Artificial intelligence and high-resolution anoscopy: automatic identification of anal squamous cell carcinoma precursors using a convolutional neural network.
Anal cancer
Artificial intelligence
HSIL
High-resolution anoscopy
LSIL
Journal
Techniques in coloproctology
ISSN: 1128-045X
Titre abrégé: Tech Coloproctol
Pays: Italy
ID NLM: 9613614
Informations de publication
Date de publication:
11 2022
11 2022
Historique:
received:
27
03
2022
accepted:
09
08
2022
pubmed:
21
8
2022
medline:
1
10
2022
entrez:
20
8
2022
Statut:
ppublish
Résumé
High-resolution anoscopy (HRA) is the gold standard for detecting anal squamous cell cancer (ASCC) precursors. Although it is superior to other diagnostic methods, particularly cytology, the visual identification of areas suspected of having high-grade squamous intraepithelial lesions remains difficult. Convolutional neural networks (CNNs) have shown great potential for assessing endoscopic images. The aim of the present study was to develop a CNN-based system for automatic detection and differentiation of HSIL versus LSIL in HRA images. A CNN was developed based on 78 HRA exams from a total of 71 patients who underwent HRA at a single high-volume center (GH Paris Saint-Joseph, Paris, France) between January 2021 and January 2022. A total of 5026 images were included, 1517 images containing HSIL and 3509 LSIL. A training dataset comprising 90% of the total pool of images was defined for the development of the network. The performance of the CNN was evaluated using an independent testing dataset comprising the remaining 10%. The sensitivity, specificity, accuracy, positive and negative predictive values, and area under the curve (AUC) were calculated. The algorithm was optimized for the automatic detection of HSIL and its differentiation from LSIL. Our model had an overall accuracy of 90.3%. The CNN had sensitivity, specificity, positive and negative predictive values of 91.4%, 89.7%, 80.9%, and 95.6%, respectively. The area under the curve was 0.97. The CNN architecture for application to HRA accurately detected precursors of squamous anal cancer. Further development and implementation of these tools in clinical practice may significantly modify the management of these patients.
Sections du résumé
BACKGROUND
High-resolution anoscopy (HRA) is the gold standard for detecting anal squamous cell cancer (ASCC) precursors. Although it is superior to other diagnostic methods, particularly cytology, the visual identification of areas suspected of having high-grade squamous intraepithelial lesions remains difficult. Convolutional neural networks (CNNs) have shown great potential for assessing endoscopic images. The aim of the present study was to develop a CNN-based system for automatic detection and differentiation of HSIL versus LSIL in HRA images.
METHODS
A CNN was developed based on 78 HRA exams from a total of 71 patients who underwent HRA at a single high-volume center (GH Paris Saint-Joseph, Paris, France) between January 2021 and January 2022. A total of 5026 images were included, 1517 images containing HSIL and 3509 LSIL. A training dataset comprising 90% of the total pool of images was defined for the development of the network. The performance of the CNN was evaluated using an independent testing dataset comprising the remaining 10%. The sensitivity, specificity, accuracy, positive and negative predictive values, and area under the curve (AUC) were calculated.
RESULTS
The algorithm was optimized for the automatic detection of HSIL and its differentiation from LSIL. Our model had an overall accuracy of 90.3%. The CNN had sensitivity, specificity, positive and negative predictive values of 91.4%, 89.7%, 80.9%, and 95.6%, respectively. The area under the curve was 0.97.
CONCLUSIONS
The CNN architecture for application to HRA accurately detected precursors of squamous anal cancer. Further development and implementation of these tools in clinical practice may significantly modify the management of these patients.
Identifiants
pubmed: 35986806
doi: 10.1007/s10151-022-02684-z
pii: 10.1007/s10151-022-02684-z
doi:
Types de publication
Journal Article
Langues
eng
Sous-ensembles de citation
IM
Pagination
893-900Informations de copyright
© 2022. Springer Nature Switzerland AG.
