Research on Arthroscopic Images Bleeding Detection Algorithm Based on ViT-ResNet50 Integrated Model and Transfer Learning
Arthroscopic surgery is a major technique for the treatment of joint-related diseases, however, intraoperative bleeding often produces a blood mist that severely affects the surgeon’s field of vision and requires prompt high-flow drainage to remove the mist. Therefore, accurate bleeding d...
Saved in:
| Main Authors: | , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
IEEE
2024-01-01
|
| Series: | IEEE Access |
| Subjects: | |
| Online Access: | https://ieeexplore.ieee.org/document/10771729/ |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1841533443103522816 |
|---|---|
| author | Zewen Liu Shaoyi Zhou Jianqiao Chu Zhiyuan Chai Dongdong Chang Yi Yuan Jinling Qin Xiancheng Wang |
| author_facet | Zewen Liu Shaoyi Zhou Jianqiao Chu Zhiyuan Chai Dongdong Chang Yi Yuan Jinling Qin Xiancheng Wang |
| author_sort | Zewen Liu |
| collection | DOAJ |
| description | Arthroscopic surgery is a major technique for the treatment of joint-related diseases, however, intraoperative bleeding often produces a blood mist that severely affects the surgeon’s field of vision and requires prompt high-flow drainage to remove the mist. Therefore, accurate bleeding detection is a prerequisite for effective blood mist removal. This paper proposes an arthroscopic image bleeding detection method based on the ViT-ResNet50 integrated model and transfer learning to solve the problem of relying on naked eye to identify bleeding in existing arthroscopic surgery. Firstly, Vision Transformer model and ResNet50 model are used to learn features by transfer learning on ImageNet dataset respectively. Then, a difference-enhanced proportional sampling method is proposed to enhance the unbalanced data. Finally, the two sub-network models are integrated through weighted soft voting method to realize bleeding detection in arthroscopic images. In order to evaluate the performance of the model proposed in this paper, experimental results on real data show that the integrated model is superior to a single deep learning model in various performance indicators and has good effects in detecting bleeding in arthroscopic images. |
| format | Article |
| id | doaj-art-d55a475ee1c340d78570bdfa440a56c2 |
| institution | Kabale University |
| issn | 2169-3536 |
| language | English |
| publishDate | 2024-01-01 |
| publisher | IEEE |
| record_format | Article |
| series | IEEE Access |
| spelling | doaj-art-d55a475ee1c340d78570bdfa440a56c22025-01-16T00:02:17ZengIEEEIEEE Access2169-35362024-01-011218143618145310.1109/ACCESS.2024.350879710771729Research on Arthroscopic Images Bleeding Detection Algorithm Based on ViT-ResNet50 Integrated Model and Transfer LearningZewen Liu0https://orcid.org/0009-0009-0276-5668Shaoyi Zhou1https://orcid.org/0009-0005-7075-4873Jianqiao Chu2Zhiyuan Chai3Dongdong Chang4Yi Yuan5https://orcid.org/0000-0003-3108-1918Jinling Qin6https://orcid.org/0000-0003-1539-2011Xiancheng Wang7https://orcid.org/0000-0003-0433-9004Ningbo Clinical Research Center for Orthopedics and Exercise Rehabilitation, Ningbo No. 2 Hospital, Ningbo, ChinaCollege of Science and Technology, Ningbo University, Ningbo, ChinaCollege of Science and Technology, Ningbo University, Ningbo, ChinaCollege of Science and Technology, Ningbo University, Ningbo, ChinaCollege of Science and Technology, Ningbo University, Ningbo, ChinaNingbo Clinical Research Center for Orthopedics and Exercise Rehabilitation, Ningbo No. 2 Hospital, Ningbo, ChinaNingbo Clinical Research Center for Orthopedics and Exercise Rehabilitation, Ningbo No. 2 Hospital, Ningbo, ChinaNingbo Clinical Research Center for Orthopedics and Exercise Rehabilitation, Ningbo No. 2 