Feature detection of B-ultrasound images of intussusception in children based on improved YOLOv8n_Journal of Biomedical Engineering

Authors：

LIU Chenyu ¹ ,  XU Jian ¹ , LI Ke ² , WANG Lu ³

1. School of Electronic Information, Xi’an Polytechnic University, Xi’an 710600, P. R. China;
2. Department of Ultrasound Medicine, Xijing Hospital, Air Force Medical University, Xi’an 710000, P. R. China;
3. Department of Ultrasound Medicine, Tangdu Hospital, Air Force Medical University, Xi’an 710038, P. R. China;

Corresponding author：

XU Jian, Email: xu0910@sina.com

Keywords：

Intussusception lesions; EMC-YOLOv8n; EfficientViT; C2fMBC; Coordinate attention module

DOI：

10.7507/1001-5515.202401017

Video：

Export PDF Favorites Scan Get Citation

Abstract Full text Figures/Tables Video References Cited by

To assist grassroots sonographers in accurately and rapidly detecting intussusception lesions from children's abdominal ultrasound images, this paper proposes an improved YOLOv8n children's intussusception detection algorithm, called EMC-YOLOv8n. Firstly, the EfficientViT network with a cascaded group attention module was used as the backbone network to enhance the speed of target detection. Secondly, the improved C2fMBC module was used to replace the C2f module in the neck network to reduce network complexity, and the coordinate attention (CA) module was introduced after each C2fMBC module to enhance attention to positional information. Finally, experiments were conducted on the self-built dataset of intussusception in children. The results showed that the recall rate, average detection accuracy (mAP@0.5) and precision of the EMC-YOLOv8n algorithm improved by 3.9%, 2.1% and 0.9%, respectively, compared to the baseline algorithm. Despite slightly increased network parameters and computational load, significant improvements in detection accuracy enable efficient completion of detection tasks, demonstrating substantial economic and social value.

Citation： LIU Chenyu, XU Jian, LI Ke, WANG Lu. Feature detection of B-ultrasound images of intussusception in children based on improved YOLOv8n. Journal of Biomedical Engineering, 2024, 41(5): 903-910. doi: 10.7507/1001-5515.202401017 Copy

