Computer-aided Diagnostic System with Automated Deep Learning Method Based on the AutoGluon Framework Improved the Diagnostic Accuracy of Early Esophageal Cancer

Overview

Journal J Gastrointest Oncol

Date 2024 May 17

PMID 38756633

Authors

Xin Gao

Jiaxi Lin

Changju Qu

Chao Wang

Airong Wu

Jinzhou Zhu

Chunfang Xu

Affiliations

Soon will be listed here.

Abstract

Background: There have been studies on the application of computer-aided diagnosis (CAD) in the endoscopic diagnosis of early esophageal cancer (EEC), but there is still a significant gap from clinical application. We developed an endoscopic CAD system for EEC based on the AutoGluon framework, aiming to explore the feasibility of automatic deep learning (DL) in clinical application.

Methods: The endoscopic pictures of normal esophagus, esophagitis, and EEC were collected from The First Affiliated Hospital of Soochow University (September 2015 to December 2021) and the Norwegian HyperKvasir database. All images of non-cancerous esophageal lesions and EEC in this study were pathologically examined. There were three tasks: task A was normal lesion classification under non-magnifying endoscopy (n=932 1,092); task B was non-cancer lesion EEC classification under non-magnifying endoscopy (n=594 429); and task C was non-cancer lesion EEC classification under magnifying endoscopy (n=505 824). In all classification tasks, we took 100 pictures as the verification set, and the rest comprised as the training set. The CAD system was established based on the AutoGluon framework. Diagnostic performance of the model was compared with that of endoscopists grouped according to years of experience (senior >15 years; junior <5 years). Model evaluation indicators included accuracy, recall rate, precision, F1 value, interpretation time, and the area under the receiver operating characteristic (ROC) curve (AUC).

Results: In tasks A and B, the accuracies of medium-performance CAD and high-performance CAD were lower than those of junior doctors and senior doctors. In task C, the medium-performance and high-performance CAD accuracies were close to those of junior doctors and senior doctors. The high-performance CAD model outperformed the junior doctors in both task A (0.850 0.830) and task C (0.840 0.830) in sensitivity comparison, but there was still a large gap between high-performance CAD models and doctors in sensitivity comparison. In task A, with the aid of CAD pre-interpretation, the accuracy of junior and senior physicians were significantly improved (from 0.880 to 0.915 and from 0.920 to 0.945, respectively); the time spent on film reading was significantly shortened (junior: from 11.3 to 8.7 s; senior: from 6.7 to 5.5 s). In task C, with the aid of CAD pre-interpretation, the accuracy of junior and senior physicians were significantly improved (from 0.850 to 0.865 and from 0.915 to 0.935, respectively); the reading time was significantly shortened (junior: from 9.5 to 7.7 s; senior: from 5.6 to 3.0 s).

Conclusions: The CAD system based on the AutoGluon framework can assist doctors to improve the diagnostic accuracy and reading time of EEC under endoscopy. This study reveals that automatic DL methods are promising in clinical application.

References

Ohmori M, Ishihara R, Aoyama K, Nakagawa K, Iwagami H, Matsuura N . Endoscopic detection and differentiation of esophageal lesions using a deep neural network. Gastrointest Endosc. 2019; 91(2):301-309.e1. DOI: 10.1016/j.gie.2019.09.034. View

Cui R, Wang L, Lin L, Li J, Lu R, Liu S . Deep Learning in Barrett's Esophagus Diagnosis: Current Status and Future Directions. Bioengineering (Basel). 2023; 10(11). PMC: 10669008. DOI: 10.3390/bioengineering10111239. View

Su F, Zhang W, Liu Y, Chen S, Lin M, Feng M . The development and validation of pathological sections based U-Net deep learning segmentation model for the detection of esophageal mucosa and squamous cell neoplasm. J Gastrointest Oncol. 2023; 14(5):1982-1992. PMC: 10643591. DOI: 10.21037/jgo-23-587. View

Bo Z, Chen B, Zhao Z, He Q, Mao Y, Yang Y . Prediction of Response to Lenvatinib Monotherapy for Unresectable Hepatocellular Carcinoma by Machine Learning Radiomics: A Multicenter Cohort Study. Clin Cancer Res. 2023; 29(9):1730-1740. DOI: 10.1158/1078-0432.CCR-22-2784. View

de Groof A, Struyvenberg M, van der Putten J, van der Sommen F, Fockens K, Curvers W . Deep-Learning System Detects Neoplasia in Patients With Barrett's Esophagus With Higher Accuracy Than Endoscopists in a Multistep Training and Validation Study With Benchmarking. Gastroenterology. 2019; 158(4):915-929.e4. DOI: 10.1053/j.gastro.2019.11.030. View

Zhang J, Mi J, Wang R . Application of convolutional neural network-based endoscopic imaging in esophageal cancer or high-grade dysplasia: A systematic review and meta-analysis. World J Gastrointest Oncol. 2023; 15(11):1998-2016. PMC: 10701233. DOI: 10.4251/wjgo.v15.i11.1998. View

Wu X, Wu H, Miao S, Cao G, Su H, Pan J . Deep learning prediction of esophageal squamous cell carcinoma invasion depth from arterial phase enhanced CT images: a binary classification approach. BMC Med Inform Decis Mak. 2024; 24(1):3. PMC: 10759510. DOI: 10.1186/s12911-023-02386-y. View

Tian H, Xiao S, Jiang X, Tao P . PASSer: fast and accurate prediction of protein allosteric sites. Nucleic Acids Res. 2023; 51(W1):W427-W431. PMC: 10320119. DOI: 10.1093/nar/gkad303. View

Zhu C, Xie Y, Li Q, Zhang Z, Chen J, Zhang K . CPSF6-mediated XBP1 3'UTR shortening attenuates cisplatin-induced ER stress and elevates chemo-resistance in lung adenocarcinoma. Drug Resist Updat. 2023; 68():100933. DOI: 10.1016/j.drup.2023.100933. View

10.

Duan Y, Wang J, Wu P, Shao Y, Chen H, Wang H . AS-NeSt: A Novel 3D Deep Learning Model for Radiation Therapy Dose Distribution Prediction in Esophageal Cancer Treatment With Multiple Prescriptions. Int J Radiat Oncol Biol Phys. 2023; 119(3):978-989. DOI: 10.1016/j.ijrobp.2023.12.001. View

11.

Ju W, Zheng R, Zhang S, Zeng H, Sun K, Wang S . Cancer statistics in Chinese older people, 2022: current burden, time trends, and comparisons with the US, Japan, and the Republic of Korea. Sci China Life Sci. 2022; 66(5):1079-1091. DOI: 10.1007/s11427-022-2218-x. View

12.

Stoyanova R, Katzberger P, Komissarov L, Khadhraoui A, Sach-Peltason L, Groebke Zbinden K . Computational Predictions of Nonclinical Pharmacokinetics at the Drug Design Stage. J Chem Inf Model. 2023; 63(2):442-458. DOI: 10.1021/acs.jcim.2c01134. View

13.

Seo K, Chung B, Panchaseelan H, Kim T, Park H, Oh B . Forecasting the Walking Assistance Rehabilitation Level of Stroke Patients Using Artificial Intelligence. Diagnostics (Basel). 2021; 11(6). PMC: 8232707. DOI: 10.3390/diagnostics11061096. View

14.

Zou Y, Ye F, Kong Y, Hu X, Deng X, Xie J . The Single-Cell Landscape of Intratumoral Heterogeneity and The Immunosuppressive Microenvironment in Liver and Brain Metastases of Breast Cancer. Adv Sci (Weinh). 2022; 10(5):e2203699. PMC: 9929130. DOI: 10.1002/advs.202203699. View

15.

Sankaranarayanan S, Balan J, Walsh J, Wu Y, Minnich S, Piazza A . COVID-19 Mortality Prediction From Deep Learning in a Large Multistate Electronic Health Record and Laboratory Information System Data Set: Algorithm Development and Validation. J Med Internet Res. 2021; 23(9):e30157. PMC: 8480399. DOI: 10.2196/30157. View

16.

Constantin A, Constantinoiu S, Achim F, Socea B, Costea D, Predescu D . Esophageal diverticula: from diagnosis to therapeutic management-narrative review. J Thorac Dis. 2023; 15(2):759-779. PMC: 9992562. DOI: 10.21037/jtd-22-861. View

17.

Liu G, Hua J, Wu Z, Meng T, Sun M, Huang P . Automatic classification of esophageal lesions in endoscopic images using a convolutional neural network. Ann Transl Med. 2020; 8(7):486. PMC: 7210177. DOI: 10.21037/atm.2020.03.24. View

18.

Hosseini F, Asadi F, Emami H, Ebnali M, Harari R . Machine learning applications for early detection of esophageal cancer: a systematic review. BMC Med Inform Decis Mak. 2023; 23(1):124. PMC: 10351192. DOI: 10.1186/s12911-023-02235-y. View

19.

Li B, Cai S, Tan W, Li J, Yalikong A, Feng X . Comparative study on artificial intelligence systems for detecting early esophageal squamous cell carcinoma between narrow-band and white-light imaging. World J Gastroenterol. 2021; 27(3):281-293. PMC: 7814365. DOI: 10.3748/wjg.v27.i3.281. View

20.

Merchan Gomez B, Milla Collado L, Rodriguez M . Artificial intelligence in esophageal cancer diagnosis and treatment: where are we now?-a narrative review. Ann Transl Med. 2023; 11(10):353. PMC: 10477654. DOI: 10.21037/atm-22-3977. View