A Unified DINOv2-Based Framework for LVEF Estimation, GLS Dysfunction Classification, and Early Cardiotoxicity Prediction

• URL: http://arxiv.org/abs/2608.14750v1
• Date: Fri, 14 Aug 2026 02:46:37 GMT
• Title: A Unified DINOv2-Based Framework for LVEF Estimation, GLS Dysfunction Classification, and Early Cardiotoxicity Prediction
• Abstract summary: Left ventricular ejection fraction estimation, global longitu-dinal strain (GLS)-based dysfunction classification, and early cardi-otoxicity prediction provide complementary information for cardio- oncology assessment.<n>We employ a DINOv2-based framework with task-specific adap-tation and prediction heads.<n>On a patient-level split containing 1,203 training videos from 237 patients and 300 validation videos from 59 independent patients, the framework achieved a mean abso-lute error (MAE) of 5.03% for Task 1, an AUC-ROC of 76.48% for Task 2, and an AUC-ROC of 70
• Score: 9.254921162350522
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Left ventricular ejection fraction (LVEF) estimation (Task 1), global longitu-dinal strain (GLS)-based dysfunction classification (Task 2), and early cardi-otoxicity prediction (Task 3) provide complementary information for cardio-oncology assessment. LVEF reflects macroscopic ventricular volume chang-es as the clinical standard, whereas GLS captures subtle myocardial defor-mation, indicating subclinical cardiotoxicity before overt LVEF decline. Fur-thermore, predicting cardiotoxicity from baseline echocardiography prior to treatment enables preventive interventions at an early stage. To address these three tasks, we employ a DINOv2-based framework with task-specific adap-tation and prediction heads. Built upon a frozen foundation encoder, the framework incorporates parameter-efficient Low-Rank Adaptation (LoRA) and temporal aggregation to learn task-specialized representations, ensuring robust generalization. Crucially, during inference, it operates in a fully cycle-detection-free and phase-free manner, requiring neither cardiac cycle seg-mentation nor explicit End-Diastolic/End-Systolic (ED/ES) annotations. Ad-ditionally, we introduce an ED/ES-guided 2D/3D hybrid multi-view regres-sion model specifically to optimize Task 1. On a patient-level split containing 1,203 training videos from 237 patients and 300 validation videos from 59 independent patients, the DINOv2-based framework achieved a mean abso-lute error (MAE) of 5.03% for Task 1, an AUC-ROC of 76.48% for Task 2, and an AUC-ROC of 70.26% for Task 3. For Task 1, the specialized ED/ES-guided model further improves performance, achieving an MAE of 4.64%. This framework demonstrates the effectiveness of foundation model repre-sentations across diverse cardio-oncology tasks and the additional benefit of physiology-guided modeling for accurate LVEF estimation.

