Segmenting the liver and liver tumors in computed tomography (CT) images is an important step toward quantifiable biomarkers for a computer-aided decision-making system and precise medical diagnosis. Radiologists and specialized physicians use CT images to diagnose and classify liver organs and tumors. Because these organs have similar characteristics in form, texture, and light intensity values, other internal organs such as the heart, spleen, stomach, and kidneys confuse visual recognition of the liver and tumor division. Furthermore, visual identification of liver tumors is time-consuming, complicated, and error-prone, and incorrect diagnosis and segmentation can hurt the patient’s life. Many automatic and semi-automatic methods based on machine learning algorithms have recently been suggested for liver organ recognition and tumor segmentation. However, there are still difficulties due to poor recognition precision and speed and a lack of dependability. This paper presents a novel deep learning-based technique for segmenting liver tumors and identifying liver organs in computed tomography maps. Based on the LiTS17 database, the suggested technique comprises four Chebyshev graph convolution layers and a fully connected layer that can accurately segment the liver and liver tumors. Thus, the accuracy, Dice coefficient, mean IoU, sensitivity, precision, and recall obtained based on the proposed method according to the LiTS17 dataset are around 99.1%, 91.1%, 90.8%, 99.4%, 99.4%, and 91.2%, respectively. In addition, the effectiveness of the proposed method was evaluated in a noisy environment, and the proposed network could withstand a wide range of environmental signal-to-noise ratios (SNRs). Thus, at SNR = −4 dB, the accuracy of the proposed method for liver organ segmentation remained around 90%. The proposed model has obtained satisfactory and favorable results compared to previous research. According to the positive results, the proposed model is expected to be used to assist radiologists and specialist doctors in the near future.

The most widespread illness of the diabetic eye that causes missing eye vision is diabetic retinopathy (DR), which requires disclosure soon to prevent the blindness of the sick. In this study, two features are extracted from retina images with for multiclass DR classification, which include color-based Blood Vessel (BV) segmentation and color-based Contrast-Limited-Adaptive-Histogram-Equalization-Top-Hat (CLAH-TH) segmentation. These features are integrated to enhance the accuracy of classification and detection of DR. Variant models, especially VGG19 and InceptionV3, are trained using a transfer learning approach on the proposed extracted features for DR grading. The data augmentation strategy is employed to improve the accuracy and performance of the proposed method by balancing the dataset and aligning the number of images in each class. Experimental results demonstrate that the proposed method outperforms contemporary CNN models when utilizing the suggested features. The best results obtained from experiments on the Kaggle DR database using the pretrained VGG19 model include an accuracy of 96.7%, a sensitivity of 0.971, and a specificity of 0.981.

Background/Objectives: Accurate segmentation of brain stroke lesions from MRI images is a critical task in medical image analysis that is essential for timely diagnosis and treatment planning. Methods: This paper presents a novel approach for segmenting brain stroke lesions using a deep learning model based on the U-Net neural network architecture. We enhanced the traditional U-Net by integrating a transformer-based backbone, specifically the Mix Vision Transformer (MiT), and compared its performance against other commonly used backbones such as ResNet and EfficientNet. Additionally, we implemented a 2.5D method, which leverages 2D networks to process three-dimensional data slices, effectively balancing the rich spatial context of 3D methods and the simplicity of 2D methods. The 2.5D approach captures inter-slice dependencies, leading to improved lesion delineation without the computational complexity of full 3D models. Utilizing the 2015 ISLES dataset, which includes MRI images and corresponding lesion masks for 20 patients, we conducted our experiments with 4-fold cross-validation to ensure robustness and reliability. To evaluate the effectiveness of our method, we conducted comparative experiments with several state-of-the-art (SOTA) segmentation models, including CNN-based UNet, nnU-Net, TransUNet, and SwinUNet. Results: Our proposed model outperformed all competing methods in terms of Dice Coefficient and Intersection over Union (IoU), demonstrating its robustness and superiority. Our extensive experiments demonstrate that the proposed U-Net with the MiT Backbone, combined with 2.5D data preparation, achieves superior performance metrics, specifically achieving DICE and IoU scores of 0.8153 ± 0.0101 and 0.7835 ± 0.0079, respectively, outperforming other backbone configurations. Conclusions: These results indicate that the integration of transformer-based backbones and 2.5D techniques offers a significant advancement in the accurate segmentation of brain stroke lesions, paving the way for more reliable and efficient diagnostic tools in clinical settings.

In numerical computation of neuromodulator such as transcranial direct current stimulation (tDCS) and transcranial magnetic stimulation (TMS), the quality of the tetrahedral mesh is a significant criterion to achieve accurate results in simulating the electric field distribution. Although there are various algorithms and software products have been proposed to achieve this goal, but most of them have challenges in ease of use or in the quality of the final mesh. Even with the production of tetrahedral mesh, there is still a deficiency in the quality of the tetrahedral mesh that leads to reduced accuracy in the final result. In this paper, a new MATLAB toolbox (SimUTab)a is presented that uses several useful algorithms in this field and also employs new methods to generate high-quality meshes for head models. The proposed method reduces the difficulties and makes it easy to use. The user interface implemented in MATLAB makes easily designing electrodes even with unusual shapes and hence provides the basis for examining the effect of electrode shapes on the electric field distribution of the target area. The proposed method is tested and compared with other active pipelines. The results confirm the superiority of the proposed method and show an improvement in the quality of the final mesh.