Abstract: Globally, cervical cancer is one of the top causes of death for women, especially in areas with poor access to medical treatment. Early detection and diagnosis are critical for effective treatment, yet conventional screening techniques, such HPV testing and Pap smears, often face challenges related to subjectivity, time constraints, and the need for skilled professionals. To overcome these challenges, a novel deep learning-based ACERNET model is proposed an automated cervical cancer detection. Initially, the input cervicography images are collected from Publicly available dataset. Then the 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 Cervical cancer. Finally, the extracted features are subsequently fed into Random Forest (RM) classifier that classify Adenocarcinoma and Squamous cell carcinoma. The effectiveness of the proposed ACERNET was evaluated using F1 score, accuracy, precision, recall, and specificity. The proposed ACERNET model achieved a classification accuracy of 98.88%. The proposed model enhanced the total accuracy by 0.67%, 5.91%, 1.04% better than Cervi Former, CYENET, C3Net respectively.

Abstract: Glaucoma is a major contributor to irreversible blindness, a condition marked caused by optic nerve injury, which is frequently brought on by high intraocular pressure. For vision loss to be effectively managed and prevented, early detection is essential. Conventional diagnostic techniques mostly rely on labor-intensive, error-prone manual analysis. To overcome these challenges, a novel deep learning based GD2-EffiNet model is proposed for the detecting of Glaucoma disease. Initially, images are pre-processed using the Gaussian Star Filter (GaSF) to enhance image quality and remove noise. EfficientNet-B0 is employed to extract deep features, enabling the classification of normal and abnormal glaucoma images. Finally, UNet is used to segment the abnormal regions, facilitating early diagnosis. The effectiveness of the proposed GD2-EffiNet method using metrics like F1 score, sensitivity, accuracy, and specificity. The classification accuracy of the proposed GD2-EffiNet model was 99.41%. The proposed model enhanced the total accuracy 0.03%, 1.56%, and 0.59% better than CG-EffiNet, ODGNet, SEG-UNet respectively. The proposed GD2-EffiNet model offers a reliable and efficient solution for automated Glaucoma disease detection, which is essential for early diagnosis and effective management of the condition.

Abstract: Skin cancer is one of the most prevalent types of cancer, has been rising quickly in recent decades. Smoking, Ultraviolet rays, DNA changes and poor lifestyle choices are the main contributors of skin cancer. This paper presented a novel deep learning-based GOA-CRA method is used for sequentially identifying images in the skin cancer. Initially, the images are gathered from the ISIC dataset and undergo multi-scale retinex pre-processing (MSR) to improve the quality of the images. Then, the pre-processed images are used as input for the Grasshopper Optimization Algorithm (GOA) for removing the hairs overlapping in the area of skin. The segmented hair region with the mask and the pre-processed images are taken as an input to the Contextual Residual Aggregation (CRA) network for recreating the image by inpainting the missing pixels. Finally, the proposed GOA-CRA method is used to classify the skin cancer as melanoma skin cancer or not. The proposed GOA-CRA improves the overall accuracy of 5.42%, 4.21%, 5.06% and 2.93% better than U-Net, Link Net, Dense Net, Res Net respectively

Abstract: Leukemia is a heterogeneous group of hematologic malignancies, and remains a critical healthcare concern, affecting both pediatric and adult populations. Despite the complexity of its subtypes: Chronic Myeloid Leukemia (CML), Acute Lymphoblastic Leukemia (ALL), Chronic Lymphocytic Leukemia (CLL), and Acute Myeloid Leukemia (AML) recent scientific advancements have significantly enhanced our understanding of this disease. Innovations in molecular biology, genomics, and immunotherapy have led to increased diagnostic accuracy and the development of novel therapeutic strategies. This review discovers the evolution of leukemia diagnosis, highlighting the role of Next-Generation Sequencing (NGS), flow cytometry, and molecular biomarkers. Furthermore, cutting-edge treatments such as targeted therapies, Chimeric Antigen Receptor (CAR) T-cell therapy, and stem cell transplantation are reshaping patient outcomes. These advancements underscore the potential for medicine to revolutionize leukemia treatment by tailoring therapies to patient profiles. Reviewing the current landscape of leukemia research, this article aims to provide insight into the future directions for improving patient care, overcoming therapeutic resistance, and reducing treatment-related toxicity.

Abstract: Diabetic retinopathy (DR) is a frequent eye disorder mostly affecting diabetics. It affects millions of individuals worldwide and is the leading cause of blindness and visual impairment in diabetics. DR occurs when excessive blood sugar levels damage the retina's small blood vessels. In this paper a novel deep learning-based approach for classifying retinal images into three categories: normal retina, good retina, and bad retina. The proposed system utilizes convolutional neural networks (CNNs) for automated feature extraction and classification. The pipeline begins with image preprocessing, including rescaling, train-test splitting, and data augmentation, to enhance model performance and generalization. The preprocessed images are then fed into a CNN model, which extracts features using several convolutional layers, ReLU activation, and pooling layers to minimize spatial dimensionality. The collected features are flattened and processed through fully linked layers, resulting in a SoftMax activation function that produces probabilistic classification results. The accuracy of the suggested method can reach 99.04%, compared to 83.1%, 83%, and 92.1% for conventional models like the Structured learning, High speed detection, and Fuzzy broad learning. In comparison to the existing approaches, the accuracy of the suggested methodology increased by 16.09%, 13.8%, and 3.75%, respectively.