Related papers

• SV-Cine: Diagnosis-Conditioned Segmentation of Single Ventricle Physiology via Generative Data Augmentation [8.00573700660471]
  Single Ventricle Physiology (SVP) is a rare subtype of congenital heart disease characterized by the presence of a single functional cardiac ventricle.<n>We propose a cardiac MRI segmentation framework focused on ventricular chambers and myocardium segmentation tailored for SVP.
  arXiv  Detail & Related papers  (2026-09-11T15:59:06Z)
• Physics-Informed Deep Learning for False Ventricular Tachycardia Alarm Reduction in the ICU [44.313512671851306]
  False ventricular tachycardia (VT) alarms are a leading contributor to alarm fatigue in intensive care units.<n>We propose a deep learning framework combining a 1D SE-ResNet with ICU-realistic data augmentations and a physics-informed auxiliary reconstruction task.
  arXiv  Detail & Related papers  (2026-09-08T16:33:07Z)
• EchoRisk: A Multicentre Echocardiography Dataset and Benchmark for Cardio-Oncology [1.1201128439299002]
  Therapy-induced cardiotoxicity is the leading non-oncological cause of treatment interruption in breast cancer patients.<n>We present EchoRisk, the first curated, multicentre, longitudinal echocardiography dataset with explicit cardiotoxicity labels.<n>The dataset comprises 422 patients enrolled in the EU-funded CARDIOCARE prospective study across five European sites.
  arXiv  Detail & Related papers  (2026-07-01T15:05:10Z)
• A Latent ODE Approach to Spatiotemporal Modeling of Cine Cardiac MRI [35.84205082882139]
  We present a latent dynamical model that encodes bi-ventricular anatomy and full-cycle cine motion as a continuous trajectory.<n>We studied 72,386 UK Biobank participants without baseline cardiovascular disease, including 367 incident heart failure events.
  arXiv  Detail & Related papers  (2026-06-25T07:53:45Z)
• Biosignal Fingerprinting: A Cross-Modal PPG-ECG Foundation Model [30.913143342078612]
  Biosignal fingerprints encode an individual's cardiovascular state in a modality-agnostic, privacy-preserving form reusable across clinical tasks.<n>Across 7 downstream tasks, spanning cross-modal reconstruction, cardiovascular disease classification, hypertension detection, mortality prediction, and demographic inference, biosignal fingerprints achieve competitive or superior performance.
  arXiv  Detail & Related papers  (2026-05-10T14:40:58Z)
• CardioMOD-Net: A Modal Decomposition-Neural Network Framework for Diagnosis and Prognosis of HFpEF from Echocardiography Cine Loops [4.50720422463361]
  Heart failure with preserved ejection fraction (HFpEF) arises from diverse comorbidities and progresses through prolonged subclinical stages.<n>Current echocardiography-based Artificial Intelligence (AI) models focus primarily on binary HFpEF detection in humans.<n>We developed a unified AI framework, CardioMOD-Net, to perform multiclass diagnosis and continuous prediction of HFpEF onset.
  arXiv  Detail & Related papers  (2026-01-03T12:41:14Z)
• Conditional Diffusion Model with Anatomical-Dose Dual Constraints for End-to-End Multi-Tumor Dose Prediction [13.716930604289924]
  ADDiff-Dose is an Anatomical-Dose Dual Constraints Diffusion Model for end-to-end multi-tumor dose prediction.<n>It incorporates conditional features via a multi-head attention mechanism and utilizes a composite loss function combining MSE, conditional terms, and KL divergence.<n>It significantly outperforms traditional baselines, achieving an MAE of 0.101-0.154, a DICE coefficient of 0.927, and limiting spinal cord maximum dose error to within 0.1 Gy.
  arXiv  Detail & Related papers  (2025-08-04T04:25:47Z)
• Multi-Model Ensemble Approach for Accurate Bi-Atrial Segmentation in LGE-MRI of Atrial Fibrillation Patients [3.676588766498097]
  Atrial fibrillation (AF) is the most prevalent form of cardiac arrhythmia and is associated with increased morbidity and mortality. This work presents an ensemble approach that integrates multiple machine learning models, including Unet, ResNet, EfficientNet and VGG, to perform automatic bi-atrial segmentation from LGE-MRI data.
  arXiv  Detail & Related papers  (2024-09-24T13:33:46Z)
• Development of Automated Neural Network Prediction for Echocardiographic Left ventricular Ejection Fraction [36.58987036154144]
  This paper proposes a new pipeline method based on deep neural networks and ensemble learning to quantify left ventricular ejection fraction (LVEF) The method was developed and validated in an open-source dataset containing 10,030 echocardiograms. This study demonstrates that an automated neural network-based calculation of LVEF is comparable to expert clinicians performing frame-by-frame manual evaluation of cardiac systolic function.
  arXiv  Detail & Related papers  (2024-03-18T18:09:22Z)
• Fusion of Diffusion Weighted MRI and Clinical Data for Predicting Functional Outcome after Acute Ischemic Stroke with Deep Contrastive Learning [1.4149937986822438]
  Stroke is a common disabling neurological condition that affects about one-quarter of the adult population over age 25. Our proposed fusion model achieves 0.87, 0.80 and 80.45% for AUC, F1-score and accuracy, respectively.
  arXiv  Detail & Related papers  (2024-02-16T18:51:42Z)
• Self-Supervised Pretraining Improves Performance and Inference Efficiency in Multiple Lung Ultrasound Interpretation Tasks [65.23740556896654]
  We investigated whether self-supervised pretraining could produce a neural network feature extractor applicable to multiple classification tasks in lung ultrasound analysis. When fine-tuning on three lung ultrasound tasks, pretrained models resulted in an improvement of the average across-task area under the receiver operating curve (AUC) by 0.032 and 0.061 on local and external test sets respectively.
  arXiv  Detail & Related papers  (2023-09-05T21:36:42Z)
• Successive Subspace Learning for Cardiac Disease Classification with Two-phase Deformation Fields from Cine MRI [36.044984400761535]
  This work proposes a lightweight successive subspace learning framework for CVD classification. It is based on an interpretable feedforward design, in conjunction with a cardiac atlas. Compared with 3D CNN-based approaches, our framework achieves superior classification performance with 140$times$ fewer parameters.
  arXiv  Detail & Related papers  (2023-01-21T15:00:59Z)
• Segmentation of the Myocardium on Late-Gadolinium Enhanced MRI based on 2.5 D Residual Squeeze and Excitation Deep Learning Model [55.09533240649176]
  The aim of this work is to develop an accurate automatic segmentation method based on deep learning models for the myocardial borders on LGE-MRI. A total number of 320 exams (with a mean number of 6 slices per exam) were used for training and 28 exams used for testing. The performance analysis of the proposed ensemble model in the basal and middle slices was similar as compared to intra-observer study and slightly lower at apical slices.
  arXiv  Detail & Related papers  (2020-05-27T20:44:38Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.