Convolutional Neural Network-based Artificial Intelligence for the Diagnosis of Early Esophageal Cancer Based on Endoscopic Images: A Meta-analysis

Overview

Journal Saudi J Gastroenterol

Specialty Gastroenterology

Date 2022 Jul 18

PMID 35848703

Authors

Hongbiao Ma

Longlun Wang

Yinlin Chen

Lu Tian

Affiliations

Soon will be listed here.

Abstract

Background: Early screening and treatment of esophageal cancer (EC) is particularly important for the survival and prognosis of patients. However, early EC is difficult to diagnose by a routine endoscopic examination. Therefore, convolutional neural network (CNN)-based artificial intelligence (AI) has become a very promising method in the diagnosis of early EC using endoscopic images. The aim of this study was to evaluate the diagnostic performance of CNN-based AI for detecting early EC based on endoscopic images.

Methods: A comprehensive search was performed to identify relevant English articles concerning CNN-based AI in the diagnosis of early EC based on endoscopic images (from the date of database establishment to April 2022). The pooled sensitivity (SEN), pooled specificity (SPE), positive likelihood ratio (LR+), negative likelihood ratio (LR-), diagnostic odds ratio (DOR) with 95% confidence interval (CI), summary receiver operating characteristic (SROC) curve, and area under the curve (AUC) for the accuracy of CNN-based AI in the diagnosis of early EC based on endoscopic images were calculated. We used the I test to assess heterogeneity and investigated the source of heterogeneity by performing meta-regression analysis. Publication bias was assessed using Deeks' funnel plot asymmetry test.

Results: Seven studies met the eligibility criteria. The SEN and SPE were 0.90 (95% confidence interval [CI]: 0.82-0.94) and 0.91 (95% CI: 0.79-0.96), respectively. The LR+ of the malignant ultrasonic features was 9.8 (95% CI: 3.8-24.8) and the LR- was 0.11 (95% CI: 0.06-0.21), revealing that CNN-based AI exhibited an excellent ability to confirm or exclude early EC on endoscopic images. Additionally, SROC curves showed that the AUC of the CNN-based AI in the diagnosis of early EC based on endoscopic images was 0.95 (95% CI: 0.93-0.97), demonstrating that CNN-based AI has good diagnostic value for early EC based on endoscopic images.

Conclusions: Based on our meta-analysis, CNN-based AI is an excellent diagnostic tool with high sensitivity, specificity, and AUC in the diagnosis of early EC based on endoscopic images.

Citing Articles

Diagnostic Accuracy of Artificial Intelligence in Endoscopy: Umbrella Review.

Zha B, Cai A, Wang G JMIR Med Inform. 2024; 12:e56361.

PMID: 39093715 PMC: 11296324. DOI: 10.2196/56361.

Identification of runner fatigue stages based on inertial sensors and deep learning.

Chang P, Wang C, Chen Y, Wang G, Lu A Front Bioeng Biotechnol. 2023; 11:1302911.

PMID: 38047289 PMC: 10691589. DOI: 10.3389/fbioe.2023.1302911.

The Advent of Domain Adaptation into Artificial Intelligence for Gastrointestinal Endoscopy and Medical Imaging.

Kim M, Kim S, Kim S, Nam J, Hwang Y, Lim Y Diagnostics (Basel). 2023; 13(19).

PMID: 37835766 PMC: 10572560. DOI: 10.3390/diagnostics13193023.

The Saudi Gastroenterology Association guidelines for quality indicators in gastrointestinal endoscopic procedures.

Alsohaibani F, Aljohany H, Almakadma A, Hamed A, Alkhiari R, Aljahdli E Saudi J Gastroenterol. 2023; 29(3):148-157.

PMID: 36891939 PMC: 10358793. DOI: 10.4103/sjg.sjg_391_22.

References

Rasouli P, Moghadam A, Eslami P, Aghajanpoor Pasha M, Aghdaei H, Mehrvar A . The role of artificial intelligence in colon polyps detection. Gastroenterol Hepatol Bed Bench. 2020; 13(3):191-199. PMC: 7417492. View

Liu X, Wu W, Zhang S, Tan W, Qiu Y, Liao K . Effect of miR-630 expression on esophageal cancer cell invasion and migration. J Clin Lab Anal. 2021; 35(6):e23815. PMC: 8183945. DOI: 10.1002/jcla.23815. View

Cai S, Li B, Tan W, Niu X, Yu H, Yao L . Using a deep learning system in endoscopy for screening of early esophageal squamous cell carcinoma (with video). Gastrointest Endosc. 2019; 90(5):745-753.e2. DOI: 10.1016/j.gie.2019.06.044. View

Methley A, Campbell S, Chew-Graham C, McNally R, Cheraghi-Sohi S . PICO, PICOS and SPIDER: a comparison study of specificity and sensitivity in three search tools for qualitative systematic reviews. BMC Health Serv Res. 2014; 14:579. PMC: 4310146. DOI: 10.1186/s12913-014-0579-0. View

