Artificial Intelligence Assisted Cytological Detection for Early Esophageal Squamous Epithelial Lesions by Using Low-grade Squamous Intraepithelial Lesion As Diagnostic Threshold

Overview

Journal Cancer Med

Specialty Oncology

Date 2022 Jun 29

PMID 35766144

Authors

Bin Yao

Yadong Feng

Kai Zhao

Yan Liang

Peilin Huang

Juncai Zang

Jie Song

Mengjie Li

Xiaofen Wang

Huazhong Shu

Ruihua Shi

Affiliations

Soon will be listed here.

Abstract

Background: Manual cytological diagnosis for early esophageal squamous cell carcinoma (early ESCC) and high-grade intraepithelial neoplasia (HGIN) is unsatisfactory. Herein, we have introduced an artificial intelligence (AI)-assisted cytological diagnosis for such lesions.

Methods: Low-grade squamous intraepithelial lesion or worse was set as the diagnostic threshold for AI-assisted diagnosis. The performance of AI-assisted diagnosis was evaluated and compared to that of manual diagnosis. Feasibility in large-scale screening was also assessed.

Results: AI-assisted diagnosis for abnormal cells was superior to manual reading by presenting a higher efficiency for each slide (50.9 ± 0.8 s vs 236.8 ± 3.9 s, p = 1.52 × 10 ) and a better interobserver agreement (93.27% [95% CI, 92.76%-93.74%] vs 65.29% [95% CI, 64.35%-66.22%], p = 1.03 × 10 ). AI-assisted detection showed a higher diagnostic accuracy (96.89% [92.38%-98.57%] vs 72.54% [65.85%-78.35%], p = 1.42 × 10 ), sensitivity (99.35% [95.92%-99.97%] vs 68.39% [60.36%-75.48%], p = 7.11 × 10 ), and negative predictive value (NPV) (97.06% [82.95%-99.85%] vs 40.96% [30.46%-52.31%], p = 1.42 × 10 ). Specificity and positive predictive value (PPV) were not significantly differed. AI-assisted diagnosis demonstrated a smaller proportion of participants of interest (3.73%, [79/2117] vs.12.84% [272/2117], p = 1.59 × 10 ), a higher consistence between cytology and endoscopy (40.51% [32/79] vs. 12.13% [33/272], p = 1.54 × 10 8), specificity (97.74% [96.98%-98.32%] vs 88.52% [87.05%-89.84%], p = 3.19 × 10 ), and PPV (40.51% [29.79%-52.15%] vs 12.13% [8.61%-16.75%], p = 1.54 × 10 ) in community-based screening. Sensitivity and NPV were not significantly differed. AI-assisted diagnosis as primary screening significantly reduced average cost for detecting positive cases.

Conclusion: Our study provides a novel cytological method for detecting and screening early ESCC and HGIN.

Citing Articles

Impact of human and artificial intelligence collaboration on workload reduction in medical image interpretation.

Chen M, Wang Y, Wang Q, Shi J, Wang H, Ye Z NPJ Digit Med. 2024; 7(1):349.

PMID: 39616244 PMC: 11608314. DOI: 10.1038/s41746-024-01328-w.

Efficiency of endoscopic artificial intelligence in the diagnosis of early esophageal cancer.

Tao Y, Fang L, Qin G, Xu Y, Zhang S, Zhang X Thorac Cancer. 2024; 15(16):1296-1304.

PMID: 38685604 PMC: 11147664. DOI: 10.1111/1759-7714.15261.

The current state of artificial intelligence in endoscopic diagnosis of early esophageal squamous cell carcinoma.

Pan Y, He L, Chen W, Yang Y Front Oncol. 2023; 13:1198941.

PMID: 37293591 PMC: 10247226. DOI: 10.3389/fonc.2023.1198941.

Artificial intelligence assisted cytological detection for early esophageal squamous epithelial lesions by using low-grade squamous intraepithelial lesion as diagnostic threshold.

Yao B, Feng Y, Zhao K, Liang Y, Huang P, Zang J Cancer Med. 2022; 12(2):1228-1236.

PMID: 35766144 PMC: 9883535. DOI: 10.1002/cam4.4984.

References

He Z, Zhao Y, Guo C, Liu Y, Sun M, Liu F . Prevalence and risk factors for esophageal squamous cell cancer and precursor lesions in Anyang, China: a population-based endoscopic survey. Br J Cancer. 2010; 103(7):1085-8. PMC: 2965859. DOI: 10.1038/sj.bjc.6605843. View

Bocking A, Friedrich D, Meyer-Ebrecht D, Zhu C, Feider A, Biesterfeld S . Automated detection of cancer cells in effusion specimens by DNA karyometry. Cancer Cytopathol. 2018; 127(1):18-25. PMC: 6587753. DOI: 10.1002/cncy.22072. View

Nayar R, Wilbur D . The Bethesda System for Reporting Cervical Cytology: A Historical Perspective. Acta Cytol. 2017; 61(4-5):359-372. DOI: 10.1159/000477556. View

Gao Y, Xin L, Feng Y, Yao B, Lin H, Sun C . Feasibility and Accuracy of Artificial Intelligence-Assisted Sponge Cytology for Community-Based Esophageal Squamous Cell Carcinoma Screening in China. Am J Gastroenterol. 2021; 116(11):2207-2215. DOI: 10.14309/ajg.0000000000001499. View

