Advertisement

Accuracy of computer-aided diagnosis based on narrow-band imaging endocytoscopy for diagnosing colorectal lesions: comparison with experts

  • 640 Accesses

  • 13 Citations

Abstract

Purpose

Real-time characterization of colorectal lesions during colonoscopy is important for reducing medical costs, given that the need for a pathological diagnosis can be omitted if the accuracy of the diagnostic modality is sufficiently high. However, it is sometimes difficult for community-based gastroenterologists to achieve the required level of diagnostic accuracy. In this regard, we developed a computer-aided diagnosis (CAD) system based on endocytoscopy (EC) to evaluate cellular, glandular, and vessel structure atypia in vivo. The purpose of this study was to compare the diagnostic ability and efficacy of this CAD system with the performances of human expert and trainee endoscopists.

Methods

We developed a CAD system based on EC with narrow-band imaging that allowed microvascular evaluation without dye (ECV-CAD). The CAD algorithm was programmed based on texture analysis and provided a two-class diagnosis of neoplastic or non-neoplastic, with probabilities. We validated the diagnostic ability of the ECV-CAD system using 173 randomly selected EC images (49 non-neoplasms, 124 neoplasms). The images were evaluated by the CAD and by four expert endoscopists and three trainees. The diagnostic accuracies for distinguishing between neoplasms and non-neoplasms were calculated.

Results

ECV-CAD had higher overall diagnostic accuracy than trainees (87.8 vs 63.4%; \(P=0.01\)), but similar to experts (87.8 vs 84.2%; \(P=0.76\)). With regard to high-confidence cases, the overall accuracy of ECV-CAD was also higher than trainees (93.5 vs 71.7%; \(P<0.001\)) and comparable to experts (93.5 vs 90.8%; \(P=0.38\)).

Conclusions

ECV-CAD showed better diagnostic accuracy than trainee endoscopists and was comparable to that of experts. ECV-CAD could thus be a powerful decision-making tool for less-experienced endoscopists.

This is a preview of subscription content, log in to check access.

Access options

Buy single article

Instant unlimited access to the full article PDF.

US$ 39.95

Price includes VAT for USA

Subscribe to journal

Immediate online access to all issues from 2019. Subscription will auto renew annually.

US$ 99

This is the net price. Taxes to be calculated in checkout.

Fig. 1
Fig. 2
Fig. 3
Fig. 4
Fig. 5
Fig. 6

Abbreviations

EC:

Endocytoscopy

CAD:

Computer-aided diagnosis

CRC:

Colorectal cancer

SSA/P:

Sessile serrated adenoma/polyp

ECV-CAD:

CAD system for endocytoscopic vascular pattern

NBI:

Narrow-band imaging

NPV:

Negative predictive value

PPV:

Positive predictive value

CI:

Confidence interval

SVM:

Support vector machine

ASGE:

American Society for Gastrointestinal Endoscopy

PIVI:

Preservation and Incorporation of Valuable Endoscopic Innovations

ROI:

Region of interest

References

  1. 1.

    Arnold M, Sierra MS, Laversanne M, Soerjomataram I, Jemal A, Bray F (2016) Global patterns and trends in colorectal cancer incidence and mortality. Gut. doi:10.1136/gutjnl-2015-310912

  2. 2.

    Zauber AG, Winawer SJ, O’Brien MJ, Lansdorp-Vogelaar I, van Ballegooijen M, Hankey BF, Shi W, Bond JH, Schapiro M, Panish JF, Stewart ET, Waye JD (2012) Colonoscopic polypectomy and long-term prevention of colorectal-cancer deaths. N Engl J Med 366(8):687–696. doi:10.1056/NEJMoa1100370

  3. 3.

    Ladabaum U, Fioritto A, Mitani A, Desai M, Kim JP, Rex DK, Imperiale T, Gunaratnam N (2013) Real-time optical biopsy of colon polyps with narrow band imaging in community practice does not yet meet key thresholds for clinical decisions. Gastroenterology 144(1):81–91. doi:10.1053/j.gastro.2012.09.054

  4. 4.

    Rees CJ, Rajasekhar PT, Wilson A, Close H, Rutter MD, Saunders BP, East JE, Maier R, Moorghen M, Muhammad U, Hancock H, Jayaprakash A, MacDonald C, Ramadas A, Dhar A, Mason JM (2016) Narrow band imaging optical diagnosis of small colorectal polyps in routine clinical practice: the Detect Inspect Characterise Resect and Discard 2 (DISCARD 2) study. Gut. doi:10.1136/gutjnl-2015-310584

  5. 5.

