nach oben

Erschienen in:

16.02.2021

A novel machine learning-based algorithm to identify and classify lesions and anatomical landmarks in colonoscopy images

verfasst von: Ying-Chun Jheng, Yen-Po Wang, Hung-En Lin, Kuang-Yi Sung, Yuan-Chia Chu, Huann-Sheng Wang, Jeng-Kai Jiang, Ming-Chih Hou, Fa-Yauh Lee, Ching-Liang Lu

Erschienen in: Surgical Endoscopy | Ausgabe 1/2022

Einloggen, um Zugang zu erhalten

Abstract

Objectives

Computer-aided diagnosis (CAD)-based artificial intelligence (AI) has been shown to be highly accurate for detecting and characterizing colon polyps. However, the application of AI to identify normal colon landmarks and differentiate multiple colon diseases has not yet been established. We aimed to develop a convolutional neural network (CNN)-based algorithm (GUTAID) to recognize different colon lesions and anatomical landmarks.

Methods

Colonoscopic images were obtained to train and validate the AI classifiers. An independent dataset was collected for verification. The architecture of GUTAID contains two major sub-models: the Normal, Polyp, Diverticulum, Cecum and CAncer (NPDCCA) and Narrow-Band Imaging for Adenomatous/Hyperplastic polyps (NBI-AH) models. The development of GUTAID was based on the 16-layer Visual Geometry Group (VGG16) architecture and implemented on Google Cloud Platform.

Results

In total, 7838 colonoscopy images were used for developing and validating the AI model. An additional 1273 images were independently applied to verify the GUTAID. The accuracy for GUTAID in detecting various colon lesions/landmarks is 93.3% for polyps, 93.9% for diverticula, 91.7% for cecum, 97.5% for cancer, and 83.5% for adenomatous/hyperplastic polyps.

Conclusions

A CNN-based algorithm (GUTAID) to identify colonic abnormalities and landmarks was successfully established with high accuracy. This GUTAID system can further characterize polyps for optical diagnosis. We demonstrated that AI classification methodology is feasible to identify multiple and different colon diseases.

Nur mit Berechtigung zugänglich

Wolff WI, Shinya H (1974) Earlier diagnosis of cancer of the colon through colonic endoscopy (colonoscopy). Cancer 34(Suppl):912–931CrossRef

Wolf AMD, Fontham ETH, Church TR, Flowers CR, Guerra CE, LaMonte SJ, Etzioni R, McKenna MT, Oeffinger KC, Shih YT, Walter LC, Andrews KS, Brawley OW, Brooks D, Fedewa SA, Manassaram-Baptiste D, Siegel RL, Wender RC, Smith RA (2018) Colorectal cancer screening for average-risk adults: 2018 guideline update from the American Cancer Society. CA Cancer J Clin 68:250–281CrossRef

Topol EJ (2019) High-performance medicine: the convergence of human and artificial intelligence. Nat Med 25:44–56CrossRef

Hosny A, Parmar C, Quackenbush J, Schwartz LH, Aerts H (2018) Artificial intelligence in radiology. Nat Rev Cancer 18:500–510CrossRef

Hogarty DT, Su JC, Phan K, Attia M, Hossny M, Nahavandi S, Lenane P, Moloney FJ, Yazdabadi A (2020) Artificial intelligence in dermatology—where we are and the way to the future: a review. Am J Clin Dermatol 21:41–47CrossRef

Kudo SE, Mori Y, Misawa M, Takeda K, Kudo T, Itoh H, Oda M, Mori K (2019) Artificial intelligence and colonoscopy: current status and future perspectives. Dig Endosc 31:363–371CrossRef

Misawa M, Kudo SE, Mori Y, Cho T, Kataoka S, Yamauchi A, Ogawa Y, Maeda Y, Takeda K, Ichimasa K, Nakamura H, Yagawa Y, Toyoshima N, Ogata N, Kudo T, Hisayuki T, Hayashi T, Wakamura K, Baba T, Ishida F, Itoh H, Roth H, Oda M, Mori K (2018) Artificial intelligence-assisted polyp detection for colonoscopy: initial experience. Gastroenterology 154:2027-2029.e2023CrossRef

Becq A, Chandnani M, Bharadwaj S, Baran B, Ernest-Suarez K, Gabr M, Glissen-Brown J, Sawhney M, Pleskow DK, Berzin TM (2020) Effectiveness of a deep-learning polyp detection system in prospectively collected colonoscopy videos with variable bowel preparation quality. J Clin Gastroenterol 54:554–557CrossRef

Wang P, Berzin TM, Glissen Brown JR, Bharadwaj S, Becq A, Xiao X, Liu P, Li L, Song Y, Zhang D, Li Y, Xu G, Tu M, Liu X (2019) Real-time automatic detection system increases colonoscopic polyp and adenoma detection rates: a prospective randomised controlled study. Gut 68:1813–1819CrossRef

10.