1.	韦天军, 胡国兵, 朱向明, 等. 彩色多普勒超声诊断小儿急性肠套叠的应用价值. 皖南医学院学报, 2016, 35(3): 267-268.
2.	Li X Z, Wang H, Song J, et al. Ultrasonographic diagnosis of intussusception in children: a systematic review and meta‐analysis. J Ultras Med, 2021, 40(6): 1077-1084.
3.	Tsou P Y, Wang Y H, Ma Y K, et al. Accuracy of point-of-care ultrasound and radiology-performed ultrasound for intussusception: a systematic review and meta-analysis. Am J Emerg Med, 2019, 37(9): 1760-1769.
4.	Edwards E A, Pigg N, Courtier J, et al. Intussusception: past, present and future. Pediatr Radiol, 2017, 47(9): 1101-1108.
5.	Hryhorczuk A L, Strouse P J. Validation of US as a first-line diagnostic test for assessment of pediatric ileocolic intussusception. Pediatr Radiol, 2009, 39(10): 1075-1079.
6.	Henrikson S, Blane C E, Koujok K, et al. The effect of screening sonography on the positive rate of enemas for intussusception. Pediatr Radiol, 2003, 33(3): 190-193.
7.	宫进昌, 赵尚义, 王远军. 基于深度学习的医学图像分割研究进展. 中国医学物理学杂志, 2019, 36(4): 420-424.
8.	尹宏鹏, 陈波, 柴毅, 等. 基于视觉的目标检测与跟踪综述. 自动化学报, 2016, 42(10): 1466-1489.
9.	He K, Gkioxari G, Dollár P, et al. Mask R-CNN// Proceedings of the IEEE International Conference on Computer Vision (ICCV). Venice: IEEE, 2017: 2961-2969.
10.	Girshick R. Fast R-CNN/ /Proceedings of the IEEE International Conference on Computer Vision (ICCV). Santiago: IEEE, 2015: 1440-1448.
11.	Jiang P, Ergu D, Liu F, et al. A review of YOLO algorithm developments. Procedia Comput, 2022, 199: 1066-1073.
12.	Liu W, Anguelov D, Erhan D, et al. SSD: single shot multibox detector// Bastian L, Jiri M, Nicu S, et al. Computer Vision–ECCV 2016: 14th European Conference, Proceedings. Amsterdam: Springer International Publishing, 2016: 21-37.
13.	Kim S, Yoon H, Lee M J, et al. Performance of deep learning-based algorithm for detection of ileocolic intussusception on abdominal radiographs of young children. Sci Rep, 2019, 9(1): 19420.
14.	Kwon G, Ryu J, Oh J, et al. Deep learning algorithms for detecting and visualising intussusception on plain abdominal radiography in children: a retrospective multicenter study. Sci Rep, 2020, 10(1): 17582.
15.	Li Z, Song C, Huang J, et al. Performance of deep learning-based algorithm for detection of pediatric intussusception on abdominal ultrasound images. Gastroent Res Pract, 2022, 2022(1): 9285238.
16.	Kim S W, Cheon J E, Choi Y H, et al. Feasibility of a deep learning artificial intelligence model for the diagnosis of pediatric ileocolic intussusception with grayscale ultrasonography. Ultrasonography, 2024, 43(1): 57.
17.	Ju R Y, Cai W. Fracture detection in pediatric wrist trauma X-ray images using YOLOv8 algorithm. Sci Rep, 2023, 13(1): 20077.
18.	Liu X, Peng H, Zheng N, et al. EfficientViT: memory efficient vision transformer with cascaded group attention// Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR). Vancouver: IEEE/CVF, 2023: 14420-14430.
19.	Mahasin M, Dewi I A. Comparison of CSPDarkNet53, CSPResNeXt-50, and EfficientNet-B0 backbones on YOLOv4 as object detector. IJEST, 2022, 2(3): 64-72.
20.	Wang C Y, Bochkovskiy A, Liao H Y M. YOLOv7: trainable bag-of-freebies sets new state-of-the-art for real-time object detectors// Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR). Vancouver: IEEE/CVF, 2023: 7464-7475.
21.	Hou Q, Zhou D, Feng J. Coordinate attention for efficient mobile network design// Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR). Nashville: IEEE/CVF, 2021: 13708-13717.
22.	Xie E, Wang W, Yu Z, et al. SegFormer: simple and efficient design for semantic segmentation with transformers. NIPS, 2021, 34: 12077-12090.
23.	Tan M, Le Q. EfficientNet: rethinking model scaling for convolutional neural networks// International Conference on Machine Learning (ICML). Long Beach: PMLR, 2019: 6105-6114.

