Application of artificial intelligence using a convolutional neural network for diagnosis of early gastric cancer based on magnifying endoscopy with narrow-band imaging

Hiroya Ueyama, Yusuke Kato, Yoichi Akazawa, Noboru Yatagai, Hiroyuki Komori, Tsutomu Takeda, Kohei Matsumoto, Kumiko Ueda, Kenshi Matsumoto, Mariko Hojo, Takashi Yao, Akihito Nagahara, Tomohiro Tada, Hiroya Ueyama, Yusuke Kato, Yoichi Akazawa, Noboru Yatagai, Hiroyuki Komori, Tsutomu Takeda, Kohei Matsumoto, Kumiko Ueda, Kenshi Matsumoto, Mariko Hojo, Takashi Yao, Akihito Nagahara, Tomohiro Tada

Abstract

Background and aim: Magnifying endoscopy with narrow-band imaging (ME-NBI) has made a huge contribution to clinical practice. However, acquiring skill at ME-NBI diagnosis of early gastric cancer (EGC) requires considerable expertise and experience. Recently, artificial intelligence (AI), using deep learning and a convolutional neural network (CNN), has made remarkable progress in various medical fields. Here, we constructed an AI-assisted CNN computer-aided diagnosis (CAD) system, based on ME-NBI images, to diagnose EGC and evaluated the diagnostic accuracy of the AI-assisted CNN-CAD system.

Methods: The AI-assisted CNN-CAD system (ResNet50) was trained and validated on a dataset of 5574 ME-NBI images (3797 EGCs, 1777 non-cancerous mucosa and lesions). To evaluate the diagnostic accuracy, a separate test dataset of 2300 ME-NBI images (1430 EGCs, 870 non-cancerous mucosa and lesions) was assessed using the AI-assisted CNN-CAD system.

Results: The AI-assisted CNN-CAD system required 60 s to analyze 2300 test images. The overall accuracy, sensitivity, specificity, positive predictive value, and negative predictive value of the CNN were 98.7%, 98%, 100%, 100%, and 96.8%, respectively. All misdiagnosed images of EGCs were of low-quality or of superficially depressed and intestinal-type intramucosal cancers that were difficult to distinguish from gastritis, even by experienced endoscopists.

Conclusions: The AI-assisted CNN-CAD system for ME-NBI diagnosis of EGC could process many stored ME-NBI images in a short period of time and had a high diagnostic ability. This system may have great potential for future application to real clinical settings, which could facilitate ME-NBI diagnosis of EGC in practice.

Keywords: artificial intelligence; convolutional neural network; early gastric cancer; magnifying endoscopy; narrow-band imaging.

© 2020 The Authors. Journal of Gastroenterology and Hepatology published by Journal of Gastroenterology and Hepatology Foundation and John Wiley & Sons Australia, Ltd.

Figures

Figure 1
Figure 1
Educational endoscopic images used for the CNN. (a) Differentiated‐type cancer (0‐IIc, tub1), (b) differentiated‐type cancer (0‐IIc, tub2), (c) differentiated‐type cancer (0‐IIa, tub1), (d–f) fundic gland mucosa, (g–i) pyloric gland mucosa, (j, k) patchy redness, (l) adenoma, (m) xanthoma, (n) focal atrophy, and (o) ulcer scar. 0‐IIa, flatly elevated; 0‐IIc, flatly depressed; CNN, convolution neural network; tub1, well differentiated adenocarcinoma; tub2, moderately differentiated adenocarcinoma.
Figure 2
Figure 2
Misdiagnosed endoscopic images shown by the CNN. (a–c) False negatives: lesions appear as intestinal metaplasia or gastritis. (a) Differentiated‐type cancer (0‐IIc, tub1, after Hp eradication): regular MVP + regular MSP with a DL. (b) Differentiated‐type cancer (0‐IIc, tub2, after Hp eradication): regular MVP + regular MSP with a DL. (c) Differentiated‐type cancer (0‐IIa, tub1, after Hp eradication): regular MVP + regular MSP with a DL. (d) False negative: bleeding. (e) False negative: low‐power view and out of focus. 0‐IIc, flatly depressed; CNN, convolution neural network; DL, demarcation line; Hp, Helicobacter pylori; MSP, microsurface pattern; MVP, microvascular pattern; tub1, well differentiated adenocarcinoma; tub2, moderately differentiated adenocarcinoma.
Figure 3
Figure 3
Heatmap of occlusion analysis. (a) Differentiated‐type cancer (0‐IIc, tub1). (b) Differentiated‐type cancer (0‐IIc, tub1). (c) Patchy redness. (d) Adenoma. (A–D) Heatmaps of each lesion. 0‐IIc, flatly depressed; tub1, well differentiated adenocarcinoma.

