Diabetic retinopathy (DR) is a leading cause of vision loss in working-age adults. While screening reduces the risk of blindness, traditional imaging is often costly and inaccessible. Artificial intelligence (AI) algorithms present a scalable diagnostic solution, but concerns regarding fairness and generalization persist. This work evaluates the fairness and performance of image-trained models in DR prediction, as well as the impact of disentanglement as a bias mitigation technique, using the diverse mBRSET fundus dataset. Three models, ConvNeXt V2, DINOv2, and Swin V2, were trained on macula images to predict DR and sensitive attributes (SAs) (e.g., age and gender/sex). Fairness was assessed between subgroups of SAs, and disentanglement was applied to reduce bias. All models achieved high DR prediction performance in diagnosing (up to 94% AUROC) and could reasonably predict age and gender/sex (91% and 77% AUROC, respectively). Fairness assessment suggests disparities, such as a 10% AUROC gap between age groups in DINOv2. Disentangling SAs from DR prediction had varying results, depending on the model selected. Disentanglement improved DINOv2 performance (2% AUROC gain), but led to performance drops in ConvNeXt V2 and Swin V2 (7% and 3%, respectively). These findings highlight the complexity of disentangling fine-grained features in fundus imaging and emphasize the importance of fairness in medical imaging AI to ensure equitable and reliable healthcare solutions.

This study conducts a comprehensive comparison of four neural network architectures: Convolutional Neural Network, Capsule Network, Convolutional Kolmogorov--Arnold Network, and the newly proposed Capsule--Convolutional Kolmogorov--Arnold Network. The proposed Capsule-ConvKAN architecture combines the dynamic routing and spatial hierarchy capabilities of Capsule Network with the flexible and interpretable function approximation of Convolutional Kolmogorov--Arnold Networks. This novel hybrid model was developed to improve feature representation and classification accuracy, particularly in challenging real-world biomedical image data. The architectures were evaluated on a histopathological image dataset, where Capsule-ConvKAN achieved the highest classification performance with an accuracy of 91.21\%. The results demonstrate the potential of the newly introduced Capsule-ConvKAN in capturing spatial patterns, managing complex features, and addressing the limitations of traditional convolutional models in medical image classification.

Deep neural networks are increasingly applied for automated histopathology. Yet, whole-slide images (WSIs) are often acquired at gigapixel sizes, rendering it computationally infeasible to analyze them entirely at high resolution. Diagnostic labels are largely available only at the slide-level, because expert annotation of images at a finer (patch) level is both laborious and expensive. Moreover, regions with diagnostic information typically occupy only a small fraction of the WSI, making it inefficient to examine the entire slide at full resolution. Here, we propose SASHA -- {\it S}equential {\it A}ttention-based {\it S}ampling for {\it H}istopathological {\it A}nalysis -- a deep reinforcement learning approach for efficient analysis of histopathological images. First, SASHA learns informative features with a lightweight hierarchical, attention-based multiple instance learning (MIL) model. Second, SASHA samples intelligently and zooms selectively into a small fraction (10-20\%) of high-resolution patches, to achieve reliable diagnosis. We show that SASHA matches state-of-the-art methods that analyze the WSI fully at high-resolution, albeit at a fraction of their computational and memory costs. In addition, it significantly outperforms competing, sparse sampling methods. We propose SASHA as an intelligent sampling model for medical imaging challenges that involve automated diagnosis with exceptionally large images containing sparsely informative features.

Synthetic images are an option for augmenting limited medical imaging datasets to improve the performance of various machine learning models. A common metric for evaluating synthetic image quality is the Fr\'echet Inception Distance (FID) which measures the similarity of two image datasets. In this study we evaluate the relationship between this metric and the improvement which synthetic images, generated by a Progressively Growing Generative Adversarial Network (PGGAN), grant when augmenting Diabetes-related Macular Edema (DME) intraretinal fluid segmentation performed by a U-Net model with limited amounts of training data. We find that the behaviour of augmenting with standard and synthetic images agrees with previously conducted experiments. Additionally, we show that dissimilar (high FID) datasets do not improve segmentation significantly. As FID between the training and augmenting datasets decreases, the augmentation datasets are shown to contribute to significant and robust improvements in image segmentation. Finally, we find that there is significant evidence to suggest that synthetic and standard augmentations follow separate log-normal trends between FID and improvements in model performance, with synthetic data proving more effective than standard augmentation techniques. Our findings show that more similar datasets (lower FID) will be more effective at improving U-Net performance, however, the results also suggest that this improvement may only occur when images are sufficiently dissimilar.

