OCT layer segmentation using U-NET semantic segmentation and RESNET34 encoder-decoder

Assessment of Artifacts and Reproducibility across Spectral- and Time-Domain Optical Coherence Tomography Devices

Age-related macular degeneration (AMD) is a complex eye disorder affecting millions worldwide. This article uses deep learning techniques to investigate the relationship between AMD, genetics and optical coherence tomography (OCT) scans. The cohort consisted of 332 patients, of which 235 were diagnosed with AMD and 97 were controls with no signs of AMD. The genome-wide association studies summary statistics utilized to establish the polygenic risk score (PRS) in relation to AMD were derived from the GERA European study. A PRS estimation based on OCT volumes for both eyes was performed using a proprietary convolutional neural network (CNN) model supported by machine learning models. The method's performance was assessed using numerical evaluation metrics, and the Grad-CAM technique was used to evaluate the results by visualizing the features learned by the model. The best results were obtained with the CNN and the Extra Tree regressor (MAE = 0.55, MSE = 0.49, RMSE = 0.70, R2 = 0.34). Extending the feature vector with additional information on AMD diagnosis, age and smoking history improved the results slightly, with mainly AMD diagnosis used by the model (MAE = 0.54, MSE = 0.44, RMSE = 0.66, R2 = 0.42). Grad-CAM heatmap evaluation showed that the model decisions rely on retinal morphology factors relevant to AMD diagnosis. The developed method allows an efficient PRS estimation from OCT images. A new technique for analysing the association of OCT images with PRS of AMD, using a deep learning approach, may provide an opportunity to discover new associations between genotype-based AMD risk and retinal morphology.

Glaucoma is a leading cause of irreversible blindness worldwide, yet early detection can prevent vision loss. This paper proposes a novel deep learning approach that combines two ophthalmic imaging modalities, fundus photographs and optical coherence tomography scans, as paired images from the same eye of each patient for automated glaucoma detection. We develop separate convolutional neural network models for fundus and optical coherence tomography images and a fusion model that integrates features from both modalities for each eye. The models are trained and evaluated on a private clinical dataset (Bangladesh Eye Hospital and Institute Ltd.) consisting of 216 healthy eye images (108 fundus, 108 optical coherence tomography) from 108 patients and 200 glaucomatous eye images (100 fundus, 100 optical coherence tomography) from 100 patients. Our methodology includes image preprocessing pipelines for each modality, custom convolutional neural network/ResNet-based architectures for single-modality analysis, and a two-branch fusion network combining fundus and optical coherence tomography feature representations. We report the performance (accuracy, sensitivity, specificity, and area under curve) of the fundus-only, optical coherence tomography-only, and fusion models. In addition to a fixed test set evaluation, we perform five-fold cross-validation, confirming the robustness and consistency of the fusion model across multiple data partitions. On our fixed test set, the fundus-only model achieves 86% accuracy (AUC 0.89) and the optical coherence tomography-only model, 84% accuracy (AUC 0.87). Our fused model reaches 92% accuracy (AUC 0.95), an absolute improvement of 6 percentage points and 8 percentage points over the fundus and OCT baselines, respectively. McNemar’s test on pooled five-fold validation predictions (b = 3, c = 18) yields (p = 0.001), and on optical coherence tomography-only vs. fused (b_o = 5, c_o = 20) (p = 0.003), confirming that the fusion gains are significant. Five-fold cross-validation further confirms these improvements (mean AUC . We also compare our results with the existing literature and discuss the clinical significance, limitations, and future work. To the best of our knowledge, this is the first time a novel deep learning model has been used on a fusion of paired fundus and optical coherence tomography images of the same patient for the detection of glaucoma.

Early detection of sexually transmitted infections from skin lesions with deep learning: a systematic review and meta-analysis.

—Stress is a common psychological state that significantly impacts human well-being, productivity, and overall health. The ability to accurately detect stress in individuals is crucial for mitigating its harmful effects. In recent years, machine learning (ML) and deep learning (DL) have emerged as powerful tools for stress detection, utilizing physiological data, behavioral cues, and other relevant information. This survey paper provides a comprehensive review of the existing ML and DL approaches used for stress detection, exploring a wide range of models, datasets, and applications. We highlight various techniques, including supervised and unsupervised learning, feature extraction methods, and performance evaluation metrics. Additionally, the challenges in the field, such as data heterogeneity, real- time detection, and model interpretability, are discussed, along with future research directions that could further enhance the effectiveness of stress detection systems.