Références
Islami F, Ferlay J, Lortet-Tieulent J, Bray F, Jemal A (2017) International trends in anal cancer incidence rates. Int J Epidemiol 46(3):924–938. https://doi.org/10.1093/ije/dyw276
doi: 10.1093/ije/dyw276
pubmed: 27789668
Smittenaar CR, Petersen KA, Stewart K, Moitt N (2016) Cancer incidence and mortality projections in the UK until 2035. Br J Cancer 115(9):1147–1155. https://doi.org/10.1038/bjc.2016.304
doi: 10.1038/bjc.2016.304
pubmed: 27727232
pmcid: 5117795
Ebisch RMF, Rutten DWE, IntHout J et al (2017) Long-lasting increased risk of human papillomavirus-related carcinomas and premalignancies after cervical intraepithelial neoplasia grade 3: a population-based cohort study. J Clin Oncol 35(22):2542–2550. https://doi.org/10.1200/jco.2016.71.4543
doi: 10.1200/jco.2016.71.4543
pubmed: 28541790
Deshmukh AA, Suk R, Shiels MS et al (2020) Recent trends in squamous cell carcinoma of the anus incidence and mortality in the United States, 2001–2015. J Natl Cancer Inst 112(8):829–838. https://doi.org/10.1093/jnci/djz219
doi: 10.1093/jnci/djz219
pubmed: 31742639
Maugin F, Lesage AC, Hoyeau N et al (2020) Early detection of anal high-grade squamous intraepithelial lesion: do we have an impact on progression to invasive anal carcinoma? J Low Genit Tract Dis 24(1):82–86. https://doi.org/10.1097/lgt.0000000000000505
doi: 10.1097/lgt.0000000000000505
pubmed: 31860581
De Vuyst H, Clifford GM, Nascimento MC, Madeleine MM, Franceschi S (2009) Prevalence and type distribution of human papillomavirus in carcinoma and intraepithelial neoplasia of the vulva, vagina and anus: a meta-analysis. Int J Cancer 124(7):1626–1636. https://doi.org/10.1002/ijc.24116
doi: 10.1002/ijc.24116
pubmed: 19115209
Machalek DA, Grulich AE, Jin F, Templeton DJ, Poynten IM (2012) The epidemiology and natural history of anal human papillomavirus infection in men who have sex with men. Sex Health 9(6):527–537. https://doi.org/10.1071/sh12043
doi: 10.1071/sh12043
pubmed: 23380235
Bull-Henry K, Morris B, Buchwald UK (2020) The importance of anal cancer screening and high-resolution anoscopy to gastroenterology practice. Curr Opin Gastroenterol 36(5):393–401. https://doi.org/10.1097/mog.0000000000000661
doi: 10.1097/mog.0000000000000661
pubmed: 32701604
Albuquerque A, Rios E, Schmitt F (2019) Recommendations favoring anal cytology as a method for anal cancer screening: a systematic review. Cancers (Basel). https://doi.org/10.3390/cancers11121942
doi: 10.3390/cancers11121942
Mistrangelo M, Salzano A (2019) Progression of LSIL to HSIL or SCC: is anoscopy and biopsy good enough? Tech Coloproctol 23(4):303–304. https://doi.org/10.1007/s10151-019-02001-1
doi: 10.1007/s10151-019-02001-1
pubmed: 31104190
Albuquerque A, Sheaff M, Stirrup O et al (2018) Performance of anal cytology compared with high-resolution anoscopy and histology in women with lower anogenital tract neoplasia. Clin Infect Dis 67(8):1262–1268. https://doi.org/10.1093/cid/ciy273
doi: 10.1093/cid/ciy273
pubmed: 29659752
Stewart DB, Gaertner WB, Glasgow SC, Herzig DO, Feingold D, Steele SR (2018) The American Society of colon and rectal surgeons clinical practice guidelines for anal squamous cell cancers (revised 2018). Dis Colon Rectum 61(7):755–774. https://doi.org/10.1097/dcr.0000000000001114
doi: 10.1097/dcr.0000000000001114
pubmed: 29878949
Albuquerque A (2015) High-resolution anoscopy: unchartered territory for gastroenterologists? World J Gastrointest Endosc 7(13):1083–1087. https://doi.org/10.4253/wjge.v7.i13.1083
doi: 10.4253/wjge.v7.i13.1083
pubmed: 26421104
pmcid: 4580949
Ishiyama M, Kudo S-E, Misawa M et al (2022) Impact of the clinical use of artificial intelligence-assisted neoplasia detection for colonoscopy: a large-scale prospective, propensity score-matched study (with video). Gastrointest Endosc 95(1):155–163. https://doi.org/10.1016/j.gie.2021.07.022
doi: 10.1016/j.gie.2021.07.022
pubmed: 34352255
Wu L, Xu M, Jiang X et al (2022) Real-time artificial intelligence for detecting focal lesions and diagnosing neoplasms of the stomach by white-light endoscopy (with videos). Gastrointest Endosc 95(2):269-280.e266. https://doi.org/10.1016/j.gie.2021.09.017
doi: 10.1016/j.gie.2021.09.017
pubmed: 34547254
Darragh TM, Colgan TJ, Cox JT et al (2012) The lower anogenital squamous terminology standardization project for HPV-associated lesions: background and consensus recommendations from the College of American Pathologists and the American Society for Colposcopy and Cervical Pathology. J Low Genit Tract Dis 16(3):205–242. https://doi.org/10.1097/LGT.0b013e31825c31dd
