1
|
Gao Z, Jia S, Li Q, Lu D, Zhang S, Xiao W. [Deep learning approach for automatic segmentation of auricular acupoint divisions]. Sheng Wu Yi Xue Gong Cheng Xue Za Zhi 2024; 41:114-120. [PMID: 38403611 PMCID: PMC10894748 DOI: 10.7507/1001-5515.202309010] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Abstract] [Key Words] [MESH Headings] [Subscribe] [Scholar Register] [Received: 09/05/2023] [Revised: 12/28/2023] [Indexed: 02/27/2024]
Abstract
The automatic segmentation of auricular acupoint divisions is the basis for realizing intelligent auricular acupoint therapy. However, due to the large number of ear acupuncture areas and the lack of clear boundary, existing solutions face challenges in automatically segmenting auricular acupoints. Therefore, a fast and accurate automatic segmentation approach of auricular acupuncture divisions is needed. A deep learning-based approach for automatic segmentation of auricular acupoint divisions is proposed, which mainly includes three stages: ear contour detection, anatomical part segmentation and keypoints localization, and image post-processing. In the anatomical part segmentation and keypoints localization stages, K-YOLACT was proposed to improve operating efficiency. Experimental results showed that the proposed approach achieved automatic segmentation of 66 acupuncture points in the frontal image of the ear, and the segmentation effect was better than existing solutions. At the same time, the mean average precision (mAP) of the anatomical part segmentation of the K-YOLACT was 83.2%, mAP of keypoints localization was 98.1%, and the running speed was significantly improved. The implementation of this approach provides a reliable solution for the accurate segmentation of auricular point images, and provides strong technical support for the modern development of traditional Chinese medicine.
Collapse
Affiliation(s)
- Zhenyue Gao
- School of Automation and Electrical Engineering, University of Science and Technology Beijing, Beijing 100083, P. R. China
- Beijing Engineering Research Center of Industrial Spectrum Imaging, University of Science and Technology Beijing, Beijing 100083, P. R. China
- Shunde Innovation School, University of Science and Technology Beijing, Shunde, Guangdong 528399, P. R. China
| | - Shijin Jia
- School of Automation and Electrical Engineering, University of Science and Technology Beijing, Beijing 100083, P. R. China
- Shunde Innovation School, University of Science and Technology Beijing, Shunde, Guangdong 528399, P. R. China
| | - Qingfeng Li
- Mobile Health Management System Engineering Research Center of the Ministry of Education, Hangzhou Normal University, Hangzhou 311121, P. R. China
| | - Dongxin Lu
- Mobile Health Management System Engineering Research Center of the Ministry of Education, Hangzhou Normal University, Hangzhou 311121, P. R. China
| | - Sen Zhang
- School of Automation and Electrical Engineering, University of Science and Technology Beijing, Beijing 100083, P. R. China
- Beijing Engineering Research Center of Industrial Spectrum Imaging, University of Science and Technology Beijing, Beijing 100083, P. R. China
| | - Wendong Xiao
- School of Automation and Electrical Engineering, University of Science and Technology Beijing, Beijing 100083, P. R. China
- Beijing Engineering Research Center of Industrial Spectrum Imaging, University of Science and Technology Beijing, Beijing 100083, P. R. China
- Shunde Innovation School, University of Science and Technology Beijing, Shunde, Guangdong 528399, P. R. China
| |
Collapse
|
2
|
Zhang X, Ji X, Wang J, Fan Y, Tao C. Renal surface reconstruction and segmentation for image-guided surgical navigation of laparoscopic partial nephrectomy. Biomed Eng Lett 2023; 13:165-174. [PMID: 37124114 PMCID: PMC10130295 DOI: 10.1007/s13534-023-00263-1] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Abstract] [Key Words] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 09/24/2022] [Revised: 12/01/2022] [Accepted: 01/22/2023] [Indexed: 02/04/2023] Open
Abstract