We present RetOCTNet, a deep learning tool to segment the retinal nerve fiber layer (RNFL) and total retinal thickness automatically from optical coherence tomography (OCT) scans in rats following retinal ganglion cell (RGC) injury. We created unilateral RGC injury by ocular hypertension (OHT) or optic nerve crush (ONC), and contralateral eyes were not injured. We manually segmented the RNFL and total retina of 3.0-mm radial OCT scans (1000 A-scans per B-scan, 20 frames per B-scan) as ground truth (n = 192 scans). We used these segmentations for training (80%), testing (10%), and validation (10%) to optimize the F1 score. To determine the generalizability of RetOCTNet, we tested it on volumetric scans of a separate cohort at baseline and 4, 8, and 12 weeks post-ONC. RetOCTNet's segmentations achieved high F1 scores relative to the ground-truth segmentations created by human annotators: 0.88 (RNFL) and 0.98 (retinal thickness) for control eyes, 0.84 and 0.98 for OHT eyes, and 0.78 and 0.96 for ONC eyes, respectively. On volumetric scans 12 weeks post-ONC, RetOCTNet calculated thinning of 29.49% and 10.82% in the RNFL and retina at the optic nerve head (ONH) and thinning of 38.34% and 9.85% in the RNFL and retina superior to the ONH. RetOCTNet can segment the RNFL and total retinal thickness of both radial and volume OCT scans. RetOCTNet can be applied to longitudinally monitor RNFL in rodent models of RGC injury. This tool automates RNFL and retinal thickness measurement for rat OCT scans following RGC injury, reducing analysis time and increasing the consistency between studies.

Optical Coherence Tomography (OCT) is a standard tool for cross-sectional imaging of retinal tissues. A large number of OCT scans are performed yearly, and ophthalmologists examine the OCT scans to detect eye diseases. Computer-assisted diagnosis (CAD) or decision support system is needed to screen OCT scans for disease detection. Earlier machine learning models were based on finding the most discriminative features by domain experts and then building the machine learning classifier. But recent research shows deep learning models are more suitable and give promising results. This paper summarizes the major deep learning approaches for OCT image classification for the detection of the most common retinal diseases, namely, AMD (Age-related Macular degeneration), DME (Diabetic Macular Edema), and CNV (Choroidal Neovascularization). We have discussed the advantages and challenges of deep learning models for OCT image classification, which can give directions for future research.

This study evaluates how accurately humans and artificial intelligence can identify the type of surgery performed for epiretinal membrane (ERM) removal by analyzing postoperative optical coherence tomography (OCT) scans. A retrospective analysis at the University of California San Diego included 250 eyes from 239 patients who underwent vitrectomy for idiopathic ERM between January 2013 and October 2024. Eyes were categorized into two groups: one with both the internal limiting membrane and ERM removed using indocyanine green staining, and another with only ERM removal, guided by triamcinolone. Postoperative OCT scans were labeled as either ERM-only or internal limiting membrane + ERM peel based on surgical notes. Both the human grader and artificial intelligence model were trained on 200 labeled OCT scans and tested on 50 masked OCT scans to classify the surgery type. Accuracy of the human grader in identifying the surgical technique was 50%, while the artificial intelligence models demonstrated significantly higher accuracy. The ResNet18 model achieved 61 ± 3%, while UwU-OrthLatt with DB4 initialization and UwU-PR-Relax with Symlet4 initialization reached 70 ± 5% and 69 ± 3%, respectively. Artificial intelligence outperformed human grading in detecting internal limiting membrane removal from OCT scans, demonstrating artificial intelligence's potential in improving ophthalmic imaging for clinical use.

To investigate the repeatability of choroidal vascularity index (CVI) measurements in centered and decentered (regarding pupil entry position of the beam) directional subfoveal optical coherence tomography (OCT) scans with (CVI1) and without (CVI2) brightness adjustment. Thirty-two eyes of 32 healthy volunteers were included in this prospective study. First, the fovea was evaluated by a single horizontal enhanced depth imaging OCT scan in a centered direction. Then, the same subfoveal horizontal line was scanned in a decentered direction. The agreement between CVIs obtained from these centered and decentered directional OCT scans was investigated using Bland-Altman analysis and intraclass correlation coefficient. Intraclass correlation coefficient between centered and decentered CVI1 was 0.71 (95% CI: 0.48-0.85, P value < 0.001). Intraclass correlation coefficient between centered and decentered CVI2 was 0.73 (95% CI: 0.5-0.86, P value < 0.001). The mean difference between centered and decentered directional measurements for CVI1 and CVI2 were 0.5 and 0.8, respectively. There is moderate agreement between CVIs obtained from centered and decentered directional single OCT scans of the same subfoveal area. Studies investigating choroidal vascularity should be standardized by using the same OCT beam direction in all scans.