doi: 10.1097/LGT.0b013e31825c31dd
pubmed: 22820980
Bradsky G (2000) The OpenCV library. Dr Dobb’s J Softw Tools 120:122–125
Saraiva MM, Ribeiro T, Ferreira JPS et al (2022) Artificial intelligence for automatic diagnosis of biliary stricture malignancy status in single-operator cholangioscopy: a pilot study. Gastrointest Endosc 95(2):339–348. https://doi.org/10.1016/j.gie.2021.08.027
doi: 10.1016/j.gie.2021.08.027
pubmed: 34508767
Aoki T, Yamada A, Aoyama K et al (2019) Automatic detection of erosions and ulcerations in wireless capsule endoscopy images based on a deep convolutional neural network. Gastrointest Endosc 89(2):357-363.e352. https://doi.org/10.1016/j.gie.2018.10.027
doi: 10.1016/j.gie.2018.10.027
pubmed: 30670179
Repici A, Badalamenti M, Maselli R et al (2020) Efficacy of real-time computer-aided detection of colorectal neoplasia in a randomized trial. Gastroenterology 159(2):512-520.e517. https://doi.org/10.1053/j.gastro.2020.04.062
doi: 10.1053/j.gastro.2020.04.062
pubmed: 32371116
Marya NB, Powers PD, Chari ST et al (2020) Utilisation of artificial intelligence for the development of an EUS-convolutional neural network model trained to enhance the diagnosis of autoimmune pancreatitis. Gut. https://doi.org/10.1136/gutjnl-2020-322821
doi: 10.1136/gutjnl-2020-322821
pubmed: 33028668
Nahas CS, da Silva Filho EV, Segurado AA et al (2009) Screening anal dysplasia in HIV-infected patients: is there an agreement between anal pap smear and high-resolution anoscopy-guided biopsy? Dis Colon Rectum 52(11):1854–1860. https://doi.org/10.1007/DCR.0b013e3181b98f36
doi: 10.1007/DCR.0b013e3181b98f36
pubmed: 19966632
Dalla Pria A, Alfa-Wali M, Fox P et al (2014) High-resolution anoscopy screening of HIV-positive MSM: longitudinal results from a pilot study. AIDS 28(6):861–867. https://doi.org/10.1097/qad.0000000000000160
doi: 10.1097/qad.0000000000000160
pubmed: 24441516
Camus M, Lesage AC, Fléjou JF, Hoyeau N, Atienza P, Etienney I (2015) Which lesions should be biopsied during high-resolution anoscopy? Prospective descriptive study of simple morphological criteria. J Low Genit Tract Dis 19(2):156–160. https://doi.org/10.1097/lgt.0000000000000064
doi: 10.1097/lgt.0000000000000064
pubmed: 24983348
Jay N, Berry JM, Miaskowski C et al (2015) Colposcopic characteristics and lugol’s staining differentiate anal high-grade and low-grade squamous intraepithelial lesions during high resolution anoscopy. Papillomavirus Res 1:101–108. https://doi.org/10.1016/j.pvr.2015.06.004
doi: 10.1016/j.pvr.2015.06.004
pubmed: 26640825
pmcid: 4666550
Richel O, Hallensleben ND, Kreuter A, van Noesel CJ, Prins JM, de Vries HJ (2013) High-resolution anoscopy: clinical features of anal intraepithelial neoplasia in HIV-positive men. Dis Colon Rectum 56(11):1237–1242. https://doi.org/10.1097/DCR.0b013e3182a53568
doi: 10.1097/DCR.0b013e3182a53568
pubmed: 24104998
Hillman RJ, Cuming T, Darragh T et al (2016) 2016 IANS international guidelines for practice standards in the detection of anal cancer precursors. J Low Genit Tract Dis 20(4):283–291. https://doi.org/10.1097/lgt.0000000000000256
doi: 10.1097/lgt.0000000000000256
pubmed: 27561134
Nowak RG, Nnaji CH, Dauda W et al (2020) Satisfaction with high-resolution anoscopy for anal cancer screening among men who have sex with men: a cross-sectional survey in Abuja, Nigeria. BMC Cancer 20(1):98. https://doi.org/10.1186/s12885-020-6567-3
doi: 10.1186/s12885-020-6567-3
pubmed: 32024521
pmcid: 7003335
Lam JO, Barnell GM, Merchant M, Ellis CG, Silverberg MJ (2018) Acceptability of high-resolution anoscopy for anal cancer screening in HIV-infected patients. HIV Med 19(10):716–723. https://doi.org/10.1111/hiv.12663
doi: 10.1111/hiv.12663
pubmed: 30084191
Siegenbeek van Heukelom ML, Marra E, Cairo I et al (2018) Detection rate of high-grade squamous intraepithelial lesions as a quality assurance metric for high-resolution anoscopy in HIV-positive men. Dis Colon Rectum 61(7):780–786. https://doi.org/10.1097/dcr.0000000000001039
doi: 10.1097/dcr.0000000000001039
pubmed: 29771801
Palefsky JM, Lee JY, Jay N et al (2022) Treatment of anal high-grade squamous intraepithelial lesions to prevent anal cancer. N Engl J Med 386(24):2273–2282. https://doi.org/10.1056/NEJMoa2201048
doi: 10.1056/NEJMoa2201048
pubmed: 35704479