PurposeWe report on a deep learning-based approach to the segmentation of geographic atrophy (GA) in patients with advanced age-related macular degeneration (AMD). MethodThree-dimensional (3D) optical coherence tomography (OCT) data was collected from two instruments at two different retina practices. This totaled 367 and 348 volumes, respectively, of routinely collected clinical data. For all data, the accuracy of a 3D-to-2D segmentation model was assessed relative to ground-truth manual labeling. ResultsDice Similarity Scores (DSC) averaged 0.824 and 0.826 for each data set. Correlations (r2) between manual and automated areas were 0.883 and 0.906, respectively. The inclusion of near Infra-red imagery as an additional information channel to the algorithm did not notably improve performance. ConclusionAccurate assessment of GA in real-world clinical OCT data can be achieved using deep learning. In the advent of therapeutics to slow the rate of GA progression, reliable, automated assessment is a clinical objective and this work validates one such method.

Photorefractive Keratectomy (PRK) is a widely used laser-assisted refractive surgical technique. In some cases, it leads to temporary subepithelial inflammation or fibrosis linked to visual haze. There are to our knowledge no physics based and quantitative tools to monitor these symptoms. We here present a comprehensive machine learning-based algorithm for the detection of fibrosis based on spectral domain optical coherence tomography images recorded in vivo on standard clinical devices. Because of the rarity of these phenomena, we trained the model on corneas presenting Fuchs dystrophy causing similar, but permanent, fibrosis symptoms, and applied it to images from patients who have undergone PRK surgery. Our study shows that the model output (probability of Fuchs dystrophy classification) provides a quantified and explainable indicator of corneal healing for post-operative follow-up.

Image quality assessment (IQA) is crucial in the evaluation stage of novel algorithms operating on images, including traditional and machine learning based methods. Due to the lack of available quality-rated medical images, most commonly used IQA methods employing reference images (i.e. full-reference IQA) have been developed and tested for natural images. Reported application inconsistencies arising when employing such measures for medical images are not surprising, as they rely on different properties than natural images. In photoacoustic imaging (PAI), especially, standard benchmarking approaches for assessing the quality of image reconstructions are lacking. PAI is a multi-physics imaging modality, in which two inverse problems have to be solved, which makes the application of IQA measures uniquely challenging due to both, acoustic and optical, artifacts. To support the development and testing of full- and no-reference IQA measures we assembled PhotIQA, a data set consisting of 1134 reconstructed photoacoustic (PA) images that were rated by 2 experts across five quality properties (overall quality, edge visibility, homogeneity, inclusion and background intensity), where the detailed rating enables usage beyond PAI. To allow full-reference assessment, highly characterised imaging test objects were used, providing a ground truth. Our baseline experiments show that HaarPSI$_{med}$ significantly outperforms SSIM in correlating with the quality ratings (SRCC: 0.83 vs. 0.62). The dataset is publicly available at https://doi.org/10.5281/zenodo.13325196.

PurposeTo quantify spectral-domain optical coherence tomography (SD-OCT) images cross-sectionally and longitudinally in a large cohort of molecularly characterized patients with inherited retinal disease (IRDs) from the UK. DesignRetrospective study of imaging data. ParticipantsPatients with a clinical and molecularly confirmed diagnosis of IRD who have undergone macular SD-OCT imaging at Moorfields Eye Hospital (MEH) between 2011 and 2019. We retrospectively identified 4,240 IRD patients from the MEH database (198 distinct IRD genes), including 69,664 SD-OCT macular volumes. MethodsEight features of interest were defined: retina, fovea, intraretinal cystic spaces (ICS), subretinal fluid (SRF), subretinal hyper-reflective material (SHRM), pigment epithelium detachment (PED), ellipsoid zone loss (EZ-loss) and retinal pigment epithelium loss (RPE-loss). Manual annotations of five b-scans per SD-OCT volume was performed for the retinal features by four graders based on a defined grading protocol. A total of 1,749 b-scans from 360 SD-OCT volumes across 275 patients were annotated for the eight retinal features for training and testing of a neural-network-based segmentation model, AIRDetect-OCT, which was then applied to the entire imaging dataset. Main Outcome MeasuresPerformance of AIRDetect-OCT, comparing to inter-grader agreement was evaluated using Dice score on a held-out dataset. Feature prevalence, volume and area were analysed cross-sectionally and longitudinally. ResultsThe inter-grader Dice score for manual segmentation was [&ge;]90% for retina, ICS, SRF, SHRM and PED, >77% for both EZ-loss and RPE-loss. Model-grader agreement was >80% for segmentation of retina, ICS, SRF, SHRM, and PED, and >68% for both EZ-loss and RPE-loss. Automatic segmentation was applied to 272,168 b-scans across 7,405 SD-OCT volumes from 3,534 patients encompassing 176 unique genes. Accounting for age, male patients exhibited significantly more EZ-loss (19.6mm2 vs 17.9mm2, p<2.8x10-4) and RPE-loss (7.79mm2 vs 6.15mm2, p<3.2x10-6) than females. RPE-loss was significantly higher in Asian patients than other ethnicities (9.37mm2 vs 7.29mm2, p<0.03). ICS average total volume was largest in RS1 (0.47mm3) and NR2E3 (0.25mm3), SRF in BEST1 (0.21mm3) and PED in EFEMP1 (0.34mm3). BEST1 and PROM1 showed significantly different patterns of EZ-loss (p<10-4) and RPE-loss (p<0.02) comparing the dominant to the recessive forms. Sectoral analysis revealed significantly increased EZ-loss in the inferior quadrant compared to superior quadrant for RHO ({Delta}=-0.414 mm2, p=0.036) and EYS ({Delta}=-0.908 mm2, p=1.5x10-4). In ABCA4 retinopathy, more severe genotypes (group A) were associated with faster progression of EZ-loss (2.80{+/-}0.62 mm2/yr), whilst the p.(Gly1961Glu) variant (group D) was associated with slower progression (0.56 {+/-}0.18 mm2/yr). There were also sex differences within groups with males in group A experiencing significantly faster rates of progression of RPE-loss (2.48 {+/-}1.40 mm2/yr vs 0.87 {+/-}0.62 mm2/yr, p=0.047), but lower rates in groups B, C, and D. ConclusionsAIRDetect-OCT, a novel deep learning algorithm, enables large-scale OCT feature quantification in IRD patients uncovering cross-sectional and longitudinal phenotype correlations with demographic and genotypic parameters.

