Computer-vision based analysis of the neurosurgical scene – A systematic review

• Published in: Brain & spine Vol. 3; p. 102706
• Main Authors: Buyck, Félix, Vandemeulebroucke, Jef, Ceranka, Jakub, Van Gestel, Frederick, Cornelius, Jan Frederick, Duerinck, Johnny, Bruneau, Michaël
• Format: Journal Article
• Language: English
• Published: Netherlands Elsevier B.V 2023; Elsevier
• Subjects: Automated detection; computer vision; Neuroanatomy; Neurosurgery; Surgical instruments; Surgical phase recognition; Surgical videos; Surgical instruments; Automated detection; Surgical videos; Surgical phase recognition; Neuroanatomy; computer vision
• ISSN: 2772-5294; 2772-5294
• DOI: 10.1016/j.bas.2023.102706

With increasing use of robotic surgical adjuncts, artificial intelligence and augmented reality in neurosurgery, the automated analysis of digital images and videos acquired over various procedures becomes a subject of increased interest. While several computer vision (CV) methods have been developed and implemented for analyzing surgical scenes, few studies have been dedicated to neurosurgery. In this work, we present a systematic literature review focusing on CV methodologies specifically applied to the analysis of neurosurgical procedures based on intra-operative images and videos. Additionally, we provide recommendations for the future developments of CV models in neurosurgery. We conducted a systematic literature search in multiple databases until January 17, 2023, including Web of Science, PubMed, IEEE Xplore, Embase, and SpringerLink. We identified 17 studies employing CV algorithms on neurosurgical videos/images. The most common applications of CV were tool and neuroanatomical structure detection or characterization, and to a lesser extent, surgical workflow analysis. Convolutional neural networks (CNN) were the most frequently utilized architecture for CV models (65%), demonstrating superior performances in tool detection and segmentation. In particular, mask recurrent-CNN manifested most robust performance outcomes across different modalities. Our systematic review demonstrates that CV models have been reported that can effectively detect and differentiate tools, surgical phases, neuroanatomical structures, as well as critical events in complex neurosurgical scenes with accuracies above 95%. Automated tool recognition contributes to objective characterization and assessment of surgical performance, with potential applications in neurosurgical training and intra-operative safety management. •Robotic surgery & AI in neurosurgery raise interest in automated surgical image analysis.•Systematic review: Computer vision methods for automated analysis of digital images and videos in neurosurgery.•Studies report the use of CV models for the analysis of tools, neuroanatomy, workflow and critical events in neurosurgery.•CNN predominant (65%) for accurate tool detection & segmentation.•CV models may aid in objective surgical assessment & training enhancement.