Preparing Well for Esophageal Endoscopic Detection Using a Hybrid Model and Transfer Learning

SIMPLE SUMMARY: The timely detection and accurate classification of esophageal cancer are critical for providing optimal treatment. However, assessing and categorizing pathological conditions related to the esophagus face limitations as they rely on reference document photo-documentation, and the accuracy heavily relies on the endoscopist’s expertise. In recent times, computer-aided endoscopic image classification has achieved remarkable success in this domain. For this study, a dataset of 1002 endoscopic images, comprising 650 white-light images and 352 narrow-band images, was collected for training. The esophageal neoplasms were categorized into three groups: squamous cell carcinoma, high-grade dysplasia, and normal cases. To enhance the prediction results, a hybrid model was proposed, yielding an impressive accuracy of 96.32%, precision of 96.44%, recall of 95.70%, and f1-score of 96.04%. The introduction of AI-based diagnostic platforms is expected to effectively support medical professionals in formulating well-informed treatment regimens. ABSTRACT: Early detection of esophageal cancer through endoscopic imaging is pivotal for effective treatment. However, the intricacies of endoscopic diagnosis, contingent on the physician’s expertise, pose challenges. Esophageal cancer features often manifest ambiguously, leading to potential confusions with other inflammatory esophageal conditions, thereby complicating diagnostic accuracy. In recent times, computer-aided diagnosis has emerged as a promising solution in medical imaging, particularly within the domain of endoscopy. Nonetheless, contemporary AI-based diagnostic models heavily rely on voluminous data sources, limiting their applicability, especially in scenarios with scarce datasets. To address this limitation, our study introduces novel data training strategies based on transfer learning, tailored to optimize performance with limited data. Additionally, we propose a hybrid model integrating EfficientNet and Vision Transformer networks to enhance prediction accuracy. Conducting rigorous evaluations on a carefully curated dataset comprising 1002 endoscopic images (comprising 650 white-light images and 352 narrow-band images), our model achieved exceptional outcomes. Our combined model achieved an accuracy of 96.32%, precision of 96.44%, recall of 95.70%, and f1-score of 96.04%, surpassing state-of-the-art models and individual components, substantiating its potential for precise medical image classification. The AI-based medical image prediction platform presents several advantageous characteristics, encompassing superior prediction accuracy, a compact model size, and adaptability to low-data scenarios. This research heralds a significant stride in the advancement of computer-aided endoscopic imaging for improved esophageal cancer diagnosis.