References

    1. Hamashima C, Okamoto M, Shabana M et al. Sensitivity ofendoscopic screening for gastric cancer by the incidence method. Int. J. Cancer 2013; 133: 653–659.
    1. Gono K, Yamazaki K, Douguchi N et al. Endoscopic observation of tissue by narrow band illumination. Optical Review 2003; 10: 211–215.
    1. Yao K, Anagnostopoulos GK, Ragunath K. Magnifying endoscopy for diagnosing and delineating early gastric cancer. Endoscopy 2009; 41: 462–467.
    1. Yao K, Iwashita A, Tanabe H et al. Novel zoom endoscopy technique for diagnosis of small flat gastric cancer: a prospective, blind study. Clin. Gastroenterol. Hepatol. 2007; 5: 869–878.
    1. Kato M, Kaise M, Yonezawa J et al. Magnifying endoscopy with narrow‐band imaging achieves superior accuracy in the differential diagnosis of superficial gastric lesions identified with white‐light endoscopy: a prospective study. Gastrointest. Endosc. 2010; 72: 523–529.
    1. Ezoe Y, Muto M, Uedo N et al. Magnifying narrowband imaging is more accurate than conventional white‐light imaging in diagnosis of gastric mucosal cancer. Gastroenterology 2011; 141: 2017–2025.
    1. Yao K, Doyama H, Gotoda T et al. Diagnostic performance and limitations of magnifying narrow‐band imaging in screening endoscopy of early gastric cancer: a prospective multicenter feasibility study. Gastric Cancer 2014; 17: 669–679.
    1. Yamada S, Doyama H, Yao K et al. An efficient diagnostic strategy for small, depressed early gastric cancer with magnifying narrow‐band imaging: a post‐hoc analysis of a prospective randomized controlled trial. Gastrointest. Endosc. 2014; 79: 55–63.
    1. Muto M, Yao K, Kaise M et al. Magnifying endoscopy simplediagnostic algorithm for early gastric cancer (MESDA‐G). Dig. Endosc. 2016; 28: 379–393.
    1. Nakanishi H, Doyama H, Ishikawa H et al. Evaluation of an e‐learning system for diagnosis of gastric lesions using magnifying narrow‐band imaging: a multicenter randomized controlled study. Endoscopy 2017; 49: 957–967.
    1. Esteva A, Kuprel B, Novoa RA et al. Dermatologist‐level classification of skin cancer with deep neural networks. Nature 2017; 542: 115–118.
    1. Ehteshami Bejnordi B, Veta M, Johannes van Diest P et al. Diagnostic assessment of deep learning algorithms for detection of lymph node metastases in women with breast cancer. JAMA 2017; 318: 2199–2210.
    1. Kodashima S, Fujishiro M, Takubo K et al. Ex vivo pilot study using computed analysis of endo‐cytoscopic images to differentiate normal and malignant squamous cell epithelia in the oesophagus. Dig. Liver Dis. 2007; 39: 762–766.
    1. Horie Y, Yoshio T, Aoyama K et al. Diagnostic outcomes of esophageal cancer by artificial intelligence using convolutional neural networks. Gastrointest. Endosc. 2019; 89: 25–32.
    1. Miyaki R, Yoshida S, Tanaka S et al. Quantitative identification of mucosal gastric cancer under magnifying endoscopy with flexible spectral imaging color enhancement. J. Gastroenterol. Hepatol. 2013; 28: 841–847.
    1. Kanesaka T, Lee TC, Uedo N et al. Computer‐aided diagnosis for identifying and delineating early gastric cancers in magnifying narrow‐band imaging. Gastrointest. Endosc. 2018; 87: 1339–1344.
