Abstract: Proximal humeral fractures are common injuries, especially in youngsters and the elderly, and usually correspond to 5–6% of all fractures. There has been a general increase in upper extremity fractures in children. Detecting PHF is the time-consuming process of manual diagnosis by professionals using X-ray images. In this paper, a novel deep learning-based BON-VNET model is proposed for the detection of fracture in bones. Initially, the input CT image is pre-processed utilizing adaptive bilateral filter. Then, the pre-processed images are segmented using V-Net segmentation model. Afterward the segmented images are fed as an input the HOG based feature extraction phase for extracting the relevant features. Finally, the machine learning (ML) based ANFIS approach is employed for the classification of PHF images. From the trail result, the proposed BON-VNET model achieves 99.77% of accuracy rate, which is more than that of the conventional DL networks. Proposed BON-VNET model exhibits an overall accuracy improvement of 13.83%, 8.82%, and 16.95% compared to InceptionV3 Near classification and SVM, respectively.

Abstract: Cervical cancer (CC) is the fourth most frequent form of cancer in women. The HPV-related condition most usually associated with HPV infection is CC in general. One of the often-used methods to find CC is the pap smear. However, some drawbacks include a long wait for findings, a reduction in sensitivity, and a reduction in laboratory quality control. In this research, a novel CER-XNET approach to identifying CC and reducing death rates has been proposed to address these drawbacks. Images from the dataset are initially acquired for MRI cervical scans. The classification of several MRI scans of CC is then done utilizing the deep learning (DL) network. Next, feature extraction is performed on the pre-processed images using capsule network. Using an Xception network, the images are then divided into normal and abnormal classes. The suggested based on its F1score, precision, recall, specificity, and accuracy. The accuracy of the suggested CER-XNET method is 99.24%. The accuracy of the L1reg CNN network strategy outperformed the majority of the reported existing methods, which suggests successful outcomes.

Abstract: The prediction of Abdominal Aortic Aneurysm (AAA) develpoment is crucial to early treatment and surgical intervention. It is critically important to capture key vascular growth factors like blood flow and intraluminal thrombus (ILT) accumulation in order to understand how vascular adaptation occurs. In this paper a novel has been proposed for detecting the AAA. Initially the input CT images are pre-processed using AUG filter to enhance the quality of the images. Then the enhanced images are fed into Modified Deep V3+ for segmenting the required features from the image. The segmented images are inputted into feature extraction process for extracting the required features using Effective Net. Finally, the normal and abnormal classes of the aortic aneurysm detection is classified using DBN classifier. The proposed archives an accuracy rate of 99.34% in the normal classes and 99.28% in the abnormal classes. The accuracy rating of 99.31% achieved by the suggested is higher than that of the current techniques. In this, the proposed achieves an overall accuracy rate of 0.77%, 0.31% and 1.17% over the existing methods such as CTA, PRAEVAorta and ATAAs respectively.

Abstract: Melanoma is the most aggressive form of skin cancer responsible for a significant percentage of skin cancer-related fatalities. However, existing deep learning-based melanoma detection methods face several challenges, including dataset imbalance, which affects model generalizability across different skin tones. Additionally, many models require extensive computational resources, lack interpretability, and struggle with variations in image quality and lesion morphology, leading to potential misclassifications. To overcome these challenges, a novel deep learning-based approaches for automated melanoma detection using Random Forest. Initially, the input image is preprocessed using Gaussian filters (GF) to enhance clarity by reducing noise. The deep learning-based ResNet50 is used for extracting features from the Melanoma images. Finally, the extracted features are subsequently fed into Random Forest (RM) classifier that classify Melanoma and Non-Melanoma. The effectiveness of the proposed AMENET was evaluated using F1 score, accuracy, precision, recall, and specificity. The proposed AMENET model achieved a classification accuracy of 98.88%. The proposed AMENET model enhances the total accuracy by 3.85%, 0.86%, 1.03% better than ConvNeXtV2, DSCIMABNet, CNN-ViT respectively.

Abstract: Melanoma is the most dangerous form of skin cancer and is responsible for more than 70 percent of skin cancer deaths. Melanomas develop from malignant melanocytes. Based on the years lost to cancer, melanoma would merit a higher ranking because relatively young people are affected by this malignancy. Melanoma is usually diagnosed in patients of a relatively young age; overall, the total number of patients suffering from melanoma is accumulating. The automated computerized diagnosis mechanism helps to improve the accurate analysis of skin cancer which helps the dermatologists to accelerate the diagnostic time and improve the better treatment for the patients. Detecting melanoma skin cancer using CNN involves leveraging deep learning techniques to automatically extract and learn hierarchical features from dermoscopic images. CNNs process input images through multiple convolutional layers, capturing essential patterns such as texture, shape, and color variations indicative of melanoma. Pretrained models like SVM, ResNet, U-Net and YOLO are often used to enhance accuracy through transfer learning. YOLO, SVM, CNN, ResNet, U-net and MobileNetv3 network are employs dataset for the detection of skin cancer with 96.46%, 90.35%, 91.23%, 97.87% of success rate respectively