MBTFCN: A novel modular fully convolutional network for MRI brain tumor multi-classification

Abstract

Brain tumors represent one of the most challenging tumors that affect the human body due to the nonlinear characteristics of their morphological and textural appearance. Automated brain tumor diagnosis systems based on magnetic resonance images (MRI) help surgeons select suitable clinical practices for the patient. Therefore, increasing the performance of such systems plays a vital role in saving human life. A new modular deep fully convolutional neural network is designed to address this problem. The proposed network consists of four modules namely, Feature Extraction (FE), Residual Strip Pooling Attention (RSPA), Atrous Spatial Pyramid Pooling (ASPP), and classification module. First, discriminative brain tumor features using multiple residual convolutional blocks are extracted by the FE module, and then prominent tumor regions relevant to brain tumor classification are strengthened by the RSPA module. Multi-scale features which carry informative context information are captured by the ASPP module. Finally, the classification module is adopted using convolutional layers with adjusted stride values to classify the extracted multiscale features. The combination of these modules helps to extract both local and contextual information appropriate for brain tumor classification. Four public benchmark datasets containing 9581 brain magnetic resonance images are utilized. The datasets contain different classification tasks, number of samples, image sizes, contrast, and planes. The experimental results show that the proposed method surpasses the performance of other state-of-the-art methods. The proposed method encourages the diagnosis of medical imaging and can solve the problem of large intra-class variations and small-size datasets in medical image classification.