Application of deep learning for semantic segmentation in robotic prostatectomy: Comparison of convolutional neural networks and visual transformers.

Journal: Investigative and clinical urology
PMID:

Abstract

PURPOSE: Semantic segmentation is a fundamental part of the surgical application of deep learning. Traditionally, segmentation in vision tasks has been performed using convolutional neural networks (CNNs), but the transformer architecture has recently been introduced and widely investigated. We aimed to investigate the performance of deep learning models in segmentation in robot-assisted radical prostatectomy (RARP) and identify which of the architectures is superior for segmentation in robotic surgery.

Authors

  • Sahyun Pak
    Department of Urology, Kangnam Sacred Heart Hospital, Hallym University College of Medicine, Seoul, Korea.
  • Sung Gon Park
    Department of Urology, Kangnam Sacred Heart Hospital, Hallym University College of Medicine, Seoul, Korea.
  • Jeonghyun Park
    STARLABS Corp., Seoul, Korea.
  • Hong Rock Choi
    STARLABS Corp., Seoul, Korea.
  • Jun Ho Lee
    STARLABS Corp., Seoul, Korea.
  • Wonchul Lee
    Department of Urology, Hallym University Dongtan Sacred Heart Hospital, Hwaseong, Korea.
  • Sung Tae Cho
    Department of Physical Therapy, Graduate School, Sahmyook University, Seoul, Republic of Korea.
  • Young Goo Lee
    Department of Urology, Hallym University of Korea College of Medicine, Seoul, Korea.
  • Hanjong Ahn
    Department of Urology, University of Ulsan College of Medicine, Asan Medical Center, Seoul, Korea.