    Mori Y, S-e Kudo, Wakamura K, Misawa M, Ogawa Y, Kutsukawa M, Kudo T, Hayashi T, Miyachi H, Ishida F (2015) Novel computer-aided diagnostic system for colorectal lesions by using endocytoscopy (with videos). Gastrointest Endosc 81(3):621–629

  6. 6.

    Misawa M, Kudo SE, Mori Y, Nakamura H, Kataoka S, Maeda Y, Kudo T, Hayashi T, Wakamura K, Miyachi H, Katagiri A, Baba T, Ishida F, Inoue H, Nimura Y, Mori K (2016) Characterization of colorectal lesions using a computer-aided diagnostic system for narrow-band imaging endocytoscopy. Gastroenterology 150(7):1531–1532.e3. doi:10.1053/j.gastro.2016.04.004

  7. 7.

    Inoue H, Kazawa T, Sato Y, Satodate H, Sasajima K, Kudo SE, Shiokawa A (2004) In vivo observation of living cancer cells in the esophagus, stomach, and colon using catheter-type contact endoscope, ”Endo-Cytoscopy system”. Gastrointest Endosc Clin N Am 14(3):589–594, x–xi. doi:10.1016/j.giec.2004.03.013

  8. 8.

    Neumann H, Kudo SE, Kiesslich R, Neurath MF (2015) Advanced colonoscopic imaging using endocytoscopy. Dig Endosc 27(2):232–238

  9. 9.

    Maeda Y, Ohtsuka K, Kudo SE, Wakamura K, Mori Y, Ogata N, Wada Y, Misawa M, Yamauchi A, Hayashi S, Kudo T, Hayashi T, Miyachi H, Yamamura F, Ishida F, Inoue H, Hamatani S (2015) Endocytoscopic narrow-band imaging efficiency for evaluation of inflammatory activity in ulcerative colitis. World J Gastroenterol 21(7):2108–2115. doi:10.3748/wjg.v21.i7.2108

  10. 10.

    Kutsukawa M, Kudo SE, Ikehara N, Ogawa Y, Wakamura K, Mori Y, Ichimasa K, Misawa M, Kudo T, Wada Y, Hayashi T, Miyachi H, Inoue H, Hamatani S (2014) Efficiency of endocytoscopy in differentiating types of serrated polyps. Gastrointest Endosc 79(4):648–656. doi:10.1016/j.gie.2013.08.029

  11. 11.

    Kudo SE, Wakamura K, Ikehara N, Mori Y, Inoue H, Hamatani S (2011) Diagnosis of colorectal lesions with a novel endocytoscopic classification—a pilot study. Endoscopy 43(10):869–875. doi:10.1055/s-0030-1256663

  12. 12.

    Kudo SE, Mori Y, Wakamura K, Ikehara N, Ichimasa K, Wada Y, Kutsukawa M, Misawa M, Kudo T, Hayashi T, Miyachi H, Inoue H, Hamatani S (2014) Endocytoscopy can provide additional diagnostic ability to magnifying chromoendoscopy for colorectal neoplasms. J Gastroenterol Hepatol 29(1):83–90. doi:10.1111/jgh.12374

  13. 13.

    Kudo SE, Misawa M, Wada Y, Nakamura H, Kataoka S, Maeda Y, Toyoshima N, Hayashi S, Kutsukawa M, Oikawa H, Mori Y, Ogata N, Kudo T, Hisayuki T, Hayashi T, Wakamura K, Miyachi H, Ishida F, Inoue H (2015) Endocytoscopic microvasculature evaluation is a reliable new diagnostic method for colorectal lesions (with video). Gastrointest Endosc 82(5):912–923. doi:10.1016/j.gie.2015.04.039

  14. 14.

    Mori Y, Kudo SE, Ogawa Y, Wakamura K, Kudo T, Misawa M, Hayashi T, Katagiri A, Miyachi H, Inoue H, Oka S, Matsuda T (2016) Diagnosis of sessile serrated adenomas/polyps using endocytoscopy (with videos). Dig Endosc 28(Suppl 1):43–48. doi:10.1111/den.12601

  15. 15.