    1. Hirasawa T, Aoyama K, Tanimoto T et al. Application of artificial intelligence using a convolutional neural network for detecting gastric cancer in endoscopic images. Gastric Cancer 2018; 21: 653–660.
    1. Shichijo S, Nomura S, Aoyama K et al. Application of convolutional neural networks in the diagnosis of Helicobacter pylori infection based on endoscopic images. EBioMedicine 2017; 25: 106–111.
    1. Nakashima H, Kawahira H, Kawachi H, Sakaki N. Artificial intelligence diagnosis of Helicobacter pylori infection using blue laser imaging‐bright and linked color imaging: a singlecenter prospective study. Ann. Gastroenterol. 2018; 31: 462–468.
    1. Horiuchi Y, Aoyama K, Tokai Y et al. Convolutional neural network for differentiating gastric cancer from gastritis using magnified endoscopy with narrow band imaging. Dig. Dis. Sci. 2020; 65: 1355–1363.
    1. Li L, Chen Y, Shen Z et al. Convolutional neural network for the diagnosis of early gastric cancer based on magnifying narrow band imaging. Gastric Cancer 2020; 23: 126–132.
    1. Akazawa Y, Ueyama H, Yao T et al. Usefulness of demarcation of differentiated‐type early gastric cancers after Helicobacter pylori eradication by magnifying endoscopy with narrow‐band imaging. Digestion 2018; 98: 175–184.
    1. Ueyama H, Yao T, Nakashima Y et al. Gastric adenocarcinoma of fundic gland type (chief cell predominant type) proposal for a new entity of gastric adenocarcinoma. Am. J. Surg. Pathol. 2010; 34: 609–619.
    1. Ueyama H, Matsumoto K, Nagahara A et al. Gastric adenocarcinoma of the fundic gland type (chief cell predominant type). Endoscopy 2014; 46: 153–157.
    1. Japanese Gastric Cancer Association . Japaneses classification of gastric carcinoma: 3rd English edition. Gastric Cancer 2011; 14: 101–112.
    1. He K, Zhang X, Ren S, Sun J, Deep residual learning for image recognition. arXiv:1512.03385.
    1. Selvaraju RR, Cogswell M, Das A, Vedantam R, Parikh D, Batra D. Grad‐CAM: visual explanations from deep networks via gradient‐based localization. arXiv:1610.02391. 2017.
    1. Kanda Y. Investigation of the freely available easy‐to‐use software “EZR” for medical statistics. Bone Marrow Transplant. 2013; 48: 452–458.
    1. Zhu Y, Wang QC, Xu MD et al. Application of convolutional neural network in the diagnosis of the invasion depth of gastric cancer based on conventional endoscopy. Gastrointest. Endosc. 2019; 89: 806–815.
    1. Shichijo S, Endo Y, Aoyama K et al. Application of convolutional neural networks for evaluating Helicobacter pylori infection status on the basis of endoscopic images. Scand. J. Gastroenterol. 2018; 53: 940–946. 10.1080/00365521.2019.1577486.
    1. Takiyama H, Ozawa T, Ishihara S et al. Automatic anatomical classification of esophagogastroduodenoscopy images using deep convolutional neural networks. Scientific Reports 2018; 8: 7497. 10.1038/s41598-018-25842-6.
    1. Mori Y, Kudo SE, Wakamura K et al. Novel computer‐aided diagnostic system for colorectal lesions by using endocytoscopy (with videos). Gastrointest. Endosc. 2015; 81: 621–629.
    1. Matumoto K, Ueyama H, Yao K et al. Diagnostic limitations of magnifying endoscopy with narrow band imaging in early gastric cancer. Endosc Int Open. 2020. in press.

Source: PubMed

Sponsor e collaboratori

Condizioni mediche

Interventi farmacologici

3
Sottoscrivi