arXiv subjects

Joachim A. Behar

Publications and source records attributed to Joachim A. Behar.

At least 19 recordsLinked to original sources

arXiv2026

Modeling Day-Long ECG Signals to Predict Heart Failure Risk with Explainable AI

Heart failure (HF) affects 11.8% of adults aged 65 and older, reducing quality of life and longevity. Preventing HF can reduce morbidity and mortality. We hypothesized that artificial intelligence (AI) applied to 24-hour single-lead electrocardiogram (ECG) data could predict the risk of HF within five years. To research this, the Technion-Leumit Holter ECG (TLHE) dataset, including 69,663 recordings from 47,729 patients, collected over 20 years was used. Our deep learning model, DeepHHF, trained on 24-hour ECG recordings, achieved an area under the receiver operating characteristic curve of 0.80 that outperformed a model using 30-second segments and a clinical score. High-risk individuals identified by DeepHHF had a two-fold chance of hospitalization or death incidents. Explainability analysis showed DeepHHF focused on arrhythmias and heart abnormalities. This study highlights the feasibility of deep learning to model 24-hour continuous ECG data, capturing paroxysmal events essential for reliable risk prediction. Artificial intelligence applied to single-lead Holter ECG is non-invasive, inexpensive, and widely accessible, making it a promising tool for HF risk prediction.

eess.SP↗

arXiv2026

uPVC-Net: A Universal Premature Ventricular Contraction Detection Deep Learning Algorithm

Introduction: Premature Ventricular Contractions (PVCs) are common cardiac arrhythmias originating from the ventricles. Accurate detection remains challenging due to variability in electrocardiogram (ECG) waveforms caused by differences in lead placement, recording conditions, and population demographics. Methods: We developed uPVC-Net, a universal deep learning model to detect PVCs from any single-lead ECG recordings. The model is developed on four independent ECG datasets comprising a total of 8.3 million beats collected from Holter monitors and a modern wearable ECG patch. uPVC-Net employs a custom architecture and a multi-source, multi-lead training strategy. For each experiment, one dataset is held out to evaluate out-of-distribution (OOD) generalization. Results: uPVC-Net achieved an AUC between 97.8% and 99.1% on the held-out datasets. Notably, performance on wearable single-lead ECG data reached an AUC of 99.1%. Conclusion: uPVC-Net exhibits strong generalization across diverse lead configurations and populations, highlighting its potential for robust, real-world clinical deployment.

cs.LG↗

arXiv2025

Benchmarking Ophthalmology Foundation Models for Clinically Significant Age Macular Degeneration Detection

Self-supervised learning (SSL) has enabled Vision Transformers (ViTs) to learn robust representations from large-scale natural image datasets, enhancing their generalization across domains. In retinal imaging, foundation models pretrained on either natural or ophthalmic data have shown promise, but the benefits of in-domain pretraining remain uncertain. To investigate this, we benchmark six SSL-pretrained ViTs on seven digital fundus image (DFI) datasets totaling 70,000 expert-annotated images for the task of moderate-to-late age-related macular degeneration (AMD) identification. Our results show that iBOT pretrained on natural images achieves the highest out-of-distribution generalization, with AUROCs of 0.80-0.97, outperforming domain-specific models, which achieved AUROCs of 0.78-0.96 and a baseline ViT-L with no pretraining, which achieved AUROCs of 0.68-0.91. These findings highlight the value of foundation models in improving AMD identification and challenge the assumption that in-domain pretraining is necessary. Furthermore, we release BRAMD, an open-access dataset (n=587) of DFIs with AMD labels from Brazil.

eess.IV↗

arXiv2025

HYAMD High-Resolution Fundus Image Dataset for age related macular degeneration (AMD) Diagnosis