We present the first comparative study of two fundamentally distinct feature extraction techniques: Histogram of Oriented Gradients (HOG) and Topological Data Analysis (TDA), for medical image classification using retinal fundus images. HOG captures local texture and edge patterns through gradient orientation histograms, while TDA, using cubical persistent homology, extracts high-level topological signatures that reflect the global structure of pixel intensities. We evaluate both methods on the large APTOS dataset for two classification tasks: binary detection (normal versus diabetic retinopathy) and five-class diabetic retinopathy severity grading. From each image, we extract 26244 HOG features and 800 TDA features, using them independently to train seven classical machine learning models with 10-fold cross-validation. XGBoost achieved the best performance in both cases: 94.29 percent accuracy (HOG) and 94.18 percent (TDA) on the binary task; 74.41 percent (HOG) and 74.69 percent (TDA) on the multi-class task. Our results show that both methods offer competitive performance but encode different structural aspects of the images. This is the first work to benchmark gradient-based and topological features on retinal imagery. The techniques are interpretable, applicable to other medical imaging domains, and suitable for integration into deep learning pipelines.

Artificial intelligence (AI) models are effective for analyzing high-quality slit-lamp images but often face challenges in real-world clinical settings due to image variability. This study aims to develop and evaluate a hybrid AI-based image quality control system to classify slit-lamp images, improving diagnostic accuracy and efficiency, particularly in telemedicine applications. Cross-sectional study. Our Zhejiang Eye Hospital dataset comprised 2982 slit-lamp images as the internal dataset. Two external datasets were included: 13,554 images from the Aier Guangming Eye Hospital (AGEH) and 9853 images from the First People's Hospital of Aksu District in Xinjiang (FPH of Aksu). We developed a Hybrid Prior-Net (HP-Net), a novel network that combines a ResNet-based classification branch with a prior knowledge branch leveraging Hough circle transform and frequency domain blur detection. The two branches' features are channel-wise concatenated at the fully connected layer, enhancing representational power and improving the network's ability to classify eligible, misaligned, blurred, and underexposed corneal images. Model performance was evaluated using metrics such as accuracy, precision, recall, specificity, and F1-score, and compared against the performance of other deep learning models. The HP-Net outperformed all other models, achieving an accuracy of 99.03 %, precision of 98.21 %, recall of 95.18 %, specificity of 99.36 %, and an F1-score of 96.54 % in image classification. The results demonstrated that HP-Net was also highly effective in filtering slit-lamp images from the other two datasets, AGEH and FPH of Aksu with accuracies of 97.23 % and 96.97 %, respectively. These results underscore the superior feature extraction and classification capabilities of HP-Net across all evaluated metrics. Our AI-based image quality control system offers a robust and efficient solution for classifying corneal images, with significant implications for telemedicine applications. By incorporating slightly blurred but diagnostically usable images into training datasets, the system enhances the reliability and adaptability of AI tools for medical imaging quality control, paving the way for more accurate and efficient diagnostic workflows.