Bleeding contour detection for craniotomy. (March 2022)

• Record Type: Journal Article
• Authors: Tang, Jie; Gong, Yi; Xu, Lixin; Wang, Zehao; Zhang, Yucheng; Ren, Zifeng; Wang, He; Xia, Yijing; Li, Xintong; Wang, Junchen; Jin, Mengdi; Su, Baiquan
• Is Part Of: Biomedical signal processing and control. Volume 73(2022)
• Publication Date: 2022-03
• Subjects: Bleeding contour detection -- Craniotomy -- Mask R-CNN -- Neurosurgery; Signal processing -- Periodicals; Biomedical engineering -- Periodicals; Signal Processing, Computer-Assisted -- Periodicals; Image Processing, Computer-Assisted -- Periodicals; Biomedical Engineering -- Periodicals; 610.28
• DOI: 10.1016/j.bspc.2021.103419
• Languages: English
• ISSNs: 1746-8094

Abstract

Highlights: The first result on the bleeding contour detection during craniotomy for the images obtained by a visible-light CCD. All types of texture of the surgical area in all three neurosurgical phases are covered and the algorithm can detect the bleeding contour successfully. The resultant algorithmic pipeline forms a technique solution for autonomous bleeding removal operation by a medical robot. Abstract: Objective: Bleeding impairs observation during neurosurgery, and excessive bleeding endangers the life of a patient. Thus, hemostasis is important during neurosurgery. The detection of bleeding areas is a prerequisite for hemostasis. Methods: To the best of our knowledge, this paper is the first to present results on the detection of neurosurgical craniotomy bleeding scenarios, i.e., scalp incision bleeding, skull incision bleeding, and dura matter-incision bleeding. This is realized via a workflow that combines craniotomy image data preparation and a Mask R-CNN framework. Bleeding images on a porcine skin tissue with a simulated blood injected by a syringe are taken by a visible light camera, and the video frames of the scalp incision, skull incision, and dura matter-incision bleeding are extracted from neurosurgical videos. Results: The precision of bleeding areas detection for the simulated bleeding scenario and the three craniotomy phase scenarios were 94.40%, 84.44%, 89.48%, and 90.46%. Conclusion: The contours of the neurosurgical craniotomy bleeding regions can be detected along with the bleeding areas. Significance: It is beneficial for neurosurgeons to identify the bleeding areas by sending prioritized alerts for bleeding events. Furthermore, it is valuable for a task-level medical robot designed for a neurosurgical procedure, such as craniotomy, or a high-level robot designed for an entire neurosurgery procedure.