Advanced CNN models in gastric cancer diagnosis: enhancing endoscopic image analysis with deep transfer learning
For the complete images of gastric cancer, EfficientNetB6 computed the top performance with 99.88% accuracy on a loss of 0.049. Additionally, InceptionV3 achieved the highest testing accuracy of 97.94% for detecting normal pylorus, while EfficientNetB6 excelled in detecting ulcerative colitis and normal Z-line with accuracies of 98.8% and 97.85%, respectively. EfficientNetB5 performed best for polyps and stool with accuracies of 98.40% and 96.86%, respectively.The study demonstrates that deep transfer learning techniques can effectively predict and classify different types of gastric cancer at early stages, aiding experts in diagnosis and detection.
Authors
- Muhammad Fazal Ijaz (ORCID: https://orcid.org/0000-0001-5206-272X)
- SeongKi Kim (ORCID: https://orcid.org/0000-0002-2664-3632)
- Priya Bhardwaj (ORCID: https://orcid.org/0000-0002-3147-3500)
- Apeksha Koul (ORCID: https://orcid.org/0000-0002-2387-9025)
- Ankur Changela (ORCID: https://orcid.org/0000-0002-2171-8383)
- Jana Shafi (ORCID: https://orcid.org/0000-0001-6859-670X)
- Yogesh Kumar (ORCID: https://orcid.org/0000-0002-2879-0441)
Institutions
- Prince Sattam Bin Abdulaziz University (SA)
- Melbourne School of Theology (AU)
- Bennett University (IN)
- Pandit Deendayal Energy University (IN)
- Dehradun Institute of Technology University (IN)
Publication Details
- Journal
- Frontiers in Oncology
- Published
- 2024-09-16
- DOI
- https://doi.org/10.3389/fonc.2024.1431912
- Citations
- 8
- Primary Topic
- Gastric Cancer Management and Outcomes
- Type
- article
- Field-Weighted Citation Impact
- 3.35
Funders
- Prince Sattam bin Abdulaziz University
- National Research Foundation
- National Research Foundation of Korea
- Ministry of Science and ICT, South Korea