The Hillel Yaffe Age Related Macular Degeneration (HYAMD) dataset is a longitudinal collection of 1,560 Digital Fundus Images (DFIs) from 325 patients examined at the Hillel Yaffe Medical Center (Hadera, Israel) between 2021 and 2024. The dataset includes an AMD cohort of 147 patients (aged 54-94) with varying stages of AMD and a control group of 190 diabetic retinopathy (DR) patients (aged 24-92). AMD diagnoses were based on comprehensive clinical ophthalmic evaluations, supported by Optical Coherence Tomography (OCT) and OCT angiography. Non-AMD DFIs were sourced from DR patients without concurrent AMD, diagnosed using macular OCT, fluorescein angiography, and widefield imaging. HYAMD provides gold-standard annotations, ensuring AMD labels were assigned following a full clinical assessment. Images were captured with a DRI OCT Triton (Topcon) camera, offering a 45 deg field of view and 1960 x 1934 pixel resolution. To the best of our knowledge, HYAMD is the first open-access retinal dataset from an Israeli sample, designed to support AMD identification using machine learning models.

eess.IV↗

arXiv2025

Generalization in medical AI: a perspective on developing scalable models

The scientific community is increasingly recognizing the importance of generalization in medical AI for translating research into practical clinical applications. A three-level scale is introduced to characterize out-of-distribution generalization performance of medical AI models. This scale addresses the diversity of real-world medical scenarios as well as whether target domain data and labels are available for model recalibration. It serves as a tool to help researchers characterize their development settings and determine the best approach to tackling the challenge of out-of-distribution generalization.

cs.LG↗

arXiv2025

Enhancing Retinal Vessel Segmentation Generalization via Layout-Aware Generative Modelling

Generalization in medical segmentation models is challenging due to limited annotated datasets and imaging variability. To address this, we propose Retinal Layout-Aware Diffusion (RLAD), a novel diffusion-based framework for generating controllable layout-aware images. RLAD conditions image generation on multiple key layout components extracted from real images, ensuring high structural fidelity while enabling diversity in other components. Applied to retinal fundus imaging, we augmented the training datasets by synthesizing paired retinal images and vessel segmentations conditioned on extracted blood vessels from real images, while varying other layout components such as lesions and the optic disc. Experiments demonstrated that RLAD-generated data improved generalization in retinal vessel segmentation by up to 8.1%. Furthermore, we present REYIA, a comprehensive dataset comprising 586 manually segmented retinal images. To foster reproducibility and drive innovation, both our code and dataset will be made publicly accessible.

cs.CV↗

arXiv2025

Machine learning for triage of strokes with large vessel occlusion using photoplethysmography biomarkers

Objective. Large vessel occlusion (LVO) stroke presents a major challenge in clinical practice due to the potential for poor outcomes with delayed treatment. Treatment for LVO involves highly specialized care, in particular endovascular thrombectomy, and is available only at certain hospitals. Therefore, prehospital identification of LVO by emergency ambulance services, can be critical for triaging LVO stroke patients directly to a hospital with access to endovascular therapy. Clinical scores exist to help distinguish LVO from less severe strokes, but they are based on a series of examinations that can take minutes and may be impractical for patients with dementia or those who cannot follow commands due to their stroke. There is a need for a fast and reliable method to aid in the early identification of LVO. In this study, our objective was to assess the feasibility of using 30-second photoplethysmography (PPG) recording to assist in recognizing LVO stroke. Method. A total of 88 patients, including 25 with LVO, 27 with stroke mimic (SM), and 36 non-LVO stroke patients (NL), were recorded at the Liverpool Hospital emergency department in Sydney, Australia. Demographics (age, sex), as well as morphological features and beating rate variability measures, were extracted from the PPG. A binary classification approach was employed to differentiate between LVO stroke and NL+SM (NL.SM). A 2:1 train-test split was stratified and repeated randomly across 100 iterations. Results. The best model achieved a median test set area under the receiver operating characteristic curve (AUROC) of 0.77 (0.71--0.82). \textit{Conclusion.} Our study demonstrates the potential of utilizing a 30-second PPG recording for identifying LVO stroke.

eess.SP↗

arXiv2025

GONet: A Generalizable Deep Learning Model for Glaucoma Detection

Glaucomatous optic neuropathy (GON) is a prevalent ocular disease that can lead to irreversible vision loss if not detected early and treated. The traditional diagnostic approach for GON involves a set of ophthalmic examinations, which are time-consuming and require a visit to an ophthalmologist. Recent deep learning models for automating GON detection from digital fundus images (DFI) have shown promise but often suffer from limited generalizability across different ethnicities, disease groups and examination settings. To address these limitations, we introduce GONet, a robust deep learning model developed using seven independent datasets, including over 119,000 DFIs with gold-standard annotations and from patients of diverse geographic backgrounds. GONet consists of a DINOv2 pre-trained self-supervised vision transformers fine-tuned using a multisource domain strategy. GONet demonstrated high out-of-distribution generalizability, with an AUC of 0.85-0.99 in target domains. GONet performance was similar or superior to state-of-the-art works and was significantly superior to the cup-to-disc ratio, by up to 21.6%. GONet is available at [URL provided on publication]. We also contribute a new dataset consisting of 768 DFI with GON labels as open access.

