{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/rsdnet-learning-to-predict-remaining-surgery","title":"RSDNet: Learning to Predict Remaining Surgery Duration from Laparoscopic Videos Without Manual Annotations","arxiv_id":"1802.03243","date":"2018-02-09","proceeding":null,"authors":["Andru Putra Twinanda","Gaurav Yengera","Didier Mutter","Jacques Marescaux","Nicolas Padoy"],"abstract":"Accurate surgery duration estimation is necessary for optimal OR planning,\nwhich plays an important role in patient comfort and safety as well as resource\noptimization. It is, however, challenging to preoperatively predict surgery\nduration since it varies significantly depending on the patient condition,\nsurgeon skills, and intraoperative situation. In this paper, we propose a deep\nlearning pipeline, referred to as RSDNet, which automatically estimates the\nremaining surgery duration (RSD) intraoperatively by using only visual\ninformation from laparoscopic videos. Previous state-of-the-art approaches for\nRSD prediction are dependent on manual annotation, whose generation requires\nexpensive expert knowledge and is time-consuming, especially considering the\nnumerous types of surgeries performed in a hospital and the large number of\nlaparoscopic videos available. A crucial feature of RSDNet is that it does not\ndepend on any manual annotation during training, making it easily scalable to\nmany kinds of surgeries. The generalizability of our approach is demonstrated\nby testing the pipeline on two large datasets containing different types of\nsurgeries: 120 cholecystectomy and 170 gastric bypass videos. The experimental\nresults also show that the proposed network significantly outperforms a\ntraditional method of estimating RSD without utilizing manual annotation.\nFurther, this work provides a deeper insight into the deep learning network\nthrough visualization and interpretation of the features that are automatically\nlearned.","url_abs":"http://arxiv.org/abs/1802.03243v2","url_pdf":"http://arxiv.org/pdf/1802.03243v2.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"rsdnet-learning-to-predict-remaining-surgery","repo_url":"https://github.com/frans-db/progress-prediction","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}}],"tasks":[],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1802.03243","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}