سيف خالد مصلح محمد الخالدي

The performance of diagnostic Computer-Aided Design (CAD) systems for retinal diseases depends on the quality of the retinal images being screened. Thus, many studies have been developed to evaluate and assess the quality of such retinal images. However, most of them did not investigate the relationship between the accuracy of the developed models and the quality of the visualization of interpretability methods for distinguishing between gradable and non-gradable retinal images. Consequently, this paper presents a novel framework called “FGR-Net” to automatically assess and interpret underlying fundus image quality by merging an autoencoder network with a classifier network. The FGR-Net model also provides an interpretable quality assessment through visualizations. In particular, FGR-Net uses a deep autoencoder to reconstruct the input image in order to extract the visual characteristics of the input fundus images based on self-supervised learning. The extracted features by the autoencoder are then fed into a deep classifier network to distinguish between gradable and ungradable fundus images. FGR-Net is evaluated with different interpretability methods, which indicates that the autoencoder is a key factor in forcing the classifier to focus on the relevant structures of the fundus images, such as the fovea, optic disk, and prominent blood vessels. Additionally, the interpretability methods can provide visual feedback for ophthalmologists to understand how our model evaluates the quality of fundus images. The experimental results showed the superiority of FGR-Net over the state-of-the-art quality assessment methods, with an accuracy of and an F1-score of . The code is publicly available at https://github.com/saifalkh/FGR-Net

Diabetic retinopathy (DR) is a common and serious complication of diabetes mellitus, often leading to blindness. Identifying DR stages accurately is essential for timely and effective treatment. This study introduces an innovative method to improve DR classification by detecting retinal lesions in fundus images (such as Hard Exudates, Soft Exudates, Microaneurysms, and Hemorrhages) and extracting visual and morphological features from these lesions. The proposed approach generates synthetic retinal lesions and creates artificial masks to highlight DR pathology regions. A segmentation model is trained to produce these masks, which are then refined using real fundus images and corresponding annotations. The model is then fine-tuned with real fundus images and corresponding masks. The model then derives morphological features (such as the number of each lesion, and maximum and minimum sizes, among others) from the generated masks and integrates them with latent features extracted from the segmentation model to enhance classification accuracy. The model can show a visual explanation generated by the to aid doctors in verifying and trusting the AI’s decisions, ultimately enhancing clinical decision-making and patient care. Experimental results on the DDR, E-Ophtha, and IDRiD datasets demonstrate the method’s effectiveness in improving lesion segmentation and DR classification. The DR classification achieved an accuracy of 88.04% and a Quadratic Weighted Kappa (QWK) score of 93.71%, surpassing state-of-the-art methods. The use of composite masks improves the model’s ability to identify subtle DR progression indicators, enabling more precise diagnostics and explainable AI-based interventions in clinical practice. The code is publicly available at https://github.com/saifalkhaldiurv/Advanced-Diabetic-retinopathy-Classification.git.

Widespread eye conditions such as cataracts, diabetic retinopathy, and glaucoma impact people worldwide. Ophthalmology uses fundus photography for diagnosing these retinal disorders, but fundus images are prone to image quality challenges. Accurate diagnosis hinges on high-quality fundus images. Therefore, there is a need for image quality assessment methods to evaluate fundus images before diagnosis. Consequently, this paper introduces a deep learning model tailored for fundus images that supports large images. Our division method centres on preserving the original image’s high-resolution features while maintaining low computing and high accuracy. The proposed approach encompasses two fundamental components: an autoencoder model for input image reconstruction and image classification to classify the image quality based on the latent features extracted by the autoencoder, all performed at the original image size, without alteration, before reassembly for decoding networks. Through post hoc interpretability methods, we verified that our model focuses on key elements of fundus image quality. Additionally, an intrinsic interpretability module has been designed into the network that allows decomposing class scores into underlying concepts quality such as brightness or presence of anatomical structures. Experimental results in our model with EyeQ, a fundus image dataset with three categories (Good, Usable, and Rejected) demonstrate that our approach produces competitive outcomes compared to other deep learning-based methods with an overall accuracy of 0.9066, a precision of 0.8843, a recall of 0.8905, and an impressive F1-score of 0.8868. The code is publicly available at https://github.com/saifalkhaldiurv/VISTA_-Image-Quality-Assessment.

Adverse Outcome Pathway (AOPs) provide a conceptual understanding of mechanistic events occurring at multiple levels of biological organization. An AOP network is a sequence of Key Events (KE), based on their biological causality events are categorised into: Molecular Initiating Event (MIE), and Adverse Outcome (AO). The intuitive linear representation of events makes it an easy to adapt tool for regulatory toxicological assessment. In AOP development cycle, the initial hypothesis and proposed structure provide the backbone of the AOP. The AOPs backbone is further strengthen by the structured evidence gathered through literature resources, in-vitro and in-vivo experiments and by integration of information from peer-reviewed databases. Finding evidence for specific event, their assessment with selective Weight of Evidence (WoE) method, and harmonized integration with other information resources is a repetitive and expert driven task. To address this challenge, we propose an ontology driven text-mining tool which assists in automated extraction, followed by assessment and curation of textual mechanistic evidence from literature, reports and biological databases.

Recently, significant progress has been achieved in developing deep learning-based approaches for estimating depth maps from monocular images. However, many existing methods rely on content and structure information extracted from RGB photographs, which often results in inaccurate depth estimation, particularly for regions with low texture or occlusions. To overcome these limitations, we propose a novel method that exploits contextual semantic information to predict precise depth maps from monocular images. Our approach leverages a deep autoencoder network incorporating high-quality semantic features from the state-of-the-art HRNet-v2 semantic segmentation model. By feeding the autoencoder network with these features, our method can effectively preserve the discontinuities of the depth images and enhance monocular depth estimation. Specifically, we exploit the semantic features related to the localization and boundaries of the objects in the image to improve the accuracy and robustness of the depth estimation. To validate the effectiveness of our approach, we tested our model on two publicly available datasets, NYU Depth v2 and SUN RGB-D. Our method outperformed several state-of-the-art monocular depth estimation techniques, achieving an accuracy of 85% , while minimizing the error 𝑅𝑒𝑙 by 0.12 , 𝑅𝑀𝑆 by 0.523 , and 𝑙𝑜𝑔10 by 0.0527 . Our approach also demonstrated exceptional performance in preserving object boundaries and faithfully detecting small object structures in the scene.

Diabetes mellitus (DM) has epidemic proportions in incidence and prevalence worldwide. The people with DM are all susceptible to acquiring diabetic retinopathy (DR). Microaneurysms, haemorrhages, and exudates are the early symptoms of DR that manifest on the surface of the retina. This paper proposes a deep learning (DL) method based on non-clinical features for grading DR in retinal fundus images. The method is based on ensampling multiple DL networks. The multi-network architecture is well suited to represent the fundus image’s features properly. The proposed model consists of three well-known DL models, mainly VGG16, DenseNet121, ResNet50. For each network, a classifier network grades DR into five classes (i.e., No DR, Mild, Moderate, Severe, and Proliferative). A maximum voting algorithm is applied to merge the three probabilities resulting from the three classifiers to achieve the final DR grading. The proposed system is assessed using the public DDR dataset. The experimental results show that the proposed method based on voting with the DenseNet121 and VGG16, and ResNet50 outperforms the state-of-the-art.