Original Research18 September 2018
A Prospective Study
    Author, Article, and Disclosure Information

    Abstract

    Background:

    Computer-aided diagnosis (CAD) for colonoscopy may help endoscopists distinguish neoplastic polyps (adenomas) requiring resection from nonneoplastic polyps not requiring resection, potentially reducing cost.

    Objective:

    To evaluate the performance of real-time CAD with endocytoscopes (×520 ultramagnifying colonoscopes providing microvascular and cellular visualization of colorectal polyps after application of the narrow-band imaging [NBI] and methylene blue staining modes, respectively).

    Design:

    Single-group, open-label, prospective study. (UMIN [University hospital Medical Information Network] Clinical Trial Registry: UMIN000027360).

    Setting:

    University hospital.

    Participants:

    791 consecutive patients undergoing colonoscopy and 23 endoscopists.

    Intervention:

    Real-time use of CAD during colonoscopy.

    Measurements:

    CAD-predicted pathology (neoplastic or nonneoplastic) of detected diminutive polyps (≤5 mm) on the basis of real-time outputs compared with pathologic diagnosis of the resected specimen (gold standard). The primary end point was whether CAD with the stained mode produced a negative predictive value (NPV) of 90% or greater for identifying diminutive rectosigmoid adenomas, the threshold required to “diagnose-and-leave” nonneoplastic polyps. Best- and worst-case scenarios assumed that polyps lacking either CAD diagnosis or pathology were true- or false-positive or true- or false-negative, respectively.

    Results:

    Overall, 466 diminutive (including 250 rectosigmoid) polyps from 325 patients were assessed by CAD, with a pathologic prediction rate of 98.1% (457 of 466). The NPVs of CAD for diminutive rectosigmoid adenomas were 96.4% (95% CI, 91.8% to 98.8%) (best-case scenario) and 93.7% (CI, 88.3% to 97.1%) (worst-case scenario) with stained mode and 96.5% (CI, 92.1% to 98.9%) (best-case scenario) and 95.2% (CI, 90.3% to 98.0%) (worst-case scenario) with NBI.

    Limitation:

    Two thirds of the colonoscopies were conducted by experts who had each experienced more than 200 endocytoscopies; 186 polyps not assessed by CAD were excluded.

    Conclusion:

    Real-time CAD can achieve the performance level required for a diagnose-and-leave strategy for diminutive, nonneoplastic rectosigmoid polyps.

    Primary Funding Source:

    Japan Society for the Promotion of Science.

