TEsoNet: knowledge transfer in surgical phase recognition from laparoscopic sleeve gastrectomy to the laparoscopic part of Ivor-Lewis esophagectomy.

Autor: Eckhoff JA; Surgical Artificial Intelligence and Innovation Laboratory, Department of Surgery, Massachusetts General Hospital, 15 Parkman Street, WAC339, Boston, MA, 02114, USA. jeckhoff@mgh.harvard.edu.; Department of General, Visceral, Tumor and Transplant Surgery, University Hospital Cologne, Kerpenerstrasse 62, 50937, Cologne, Germany. jeckhoff@mgh.harvard.edu., Ban Y; Surgical Artificial Intelligence and Innovation Laboratory, Department of Surgery, Massachusetts General Hospital, 15 Parkman Street, WAC339, Boston, MA, 02114, USA.; Computer Science and Artificial Intelligence Laboratory, Massachusetts Institute of Technology, 32 Vassar St, Cambridge, MA, 02139, USA., Rosman G; Surgical Artificial Intelligence and Innovation Laboratory, Department of Surgery, Massachusetts General Hospital, 15 Parkman Street, WAC339, Boston, MA, 02114, USA.; Computer Science and Artificial Intelligence Laboratory, Massachusetts Institute of Technology, 32 Vassar St, Cambridge, MA, 02139, USA., Müller DT; Department of General, Visceral, Tumor and Transplant Surgery, University Hospital Cologne, Kerpenerstrasse 62, 50937, Cologne, Germany., Hashimoto DA; Department of Surgery, University Hospitals Cleveland Medical Center, Cleveland, OH, 44106, USA.; Department of Surgery, Case Western Reserve School of Medicine, Cleveland, OH, 44106, USA., Witkowski E; Surgical Artificial Intelligence and Innovation Laboratory, Department of Surgery, Massachusetts General Hospital, 15 Parkman Street, WAC339, Boston, MA, 02114, USA., Babic B; Department of General, Visceral, Tumor and Transplant Surgery, University Hospital Cologne, Kerpenerstrasse 62, 50937, Cologne, Germany., Rus D; Computer Science and Artificial Intelligence Laboratory, Massachusetts Institute of Technology, 32 Vassar St, Cambridge, MA, 02139, USA., Bruns C; Department of General, Visceral, Tumor and Transplant Surgery, University Hospital Cologne, Kerpenerstrasse 62, 50937, Cologne, Germany., Fuchs HF; Department of General, Visceral, Tumor and Transplant Surgery, University Hospital Cologne, Kerpenerstrasse 62, 50937, Cologne, Germany., Meireles O; Surgical Artificial Intelligence and Innovation Laboratory, Department of Surgery, Massachusetts General Hospital, 15 Parkman Street, WAC339, Boston, MA, 02114, USA.
Jazyk: angličtina
Zdroj: Surgical endoscopy [Surg Endosc] 2023 May; Vol. 37 (5), pp. 4040-4053. Date of Electronic Publication: 2023 Mar 17.
DOI: 10.1007/s00464-023-09971-2
Abstrakt: Background: Surgical phase recognition using computer vision presents an essential requirement for artificial intelligence-assisted analysis of surgical workflow. Its performance is heavily dependent on large amounts of annotated video data, which remain a limited resource, especially concerning highly specialized procedures. Knowledge transfer from common to more complex procedures can promote data efficiency. Phase recognition models trained on large, readily available datasets may be extrapolated and transferred to smaller datasets of different procedures to improve generalizability. The conditions under which transfer learning is appropriate and feasible remain to be established.
Methods: We defined ten operative phases for the laparoscopic part of Ivor-Lewis Esophagectomy through expert consensus. A dataset of 40 videos was annotated accordingly. The knowledge transfer capability of an established model architecture for phase recognition (CNN + LSTM) was adapted to generate a "Transferal Esophagectomy Network" (TEsoNet) for co-training and transfer learning from laparoscopic Sleeve Gastrectomy to the laparoscopic part of Ivor-Lewis Esophagectomy, exploring different training set compositions and training weights.
Results: The explored model architecture is capable of accurate phase detection in complex procedures, such as Esophagectomy, even with low quantities of training data. Knowledge transfer between two upper gastrointestinal procedures is feasible and achieves reasonable accuracy with respect to operative phases with high procedural overlap.
Conclusion: Robust phase recognition models can achieve reasonable yet phase-specific accuracy through transfer learning and co-training between two related procedures, even when exposed to small amounts of training data of the target procedure. Further exploration is required to determine appropriate data amounts, key characteristics of the training procedure and temporal annotation methods required for successful transferal phase recognition. Transfer learning across different procedures addressing small datasets may increase data efficiency. Finally, to enable the surgical application of AI for intraoperative risk mitigation, coverage of rare, specialized procedures needs to be explored.
(© 2023. The Author(s).)
Databáze: MEDLINE
Externí odkaz: