# Deep Reinforcement Learning for Surgical Gesture Segmentation and Classification Source: [Deep Reinforcement Learning for Surgical Gesture Segmentation and Classification]() Collection index: [llms.txt]() Data updated: 2026-01-04T02:57:35.495Z Authors: Daochang Liu, Tingting Jiang Published: 2018-06-21T07:09:43.000Z ## Abstract Recognition of surgical gesture is crucial for surgical skill assessment and efficient surgery training. Prior works on this task are based on either variant graphical models such as HMMs and CRFs, or deep learning models such as Recurrent Neural Networks and Temporal Convolutional Networks. Most of the current approaches usually suffer from over-segmentation and therefore low segment-level edit scores. In contrast, we present an essentially different methodology by modeling the task as a sequential decision-making process. An intelligent agent is trained using reinforcement learning with hierarchical features from a deep model. Temporal consistency is integrated into our action design and reward mechanism to reduce over-segmentation errors. Experiments on JIGSAWS dataset demonstrate that the proposed method performs better than state-of-the-art methods in terms of the edit score and on par in frame-wise accuracy. Our code will be released later. ## Recorded benchmark results A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage. - [Surgical Gesture Segmentation on JIGSAWS Video suturing task](): Surgical Gesture Segmentation; JIGSAWS Video suturing task; Accuracy: 81.43. - [Surgical Gesture Recognition on JIGSAWS Suturing task](): Surgical Gesture Recognition; JIGSAWS Suturing task; Accuracy: 81.43. - [Surgical Gesture Segmentation on JIGSAWS Kinematic suturing task](): Surgical Gesture Segmentation; JIGSAWS Kinematic suturing task; Accuracy: 82.07. ## Original sources and implementation [Original paper]() [PDF]()