Non-polypoid Colorectal Lesions Detection and False Positive Detection by Artificial Intelligence under Blue Laser Imaging and Linked Color Imaging

DOI Web Site 31 References Open Access
  • Sugino Satoshi
    Department of Gastroenterology, Asahi University Hospital
  • Yoshida Naohisa
    Department of Gastroenterology, Kyoto Prefectural University of Medicine
  • Guo Zhe
    Biomedical Information Engineering Lab, The University of Aizu
  • Zhang Ruiyao
    Biomedical Information Engineering Lab, The University of Aizu
  • Inoue Ken
    Department of Gastroenterology, Kyoto Prefectural University of Medicine
  • Hirose Ryohei
    Department of Gastroenterology, Kyoto Prefectural University of Medicine
  • Dohi Osamu
    Department of Gastroenterology, Kyoto Prefectural University of Medicine
  • Itoh Yoshito
    Department of Gastroenterology, Kyoto Prefectural University of Medicine
  • Nemoto Daiki
    Department of Coloproctology, Aizu Medical Center, Fukushima Medical University
  • Togashi Kazutomo
    Department of Coloproctology, Aizu Medical Center, Fukushima Medical University
  • Yamamoto Hironori
    Department of Gastroenterology, Jichi Medical University
  • Zhu Xin
    Biomedical Information Engineering Lab, The University of Aizu

Description

<p>Objectives: Artificial intelligence (AI) with white light imaging (WLI) is not enough for detecting non-polypoid colorectal polyps and it still has high false positive rate (FPR). We developed AIs using blue laser imaging (BLI) and linked color imaging (LCI) to detect them with specific learning sets (LS).</p><p>Methods: The contents of LS were as follows, LS (WLI): 1991 WLI images of lesion of 2-10 mm, LS (IEE): 5920 WLI, BLI, and LCI images of non-polypoid and small lesions of 2-20 mm. LS (IEE) was extracted from videos and included both in-focus and out-of-focus images. We designed three AIs as follows: AI (WLI) finetuned by LS (WLI), AI (IEE) finetuned by LS (WLI)+LS (IEE), and AI (HQ) finetuned by LS (WLI)+LS (IEE) only with images in focus. Polyp detection using a test set of WLI, BLI, and LCI videos of 100 non-polypoid or non-reddish lesions of 2-20 mm and FPR using movies of 15 total colonoscopy were analyzed, compared to 2 experts and 2 trainees.</p><p>Results: The sensitivity for LCI in AI (IEE) (83%) was compared to that for WLI in AI (IEE) (76%: p=0.02), WLI in AI (WLI) (57%: p<0.01), BLI in AI (IEE) (78%: p=0.14), and LCI in trainees (74%: p<0.01). The sensitivity for LCI in AI (IEE) (83%) was significantly higher than that in AI (HQ) (78%: p<0.01). The FPR for LCI (6.5%) in AI (IEE) were significantly lower than that in AI (HQ) (17.3%: p<0.01).</p><p>Conclusions: AI finetuned by appropriate LS detected non-reddish and non-polypoid polyps under LCI.</p>

Journal

References(31)*help

See more

Keywords

Details 詳細情報について

Report a problem

Back to top