Hospital, Ningbo, ChinaArthroscopic surgery is a major technique for the treatment of joint-related diseases, however, intraoperative bleeding often produces a blood mist that severely affects the surgeon’s field of vision and requires prompt high-flow drainage to remove the mist. Therefore, accurate bleeding detection is a prerequisite for effective blood mist removal. This paper proposes an arthroscopic image bleeding detection method based on the ViT-ResNet50 integrated model and transfer learning to solve the problem of relying on naked eye to identify bleeding in existing arthroscopic surgery. Firstly, Vision Transformer model and ResNet50 model are used to learn features by transfer learning on ImageNet dataset respectively. Then, a difference-enhanced proportional sampling method is proposed to enhance the unbalanced data. Finally, the two sub-network models are integrated through weighted soft voting method to realize bleeding detection in arthroscopic images. In order to evaluate the performance of the model proposed in this paper, experimental results on real data show that the integrated model is superior to a single deep learning model in various performance indicators and has good effects in detecting bleeding in arthroscopic images.https://ieeexplore.ieee.org/document/10771729/Arthroscopy surgerybleeding detectiontransfer learningintegrated modelVision TransformerResNet50 |
| spellingShingle | Zewen Liu Shaoyi Zhou Jianqiao Chu Zhiyuan Chai Dongdong Chang Yi Yuan Jinling Qin Xiancheng Wang Research on Arthroscopic Images Bleeding Detection Algorithm Based on ViT-ResNet50 Integrated Model and Transfer Learning IEEE Access Arthroscopy surgery bleeding detection transfer learning integrated model Vision Transformer ResNet50 |
| title | Research on Arthroscopic Images Bleeding Detection Algorithm Based on ViT-ResNet50 Integrated Model and Transfer Learning |
| title_full | Research on Arthroscopic Images Bleeding Detection Algorithm Based on ViT-ResNet50 Integrated Model and Transfer Learning |
| title_fullStr | Research on Arthroscopic Images Bleeding Detection Algorithm Based on ViT-ResNet50 Integrated Model and Transfer Learning |
| title_full_unstemmed | Research on Arthroscopic Images Bleeding Detection Algorithm Based on ViT-ResNet50 Integrated Model and Transfer Learning |
| title_short | Research on Arthroscopic Images Bleeding Detection Algorithm Based on ViT-ResNet50 Integrated Model and Transfer Learning |
| title_sort | research on arthroscopic images bleeding detection algorithm based on vit resnet50 integrated model and transfer learning |
| topic | Arthroscopy surgery bleeding detection transfer learning integrated model Vision Transformer ResNet50 |
| url | https://ieeexplore.ieee.org/document/10771729/ |
| work_keys_str_mv | AT zewenliu researchonarthroscopicimagesbleedingdetectionalgorithmbasedonvitresnet50integratedmodelandtransferlearning AT shaoyizhou researchonarthroscopicimagesbleedingdetectionalgorithmbasedonvitresnet50integratedmodelandtransferlearning AT jianqiaochu researchonarthroscopicimagesbleedingdetectionalgorithmbasedonvitresnet50integratedmodelandtransferlearning AT zhiyuanchai researchonarthroscopicimagesbleedingdetectionalgorithmbasedonvitresnet50integratedmodelandtransferlearning AT dongdongchang researchonarthroscopicimagesbleedingdetectionalgorithmbasedonvitresnet50integratedmodelandtransferlearning AT yiyuan researchonarthroscopicimagesbleedingdetectionalgorithmbasedonvitresnet50integratedmodelandtransferlearning AT jinlingqin researchonarthroscopicimagesbleedingdetectionalgorithmbasedonvitresnet50integratedmodelandtransferlearning AT xianchengwang researchonarthroscopicimagesbleedingdetectionalgorithmbasedonvitresnet50integratedmodelandtransferlearning |