    References

    • 1. Nishihara RWu KLochhead PMorikawa TLiao XQian ZRet alLong-term colorectal-cancer incidence and mortality after lower endoscopy. N Engl J Med2013;369:1095-105. [PMID: 24047059] doi:10.1056/NEJMoa1301969 CrossrefMedlineGoogle Scholar
    • 2. Rex DKKahi CO'Brien MLevin TRPohl HRastogi Aet alThe 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 Endosc2011;73:419-22. [PMID: 21353837] doi:10.1016/j.gie.2011.01.023 CrossrefMedlineGoogle Scholar
    • 3. Abu Dayyeh BKThosani NKonda VWallace MBRex DKChauhan SSet alASGE Technology CommitteeASGE 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 Endosc2015;81:502. [PMID: 25597420] doi:10.1016/j.gie.2014.12.022 CrossrefMedlineGoogle Scholar
    • 4. Lahiff CEast JEEndoscopic approach to polyp recognition. Frontline Gastroenterol2017;8:98-103. [PMID: 28839893] doi:10.1136/flgastro-2016-100777 CrossrefMedlineGoogle Scholar
    • 5. Mori YKudo SEBerzin TMMisawa MTakeda KComputer-aided diagnosis for colonoscopy. Endoscopy2017;49:813-9. [PMID: 28561195] doi:10.1055/s-0043-109430 CrossrefMedlineGoogle Scholar
    • 6. Byrne MFChapados NSoudan FOertel CLinares Pérez MKelly Ret alReal-time differentiation of adenomatous and hyperplastic diminutive colorectal polyps during analysis of unaltered videos of standard colonoscopy using a deep learning model. Gut2017. [PMID: 29066576] doi:10.1136/gutjnl-2017-314547 CrossrefMedlineGoogle Scholar
    • 7. Kominami YYoshida STanaka SSanomura YHirakawa TRaytchev Bet alComputer-aided diagnosis of colorectal polyp histology by using a real-time image recognition system and narrow-band imaging magnifying colonoscopy. Gastrointest Endosc2016;83:643-9. [PMID: 26264431] doi:10.1016/j.gie.2015.08.004 CrossrefMedlineGoogle Scholar
    • 8. Misawa MKudo SEMori YNakamura HKataoka SMaeda Yet alCharacterization of colorectal lesions using a computer-aided diagnostic system for narrow-band imaging endocytoscopy. Gastroenterology2016;150:1531-2. [PMID: 27072671] doi:10.1053/j.gastro.2016.04.004 CrossrefMedlineGoogle Scholar
    • 9. Mori YKudo SEChiu PWSingh RMisawa MWakamura Ket alImpact of an automated system for endocytoscopic diagnosis of small colorectal lesions: an international Web-based study. Endoscopy2016;48:1110-8. [PMID: 27494455] CrossrefMedlineGoogle Scholar
    • 10. Mori YKudo SEWakamura KMisawa MOgawa YKutsukawa Met alNovel computer-aided diagnostic system for colorectal lesions by using endocytoscopy (with videos). Gastrointest Endosc2015;81:621-9. [PMID: 25440671] doi:10.1016/j.gie.2014.09.008 CrossrefMedlineGoogle Scholar
    • 11. Hsu CWLin CJA comparison of methods for multiclass support vector machines. IEEE Trans Neural Netw2002;13:415-25. [PMID: 18244442] doi:10.1109/72.991427 CrossrefMedlineGoogle Scholar
    • 12. Fred TBFatima CRalph HHNeil DDWHO Classification of Tumours of the Digestive System. 4th ed. Lyon, France: International Agency for Research on Cancer; 2010. Google Scholar
    • 13. Rees CJRajasekhar PTWilson AClose HRutter MDSaunders BPet alNarrow band imaging optical diagnosis of small colorectal polyps in routine clinical practice: the Detect Inspect Characterise Resect and Discard 2 (DISCARD 2) study. Gut2017;66:887-95. [PMID: 27196576] doi:10.1136/gutjnl-2015-310584 CrossrefMedlineGoogle Scholar
    • 14. Singh RCheong KLZorron Cheng Tao Pu LMangira DKoay DSCKee Cet alMulticenter randomised controlled trial comparing the high definition white light endoscopy and the bright narrow band imaging for colon polyps. World J Gastrointest Endosc2017;9:273-81. [PMID: 28690771] doi:10.4253/wjge.v9.i6.273 CrossrefMedlineGoogle Scholar
    • 15. Ladabaum UFioritto AMitani ADesai MKim JPRex DKet alReal-time optical biopsy of colon polyps with narrow band imaging in community practice does not yet meet key thresholds for clinical decisions. Gastroenterology2013;144:81-91. [PMID: 23041328] doi:10.1053/j.gastro.2012.09.054 CrossrefMedlineGoogle Scholar
    • 16. Gross STrautwein CBehrens AWinograd RPalm SLutz HHet alComputer-based classification of small colorectal polyps by using narrow-band imaging with optical magnification. Gastrointest Endosc2011;74:1354-9. [PMID: 22000791] doi:10.1016/j.gie.2011.08.001 CrossrefMedlineGoogle Scholar
    • 17. Chen PJLin MCLai MJLin JCLu HHTseng VSAccurate classification of diminutive colorectal polyps using computer-aided analysis. Gastroenterology2018;154:568-75. [PMID: 29042219] doi:10.1053/j.gastro.2017.10.010 CrossrefMedlineGoogle Scholar
    • 18. Tamai NSaito YSakamoto TNakajima TMatsuda TSumiyama Ket alEffectiveness of computer-aided diagnosis of colorectal lesions using novel software for magnifying narrow-band imaging: a pilot study. Endosc Int Open2017;5:E690-4. [PMID: 28782001] doi:10.1055/s-0043-105490 CrossrefMedlineGoogle Scholar
    • 19. East JEVleugels JLRoelandt PBhandari PBisschops RDekker Eet alAdvanced endoscopic imaging: European Society of Gastrointestinal Endoscopy (ESGE) technology review. Endoscopy2016;48:1029-45. [PMID: 27711949] CrossrefMedlineGoogle Scholar
    • 20. Kuiper TAlderlieste YATytgat KMVlug MSNabuurs JABastiaansen BAet alAutomatic optical diagnosis of small colorectal lesions by laser-induced autofluorescence. Endoscopy2015;47:56-62. [PMID: 25264763] doi:10.1055/s-0034-1378112 CrossrefMedlineGoogle Scholar
    • 21. Rath TTontini GEVieth MNägel ANeurath MFNeumann HIn vivo real-time assessment of colorectal polyp histology using an optical biopsy forceps system based on laser-induced fluorescence spectroscopy. Endoscopy2016;48:557-62. [PMID: 27009081] doi:10.1055/s-0042-102251 CrossrefMedlineGoogle Scholar
    • 22. National Institute for Health and Care Excellence. Virtual chromoendoscopy to assess colorectal polyps during colonoscopy. May 2017. Accessed at www.nice.org.uk/guidance/dg28 on 5 April 2018. Google Scholar
    • 23. Iwatate MSano YHattori SSano WHasuike NIkumoto Tet alThe addition of high magnifying endoscopy improves rates of high confidence optical diagnosis of colorectal polyps. Endosc Int Open2015;3:E140-5. [PMID: 26135657] doi:10.1055/s-0034-1391362 CrossrefMedlineGoogle Scholar
    • 24. Tanaka SSaitoh YMatsuda TIgarashi MMatsumoto TIwao Yet alJapanese Society of GastroenterologyEvidence-based clinical practice guidelines for management of colorectal polyps. J Gastroenterol2015;50:252-60. [PMID: 25559129] doi:10.1007/s00535-014-1021-4 CrossrefMedlineGoogle Scholar
    • 25. Hetzel JTHuang CSCoukos JAOmstead KCerda SRYang Set alVariation in the detection of serrated polyps in an average risk colorectal cancer screening cohort. Am J Gastroenterol2010;105:2656-64. [PMID: 20717107] doi:10.1038/ajg.2010.315 CrossrefMedlineGoogle Scholar
    • 26. Lai EJCalderwood AHDoros GFix OKJacobson BCThe Boston bowel preparation scale: a valid and reliable instrument for colonoscopy-oriented research. Gastrointest Endosc2009;69:620-5. [PMID: 19136102] doi:10.1016/j.gie.2008.05.057 CrossrefMedlineGoogle Scholar