Classification of Early Stages of Esophageal Cancer Using Transfer Learning - 05/11/21
Cet article a été publié dans un numéro de la revue, cliquez ici pour y accéder
Graphical abstract |
Highlights |
• | Studies revealed a 5-fold increase in EAC patients diagnosed with Esophagitis. |
• | Those with Barrett's Esophagus have a greater risk of EAC. |
• | Deep Convolution Neural Networks (DCNN) is used to perform classification. |
• | The ResNet50 model with transfer learning gives a better performance. |
• | The DCNN is effective for both as feature extractors and classification models. |
Abstract |
Objectives |
Esophageal Cancer is the sixth most common cancer with a high fatality rate. Early prognosis of esophageal abnormalities can improve the survival rate of the patients. The sequence of the progress of the esophageal cancer is from esophagitis to non-dysplasia Barrett's esophagus to dysplasia Barrett's esophagus to esophageal adenocarcinoma (EAC). Many studies revealed a 5-fold increase in EAC patients diagnosed with esophagitis, and those diagnosed with Barrett's esophagus have a greater risk of EAC.
Material and methods |
Convolutional Neural Network (CNN) with efficient feature extractors enable better prognosis of the pre cancerous stage, Barrett's esophagus and esophagitis. The transfer learning techniques with CNN can extract more relevant features for the automated classification of Barrett's esophagus and esophagitis. This paper presents a study on the classification of the esophagitis and Barrett's esophagus (BE) using Deep Convolution Neural Networks (DCNN).
Results |
In the first experiment, the DCNN models perform as a feature extractor, and standard classifiers do the classification. The performance analysis shows that the CNN model ResNet50 with Support Vector Machine (SVM) has an accuracy of 93.5%, recall 93.5%, precision 93.4%, f score 93.5%, AUC 89.8%. In the second experiment, the DCNN classification models perform the classification with Transfer Learning and fine-tuning. The ResNet50 model has improved accuracy of 94.46%, precision 94.46%, f score 94.46%, AUC 96.20%.
Conclusion |
The ResNet50 model with transfer learning and fine-tuning gives a better performance than the ResNet50 model with SVM classifier. Our experiments show that the DCNN is effective for diagnosing EAC, both as feature extractors and classification models with transfer learning and fine-tuning.
Le texte complet de cet article est disponible en PDF.Keywords : Barrett's esophagus, Deep convolution neural networks, Esophagitis, ResNet50, Support vector machine
Plan
Bienvenue sur EM-consulte, la référence des professionnels de santé.
L’accès au texte intégral de cet article nécessite un abonnement.
Déjà abonné à cette revue ?