Incorporating a Novel Dual Transfer Learning Approach for Medical Images

Abstract

Recently, transfer learning approaches appeared to reduce the need for many classified medical images. However, these approaches still contain some limitations due to the mismatch of the domain between the source domain and the target domain. Therefore, this study aims to propose a novel approach, called Dual Transfer Learning (DTL), based on the convergence of patterns between the source and target domains. The proposed approach is applied to four pre-trained models (VGG16, Xception, ResNet50, MobileNetV2) using two datasets: ISIC2020 skin cancer images and ICIAR2018 breast cancer images, by fine-tuning the last layers on a sufficient number of unclassified images of the same disease and on a small number of classified images of the target task, in addition to using data augmentation techniques to balance classes and to increase the number of samples. According to the obtained results, it has been experimentally proven that the proposed approach has improved the performance of all models, where without data augmentation, the performance of the VGG16 model, Xception model, ResNet50 model, and MobileNetV2 model are improved by 0.28%, 10.96%, 15.73%, and 10.4%, respectively, while, with data augmentation, the VGG16 model, Xception model, ResNet50 model, and MobileNetV2 model are improved by 19.66%, 34.76%, 31.76%, and 33.03%, respectively. The Xception model obtained the highest performance compared to the rest of the models when classifying skin cancer images in the ISIC2020 dataset, as it obtained 96.83%, 96.919%, 96.826%, 96.825%, 99.07%, and 94.58% for accuracy, precision, recall, F1-score, sensitivity, and specificity respectively. To classify the images of the ICIAR 2018 dataset for breast cancer, the Xception model obtained 99%, 99.003%, 98.995%, 99%, 98.55%, and 99.14% for accuracy, precision, recall, F1-score, sensitivity, and specificity, respectively. Through these results, the proposed approach improved the models’ performance when fine-tuning was performed on unclassified images of the same disease.

Enhanced cervical precancerous lesions detection and classification using Archimedes Optimization Algorithm with transfer learning

“…In 23 , the authors employed novel methodologies for transfer learning by using uncategorized medical images of the same ailments to mitigate the ImageNet impact. Mukhlif, Al-Khateeb, and Mohammed 24 present a Dual Transfer Learning (DTL) model. The model also integrated data augmentation for class balance and sample augmentation.…”

Diagnosis of Osteoporosis Using Transfer Learning in the Same Domain

“…Many computer-based systems are used to diagnose medical images, whether for osteoporosis, arthritis, cancer, etc. Some of these systems are based on traditional methods; others use deep learning [15][16][17][18], and some studies use transfer learning to diagnose medical images [19][20][21][22].…”

Trustworthy deep learning framework for the detection of abnormalities in X-ray shoulder images

“…TL with a convolutional neural network (CNN) aims to leverage existing generalised knowledge from related source tasks to improve performance on a specific target task with a relatively small dataset [ 11 ]. Using CNNs pre-trained on ImageNet, which is the largest publicly available dataset of natural images [ 17 , 18 ], has become the standard method for TL. However, the fundamental mismatch between medical images and ImageNet in terms of size, features, and tasks makes it unsuitable for TL in medical imaging applications [ 17 , 19 ].…”