    Inoue H, Kashida H, Kudo S, Sasako M, Shimoda T, Watanabe H, Yoshida S, Guelrud M, Lightdale CJ, Wang K, Riddell RH (2003) The Paris endoscopic classification of superficial neoplastic lesions: esophagus, stomach, and colon: November 30 to December 1, 2002. Gastrointest Endosc 58(6 Suppl):S3–S43

  16. 16.

    Sato Y, Westin C-F, Bhalerao A, Nakajima S, Shiraga N, Tamura S, Kikinis R (2000) Tissue classification based on 3D local intensity structures for volume rendering. IEEE Trans Vis Comput Graph 6(2):160–180

  17. 17.

    Schultz T (2011) Topological features in 2D symmetric higher-order tensor fields. In: Computer graphics forum, vol 3. Wiley, New York, pp 841–850

  18. 18.

    Haralick RM, Shanmugam K, Dinstein IH (1973) Textural features for image classification. IEEE Trans Syst Man Cybern 6:610–621

  19. 19.

    Cortes C, Vapnik V (1995) Support-vector networks. Mach Learn 20(3):273–297

  20. 20.

    Platt J (1999) Probabilistic outputs for support vector machines and comparisons to regularized likelihood methods. Adv Large Margin Classif 10(3):61–74

  21. 21.

    Wu T-F, Lin C-J, Weng RC (2004) Probability estimates for multi-class classification by pairwise coupling. J Mach Learn Res 5:975–1005

  22. 22.

    Rex DK, Overhiser AJ, Chen SC, Cummings OW, Ulbright TM (2009) Estimation of impact of American College of Radiology recommendations on CT colonography reporting for resection of high-risk adenoma findings. Am J Gastroenterol 104(1):149–153. doi:10.1038/ajg.2008.35

  23. 23.

    Ignjatovic A, East J, Suzuki N, Vance M, Guenther T, Saunders B (2009) Optical diagnosis of small colorectal polyps at routine colonoscopy (Detect InSpect ChAracterise Resect and Discard; DISCARD trial): a prospective cohort study. Lancet Oncol 10(12):1171–1178

  24. 24.

    Rex DK, Kahi C, O’Brien M, Levin T, Pohl H, Rastogi A, Burgart L, Imperiale T, Ladabaum U, Cohen J (2011) The American Society for Gastrointestinal Endoscopy PIVI (Preservation and Incorporation of Valuable Endoscopic Innovations) on real-time endoscopic assessment of the histology of diminutive colorectal polyps. Gastrointest Endosc 73(3):419–422

  25. 25.

    ASGE Technology Committee, 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(3):502.e1–502.e16. doi:10.1016/j.gie.2014.12.022

  26. 26.

    Patel SG, Schoenfeld P, Kim HM, Ward EK, Bansal A, Kim Y, Hosford L, Myers A, Foster S, Craft J, Shopinski S, Wilson RH, Ahnen DJ, Rastogi A, Wani S (2016) Real-time characterization of diminutive colorectal polyp histology using narrow-band imaging: implications for the resect and discard strategy. Gastroenterology 150(2):406–418. doi:10.1053/j.gastro.2015.10.042

  27. 27.

    Takeuchi Y, Hanafusa M, Kanzaki H, Ohta T, Hanaoka N, Yamamoto S, Higashino K, Tomita Y, Uedo N, Ishihara R, Iishi H (2015) An alternative option for ”resect and discard” strategy, using magnifying narrow-band imaging: a prospective ”proof-of-principle” study. J Gastroenterol 50(10):1017–1026. doi:10.1007/s00535-015-1048-1

  28. 28.

    Kudo SE, Rubio CA, Teixeira CR, Kashida H, Kogure E (2001) Pit pattern in colorectal neoplasia: endoscopic magnifying view. Endoscopy 33(4):367–373. doi:10.1055/s-2004-826104

  29. 29.

    Sasajima K, Kudo SE, Inoue H, Takeuchi T, Kashida H, Hidaka E, Kawachi H, Sakashita M, Tanaka J, Shiokawa A (2006) Real-time in vivo virtual histology of colorectal lesions when using the endocytoscopy system. Gastrointest Endosc 63(7):1010–1017. doi:10.1016/j.gie.2006.01.021

  30. 30.

