Fast instruments and tissues segmentation of micro-neurosurgical scene using high correlative non-local network.

Autor: Luo YW; School of Artificial Intelligence and Data Science, Hebei University of Technology, Tianjin, 300131, China., Chen HY; School of Artificial Intelligence and Data Science, Hebei University of Technology, Tianjin, 300131, China., Li Z; State Key Laboratory of Management and Control for Complex Systems, Institute of Automation, Chinese Academy of Sciences, Beijing, 100190, China; School of Electronic and Information Engineering, Tongji University, Shanghai, 201804, China., Liu WP; School of Artificial Intelligence and Data Science, Hebei University of Technology, Tianjin, 300131, China., Wang K; Beijing Tiantan Hospital, Capital Medical University, Beijing, 100190, China., Zhang L; School of Artificial Intelligence and Data Science, Hebei University of Technology, Tianjin, 300131, China., Fu P; State Key Laboratory of Management and Control for Complex Systems, Institute of Automation, Chinese Academy of Sciences, Beijing, 100190, China; School of Automation at Beijing Information Science and Technology University, Beijing, 100192, China., Yue WQ; School of Artificial Intelligence and Data Science, Hebei University of Technology, Tianjin, 300131, China., Bian GB; State Key Laboratory of Management and Control for Complex Systems, Institute of Automation, Chinese Academy of Sciences, Beijing, 100190, China. Electronic address: guibin.bian@ia.ac.cn.
Jazyk: angličtina
Zdroj: Computers in biology and medicine [Comput Biol Med] 2023 Feb; Vol. 153, pp. 106531. Date of Electronic Publication: 2023 Jan 03.
DOI: 10.1016/j.compbiomed.2022.106531
Abstrakt: Surgical scene segmentation provides critical information for guidance in micro-neurosurgery. Segmentation of instruments and critical tissues contributes further to robot assisted surgery and surgical evaluation. However, due to the lack of relevant scene segmentation dataset, scale variation and local similarity, micro-neurosurgical segmentation faces many challenges. To address these issues, a high correlative non-local network (HCNNet), is proposed to aggregate multi-scale feature by optimized non-local mechanism. HCNNet adopts two-branch design to generate features of different scale efficiently, while the two branches share common weights in shallow layers. Several short-term dense concatenate (STDC) modules are combined as the backbone to capture both semantic and spatial information. Besides, a high correlative non-local module (HCNM) is designed to guide the upsampling process of the high-level feature by modeling global context generated from the low-level feature. It filters out confused pixels of different classes in the non-local correlation map. Meanwhile, a large segmentation dataset named NeuroSeg is constructed, which contains 15 types of instruments and 3 types of tissues that appear in meningioma resection surgery. The proposed HCNNet achieves the state-of-the-art performance on NeuroSeg, it reaches an inference speed of 54.85 FPS with the highest accuracy of 59.62% mIoU, 74.7% Dice, 70.55% mAcc and 87.12% aAcc.
Competing Interests: Declaration of Competing Interest The authors declare the following financial interests/personal relationships which may be considered as potential competing interests: Gui-bin Bian reports financial support was provided by National Natural Science Foundation of China.
(Copyright © 2023 Elsevier Ltd. All rights reserved.)
Databáze: MEDLINE
Externí odkaz: