Automated Gastrointestinal Tract Classification Via Deep Learning and the Ensemble Method

Omair Rashed Abdulwareth Almanifi, Mohd Azraai Mohd Razman, Ismail Mohd Khairuddin, Muhammad Amirul Abdullah, Anwar P.P.Abdul Majeed*

*Corresponding author for this work

Research output: Chapter in Book or Report/Conference proceedingConference Proceedingpeer-review

3 Citations (Scopus)

Abstract

Colorectal cancer is a leading cause of death among the cancer family with a record of almost a million moralities in 2020 alone. While the treatment of colorectal cancer is very difficult, early diagnosis can help immensely with treatment, eliminating the risks, and recovery. In most cases early diagnosis is possible by catching any of the precursors of the disease, many of which appear on the Gastrointestinal tract. The use of machine learning to automate the process of gastrointestinal tract examination could accelerate the process of diagnosis, and increase its efficiency. This study suggests the use of the stacking ensemble method with multiple pre-trained CNN models for an accurate classification of GI tract using the publicly available dataset K vasir. The pre-trained models used in this study were ResNet50, MobileNetV2, and Xception, all of which were ensembled and trained on a subset of the data and tested on another to eliminate bias, and evaluates the model's capacity for generalization. Overall, the model demonstrated impressive performance at 99.2% accuracy, 0.9977 AUC, and 99.29% F1-score, especially compared to the individual constituent models and other models discussed in the review section of the study.

Original languageEnglish
Title of host publication2021 21st International Conference on Control, Automation and Systems, ICCAS 2021
PublisherIEEE Computer Society
Pages602-606
Number of pages5
ISBN (Electronic)9788993215212
DOIs
Publication statusPublished - 2021
Externally publishedYes
Event21st International Conference on Control, Automation and Systems, ICCAS 2021 - Jeju, Korea, Republic of
Duration: 12 Oct 202115 Oct 2021

Publication series

NameInternational Conference on Control, Automation and Systems
Volume2021-October
ISSN (Print)1598-7833

Conference

Conference21st International Conference on Control, Automation and Systems, ICCAS 2021
Country/TerritoryKorea, Republic of
CityJeju
Period12/10/2115/10/21

Keywords

  • CNN
  • Colorectal cancer
  • Deep learning
  • Ensemble
  • Gastrointestinal tract
  • Transfer learning

Fingerprint

Dive into the research topics of 'Automated Gastrointestinal Tract Classification Via Deep Learning and the Ensemble Method'. Together they form a unique fingerprint.

Cite this