MNet-10: A robust shallow convolutional neural network model performing ablation study on medical images assessing the effectiveness of applying optimal data augmentation technique

Abstract

Interpretation of medical images with a computer-aided diagnosis (CAD) system is arduous because of the complex structure of cancerous lesions in different imaging modalities, high degree of resemblance between inter-classes, presence of dissimilar characteristics in intra-classes, scarcity of medical data, and presence of artifacts and noises. In this study, these challenges are addressed by developing a shallow convolutional neural network (CNN) model with optimal configuration performing ablation study by altering layer structure and hyper-parameters and utilizing a suitable augmentation technique. Eight medical datasets with different modalities are investigated where the proposed model, named MNet-10, with low computational complexity is able to yield optimal performance across all datasets. The impact of photometric and geometric augmentation techniques on different datasets is also evaluated. We selected the mammogram dataset to proceed with the ablation study for being one of the most challenging imaging modalities. Before generating the model, the dataset is augmented using the two approaches. A base CNN model is constructed first and applied to both the augmented and non-augmented mammogram datasets where the highest accuracy is obtained with the photometric dataset. Therefore, the architecture and hyper-parameters of the model are determined by performing an ablation study on the base model using the mammogram photometric dataset. Afterward, the robustness of the network and the impact of different augmentation techniques are assessed by training the model with the rest of the seven datasets. We obtain a test accuracy of 97.34% on the mammogram, 98.43% on the skin cancer, 99.54% on the brain tumor magnetic resonance imaging (MRI), 97.29% on the COVID chest X-ray, 96.31% on the tympanic membrane, 99.82% on the chest computed tomography (CT) scan, and 98.75% on the breast cancer ultrasound datasets by photometric augmentation and 96.76% on the breast cancer microscopic biopsy dataset by geometric augmentation. Moreover, some elastic deformation augmentation methods are explored with the proposed model using all the datasets to evaluate their effectiveness. Finally, VGG16, InceptionV3, and ResNet50 were trained on the best-performing augmented datasets, and their performance consistency was compared with that of the MNet-10 model. The findings may aid future researchers in medical data analysis involving ablation studies and augmentation techniques.

A Lightweight Robust Deep Learning Model Gained High Accuracy in Classifying a Wide Range of Diabetic Retinopathy Images

“…The convolutional layers consume a large proportion of the computational, whereas the time pooling and fully connected layers only consume 5 to 10 percent of the computational time [73], [74]. We therefore focus on the time complexity of the convolutional layers; see Table 5 and 6 [74], [75], [76]. We compute the theoretical time complexity, which is defined in [73] as follows:…”

“…Batch size altering can also improve the performance of the model. A large batch size might result in the model taking a long time to converge [75], [76]. Some studies [77], [78], [79] suggest that reducing the batch size enables the network to train more effectively, whereas increasing the batch size degrades the test performance.…”

An Effective Ensemble Machine Learning Approach to Classify Breast Cancer Based on Feature Selection and Lesion Segmentation Using Preprocessed Mammograms

“…However, sometimes even for radiologists, this task becomes challenging due to the interference of dense tissues. Mammograms are quite a challenging dataset as it contains ROI regions that are quite complex [ 13 ]. As the objective is to extract meaningful features from the cancerous region (ROI), segmenting the ROI from the mammograms is quite crucial.…”

Fast and Efficient Lung Abnormality Identification With Explainable AI: A Comprehensive Framework for Chest CT Scan and X-Ray Images

“…For additional statistical examination of the model, the false positive rate (FPR), the false negative rate (FNR), the false discovery rate (FDR), the negative predicted value (NPV) and Matthews Correlation Coefficient (MCC) are also assessed. These evaluation metrics are produced using true negative (TN), true positive (TP), false negative (FN) and false positive (FP) values that are obtained from the confusion metrics [53].…”