Gong D, Wu L, Zhang J, Mu G, Shen L, Liu J, Wang Z, Zhou W, An P, Huang X, Jiang X, Li Y, Wan X, Hu S, Chen Y, Hu X, Xu Y, Zhu X, Li S, Yao L, He X, Chen D, Huang L, Wei X, Wang X, Yu H (2020) Detection of colorectal adenomas with a real-time computer-aided system (ENDOANGEL): a randomised controlled study. Lancet Gastroenterol Hepatol 5:352–361CrossRef

11.

Berzin TM, Topol EJ (2020) Adding artificial intelligence to gastrointestinal endoscopy. Lancet 395:485CrossRef

12.

Chen PJ, Lin MC, Lai MJ, Lin JC, Lu HH, Tseng VS (2018) Accurate classification of diminutive colorectal polyps using computer-aided analysis. Gastroenterology 154:568–575CrossRef

13.

Byrne MF, Chapados N, Soudan F, Oertel C, Linares Perez M, Kelly R, Iqbal N, Chandelier F, Rex DK (2019) Real-time differentiation of adenomatous and hyperplastic diminutive colorectal polyps during analysis of unaltered videos of standard colonoscopy using a deep learning model. Gut 68:94–100CrossRef

14.

Kudo SE, Misawa M, Mori Y, Hotta K, Ohtsuka K, Ikematsu H, Saito Y, Takeda K, Nakamura H, Ichimasa K, Ishigaki T, Toyoshima N, Kudo T, Hayashi T, Wakamura K, Baba T, Ishida F, Inoue H, Itoh H, Oda M, Mori K (2020) Artificial intelligence-assisted system improves endoscopic identification of colorectal neoplasms. Clin Gastroenterol Hepatol 18:1874-1881.e1872CrossRef

15.

Chiu H-M, Chou Y-H, Lu P-Y, Lin P-C, Hung S-H, Chang L-C, Hsu W-F, Lee Y-C, Chen C-P, Wu M-S (2018) Su1737—novel computer-aided recognition system applying deep learning technology for verification of cecal intubation. Gastroenterology 154:S-572CrossRef

16.

Cho M, Kim JH, Kong HJ, Hong KS, Kim S (2018) A novel summary report of colonoscopy: timeline visualization providing meaningful colonoscopy video information. Int J Colorectal Dis 33:549–559CrossRef

17.

Takenaka K, Ohtsuka K, Fujii T, Negi M, Suzuki K, Shimizu H, Oshima S, Akiyama S, Motobayashi M, Nagahori M, Saito E, Matsuoka K, Watanabe M (2020) Development and validation of a deep neural network for accurate evaluation of endoscopic images from patients with ulcerative colitis. Gastroenterology 158:2150–2157CrossRef

18.

Ding Z, Shi H, Zhang H, Meng L, Fan M, Han C, Zhang K, Ming F, Xie X, Liu H, Liu J, Lin R, Hou X (2019) Gastroenterologist-level identification of small-bowel diseases and normal variants by capsule endoscopy using a deep-learning model. Gastroenterology 157:1044-1054.e1045CrossRef

19.

Owais M, Arsalan M, Choi J, Mahmood T, Park KR (2019) Artificial intelligence-based classification of multiple gastrointestinal diseases using endoscopy videos for clinical diagnosis. J Clin Med. https://doi.org/10.3390/jcm8070986CrossRefPubMedPubMedCentral

20.

Borgli H, Thambawita V, Smedsrud PH, Hicks S, Jha D, Eskeland SL, Randel KR, Pogorelov K, Lux M, Nguyen DTD, Johansen D, Griwodz C, Stensland HK, Ceja EG, Schmidt PT, Hammer HL, Riegler M, Halvorsen P, de Lange T (2019) Hyper-Kvasir: a comprehensive multi-class image and video dataset for gastrointestinal endoscopy. Sci Data. https://doi.org/10.1038/s41597-020-00622-yCrossRef

21.