Medical image segmentation is a critical field in the domain of computer vision and with the growing acclaim of deep learning based models, research in this field is constantly expanding. Optical coherence tomography (OCT) is a non-invasive method that scans the human's retina with depth. It has been hypothesized that the thickness of the retinal layers extracted from OCTs could be an efficient and effective biomarker for early diagnosis of AD. In this work, we aim to design a self-training model architecture for the task of segmenting the retinal layers in OCT scans. Neural architecture search (NAS) is a subfield of AutoML domain, which has a significant impact on improving the accuracy of machine vision tasks. We integrate the NAS algorithm with a Unet auto-encoder architecture as its backbone. Then, we employ our proposed model to segment the retinal nerve fiber layer in our preprocessed OCT images with the aim of AD diagnosis. In this work, we trained a super-resolution generative adversarial network on the raw OCT scans to improve the quality of the images before the modeling stage. In our architecture search strategy, different primitive operations suggested to find down- & up-sampling Unet cell blocks and the binary gate method has been applied to make the search strategy more practical. Our architecture search method is empirically evaluated by training on the Unet and NAS-Unet from scratch. Specifically, the proposed NAS-Unet training significantly outperforms the baseline human-designed architecture by achieving 95.1% in the mean Intersection over Union metric and 79.1% in the Dice similarity coefficient.

Background: To design a novel anomaly detection and localization approach using artificial intelligence methods using optical coherence tomography (OCT) scans for retinal diseases. Methods: High-resolution OCT scans from the publicly available Kaggle dataset and a local dataset were used by four state-of-the-art self-supervised frameworks. The backbone model of all the frameworks was a pre-trained convolutional neural network (CNN), which enabled the extraction of meaningful features from OCT images. Anomalous images included choroidal neovascularization (CNV), diabetic macular edema (DME), and the presence of drusen. Anomaly detectors were evaluated by commonly accepted performance metrics, including area under the receiver operating characteristic curve, F1 score, and accuracy. Results: A total of 25,315 high-resolution retinal OCT slabs were used for training. Test and validation sets consisted of 968 and 4000 slabs, respectively. The best performing across all anomaly detectors had an area under the receiver operating characteristic of 0.99. All frameworks were shown to achieve high performance and generalize well for the different retinal diseases. Heat maps were generated to visualize the quality of the frameworks' ability to localize anomalous areas of the image. Conclusions: This study shows that with the use of pre-trained feature extractors, the frameworks tested can generalize to the domain of retinal OCT scans and achieve high image-level ROC-AUC scores. The localization results of these frameworks are promising and successfully capture areas that indicate the presence of retinal pathology. Moreover, such frameworks have the potential to uncover new biomarkers that are difficult for the human eye to detect. Frameworks for anomaly detection and localization can potentially be integrated into clinical decision support and automatic screening systems that will aid ophthalmologists in patient diagnosis, follow-up, and treatment design. This work establishes a solid basis for further development of automated anomaly detection frameworks for clinical use.

Cybercriminals have increasingly leveraged sophisticated techniques to bypass traditional signature-based detection systems through the use of Ransomware-as-a-Service (RaaS) platforms, double and triple extortion strategies, and advanced evasion mechanisms. As a result, ransomware attacks have reached unprecedented levels. Using this systematic evaluation framework, we examine the current state and effectiveness of machine learning (ML) and deep learning (DL) approaches for ransomware detection, addressing critical gaps in existing research methodologies while providing comprehensive recommendations for future research. The study analyses multiple AI paradigms including supervised learning algorithms such as Random Forests and Support Vector Machines, unsupervised techniques such as clustering and anomaly detection, and deep learning architectures such as Convolutional Neural Networks and Long Short-Term Memory networks. Hybrid approaches combining static and dynamic analysis consistently achieve superior performance, with accuracy rates exceeding 99% when properly implemented. As part of the framework, fundamental challenges are addressed such as dataset quality and diversity, feature extraction and selection methodologies, data preprocessing techniques, and performance evaluation metrics that have been tailored specifically for cybersecurity applications. Several findings indicate that ensemble learning methods outperform individual classifiers, with Random Forest algorithms being particularly effective at handling high-dimensional feature spaces while maintaining interpretability for security analysts. As a result of the study, significant limitations have been identified in current research, including an overreliance on static data sets that do not capture evolving threat landscapes, an inadequate representation of modern attack vectors, and a limited ability to generalize across different operational environments. Future directions of this research include explainable AI integration for transparent decision-making, adaptive real-time detection systems, and federated learning approaches for collaborative threat intelligence sharing while maintaining organizational privacy. It provides standardized methodologies for data curation, feature engineering, model development, and performance benchmarking, enabling fair comparisons between different AI approaches and facilitating reproducible research. This work contributes to essential guidance for cybersecurity practitioners, policymakers, and researchers in developing robust, adaptive, and interpretable ransomware detection systems capable of defending against increasingly sophisticated cyber threats while considering ethical concerns and regulatory compliance requirements in modern digital ecosystems.

