A lightweight asymmetric U-Net framework for acute ischemic stroke lesion segmentation in CT and CTP images.

BACKGROUND AND OBJECTIVES: This paper has introduced a patch-based, residual, asymmetric, encoder-decoder CNN that solves two major problems in acute ischemic stroke lesion segmentation from CT and CT perfusion data using deep neural networks. First, the class imbalance is encountered since the lesion core size covers less than 5% of the volume of the entire brain. Second, deeper neural networks face the drawback of vanishing gradients, and this degrades the learning ability of the network. METHODS: The neural network architecture has been designed for better convergence and faster inference time without compromising performance to address these difficulties. It uses a training strategy combining Focal Tversky and Binary cross-entropy loss functions to overcome the class imbalance issue. The model comprises only four resolution steps with a total of 11 convolutional layers. A base filter of 8, used for the residual connection with two convolutional blocks at the encoder side, is doubled after each resolution step. Simultaneously, the decoder consists of residual blocks with one convolutional layer and a constant number of 8 filters in each resolution step. This proposition allows for a lighter build with fewer trainable parameters as well as aids in avoiding overfitting by allowing the decoder to decode only necessary information. RESULTS: The presented method has been evaluated through submission on the publicly accessible platform of the Ischemic Stroke Lesion Segmentation (ISLES) 2018 medical image segmentation challenge achieving the second-highest testing dice similarity coefficient (DSC). The experimental results demonstrate that the proposed model achieves comparable performance to other submitted strategies in terms of DSC Precision, Recall, and Absolute Volume Difference (AVD). CONCLUSIONS: Through the proposed approach, the two major research gaps are coherently addressed while achieving high challenge scores by solving the mentioned problems. Our model can serve as a tool for clinicians and radiologists to hasten decision-making and detect strokes efficiently.

MhURI:A Supervised Segmentation Approach to Leverage Salient Brain Tissues in Magnetic Resonance Images.

BACKGROUND AND OBJECTIVES: Accurate segmentation of critical tissues from a brain MRI is pivotal for characterization and quantitative pattern analysis of the human brain and thereby, identifies the earliest signs of various neurodegenerative diseases. To date, in most cases, it is done manually by the radiologists. The overwhelming workload in some of the thickly populated nations may cause exhaustion leading to interruption for the doctors, which may pose a continuing threat to patient safety. A novel fusion method called U-Net inception based on 3D convolutions and transition layers is proposed to address this issue. METHODS: A 3D deep learning method called Multi headed U-Net with Residual Inception (MhURI) accompanied by Morphological Gradient channel for brain tissue segmentation is proposed, which incorporates Residual Inception 2-Residual (RI2R) module as the basic building block. The model exploits the benefits of morphological pre-processing for structural enhancement of MR images. A multi-path data encoding pipeline is introduced on top of the U-Net backbone, which encapsulates initial global features and captures the information from each MRI modality. RESULTS: The proposed model has accomplished encouraging outcomes, which appreciates the adequacy in terms of some of the established quality metrices when compared with some of the state-of-the-art methods while evaluating with respect to two popular publicly available data sets. CONCLUSION: The model is entirely automatic and able to segment gray matter (GM), white matter (WM), and cerebrospinal fluid (CSF) from brain MRI effectively with sufficient accuracy. Hence, it may be considered to be a potential computer-aided diagnostic (CAD) tool for radiologists and other medical practitioners in their clinical diagnosis workflow.

CSNet: A new DeepNet framework for ischemic stroke lesion segmentation.

BACKGROUND AND OBJECTIVES: Acute stroke lesion segmentation is of paramount importance as it can aid medical personnel to render a quicker diagnosis and administer consequent treatment. Automation of this task is technically exacting due to the variegated appearance of lesions and their dynamic development, medical discrepancies, unavailability of datasets, and the requirement of several MRI modalities for imaging. In this paper, we propose a composite deep learning model primarily based on the self-similar fractal networks and the U-Net model for performing acute stroke diagnosis tasks automatically to assist as well as expedite the decision-making process of medical practitioners. METHODS: We put forth a new deep learning architecture, the Classifier-Segmenter network (CSNet), involving a hybrid training strategy with a self-similar (fractal) U-Net model, explicitly designed to perform the task of segmentation. In fractal networks, the underlying design strategy is based on the repetitive generation of self-similar fractals in place of residual connections. The U-Net model exploits both spatial as well as semantic information along with parameter sharing for a faster and efficient training process. In this new architecture, we exploit the benefits of both by combining them into one hybrid training scheme and developing the concept of a cascaded architecture, which further enhances the model's accuracy by removing redundant parts from the Segmenter's input. Lastly, a voting mechanism has been employed to further enhance the overall segmentation accuracy. RESULTS: The performance of the proposed architecture has been scrutinized against the existing state-of-the-art deep learning architectures applied to various biomedical image processing tasks by submission on the publicly accessible web platform provided by the MICCAI Ischemic Stroke Lesion Segmentation (ISLES) challenge. The experimental results demonstrate the superiority of the proposed method when compared to similar submitted strategies, both qualitatively and quantitatively in terms of some of the well known evaluation metrics, such as Accuracy, Dice-Coefficient, Recall, and Precision. CONCLUSIONS: We believe that our method may find use as a handy tool for doctors to identify the location and extent of irreversibly damaged brain tissue, which is said to be a critical part of the decision-making process in case of an acute stroke.