Global ETD Search

Search theses and dissertations gathered from participating repositories worldwide. Every result links back to the library that holds it. No account is needed.

Results

Showing 1 to 5 of 5 for “"EchoNet-Dynamic"”.

  1. Using Visual Prompts to Analyze Ejection Fraction in Echocardiograms

    … classification space. When evaluated on the EchoNet Dynamic dataset using CLIP as the backbone model, our framework achieves an AUROC of 0.89. This lightweight solution provides reliable LVEF prediction while avoiding expensive retraining, demonstrating the potential of adapting …

    wvu Repository record for Using Visual Prompts to Analyze Ejection Fraction in Echocardiograms (opens in a new tab)

  2. Synthetic Ultrasound Video Generation with Generative Adversarial Networks

    … a downstream task. Extensive experiments on the EchoNet-Dynamic dataset demonstrate that the proposed model achieves an FID score of 126 and an FVD score of 233 and can be used in data augmentation tasks in small data scenarios.

    carleton Repository record for Synthetic Ultrasound Video Generation with Generative Adversarial Networks (opens in a new tab)

  3. Lightweight Transformers for Echocardiographic Ejection Fraction Estimation: Frame Encoding Strategies and Anatomical Auxiliary Supervision

    … transformer trained on 10,030 videos from EchoNet-Dynamic. Four frame encoders were evaluated: a linear projection, an ImageNet-pretrained ResNet-50, an adjacent-frame contrastive encoder, and a same-video contrastive encoder. A separately trained U-Net achieved a validation Dice score of …

    gatech Repository record for Lightweight Transformers for Echocardiographic Ejection Fraction Estimation: Frame Encoding Strategies and Anatomical Auxiliary Supervision (opens in a new tab)

  4. Unsupervised Deep Learning Image Segmentation Approaches for Echocardiogram Analysis and Clinical Risk Prediction

    … of the ejection fraction. Evaluation in the EchoNet Dynamic dataset demonstrated competitive performance with supervised methods (Dice coefficient: 0.8225, IoU: 0.7071) while using significantly fewer labeled data points. The second contribution explores the integration of Electronic Health …

    ttu Repository record for Unsupervised Deep Learning Image Segmentation Approaches for Echocardiogram Analysis and Clinical Risk Prediction (opens in a new tab) Embargoed until 2028-08-01

  5. Segmentation automatique d’images échocardiographiques à l’aide d’une architecture Shifted Windows Vision Transformer

    … est effectuée avec l’ensemble de données EchoNet-Dynamic utilisé pour entraîner notre modèle. Les résultats montrent une précision de 0,97, un coefficient de Dice de 0,87 et une Intersection over Union (IoU) de 0,78. C’est ainsi que les modèles de transformateur de Swin sont prometteurs …

    ets-quebec Download PDF for Segmentation automatique d’images échocardiographiques à l’aide d’une architecture Shifted Windows Vision Transformer (opens in a new tab)