXiv:2305.09972, 2023.
[13]CARION N, MASSA F, SYNNAEVE G, et al. End-to-end object detection with transformers[Z/OL]. arXiv:2005.12872, 2020. DOI: https://doi.org/10.1007/978-3-030-58452-8_13
[14]LIU W, ANGUELOV D, ERHAN D, et al. SSD: Single shot multibox detector//European Conference on Computer Vision. Cham: Springer, 2016: 21-37. DOI: https://doi.org/10.1007/978-3-319-46448-0_2
[15]CHEN X, GUPTA A. An implementation of faster RCNN with study for region sampling[Z/OL]. arXiv:1702.02138, 2017.
[16]KUMAR A, DHANALAKSHMI R. EYE-YOLO: a multi-spatial pyramid pooling and Focal-EIOU loss inspired tiny YOLOv7 for fundus eye disease detection. International Journal of Intelligent Computing and Cybernetics, 2024, 17(3): 503-522. DOI: https://doi.org/10.1108/IJICC-02-2024-0077
[17]LOKESH L P, POOLA R G, GORREPATI L P, et al. Real-Time Cataract Diagnosis with GhostYOLO: A GhostConv-enhanced YOLO Model. Engineering, Technology & Applied Science Research, 2025, 15(3): 22945-22952. DOI: https://doi.org/10.48084/etasr.10760
[18]WANG Y, YANG Y. A YOLOv8-based detection algorithm for hand-bone fracture images. Artificial Intelligence and Robotics Research, 2025, 14: 621. DOI: https://doi.org/10.12677/airr.2025.143061
[19]BAO Q, TANG S, LI Q, et al. Improved YOLOv8 for multi-type pulmonary nodule detection. Journal of Frontiers of Computer Science and Technology, 2025, 19(2): 429-442.
[20]ANBALAGAN K, RADHIKA K, RAMACHANDRAN V M, et al. Artificial Intelligence in Healthcare: YOLO-v7 and GRU Integration for Automated Glaucoma Detection//2025 International Conference on Computational Robotics, Testing and Engineering Evaluation. Piscataway, NJ: IEEE, 2025: 1-6. DOI: https://doi.org/10.1109/ICCRTEE64519.2025.11053046
[21]WANG G, CHEN Y, AN P, et al. UAV-YOLOv8: A Small-Object-Detection Model Based on Improved YOLOv8 for UAV Aerial Photography Scenarios. Sensors, 2023, 23: 7190. DOI: https://doi.org/10.3390/s23167190
[22]ZHANG H, LIANG M, WANG Y. YOLO-BS: a traffic sign detection algorithm based on YOLOv8. Scientific Reports, 2025, 15(1): 7558. DOI: https://doi.org/10.1038/s41598-025-88184-0
[23]RASHEED A F, ZARKOOSH M. Optimized YOLOv8 for multi-scale object detection. Journal of Real-Time Image Processing, 2025, 22(1): 6. DOI: https://doi.org/10.1007/s11554-024-01582-x
[24]LOU H, DUAN X, GUO J, et al. DC-YOLOv8: Small-Size Object Detection Algorithm Based on Camera Sensor. Electronics, 2023, 12: 2323. DOI: https://doi.org/10.3390/electronics12102323
[25]CHEN L C, PAPANDREOU G, KOKKINOS I, et al. DeepLab: Semantic image segmentation with deep convolutional nets, atrous convolution, and fully connected CRFs. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2017, 40(4): 834-848. DOI: https://doi.org/10.1109/TPAMI.2017.2699184
[26]WANG Y, XU D. A hyperspectral classification network integrating spectral-fusion GAT and bipolar self-attention. Optical Technique, 2025, 51(3): 367-376.
[27]WANG K, HE G, LI X. HSF-DETR: A Special Vehicle Detection Algorithm Based on Hypergraph Spatial Features and Bipolar Attention. Sensors, 2025, 25: 4381. DOI: https://doi.org/10.3390/s25144381
[28]WANG Y, ZUO Y, WU L, et al. Image super-resolution reconstruction based on an attention mechanism. Journal of Computer Applications, 2021, 41(3): 845-850.
[29]HAN Y. Research on object detection algorithms based on attention mechanisms and inverted residual blocks. Jinan: Shandong Normal University, 2024.
[30]ZHANG X, SONG Y, SONG T, et al. LDConv: linear deformable convolution for improving convolutional neural networks. Image and Vision Computing, 2024, 149: 105190. DOI: https://doi.org/10.1016/j.imavis.2024.105190
[31]DENG L, SHA W. SCA-YOLO: Real-time object detection based on deformable convolution and context-aware attention. Journal of Guangdong University of Technology, 2025, 42(0).
[32]REZATOFIGHI H, TSOI N, GWAK J Y, et al. Generalized intersection over union: A metric and a loss for bounding box regression//Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. Piscataway, NJ: IEEE, 2019: 658-666. DOI: https://doi.org/10.1109/CVPR.2019.00075
[33]ZHENG Z H, WANG P, LIU W, et al. Distance-IoU loss: Faster and better learning for bounding box regression//Proceedings of the AAAI Conference on Artificial Intelligence. Menlo Park, CA: AAAI Press, 2020: 12993-13000. DOI: https://doi.org/10.1609/aaai.v34i07.6999
[34]ZHENG Z H, WANG P, REN D W, et al. Enhancing geometric factors in model learning and inference for object detection and instance segmentation. IEEE Transactions on Cybernetics, 2021, 52(8): 8574-8586. DOI: https://doi.org/10.1109/TCYB.2021.3095305
[35]GEVORGYAN Z. SIoU loss: More powerful learning for bounding box regression. 2022.
[36]LIU C, WANG K, LI Q, et al. Powerful-IoU: More straightforward and faster bounding box regression loss with a nonmonotonic focusing mechanism. Neural Networks, 2024, 170: 276-284. DOI: https://doi.org/10.1016/j.neunet.2023.11.041
[37]LIU H, WATANABE H. InterpIoU: Rethinking Bounding Box Regression with Interpolation-Based IoU Optimization[Z/OL]. arXiv:2507.12420, 2025. DOI: https://doi.org/10.1016/j.neucom.2025.132230
[38]HAMADA A. Br35h: Brain tumor detection 2020[Z/OL]. Kaggle, 2021. https://www.kaggle.com/datasets/ahmedhamada0/braintumor-detection.
[39]YU Y. Research on medical imaging based on deep learning. Chengdu: University of Electronic Science and Technology of China, 2024.
[40]LIU J, LIAN J, YU Y. ChestX-det10: Chest X-ray Dataset on Detection of Thoracic Abnormalities[Z/OL]. arXiv:2006.10550, 2020.
[41]LI C, XU D, JIN S, et al. Chest X-ray emphysema detection based on channel attention and dilated convolution. Journal of Lanzhou University of Technology, 2022, 48(2): 81-89.
##submission.downloads##
已出版
##submission.dataAvailability##
The datasets used in this paper are publicly available open-source datasets. Br35H and ChestX-Det10 datasets can be obtained from Kaggle. All relevant references to these datasets are provided in the manuscript. No new datasets were generated in this work.
##submission.license##
##submission.copyrightStatement##
##submission.license.cc.by4.footer##