Browsing by Author "Rehan Raza"

Filter results by typing the first few letters
Now showing 1 - 1 of 1
  • No Thumbnail Available
    Item
    Transfer Learning based Deep Learning Approach for Brain Tumor Segmentation from MR Images
    (Library Information Services, COMSATS University Islamabad, Lahore Campus, 2021) Rehan Raza; SP20-RCS-018; LHR TP 7594; Dr. Usama Ijaz Bajwa
    Glioma is the most prevalent and dangerous type of brain tumor which can be life-threatening when its grade is high. The early detection of these tumors can improve and save the life of the patients. The automatic segmentation of brain tumors from magnetic resonance imaging (MRI) plays a vital role in treatment planning and timely diagnosis. Automatic segmentation is a challenging task due to the massive amount of information provided by MRI and the variation in the location, type, and size of the tumor. Therefore, a reliable and authentic method to segment the tumorous region from healthy tissues accurately is an open challenge in the field of deep learning-based medical image analysis. This thesis presents an end-to-end framework for automatic 3D Brain Tumor Segmentation (BTS). The proposed model is a hybrid of the deep residual network and U-Net model (dResU-Net). The residual network is used as an encoder in the proposed architecture with the decoder of the U-Net model to handle the issue of vanishing gradient. The proposed model is designed to take benefit from low and high features. In addition, shortcut connections are employed in residual convolutional blocks and skip connections between residual and convolutional blocks are utilized in the proposed architecture to accelerate the training process. The proposed architecture achieved promising results with the average dice score of 0.8357, 0.8660, and 0.8004 for the tumor core (TC), whole tumor (WT), and enhancing tumor (ET), respectively, on BraTS 2020 dataset. Furthermore, the proposed dResU-Net model is also compared with modified 3D U-Net and pre-trained ResU-Net34 and ResU Net50 to check the performance of the proposed model over the pre-trained models. To demonstrate the robustness of the proposed model in real-world clinical settings, validation of the trained model on an external cohort is performed on randomly selected 50 patients of the BraTS 2021 benchmark dataset. The achieved dice scores on external cohorts are 0.8400, 0.8601, and 0.8221 for TC, WT, and ET, respectively. The comparison of results of the proposed technique with the state-of-the-art techniques indicates that dResU- x Net can significantly improve the segmentation performance of brain tumor sub-regions.