Dataset Information

Automated segmentation by deep learning of loose connective tissue fibers to define safe dissection planes in robot-assisted gastrectomy.

ABSTRACT: The prediction of anatomical structures within the surgical field by artificial intelligence (AI) is expected to support surgeons' experience and cognitive skills. We aimed to develop a deep-learning model to automatically segment loose connective tissue fibers (LCTFs) that define a safe dissection plane. The annotation was performed on video frames capturing a robot-assisted gastrectomy performed by trained surgeons. A deep-learning model based on U-net was developed to output segmentation results. Twenty randomly sampled frames were provided to evaluate model performance by comparing Recall and F1/Dice scores with a ground truth and with a two-item questionnaire on sensitivity and misrecognition that was completed by 20 surgeons. The model produced high Recall scores (mean 0.606, maximum 0.861). Mean F1/Dice scores reached 0.549 (range 0.335-0.691), showing acceptable spatial overlap of the objects. Surgeon evaluators gave a mean sensitivity score of 3.52 (with 88.0% assigning the highest score of 4; range 2.45-3.95). The mean misrecognition score was a low 0.14 (range 0-0.7), indicating very few acknowledged over-detection failures. Thus, AI can be trained to predict fine, difficult-to-discern anatomical structures at a level convincing to expert surgeons. This technology may help reduce adverse events by determining safe dissection planes.

SUBMITTER: Kumazu Y

PROVIDER: S-EPMC8551298 | biostudies-literature | 2021 Oct

REPOSITORIES: biostudies-literature

ACCESS DATA

Publications

Automated segmentation by deep learning of loose connective tissue fibers to define safe dissection planes in robot-assisted gastrectomy.

Kumazu Yuta Y Kobayashi Nao N Kitamura Naoki N Rayan Elleuch E Neculoiu Paul P Misumi Toshihiro T Hojo Yudai Y Nakamura Tatsuro T Kumamoto Tsutomu T Kurahashi Yasunori Y Ishida Yoshinori Y Masuda Munetaka M Shinohara Hisashi H

Scientific reports 20211027 1

The prediction of anatomical structures within the surgical field by artificial intelligence (AI) is expected to support surgeons' experience and cognitive skills. We aimed to develop a deep-learning model to automatically segment loose connective tissue fibers (LCTFs) that define a safe dissection plane. The annotation was performed on video frames capturing a robot-assisted gastrectomy performed by trained surgeons. A deep-learning model based on U-net was developed to output segmentation resu ...[more]

PMID: 34707141

Similar Datasets

Project description:Radical gastrectomy with an adequate lymphadenectomy is the main procedure which makes it possible to cure patients with resectable gastric cancer (GC). A number of randomized controlled trials and meta-analysis provide phase III evidence that laparoscopic gastrectomy is technically safe and that it yields better short-term outcomes than conventional open gastrectomy for early-stage GC. While laparoscopic gastrectomy has become standard therapy for early-stage GC, especially in Asian countries such as Japan and South Korea, the use of minimally invasive techniques is still controversial for the treatment of more advanced tumours, principally due to existing concerns about its oncological adequacy and capacity to carry out an adequately extended lymphadenectomy. Some intrinsic drawbacks of the conventional laparoscopic technique have prevented the worldwide spread of laparoscopic gastrectomy for cancer and, despite technological advances in recent year, it remains a technically challenging procedure. The introduction of robotic surgery over the last ten years has implied a notable mutation of certain minimally invasive procedures, making it possible to overcome some limitations of the traditional laparoscopic technique. Robot-assisted gastric resection with D2 lymph node dissection has been shown to be safe and feasible in prospective and retrospective studies. However, to date there are no high quality comparative studies investigating the advantages of a robotic approach to GC over traditional laparoscopic and open gastrectomy. On the basis of the literature review here presented, robot-assisted surgery seems to fulfill oncologic criteria for D2 dissection and has a comparable oncologic outcome to traditional laparoscopic and open procedure. Robot-assisted gastrectomy was associated with the trend toward a shorter hospital stay with a comparable morbidity of conventional laparoscopic and open gastrectomy, but randomized clinical trials and longer follow-ups are needed to evaluate the possible influence of robot gastrectomy on GC patient survival.

Dataset Information

Automated segmentation by deep learning of loose connective tissue fibers to define safe dissection planes in robot-assisted gastrectomy.

Publications

Automated segmentation by deep learning of loose connective tissue fibers to define safe dissection planes in robot-assisted gastrectomy.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets