Enhanced Pre-Trained Xception Model Transfer Learned for Breast Cancer Detection

Abstract

Early detection and timely breast cancer treatment improve survival rates and patients’ quality of life. Hence, many computer-assisted techniques based on artificial intelligence are being introduced into the traditional diagnostic workflow. This inclusion of automatic diagnostic systems speeds up diagnosis and helps medical professionals by relieving their work pressure. This study proposes a breast cancer detection framework based on a deep convolutional neural network. To mine useful information about breast cancer through breast histopathology images of the 40× magnification factor that are publicly available, the BreakHis dataset and IDC(Invasive ductal carcinoma) dataset are used. Pre-trained convolutional neural network (CNN) models EfficientNetB0, ResNet50, and Xception are tested for this study. The top layers of these architectures are replaced by custom layers to make the whole architecture specific to the breast cancer detection task. It is seen that the customized Xception model outperformed other frameworks. It gave an accuracy of 93.33% for the 40× zoom images of the BreakHis dataset. The networks are trained using 70% data consisting of BreakHis 40× histopathological images as training data and validated on 30% of the total 40× images as unseen testing and validation data. The histopathology image set is augmented by performing various image transforms. Dropout and batch normalization are used as regularization techniques. Further, the proposed model with enhanced pre-trained Xception CNN is fine-tuned and tested on a part of the IDC dataset. For the IDC dataset training, validation, and testing percentages are kept as 60%, 20%, and 20%, respectively. It obtained an accuracy of 88.08% for the IDC dataset for recognizing invasive ductal carcinoma from H&E-stained histopathological tissue samples of breast tissues. Weights learned during training on the BreakHis dataset are kept the same while training the model on IDC dataset. Thus, this study enhances and customizes functionality of pre-trained model as per the task of classification on the BreakHis and IDC datasets. This study also tries to apply the transfer learning approach for the designed model to another similar classification task.

Comparison of Fine-Tuned Networks on Generalization for Face Spoofing Detection

“…The proposed system achieves best HTER of 0.67% which is quite good compared to the existing method for the 3D MAD dataset and 5.78% for NUAA dataset that needs to be improved. The proposed fined tuned networks perform extremely well both for the handcrafted features [24,25] and VGG features as can be seen in Table 2.…”

Baseline model for deep neural networks in resource-constrained environments: an empirical investigation

“…Currently, several pre-trained DNN models exist that have the potential as baseline models to develop new models utilizing the TL approach, such as MobileNet [28], [37], MobileNetV2 [38], [39], EfficientNetB0, EfficientNetB1, EfficientNetB2 [29], [40] DenseNet121 [41], Xception [42], InceptionV3 [43], ResNet50 [44], and InceptionResNetV2 [45]. Each of these models offers its own set of advantages and limitations.…”

Improving Tumor-Infiltrating Lymphocytes Score Prediction in Breast Cancer with Self-Supervised Learning

“…Joshi et al [ 17 ] introduced a deep CNN-based breast cancer detection method, evaluating three pre-trained CNN models (EfficientNetB0, ResNet50, and Xception) using the BreakHis and IDC datasets. Notably, the customized Xception model outperformed the others, achieving a 93.33% accuracy on 40× magnification images from the BreakHis dataset.…”