Rezende E, Ruppert G, Carvalho T, Theophilo A, Ramos F, Geus PD (2018) Malicious software classification using VGG16 deep neural network’s bottleneck features. Springer, Cham, pp 51–59

22.

Martineau M, Raveaux R, Chatelain C, Conte D, Venturini G (2018) Effective training of convolutional neural networks for insect image recognition. Springer, Cham, pp 426–437

23.

Krishnaswamy Rangarajan A, Purushothaman R (2020) Disease classification in eggplant using pre-trained VGG16 and MSVM. Sci Rep 10:2322CrossRef

24.

Lui TKL, Guo CG, Leung WK (2020) Accuracy of artificial intelligence on histology prediction and detection of colorectal polyps: a systematic review and meta-analysis. Gastrointest Endosc 92:11-22.e16CrossRef

25.

Li J, Nadel MR, Poppell CF, Dwyer DM, Lieberman DA, Steinberger EK (2010) Quality assessment of colonoscopy reporting: results from a statewide cancer screening program. Diagn Ther Endosc. https://doi.org/10.1155/2010/419796CrossRefPubMedPubMedCentral

26.

Technology Committee ASGE, Abu Dayyeh BK, Thosani N, Konda V, Wallace MB, Rex DK, Chauhan SS, Hwang JH, Komanduri S, Manfredi M, Maple JT, Murad FM, Siddiqui UD, Banerjee S (2015) ASGE Technology Committee systematic review and meta-analysis assessing the ASGE PIVI thresholds for adopting real-time endoscopic assessment of the histology of diminutive colorectal polyps. Gastrointest Endosc 81:502.e501-502.e516

27.

Jin EH, Lee D, Bae JH, Kang HY, Kwak MS, Seo JY, Yang JI, Yang SY, Lim SH, Yim JY, Lim JH, Chung GE, Chung SJ, Choi JM, Han YM, Kang SJ, Lee J, Chan Kim H, Kim JS (2020) Improved accuracy in optical diagnosis of colorectal polyps using convolutional neural networks with visual explanations. Gastroenterology 158:2169-2179.e2168CrossRef

28.

Obuch JC, Pigott CM, Ahnen DJ (2015) Sessile serrated polyps: detection, eradication, and prevention of the evil twin. Curr Treat Options Gastroenterol 13:156–170CrossRef

29.

Mori Y, Kudo S, Ogawa Y, Misawa M, Takeda K, Kudo T, Wakamura K, Hayashi T, Ichimasa K, Maeda Y, Toyoshima N, Nakamura H, Katagiri A, Baba T, Ishida F, Oda M, Mori K, Inoue H (2017) Mo1991 can artificial intelligence correctly diagnose sessile serrated adenomas/polyps? Gastrointest Endosc 85:AB510CrossRef

30.

Ozawa T, Ishihara S, Fujishiro M, Kumagai Y, Shichijo S, Tada T (2020) Automated endoscopic detection and classification of colorectal polyps using convolutional neural networks. Ther Adv Gastroenterol 13:1756284820910659CrossRef

31.

Russakovsky O, Deng J, Su H, Krause J, Satheesh S, Ma S, Huang ZH, Karpathy A, Khosla A, Bernstein M, Berg AC, Fei-Fei L (2015) ImageNet Large Scale Visual Recognition Challenge. Int J Comput Vis 115:211–252CrossRef

32.

Simonyan K, Zisserman A (2014) Very deep convolutional networks for large-scale image recognition. arXiv 14091556

33.

Ioffe S, Szegedy CJA (2015) Batch normalization: accelerating deep network training by reducing internal covariate shift. arXiv abs/1502.03167

34.

Szegedy C, Vanhoucke V, Ioffe S, Shlens J, Wojna Z (2016) Rethinking the inception architecture for computer vision. In: 2016 IEEE conference on computer vision and pattern recognition (CVPR), pp 2818–2826

35.

He K, Zhang X, Ren S, Sun J (2016) Deep residual learning for image recognition. In: 2016 IEEE conference on computer vision and pattern recognition (CVPR), pp 770–778

36.

