Automated surgical phase recognition in pediatric laparoscopic fundoplication using deep learning: a retrospective video-based study - Takeaways - MDSpire
Coming Soon: Introducing MDSpire News. Learn more
Conexiant’s news site is now MDSpire News. Learn more

Deep Learning–Based Identification of Surgical Phases in Pediatric Laparoscopic Fundoplication: A Retrospective Video Study

  • By

  • Yohei Sanmoto

  • Luning Li

  • Yudai Goto

  • Xin Zhu

  • Kouji Masumoto

  • October 8, 2026

Share

  • 1

    The study developed a deep learning system to recognize surgical phases during pediatric laparoscopic fundoplication.

  • 2

    The retrospective dataset included 38 operative videos from laparoscopic fundoplications performed at the University of Tsukuba Hospital from 2015 through 2025.

  • 3

    Investigators defined 10 workflow phases, including 8 procedural stages, camera cleaning, and other nonstandard intra-abdominal scenes.

  • 4

    Two pediatric surgeons annotated videos in 1-second increments, and a second surgeon reviewed every annotated video.

  • 5

    System performance was assessed by phase classification, reconstruction of the operative workflow, and estimation of phase duration in individual cases.

Original Source(s)

Automated surgical phase recognition in pediatric laparoscopic fundoplication using deep learning: a retrospective video-based study

  • by Yohei Sanmoto, Luning Li, Yudai Goto, Xin Zhu, Kouji Masumoto

  • October 8, 2026

Related Content

2026 ASCO Breast Cancer Highlights: SENOMAC

Harold Burstein, MD, PhD, and Laura S. Dominici, MD, FACS, discuss highlights from the SENOMAC trial which sheds light on whether some patients with early breast cancer and limited lymph node involvement can safely avoid additional axillary surgery.

  • October 15, 2026

  • 1 min
Gastric peroral endoscopic pyloromyotomy for delayed gastric conduit emptying: outcomes and predictors of treatment response

OBITUARY