eess.IV↗

arXiv2024

SHDB-AF: a Japanese Holter ECG database of atrial fibrillation

Atrial fibrillation (AF) is a common atrial arrhythmia that impairs quality of life and causes embolic stroke, heart failure and other complications. Recent advancements in machine learning (ML) and deep learning (DL) have shown potential for enhancing diagnostic accuracy. It is essential for DL models to be robust and generalizable across variations in ethnicity, age, sex, and other factors. Although a number of ECG database have been made available to the research community, none includes a Japanese population sample. Saitama Heart Database Atrial Fibrillation (SHDB-AF) is a novel open-sourced Holter ECG database from Japan, containing data from 100 unique patients with paroxysmal AF. Each record in SHDB-AF is 24 hours long and sampled at 200 Hz, totaling 24 million seconds of ECG data.

cs.LG↗

arXiv2024

SleepPPG-Net2: Deep learning generalization for sleep staging from photoplethysmography

Background: Sleep staging is a fundamental component in the diagnosis of sleep disorders and the management of sleep health. Traditionally, this analysis is conducted in clinical settings and involves a time-consuming scoring procedure. Recent data-driven algorithms for sleep staging, using the photoplethysmogram (PPG) time series, have shown high performance on local test sets but lower performance on external datasets due to data drift. Methods: This study aimed to develop a generalizable deep learning model for the task of four class (wake, light, deep, and rapid eye movement (REM)) sleep staging from raw PPG physiological time-series. Six sleep datasets, totaling 2,574 patients recordings, were used. In order to create a more generalizable representation, we developed and evaluated a deep learning model called SleepPPG-Net2, which employs a multi-source domain training approach.SleepPPG-Net2 was benchmarked against two state-of-the-art models. Results: SleepPPG-Net2 showed consistently higher performance over benchmark approaches, with generalization performance (Cohen's kappa) improving by up to 19%. Performance disparities were observed in relation to age, sex, and sleep apnea severity. Conclusion: SleepPPG-Net2 sets a new standard for staging sleep from raw PPG time-series.

cs.LG↗

arXiv2024

Lirot.ai: A Novel Platform for Crowd-Sourcing Retinal Image Segmentations

Introduction: For supervised deep learning (DL) tasks, researchers need a large annotated dataset. In medical data science, one of the major limitations to develop DL models is the lack of annotated examples in large quantity. This is most often due to the time and expertise required to annotate. We introduce Lirot. ai, a novel platform for facilitating and crowd-sourcing image segmentations. Methods: Lirot. ai is composed of three components; an iPadOS client application named Lirot. ai-app, a backend server named Lirot. ai-server and a python API name Lirot. ai-API. Lirot. ai-app was developed in Swift 5.6 and Lirot. ai-server is a firebase backend. Lirot. ai-API allows the management of the database. Lirot. ai-app can be installed on as many iPadOS devices as needed so that annotators may be able to perform their segmentation simultaneously and remotely. We incorporate Apple Pencil compatibility, making the segmentation faster, more accurate, and more intuitive for the expert than any other computer-based alternative. Results: We demonstrate the usage of Lirot. ai for the creation of a retinal fundus dataset with reference vasculature segmentations. Discussion and future work: We will use active learning strategies to continue enlarging our retinal fundus dataset by including a more efficient process to select the images to be annotated and distribute them to annotators.

cs.CV↗

arXiv2023

RawECGNet: Deep Learning Generalization for Atrial Fibrillation Detection from the Raw ECG