Chan GCY, Muhammad A, Shah SAA, Tang TB, Lu C, Meriaudeau F (2017) Transfer learning for Diabetic Macular Edema (DME) detection on Optical Coherence Tomography (OCT) images. In: 2017 IEEE international conference on signal and image processing applications (ICSIPA), pp 493–496

37.

Hwang DK, Hsu CC, Chang KJ, Chao D, Sun CH, Jheng YC, Yarmishyn AA, Wu JC, Tsai CY, Wang ML, Peng CH, Chien KH, Kao CL, Lin TC, Woung LC, Chen SJ, Chiou SH (2019) Artificial intelligence-based decision-making for age-related macular degeneration. Theranostics 9:232–245CrossRef

38.

Wang S, Dong L, Wang X, Wang X (2020) Classification of pathological types of lung cancer from CT images by deep residual neural networks with transfer learning strategy. Open Med (Wars) 15:190–197CrossRef

39.

Mori Y, Kudo SE, Misawa M, Saito Y, Ikematsu H, Hotta K, Ohtsuka K, Urushibara F, Kataoka S, Ogawa Y, Maeda Y, Takeda K, Nakamura H, Ichimasa K, Kudo T, Hayashi T, Wakamura K, Ishida F, Inoue H, Itoh H, Oda M, Mori K (2018) Real-time use of artificial intelligence in identification of diminutive polyps during colonoscopy: a prospective study. Ann Intern Med 169:357–366CrossRef

40.

Shi X, Chen Z, Wang H, Yeung D-Y, Wong W-K, Woo W-C (2015) Convolutional LSTM network: a machine learning approach for precipitation nowcasting. https://arxiv.org/abs/1506.04214v2

41.

Ribeiro MT, Singh S, Guestrin C (2016) “Why Should I Trust You?”: explaining the predictions of any classifier. In: Proceedings of the 22nd ACM SIGKDD international conference on knowledge discovery and data mining. Association for Computing Machinery, San Francisco, pp 1135–1144

42.

Rajpurkar P, Irvin J, Ball RL, Zhu K, Yang B, Mehta H, Duan T, Ding D, Bagul A, Langlotz CP, Patel BN, Yeom KW, Shpanskaya K, Blankenberg FG, Seekins J, Amrhein TJ, Mong DA, Halabi SS, Zucker EJ, Ng AY, Lungren MP (2018) Deep learning for chest radiograph diagnosis: a retrospective comparison of the CheXNeXt algorithm to practicing radiologists. PLoS Med 15:e1002686CrossRef

43.

Freedman MT, Osicka T (2008) Heat maps: an aid for data analysis and understanding of ROC CAD experiments. Acad Radiol 15:249–259CrossRef

44.

Mori Y (2019) Artificial intelligence and colonoscopy: the time is ripe to begin clinical trials. Endoscopy 51:219–220CrossRef

Titel: A novel machine learning-based algorithm to identify and classify lesions and anatomical landmarks in colonoscopy images
verfasst von: Ying-Chun Jheng
Yen-Po Wang
Hung-En Lin
Kuang-Yi Sung
Yuan-Chia Chu
Huann-Sheng Wang
Jeng-Kai Jiang
Ming-Chih Hou
Fa-Yauh Lee
Ching-Liang Lu
Publikationsdatum: 16.02.2021
Verlag: Springer US
Erschienen in: Surgical Endoscopy / Ausgabe 1/2022
Print ISSN: 0930-2794
Elektronische ISSN: 1432-2218
DOI: https://doi.org/10.1007/s00464-021-08331-2

Neu im Fachgebiet Chirurgie

Vorsicht, erhöhte Blutungsgefahr nach PCI!

10.05.2024 Koronare Herzerkrankung Nachrichten

Nach PCI besteht ein erhöhtes Blutungsrisiko, wenn die Behandelten eine verminderte linksventrikuläre Ejektionsfraktion aufweisen. Das Risiko ist umso höher, je stärker die Pumpfunktion eingeschränkt ist.

Darf man die Behandlung eines Neonazis ablehnen?

08.05.2024 Gesellschaft Nachrichten

In einer Leseranfrage in der Zeitschrift Journal of the American Academy of Dermatology möchte ein anonymer Dermatologe bzw. eine anonyme Dermatologin wissen, ob er oder sie einen Patienten behandeln muss, der eine rassistische Tätowierung trägt.