Xiao Z, Ji D, Li F, Li Z, Bao Z . Application of Artificial Intelligence in Early Gastric Cancer Diagnosis. Digestion. 2021; 103(1):69-75. DOI: 10.1159/000519601. View

Mashimo H, Gordon S, Singh S . Advanced endoscopic imaging for detecting and guiding therapy of early neoplasias of the esophagus. Ann N Y Acad Sci. 2020; 1482(1):61-76. PMC: 7780427. DOI: 10.1111/nyas.14523. View

Nakagawa K, Ishihara R, Aoyama K, Ohmori M, Nakahira H, Matsuura N . Classification for invasion depth of esophageal squamous cell carcinoma using a deep neural network compared with experienced endoscopists. Gastrointest Endosc. 2019; 90(3):407-414. DOI: 10.1016/j.gie.2019.04.245. View

Monig S, Chevallay M, Niclauss N, Zilli T, Fang W, Bansal A . Early esophageal cancer: the significance of surgery, endoscopy, and chemoradiation. Ann N Y Acad Sci. 2018; 1434(1):115-123. DOI: 10.1111/nyas.13955. View

Xie S, Santoni G, Malberg K, Lagergren P, Lagergren J . Prediction Model of Long-term Survival After Esophageal Cancer Surgery. Ann Surg. 2021; 273(5):933-939. DOI: 10.1097/SLA.0000000000003431. View

10.

Wu Y, Lin L, Wang J, Wu S . [Application of semantic segmentation based on convolutional neural network in medical images]. Sheng Wu Yi Xue Gong Cheng Xue Za Zhi. 2020; 37(3):533-540. PMC: 10319567. DOI: 10.7507/1001-5515.201906067. View

11.

Hirst J, Smithers B, Gotley D, Thomas J, Barbour A . Defining cure for esophageal cancer: analysis of actual 5-year survivors following esophagectomy. Ann Surg Oncol. 2011; 18(6):1766-74. DOI: 10.1245/s10434-010-1508-z. View

12.

Hassanzadeh T, Essam D, Sarker R . Evolutionary Deep Attention Convolutional Neural Networks for 2D and 3D Medical Image Segmentation. J Digit Imaging. 2021; 34(6):1387-1404. PMC: 8669068. DOI: 10.1007/s10278-021-00526-2. View

13.

Zheng B, Liu T, Chen G, Zhang J, Kang X . The effect of curcumin on cell adhesion of human esophageal cancer cell. Eur Rev Med Pharmacol Sci. 2018; 22(2):551-560. DOI: 10.26355/eurrev_201801_14209. View

14.

Arends L, Hamza T, van Houwelingen J, Heijenbrok-Kal M, Hunink M, Stijnen T . Bivariate random effects meta-analysis of ROC curves. Med Decis Making. 2008; 28(5):621-38. DOI: 10.1177/0272989X08319957. View

15.

McInnes M, Moher D, Thombs B, McGrath T, Bossuyt P, Clifford T . Preferred Reporting Items for a Systematic Review and Meta-analysis of Diagnostic Test Accuracy Studies: The PRISMA-DTA Statement. JAMA. 2018; 319(4):388-396. DOI: 10.1001/jama.2017.19163. View

16.

Domper Arnal M, Ferrandez Arenas A, Lanas Arbeloa A . Esophageal cancer: Risk factors, screening and endoscopic treatment in Western and Eastern countries. World J Gastroenterol. 2015; 21(26):7933-43. PMC: 4499337. DOI: 10.3748/wjg.v21.i26.7933. View

17.

Yamamoto S, Kato K . Pembrolizumab for the treatment of esophageal cancer. Expert Opin Biol Ther. 2020; 20(10):1143-1150. DOI: 10.1080/14712598.2020.1792881. View

18.

Cai W, Li Y, Huang B, Hu C . Esophageal cancer lymph node metastasis-associated gene signature optimizes overall survival prediction of esophageal cancer. J Cell Biochem. 2018; 120(1):592-600. DOI: 10.1002/jcb.27416. View

19.

Zhang C, Chen M, Wang X . Statistical Methods for Quantifying Between-study Heterogeneity in Meta-analysis with Focus on Rare Binary Events. Stat Interface. 2021; 13(4):449-464. PMC: 7901832. DOI: 10.4310/sii.2020.v13.n4.a3. View

20.

Qu Y, Yang Z, Sun F, Zhan S . [Risk on bias assessment: (6) A Revised Tool for the Quality Assessment on Diagnostic Accuracy Studies (QUADAS-2)]. Zhonghua Liu Xing Bing Xue Za Zhi. 2018; 39(4):524-531. DOI: 10.3760/cma.j.issn.0254-6450.2018.04.028. View