1. 韦天军, 胡国兵, 朱向明, 等. 彩色多普勒超声诊断小儿急性肠套叠的应用价值. 皖南医学院学报, 2016, 35(3): 267-268.
2. Li X Z, Wang H, Song J, et al. Ultrasonographic diagnosis of intussusception in children: a systematic review and meta‐analysis. J Ultras Med, 2021, 40(6): 1077-1084.
3. Tsou P Y, Wang Y H, Ma Y K, et al. Accuracy of point-of-care ultrasound and radiology-performed ultrasound for intussusception: a systematic review and meta-analysis. Am J Emerg Med, 2019, 37(9): 1760-1769.
4. Edwards E A, Pigg N, Courtier J, et al. Intussusception: past, present and future. Pediatr Radiol, 2017, 47(9): 1101-1108.
5. Hryhorczuk A L, Strouse P J. Validation of US as a first-line diagnostic test for assessment of pediatric ileocolic intussusception. Pediatr Radiol, 2009, 39(10): 1075-1079.
6. Henrikson S, Blane C E, Koujok K, et al. The effect of screening sonography on the positive rate of enemas for intussusception. Pediatr Radiol, 2003, 33(3): 190-193.
7. 宫进昌, 赵尚义, 王远军. 基于深度学习的医学图像分割研究进展. 中国医学物理学杂志, 2019, 36(4): 420-424.
8. 尹宏鹏, 陈波, 柴毅, 等. 基于视觉的目标检测与跟踪综述. 自动化学报, 2016, 42(10): 1466-1489.
9. He K, Gkioxari G, Dollár P, et al. Mask R-CNN// Proceedings of the IEEE International Conference on Computer Vision (ICCV). Venice: IEEE, 2017: 2961-2969.
10. Girshick R. Fast R-CNN/ /Proceedings of the IEEE International Conference on Computer Vision (ICCV). Santiago: IEEE, 2015: 1440-1448.
11. Jiang P, Ergu D, Liu F, et al. A review of YOLO algorithm developments. Procedia Comput, 2022, 199: 1066-1073.
12. Liu W, Anguelov D, Erhan D, et al. SSD: single shot multibox detector// Bastian L, Jiri M, Nicu S, et al. Computer Vision–ECCV 2016: 14th European Conference, Proceedings. Amsterdam: Springer International Publishing, 2016: 21-37.
13. Kim S, Yoon H, Lee M J, et al. Performance of deep learning-based algorithm for detection of ileocolic intussusception on abdominal radiographs of young children. Sci Rep, 2019, 9(1): 19420.
14. Kwon G, Ryu J, Oh J, et al. Deep learning algorithms for detecting and visualising intussusception on plain abdominal radiography in children: a retrospective multicenter study. Sci Rep, 2020, 10(1): 17582.
15. Li Z, Song C, Huang J, et al. Performance of deep learning-based algorithm for detection of pediatric intussusception on abdominal ultrasound images. Gastroent Res Pract, 2022, 2022(1): 9285238.
16. Kim S W, Cheon J E, Choi Y H, et al. Feasibility of a deep learning artificial intelligence model for the diagnosis of pediatric ileocolic intussusception with grayscale ultrasonography. Ultrasonography, 2024, 43(1): 57.
17. Ju R Y, Cai W. Fracture detection in pediatric wrist trauma X-ray images using YOLOv8 algorithm. Sci Rep, 2023, 13(1): 20077.
18. Liu X, Peng H, Zheng N, et al. EfficientViT: memory efficient vision transformer with cascaded group attention// Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR). Vancouver: IEEE/CVF, 2023: 14420-14430.
19. Mahasin M, Dewi I A. Comparison of CSPDarkNet53, CSPResNeXt-50, and EfficientNet-B0 backbones on YOLOv4 as object detector. IJEST, 2022, 2(3): 64-72.
20. Wang C Y, Bochkovskiy A, Liao H Y M. YOLOv7: trainable bag-of-freebies sets new state-of-the-art for real-time object detectors// Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR). Vancouver: IEEE/CVF, 2023: 7464-7475.
21. Hou Q, Zhou D, Feng J. Coordinate attention for efficient mobile network design// Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR). Nashville: IEEE/CVF, 2021: 13708-13717.
22. Xie E, Wang W, Yu Z, et al. SegFormer: simple and efficient design for semantic segmentation with transformers. NIPS, 2021, 34: 12077-12090.
23. Tan M, Le Q. EfficientNet: rethinking model scaling for convolutional neural networks// International Conference on Machine Learning (ICML). Long Beach: PMLR, 2019: 6105-6114.

Journal of Biomedical Engineering

Feature detection of B-ultrasound images of intussusception in children based on improved YOLOv8n

Abstract Full text Figures/Tables Video References Cited by

Previous Article

Next Article

Format

Content