Segmentation of images is a common task within medical image analysis and a necessary component of medical image segmentation. The segmentation of the liver and liver tumors is an important but challenging stage in screening and diagnosing liver diseases. Although many automated techniques have been developed for liver and tumor segmentation; however, segmentation of the liver is still challenging due to the fuzzy & complex background of the liver position with other organs. As a result, creating a considerable automated liver and tumour division from CT scans is critical for identifying liver cancer. In this article, deeply dense-network ResU-Net architecture is implemented on CT scan using the 3D-IRCADb01 dataset. An essential feature of ResU-Net is the residual block and U-Net architecture, which extract additional information from the input data compared to the traditional U-Net network. Before being fed to the deep neural network, image pre-processing techniques are applied, including data augmentation, Hounsfield windowing unit, and histogram equalization. The ResU-Net network performance is evaluated using the dice similarity coefficient (DSC) metric. The ResU-Net system with residual connections outperformed state-of-the-art approaches for liver tumour identification, with a DSC value of 0.97% for organ recognition and 0.83% for segmentation methods.

Ensuring safety compliance in underground coal mines is essential for preventing accidents and safeguarding miners. Traditional methods for monitoring helmet usage are often ineffective due to poor visibility, dust, and equipment occlusion. This study proposes an attention-enhanced Vision Transformer (ViT) model, specifically adapted for helmet detection in challenging underground environments. The model processes images as sequences of patches, leveraging multi-head self-attention mechanisms to capture global dependencies and improve feature extraction. A custom dataset was developed from underground coal mine footage, and the model was trained using supervised learning with a cross-entropy loss function. The customized ViT achieved an accuracy of 98%, outperforming other State-Of-The-Art (SOTA) models, such as YOLOv8 with attention mechanisms, Mask R-CNN, and Detectron2. The results demonstrate the effectiveness of the attention-enhanced ViT in accurately detecting helmets, even in low-light and cluttered environments. This research contributes to developing real-time, automated safety monitoring systems, which reduce human error and enhance worker safety in hazardous mining operations.