Brain Stroke Lesion Segmentation Using Computed Tomography Images based on Modified U-Net Model with ResNet Blocks

Abstract

Segmentation of brain regions affected by ischemic stroke helps to overcome the main obstacles in modern studies of stroke visualization. Unfortunately, contemporary methods of solving this problem using artificial intelligence methods are not optimal. Therefore, in the study we consider how to increase the efficiency of segmentation of the stroke focus using computer perfusion imaging using modifications based on UNet. The network was trained and tested using the ISLES 2018 dataset. The publication includes an analysis of the results obtained, as well as recommendations for future research. By choosing the appropriate model parameters, our approach can be easily applied to detect ischemic stroke. We present modified U-Net models with two ResNet blocks as U-Net+ ResNetblock 1 and U-Net +ResNetblock 2, as well as a modified UNet model. Due to the small number of images for training the model, the best results were obtained by applying data preprocessing and object representation approaches, as well as data normalization methods to avoid overfitting. The results show that the modified UNet model is superior to other models in terms of average distance and recall, that are significant parameters for segmentation of the stroke.

Case of Myocardial Infarction with Nonobstructive Coronary Arteries Caused by Thebesian Veins Thrombosis

“…The pain syndrome can be mild or atypical or absent with insufficient or even no changes on ECG, as it happened in the current patient (27). Regarding EchoCG, in the area of myocardial damage in the apical lateral segment of the left ventricle, hypo-/akinesis developed as a protective reaction to injury (stunning of the myocardium) (28)(29)(30). At stage, I, the area of the viable myocardium had to be differentiated from the hibernating myocardium.…”

Advancing Brain Tumor Segmentation in MRI Scans: Hybrid Attention-Residual UNET with Transformer Blocks

“…Among these methods, convolutional neural networks (CNNs) have emerged as highly successful in numerous medical image segmentation tasks [5]. CNN-based segmentation techniques can automatically learn hierarchical representations of medical images, enabling them to effectively capture essential image features [7,15]. This section discusses state-of-the-art techniques for medical image segmentation, including their applications, advantages, and disadvantages.…”

“…It is renowned for its capacity to handle small and typically shaped objects, making it an excellent choice for activities involving medical imaging. It consists of a contracting path and an expansive path, allowing it to learn both low-level and high-level image features [6,15]. U-Net has fewer parameters compared to other architectures, making it more computationally efficient, crucial for real-time applications.…”

Differentiated diagnostic and surgical algorithm for isolated and combined Chiari malformation Type I

“…Usually, the operation is completed within 2-3 hours. The rare complications after surgery are represented by spasms of the neck muscles, which are eliminated by muscle relaxants; development of infection, and liquorrhea (28)(29)(30). Although these studies focus on ACM I and surgical interventions, they differ in patient populations, symptom correlations, outcomes, and focus.…”