    Wanders LK, East JE, Uitentuis SE, Leeflang MM, Dekker E (2013) Diagnostic performance of narrowed spectrum endoscopy, autofluorescence imaging, and confocal laser endomicroscopy for optical diagnosis of colonic polyps: a meta-analysis. Lancet Oncol 14(13):1337–1347. doi:10.1016/S1470-2045(13)70509-6

  31. 31.

    Kiesslich R, Burg J, Vieth M, Gnaendiger J, Enders M, Delaney P, Polglase A, McLaren W, Janell D, Thomas S, Nafe B, Galle PR, Neurath MF (2004) Confocal laser endoscopy for diagnosing intraepithelial neoplasias and colorectal cancer in vivo. Gastroenterology 127(3):706–713

  32. 32.

    Inoue H, Cho JY, Satodate H, Sakashita M, Hidaka E, Fukami S, Kazawa T, Yoshida T, Shiokawa A, Kudo SE (2003) Development of virtual histology and virtual biopsy using laser-scanning confocal microscopy. Scand J Gastroenterol Suppl 237:37–39

  33. 33.

    Gross S, Trautwein C, Behrens A, Winograd R, Palm S, Lutz HH, Schirin-Sokhan R, Hecker H, Aach T, Tischendorf JJ (2011) Computer-based classification of small colorectal polyps by using narrow-band imaging with optical magnification. Gastrointest Endosc 74(6):1354–1359. doi:10.1016/j.gie.2011.08.001

  34. 34.

    Takemura Y, Yoshida S, Tanaka S, Kawase R, Onji K, Oka S, Tamaki T, Raytchev B, Kaneda K, Yoshihara M (2012) Computer-aided system for predicting the histology of colorectal tumors by using narrow-band imaging magnifying colonoscopy (with video). Gastrointest Endosc 75(1):179–185

  35. 35.

    Tamaki T, Yoshimuta J, Kawakami M, Raytchev B, Kaneda K, Yoshida S, Takemura Y, Onji K, Miyaki R, Tanaka S (2013) Computer-aided colorectal tumor classification in NBI endoscopy using local features. Med Image Anal 17(1):78–100. doi:10.1016/j.media.2012.08.003

  36. 36.

    Kominami Y, Yoshida S, Tanaka S, Sanomura Y, Hirakawa T, Raytchev B, Tamaki T, Koide T, Kaneda K, Chayama K (2016) Computer-aided diagnosis of colorectal polyp histology by using a real-time image recognition system and narrow-band imaging magnifying colonoscopy. Gastrointest Endosc 83(3):643–649. doi:10.1016/j.gie.2015.08.004

Download references

Acknowledgements

This study was funded by grants from JSPS KAKENHI (Grant Numbers 25860564 and 15K19351). We would like to express our gratitude to Mr. Takashi Wakisaka and Mr. Hideo Kahara (Cybernet Systems Co., Ltd.).

Author information

Correspondence to Masashi Misawa.

Ethics declarations

Conflict of interest

K Mori received research funding from Cybernet System Company and Olympus Company. H Inoue received a lecture fee from Olympus Company. The other authors declare no conflicts of interest.

Ethical approval

Informed consent was obtained from all study participants, and the study was approved by the Ethical Committee of Showa University (No. 1507-08). All procedures performed in this study involving human participants were in accordance with the ethical standards of the Ethical Committee of Showa University and with the 1964 Helsinki Declaration and its later amendments.

Patents

Japan patent JP 2015-036771 (patent pending) and JP 2015-200803 (patent pending).

Additional information

The results of this study were presented at JAMIT 2015, Kanazawa, and UEGweek 2016, Vienna.

Electronic supplementary material

Below is the link to the electronic supplementary material.

Supplementary material 1 (mp4 21915 KB)

Supplementary material 1 (mp4 21915 KB)

Rights and permissions

Reprints and Permissions

About this article

Verify currency and authenticity via CrossMark

Cite this article

Misawa, M., Kudo, S., Mori, Y. et al. Accuracy of computer-aided diagnosis based on narrow-band imaging endocytoscopy for diagnosing colorectal lesions: comparison with experts. Int J CARS 12, 757–766 (2017) doi:10.1007/s11548-017-1542-4

Download citation

Keywords

  • Colonoscopy
  • Narrow-band imaging
  • Endocytoscopy
  • Computer-aided diagnosis
  • Magnifying endoscopy
  • Colon polyp