. The global, regional, and national burden of oesophageal cancer and its attributable risk factors in 195 countries and territories, 1990-2017: a systematic analysis for the Global Burden of Disease Study 2017. Lancet Gastroenterol Hepatol. 2020; 5(6):582-597. PMC: 7232026. DOI: 10.1016/S2468-1253(20)30007-8. View

Yao B, Feng Y, Zhao K, Liang Y, Huang P, Zang J . Artificial intelligence assisted cytological detection for early esophageal squamous epithelial lesions by using low-grade squamous intraepithelial lesion as diagnostic threshold. Cancer Med. 2022; 12(2):1228-1236. PMC: 9883535. DOI: 10.1002/cam4.4984. View

Hull R, Mbele M, Makhafola T, Hicks C, Wang S, Reis R . A multinational review: Oesophageal cancer in low to middle-income countries. Oncol Lett. 2020; 20(4):42. PMC: 7412736. DOI: 10.3892/ol.2020.11902. View

ROTH M, Liu S, Dawsey S, Zhou B, Copeland C, Wang G . Cytologic detection of esophageal squamous cell carcinoma and precursor lesions using balloon and sponge samplers in asymptomatic adults in Linxian, China. Cancer. 1997; 80(11):2047-59. DOI: 10.1002/(sici)1097-0142(19971201)80:11<2047::aid-cncr3>3.0.co;2-u. View

Sarwar S, Dent A, Faust K, Richer M, Djuric U, Van Ommeren R . Physician perspectives on integration of artificial intelligence into diagnostic pathology. NPJ Digit Med. 2019; 2:28. PMC: 6550202. DOI: 10.1038/s41746-019-0106-0. View

10.

Pan Q, Roth M, Guo H, Kochman M, Wang G, Henry M . Cytologic detection of esophageal squamous cell carcinoma and its precursor lesions using balloon samplers and liquid-based cytology in asymptomatic adults in Llinxian, China. Acta Cytol. 2008; 52(1):14-23. DOI: 10.1159/000325430. View

11.

Mariano V, Pastrez P, Mafra Costa A, Guimaraes D, Cunha T, Neto S . Impact of Brush Cytology Analysis for the Diagnosis of Esophageal Squamous Cell Carcinoma: The Quality of Liquid-Based Preparation of Cytological Slides. Acta Cytol. 2019; 63(3):240-246. DOI: 10.1159/000496567. View

12.

Haisley K, Dolan J, Olson S, Toledo-Valdovinos S, Hart K, Bakis G . Sponge Sampling with Fluorescent In Situ Hybridization as a Screening Tool for the Early Detection of Esophageal Cancer. J Gastrointest Surg. 2016; 21(2):215-221. DOI: 10.1007/s11605-016-3239-3. View

13.

Nagtegaal I, Odze R, Klimstra D, Paradis V, Rugge M, Schirmacher P . The 2019 WHO classification of tumours of the digestive system. Histopathology. 2019; 76(2):182-188. PMC: 7003895. DOI: 10.1111/his.13975. View

14.

Bao H, Bi H, Zhang X, Zhao Y, Dong Y, Luo X . Artificial intelligence-assisted cytology for detection of cervical intraepithelial neoplasia or invasive cancer: A multicenter, clinical-based, observational study. Gynecol Oncol. 2020; 159(1):171-178. DOI: 10.1016/j.ygyno.2020.07.099. View

15.

Landau M, Pantanowitz L . Artificial intelligence in cytopathology: a review of the literature and overview of commercial landscape. J Am Soc Cytopathol. 2019; 8(4):230-241. DOI: 10.1016/j.jasc.2019.03.003. View

16.

Roshandel G, Merat S, Sotoudeh M, Khoshnia M, Poustchi H, Lao-Sirieix P . Pilot study of cytological testing for oesophageal squamous cell dysplasia in a high-risk area in Northern Iran. Br J Cancer. 2014; 111(12):2235-41. PMC: 4264437. DOI: 10.1038/bjc.2014.506. View

17.

Feng Y, Liang Y, Yao B, Xu J, Zang J, Zhang Y . A Rapid Cytological Screening as pre-Endoscopy Screening for Early Esophageal Squamous Cell Lesions: A Prospective Pilot Study from a Chinese Academic Center. Technol Cancer Res Treat. 2022; 21:15330338211066200. PMC: 8811134. DOI: 10.1177/15330338211066200. View

18.

Gao Q, Fang J . Early esophageal cancer screening in China. Best Pract Res Clin Gastroenterol. 2015; 29(6):885-93. DOI: 10.1016/j.bpg.2015.09.018. View

19.

Schmidt J, Henriksen J, McKeon D, Savik K, Gulbahce H, Pambuccian S . Visual estimates of nucleus-to-nucleus ratios: can we trust our eyes to use the Bethesda ASCUS and LSIL size criteria?. Cancer. 2008; 114(5):287-93. DOI: 10.1002/cncr.23798. View

20.

He Z, Liu Z, Liu M, Guo C, Xu R, Li F . Efficacy of endoscopic screening for esophageal cancer in China (ESECC): design and preliminary results of a population-based randomised controlled trial. Gut. 2018; 68(2):198-206. DOI: 10.1136/gutjnl-2017-315520. View