Diabetic Retinopathy affects one-third of all diabetic patients and may cause vision impairment. It has four stages of progression, i.e., mild non-proliferative, moderate non-proliferative, severe non-proliferative and proliferative Diabetic Retinopathy. The disease has no noticeable symptoms at early stages and may lead to chronic destruction, thus causing permanent blindness if not detected at an early stage. The proposed research provides deep learning frameworks for autonomous detection of Diabetic Retinopathy at an early stage using fundus images. The first framework consists of cascaded neural networks, spanned in three layers where each layer classifies data into two classes, one is the desired stage and the other output is passed to another classifier until the input image is classified as one of the stages. The second framework takes normalized, HSV and RGB fundus images as input to three Convolutional Neural Networks, and the resultant probabilistic vectors are averaged together to obtain the final output of the input image. Third framework used the Long Short Term Memory Module in CNN to emphasize the network in remembering information over a long time span. Proposed frameworks were tested and compared on the large-scale Kaggle fundus image dataset EYEPAC. The evaluations have shown that the second framework outperformed others and achieved an accuracy of 78.06% and 83.78% without and with augmentation, respectively.

Skin, the largest organ of the human body, serves as a protective barrier against the external environment, safeguarding the internal organs. It is composed of layers, namely the epidermis, dermis, and hypodermis. The analysis and detection of diseases heavily rely on identifying the penetration of biomarkers within each layer, thus highlighting the significance of accurate segmentation of each layer in disease diagnosis. In skin disease diagnosis, haematoxylin and eosin-stained whole slide images are the most commonly employed imaging modality. To enhance the efficacy of analysis and assist pathologists, computer-aided diagnostic systems have been proposed to automate the process of disease detection and classification. A crucial initial step in skin disease diagnosis is the accurate segmentation of skin layers, as it facilitates the identification of regions of interest for subsequent processing. This study presents a novel attention-based encoder-decoder architecture comprising a multi-axis encoder with an attention-mixing decoder to precisely segment the skin layers (Epidermis, Dermis, Hypodermis, Keratin) from stained whole slide image samples. The proposed Transformer-based encoder block has helped the model preserve global and local features which are then passed to the decoder block through an attention-based gated skip connection. The attention mixing decoder module has combined multi-head self-attention, spatial attention, and squeeze excitation modules to enhance the spatial information gain. Additionally, the encoder block aids in extracting high and low-level features, which are further weighted before passing to the decoder block via a gated attention mechanism, thus helping the model acquire the relevant details from all spatial dimensions. The proposed architecture has been evaluated on a publicly available dataset against various evaluation metrics i.e., F1-Score, Accuracy, Precision, Recall, and Hausdorff Distance. The model yielded the highest accuracy of 95.5% when compared with state-of-art segmentation models. Additionally, compared with the baseline framework, the model has resulted in an increased overall accuracy of 14.20%.

In the era of artificial intelligence and machine learning, computer-aided diagnostic frameworks are data-hungry and require large amounts of annotated data to automate the disease diagnosis procedure. Moreover, to enhance the performance and accuracy of disease diagnosis, procedures need to be automated to ensure timely and accurate diagnosis. We are providing a whole slide image repository comprising unstained skin biopsy images acquired using a brightfield microscope, along with Hematoxylin and Eosin chemically and virtually stained image samples, to virtualize the staining procedure and enhance the efficiency of the disease diagnosis pipeline. The dataset was utilized to train a Dual Contrastive GAN to generate virtually stained image samples. The trained model achieved an FID score of 80.47 between virtually stained and chemically stained image samples, indicating a high correlation of content between synthesized and original images. In contrast, FID scores of 342.01 and 320.40 were observed between unstained images and virtually stained slides, and between unstained images and chemically stained images, respectively, indicating less similarity in content.

Diabetic retinopathy is one of the abnormalities of the retina in which a diabetic patient suffers from severe vision loss due to an affected retina. Proliferative diabetic retinopathy (PDR) is the final and most critical stage of diabetic retinopathy. Abnormal and fragile blood vessels start to grow on the surface of the retina at this stage. It causes retinal detachment, which may lead to complete blindness in severe cases. In this paper, a novel method is proposed for the detection and grading of neovascularization. The proposed system first performs pre-processing on input retinal images to enhance the vascular pattern, followed by blood vessel segmentation and optic disc localization. Then various features are tested on the candidate regions with different thresholds. In this way, positive and negative advanced diabetic retinopathy cases are separated. Optic disc coordinates are applied for the grading of neovascularization as NVD or NVE. The proposed algorithm improves the quality of automated diagnostic systems by eliminating normal blood vessels and exudates that might cause hindrances in accurate disease detection, thus resulting in more accurate detection of abnormal blood vessels. The evaluation of the proposed system has been carried out using performance parameters such as sensitivity, specificity, accuracy, and positive predictive value (PPV) on a publicly available standard retinal image database and one of the locally available databases. The proposed algorithm gives an accuracy of 98.5% and PPV of 99.8% on MESSIDOR and an accuracy of 96.5% and PPV of 100% on the local database.

Skin diseases have a significant impact on the socio-economic landscape as they affect not only the medical health of the patient but also their psychological well-being. Moreover, as the majority of individuals suffering from skin diseases are over the age of 60, these individuals have to also cope with the stress associated to age-related conditions such as diabetes, high blood pressure, and cardiac diseases. To alleviate this burden, it is essential to identify skin diseases at an early stage, which can help prevent disease progression. With the advent of Artificial Intelligence (AI) and technology, the use of automated disease diagnosis systems has increased significantly. These systems assist medical specialists by reducing diagnosis time and accelerating the entire diagnostic process. However, deep learning models require substantial amounts of data for training. In histopathology, brightfield microscopy is the most widely used imaging modality for identifying diseases through the examination of underlying structures. We are publishing a dataset comprising 38 whole-slide Hematoxylin and Eosin-stained images along with their masks. These images were grouped into 12 classes including tissues, skin cancer, and skin layers. We have also validated the dataset using SegFormer, which resulted in an overall accuracy of 0.875.