The combination of artificial intelligence (AI) and machine learning (ML) in drug discovery has significantly transformed traditional pharmaceutical research by enabling data-driven decision-making, accelerating the identification of hits, and improving the efficiency of lead optimization. This review provides a comprehensive overview of AI/ML models, including supervised, unsupervised, semisupervised, deep learning, and reinforcement learning approaches and their applications across various stages of drug development, from target identification and virtual screening to de novo molecule design and ADME/T prediction. We highlight widely used ML algorithms, performance evaluation metrics, and AI-driven tools that have become instrumental in modern drug discovery pipelines. Despite rapid advancements, challenges such as limited data availability, heterogeneity, bias, lack of model interpretability, reproducibility concerns, clinical translational barriers, and regulatory uncertainties continue to hinder full-scale adoption. The review also discusses emerging trends, including explainable AI, federated learning, and integration with high-throughput experimental platforms, which offer promising directions for overcoming current limitations. Emphasis is placed on the importance of interdisciplinary collaboration to bridge computational predictions with experimental validation, ensuring robust, ethical, and clinically translatable AI applications in drug development.

Background Machine learning (ML) algorithm support vector machine (SVM) performed better than Thrombolysis in Myocardial Infarction (TIMI) score for ASIAN STEMI patients. However, Deep Learning (DL) effectiveness in the multiethnic ASIAN population has yet to be determined. DL has automatic learning of the feature from a given dataset without the need to conduct feature selection. However, the selected features by the algorithm is black box. Identifying features associated with mortality is essential to recognize characteristics of patients with high risk for better patient management. Purpose To develop a DL algorithm for in-hospital mortality in multiethnic STEMI patients using predictors identified from the SVM algorithm. To investigate DL performance constructed using predictors from SVM feature extraction and expert-recommended predictors. Methods We constructed four algorithms; a) DL and SVM algorithms with predictors identified from the SVM variable importance b) DL and SVM using predictors based on expert recommendation. We used registry data from the National Cardiovascular Disease Database of 11397 patient's. Fifty parameters including demographics, cardiovascular risk, medications and clinical variables were considered. The Area under the curve (AUC) is the performance evaluation metric. Algorithms were validated against the TIMI and tested using the same validation data. SVM variable importance with backward elimination was used to select and rank important variables. Results DL algorithms outperform SVM and TIMI on the validation dataset; i) DL with SVM selected predictors (15 predictors, AUC = 0.97), ii) DL with expert-recommended predictors (16 predictors, AUC = 0.96), iii) SVM with selected predictors (15 predictors, AUC = 0.92), iv) SVM with expert-recommended predictors (AUC = 0.89) and TIMI (AUC = 0.82). Common predictors across SVM feature selection, expert-recommendation and TIMI are: age, heart rate, Killip class, fasting blood glucose, systolic blood pressure, comorbid diseases and ST-elevation. SVM feature selection also identified diuretics, PCI and pharmacotherapy drugs as predictors that improve mortality prediction in STEMI patients. Our findings suggest that the TIMI score underestimates patients risk of mortality. DL algorithm using selected predictors classified 35% of nonsurvival patients as high risk (risk probabilities &amp;gt;50%) compared to only 12.7% nonsurvival patients by TIMI (score &amp;gt;5) (Figure below). Conclusions In the ASIAN population, patients with STEMI can be better classified using the DL algorithm compared to the ML and TIMI score. Combining ML feature selection with DL allows the identification of distinct factors in a unique ASIAN population for better mortality prediction than relying solely on an expert recommendation as it is a very subjective approach. Continuous validation on population-specific algorithms using DL and ML is needed before implementing in a real clinical setting. Funding Acknowledgement Type of funding sources: Public grant(s) – National budget only. Main funding source(s): Technology Development Fund 1 TIMI performance on validation setDL performance on validation set

Progression or Aging? A Deep Learning Approach for Distinguishing Glaucoma Progression From Age-Related Changes in OCT Scans