An unpredictable dynamic surgical environment makes it necessary to measure morphological information of target tissue real-time for laparoscopic image-guided navigation. The stereo vision method for intraoperative tissue 3D reconstruction has the most potential for clinical development benefiting from its high reconstruction accuracy and laparoscopy compatibility. However, existing stereo vision methods have difficulty in achieving high reconstruction accuracy in real time. Also, intraoperative tissue reconstruction results often contain complex background and instrument information that prevents clinical development for image-guided systems. Taking laparoscopic partial nephrectomy (LPN) as the research object, this paper realizes a real-time dense reconstruction and extraction of the kidney tissue surface. The central symmetrical Census based semi-global block stereo matching algorithm is proposed to generate a dense disparity map. A GPU-based pixel-by-pixel connectivity segmentation mechanism is designed to segment the renal tissue area. An in-vitro porcine heart, in-vivo porcine kidney and offline clinical LPN data were performed to evaluate the accuracy and effectiveness of our approach. The algorithm achieved a reconstruction accuracy of ± 2 mm with a real-time update rate of 21 fps for an HD image size of 960 × 540, and 91.0% target tissue segmentation accuracy even with surgical instrument occlusions. Experimental results have demonstrated that the proposed method could accurately reconstruct and extract renal surface in real-time in LPN. The measurement results can be used directly for image-guided systems. Our method provides a new way to measure geometric information of target tissue intraoperatively in laparoscopy surgery. Supplementary Information The online version contains supplementary material available at 10.1007/s13534-023-00263-1.
Collapse
Affiliation(s)
- Xiaohui Zhang
- School of Engineering Medicine, Beijing Advanced Innovation Centre for Biomedical Engineering, Beihang University, No. 37 Xueyuan Road, Haidian District, Beijing, 100083 China
| | - Xuquan Ji
- School of Biomedical Engineering, Beihang University, No. 37 Xueyuan Road, Haidian District, Beijing, 100083 China
| | - Junchen Wang
- School of Mechanical Engineering and Automation, Beijing Advanced Innovation Centre for Biomedical Engineering, Beihang Unviersity, No. 37 Xueyuan Road, Haidian District, Beijing, 100083 China
| | - Yubo Fan
- School of Engineering Medicine, Beijing Advanced Innovation Centre for Biomedical Engineering, Beihang University, No. 37 Xueyuan Road, Haidian District, Beijing, 100083 China
- School of Biomedical Engineering, Beihang University, No. 37 Xueyuan Road, Haidian District, Beijing, 100083 China
| | - Chunjing Tao
- School of Engineering Medicine, Beijing Advanced Innovation Centre for Biomedical Engineering, Beihang University, No. 37 Xueyuan Road, Haidian District, Beijing, 100083 China
| |
Collapse
|
3
|
Liu S, Sun Y, Liu W, Xiao F, Song H. Information distribution on regions of speckle patterns for imaging of multimode fiber. Heliyon 2023; 9:e13357. [PMID: 36816253 PMCID: PMC9932470 DOI: 10.1016/j.heliyon.2023.e13357] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Abstract] [Key Words] [Track Full Text] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 12/28/2022] [Revised: 01/20/2023] [Accepted: 01/29/2023] [Indexed: 02/04/2023] Open
Abstract
Multimode fibers (MMF) have been extensively investigated for transmitting images. The transmitting images are distorted into speckle patterns by MMFs, which can be reconstructed by neural networks. We studied the information distribution of MMF speckle patterns for image reconstruction. The speckle patterns, segmented by three methods of segmentation, as Centering (1), Quartering (2) and Surrounding (3), are reconstructed into input images by Complex Artificial Neural Network (CANN). Experimental results show that only about one third of full speckle patterns is enough to reconstruct the original images. The quality of reconstructed image is related to the cropping method with different frequency components in speckle patterns, under the same cropped size, Centering segmentation has 4% performance improvement compared to Surrounding segmentation. Optimized segmentation will improve the quality of reconstructed images.
Collapse
|