Colonoscopic image synthesis with generative adversarial network for enhanced detection of sessile serrated lesions using convolutional neural network.

Journal: Scientific reports
Published Date:

Abstract

Computer-aided detection (CADe) systems have been actively researched for polyp detection in colonoscopy. To be an effective system, it is important to detect additional polyps that may be easily missed by endoscopists. Sessile serrated lesions (SSLs) are a precursor to colorectal cancer with a relatively higher miss rate, owing to their flat and subtle morphology. Colonoscopy CADe systems could help endoscopists; however, the current systems exhibit a very low performance for detecting SSLs. We propose a polyp detection system that reflects the morphological characteristics of SSLs to detect unrecognized or easily missed polyps. To develop a well-trained system with imbalanced polyp data, a generative adversarial network (GAN) was used to synthesize high-resolution whole endoscopic images, including SSL. Quantitative and qualitative evaluations on GAN-synthesized images ensure that synthetic images are realistic and include SSL endoscopic features. Moreover, traditional augmentation methods were used to compare the efficacy of the GAN augmentation method. The CADe system augmented with GAN synthesized images showed a 17.5% improvement in sensitivity on SSLs. Consequently, we verified the potential of the GAN to synthesize high-resolution images with endoscopic features and the proposed system was found to be effective in detecting easily missed polyps during a colonoscopy.

Authors

  • Dan Yoon
    Interdisciplinary Program in Bioengineering, Graduate School, Seoul National University, Seoul, 08826, South Korea.
  • Hyoun-Joong Kong
    Department of Biomedical Engineering, Chungnam National University College of Medicine, Daejeon, Korea.
  • Byeong Soo Kim
    Interdisciplinary Program in Bioengineering, Graduate School, Seoul National University, Seoul, Republic of Korea.
  • Woo Sang Cho
    Interdisciplinary Program in Bioengineering, Graduate School, Seoul National University, 101, Daehak-ro, Jongno-gu, Seoul, 03080, South Korea.
  • Jung Chan Lee
    Department of Biomedical Engineering, Seoul National University College of Medicine, Seoul, Korea.
  • Minwoo Cho
    Transdisciplinary Department of Medicine and Advanced Technology, Seoul National University Hospital, Seoul, Republic of Korea.
  • Min Hyuk Lim
    Department of Biomedical Engineering, Seoul National University College of Medicine, Seoul, Korea.
  • Sun Young Yang
    Department of Internal Medicine, Healthcare Research Institute, Seoul National University Hospital Healthcare System Gangnam Center, Seoul, Korea.
  • Seon Hee Lim
    Department of Internal Medicine, Healthcare Research Institute, Seoul National University Hospital Healthcare System Gangnam Center, Seoul, Korea.
  • Jooyoung Lee
    Center for In Silico Protein Science and School of Computational Sciences, Korea Institute for Advanced Study, Seoul 130-722, Korea.
  • Ji Hyun Song
    Department of Internal Medicine and Healthcare Research Institute, Healthcare System Gangnam Center, Seoul National University Hospital, Seoul, 06236, South Korea.
  • Goh Eun Chung
    Department of Internal Medicine, Healthcare Research Institute, Seoul National University Hospital Healthcare System Gangnam Center, Seoul, Korea.
  • Ji Min Choi
    Department of Internal Medicine, Healthcare Research Institute, Seoul National University Hospital Healthcare System Gangnam Center, Seoul, Korea.
  • Hae Yeon Kang
    Department of Internal Medicine, Seoul National University Hospital Healthcare System Gangnam Center, Seoul, South Korea.
  • Jung Ho Bae
    Department of Internal Medicine, Healthcare Research Institute, Seoul National University Hospital Healthcare System Gangnam Center, Seoul, Korea.
  • Sungwan Kim
    Department of Biomedical Engineering, Seoul National University College of Medicine, Seoul, Republic of Korea.