Deutlich weniger Infektionen: Wundprotektoren schützen!

08.05.2024 Postoperative Wundinfektion Nachrichten

Der Einsatz von Wundprotektoren bei offenen Eingriffen am unteren Gastrointestinaltrakt schützt vor Infektionen im Op.-Gebiet – und dient darüber hinaus der besseren Sicht. Das bestätigt mit großer Robustheit eine randomisierte Studie im Fachblatt JAMA Surgery.

Chirurginnen und Chirurgen sind stark suizidgefährdet

07.05.2024 Suizid Nachrichten

Der belastende Arbeitsalltag wirkt sich negativ auf die psychische Gesundheit der Angehörigen ärztlicher Berufsgruppen aus. Chirurginnen und Chirurgen bilden da keine Ausnahme, im Gegenteil.

Update Chirurgie

Bestellen Sie unseren Fach-Newsletter und bleiben Sie gut informiert.

Newsletter bestellen

Aktuelle BDC Leitlinien-Webinare

S3-Leitlinie „Diagnostik und Therapie des Karpaltunnelsyndroms“

Karpaltunnelsyndrom BDC Leitlinien Webinare

CME: 2 Punkte

Das Karpaltunnelsyndrom ist die häufigste Kompressionsneuropathie peripherer Nerven. Obwohl die Anamnese mit dem nächtlichen Einschlafen der Hand (Brachialgia parästhetica nocturna) sehr typisch ist, ist eine klinisch-neurologische Untersuchung und Elektroneurografie in manchen Fällen auch eine Neurosonografie erforderlich. Im Anfangsstadium sind konservative Maßnahmen (Handgelenksschiene, Ergotherapie) empfehlenswert. Bei nicht Ansprechen der konservativen Therapie oder Auftreten von neurologischen Ausfällen ist eine Dekompression des N. medianus am Karpaltunnel indiziert.

Prof. Dr. med. Gregor Antoniadis

S2e-Leitlinie „Distale Radiusfraktur“

Radiusfraktur BDC Leitlinien Webinare

CME: 2 Punkte

Das Webinar beschäftigt sich mit Fragen und Antworten zu Diagnostik und Klassifikation sowie Möglichkeiten des Ausschlusses von Zusatzverletzungen. Die Referenten erläutern, welche Frakturen konservativ behandelt werden können und wie. Das Webinar beantwortet die Frage nach aktuellen operativen Therapiekonzepten: Welcher Zugang, welches Osteosynthesematerial? Auf was muss bei der Nachbehandlung der distalen Radiusfraktur geachtet werden?

PD Dr. med. Oliver Pieske

Dr. med. Benjamin Meyknecht

S1-Leitlinie „Empfehlungen zur Therapie der akuten Appendizitis bei Erwachsenen“

Appendizitis BDC Leitlinien Webinare

CME: 2 Punkte

Inhalte des Webinars zur S1-Leitlinie „Empfehlungen zur Therapie der akuten Appendizitis bei Erwachsenen“ sind die Darstellung des Projektes und des Erstellungswegs zur S1-Leitlinie, die Erläuterung der klinischen Relevanz der Klassifikation EAES 2015, die wissenschaftliche Begründung der wichtigsten Empfehlungen und die Darstellung stadiengerechter Therapieoptionen.

Dr. med. Mihailo Andric

Springer Medizin

Abstract

Objectives

Methods

Results

Conclusions

Bitte loggen Sie sich ein, um Zugang zu diesem Inhalt zu erhalten

Weitere Artikel der Ausgabe 1/2022

Long-term (17 years) subjective and objective evaluation of the durability of laparoscopic Heller esophagomyotomy in patients with achalasia of the esophagus (90% of follow-up): a real challenge to POEM

Endoscopic submucosal dissection for colorectal lesions: outcomes from a United States experience

Augmented reality in laparoscopic liver resection evaluated on an ex-vivo animal model with pseudo-tumours

Use of self-expandable metallic stents for endoscopic biliary decompression decreases stent complications in pancreatic cancer patients receiving chemotherapy

Gender equity in ergonomics: does muscle effort in laparoscopic surgery differ between men and women?

Development of artificial intelligence system for quality control of photo documentation in esophagogastroduodenoscopy

Update Chirurgie