Introduction: Deep learning models for detecting episodes of atrial fibrillation (AF) using rhythm information in long-term, ambulatory ECG recordings have shown high performance. However, the rhythm-based approach does not take advantage of the morphological information conveyed by the different ECG waveforms, particularly the f-waves. As a result, the performance of such models may be inherently limited. Methods: To address this limitation, we have developed a deep learning model, named RawECGNet, to detect episodes of AF and atrial flutter (AFl) using the raw, single-lead ECG. We compare the generalization performance of RawECGNet on two external data sets that account for distribution shifts in geography, ethnicity, and lead position. RawECGNet is further benchmarked against a state-of-the-art deep learning model, named ArNet2, which utilizes rhythm information as input. Results: Using RawECGNet, the results for the different leads in the external test sets in terms of the F1 score were 0.91--0.94 in RBDB and 0.93 in SHDB, compared to 0.89--0.91 in RBDB and 0.91 in SHDB for ArNet2. The results highlight RawECGNet as a high-performance, generalizable algorithm for detection of AF and AFl episodes, exploiting information on both rhythm and morphology.

eess.SP↗

arXiv2023

DRStageNet: Deep Learning for Diabetic Retinopathy Staging from Fundus Images

Diabetic retinopathy (DR) is a prevalent complication of diabetes associated with a significant risk of vision loss. Timely identification is critical to curb vision impairment. Algorithms for DR staging from digital fundus images (DFIs) have been recently proposed. However, models often fail to generalize due to distribution shifts between the source domain on which the model was trained and the target domain where it is deployed. A common and particularly challenging shift is often encountered when the source- and target-domain supports do not fully overlap. In this research, we introduce DRStageNet, a deep learning model designed to mitigate this challenge. We used seven publicly available datasets, comprising a total of 93,534 DFIs that cover a variety of patient demographics, ethnicities, geographic origins and comorbidities. We fine-tune DINOv2, a pretrained model of self-supervised vision transformer, and implement a multi-source domain fine-tuning strategy to enhance generalization performance. We benchmark and demonstrate the superiority of our method to two state-of-the-art benchmarks, including a recently published foundation model. We adapted the grad-rollout method to our regression task in order to provide high-resolution explainability heatmaps. The error analysis showed that 59\% of the main errors had incorrect reference labels. DRStageNet is accessible at URL [upon acceptance of the manuscript].

eess.IV↗

arXiv2023

End-to-end Risk Prediction of Atrial Fibrillation from the 12-Lead ECG by Deep Neural Networks

Background: Atrial fibrillation (AF) is one of the most common cardiac arrhythmias that affects millions of people each year worldwide and it is closely linked to increased risk of cardiovascular diseases such as stroke and heart failure. Machine learning methods have shown promising results in evaluating the risk of developing atrial fibrillation from the electrocardiogram. We aim to develop and evaluate one such algorithm on a large CODE dataset collected in Brazil. Results: The deep neural network model identified patients without indication of AF in the presented ECG but who will develop AF in the future with an AUC score of 0.845. From our survival model, we obtain that patients in the high-risk group (i.e. with the probability of a future AF case being greater than 0.7) are 50% more likely to develop AF within 40 weeks, while patients belonging to the minimal-risk group (i.e. with the probability of a future AF case being less than or equal to 0.1) have more than 85% chance of remaining AF free up until after seven years. Conclusion: We developed and validated a model for AF risk prediction. If applied in clinical practice, the model possesses the potential of providing valuable and useful information in decision-making and patient management processes.

cs.LG↗

arXiv2023

pyPPG: A Python toolbox for comprehensive photoplethysmography signal analysis

Photoplethysmography is a non-invasive optical technique that measures changes in blood volume within tissues. It is commonly and increasingly used for in a variety of research and clinical application to assess vascular dynamics and physiological parameters. Yet, contrary to heart rate variability measures, a field which has seen the development of stable standards and advanced toolboxes and software, no such standards and open tools exist for continuous photoplethysmogram (PPG) analysis. Consequently, the primary objective of this research was to identify, standardize, implement and validate key digital PPG biomarkers. This work describes the creation of a standard Python toolbox, denoted pyPPG, for long-term continuous PPG time series analysis recorded using a standard finger-based transmission pulse oximeter. The improved PPG peak detector had an F1-score of 88.19% for the state-of-the-art benchmark when evaluated on 2,054 adult polysomnography recordings totaling over 91 million reference beats. This algorithm outperformed the open-source original Matlab implementation by ~5% when benchmarked on a subset of 100 randomly selected MESA recordings. More than 3,000 fiducial points were manually annotated by two annotators in order to validate the fiducial points detector. The detector consistently demonstrated high performance, with a mean absolute error of less than 10 ms for all fiducial points. Based on these fiducial points, pyPPG engineers a set of 74 PPG biomarkers. Studying the PPG time series variability using pyPPG can enhance our understanding of the manifestations and etiology of diseases. This toolbox can also be used for biomarker engineering in training data-driven models. pyPPG is available on physiozoo.org

physics.med-ph↗

arXiv2023

LUNet: Deep Learning for the Segmentation of Arterioles and Venules in High Resolution Fundus Images

The retina is the only part of the human body in which blood vessels can be accessed non-invasively using imaging techniques such as digital fundus images (DFI). The spatial distribution of the retinal microvasculature may change with cardiovascular diseases and thus the eyes may be regarded as a window to our hearts. Computerized segmentation of the retinal arterioles and venules (A/V) is essential for automated microvasculature analysis. Using active learning, we created a new DFI dataset containing 240 crowd-sourced manual A/V segmentations performed by fifteen medical students and reviewed by an ophthalmologist, and developed LUNet, a novel deep learning architecture for high resolution A/V segmentation. LUNet architecture includes a double dilated convolutional block that aims to enhance the receptive field of the model and reduce its parameter count. Furthermore, LUNet has a long tail that operates at high resolution to refine the segmentation. The custom loss function emphasizes the continuity of the blood vessels. LUNet is shown to significantly outperform two state-of-the-art segmentation algorithms on the local test set as well as on four external test sets simulating distribution shifts across ethnicity, comorbidities, and annotators. We make the newly created dataset open access (upon publication).

eess.IV↗

arXiv2023

PhysioZoo: The Open Digital Physiological Biomarkers Resource

PhysioZoo is a collaborative platform designed for the analysis of continuous physiological time series. The platform currently comprises four modules, each consisting of a library, a user interface, and a set of tutorials: (1) PhysioZoo HRV, dedicated to studying heart rate variability (HRV) in humans and other mammals; (2) PhysioZoo SPO2, which focuses on the analysis of digital oximetry biomarkers (OBM) using continuous oximetry (SpO2) measurements from humans; (3) PhysioZoo ECG, dedicated to the analysis of electrocardiogram (ECG) time series; (4) PhysioZoo PPG, designed to study photoplethysmography (PPG) time series. In this proceeding, we introduce the PhysioZoo platform as an open resource for digital physiological biomarkers engineering, facilitating streamlined analysis and data visualization of physiological time series while ensuring the reproducibility of published experiments. We welcome researchers to contribute new libraries for the analysis of various physiological time series, such as electroencephalography, blood pressure, and phonocardiography. You can access the resource at physiozoo.com. We encourage researchers to explore and utilize this platform to advance their studies in the field of continuous physiological time-series analysis.

q-bio.QM↗

arXiv2023

Case Study: Fetal Breathing Movements as a Proxy for Fetal Lung Maturity Estimation

Premature births can lead to complications, with fetal lung immaturity being a primary concern. Currently, fetal lung maturity (FLM) requires an invasive surfactant extraction procedure between the 32nd and 39th weeks of pregnancy. Unfortunately, there is no non-invasive method for FLM assessment. This work hypothesized that fetal breathing movement (FBM) and surfactant levels are inversely coupled and that FBM can serve as a proxy for FLM estimation. To investigate the correlation between FBM and FLM, antenatal corticosteroid (ACS) was administered to increase fetal pulmonary surfactant levels in a high-risk 35th-week pregnant woman showing intrauterine growth restriction. Synchronous sonographic and phonographic measurements were continuously recorded for 25 minutes before and after the ASC treatments. Before the ACS injection, 268 continuous movements FBM episodes were recorded. The number of continuous FBM episodes significantly decreased to 3, 43, and 79 within 24, 48, and 72 hours, respectively, of the first injection of ACS, suggesting an inversely coupled connection between FBM and surfactant level s. Therefore, FBM may serve as a proxy for FLM estimation. Quantitative confirmation of these findings would suggest that FBM measurements could be used as a non-invasive and widely accessible FLM-assessment tool for high-risk pregnancies and routine examinations.

physics.med-ph↗