6 papers
Comparison of Loss Functions for Robust Deep Learning-based Echocardiography Segmentation when Learning with Partially Labelled Data from Multiple Domains
Iman Islam, Esther Puyol-Antón, Bram Ruijsink +2
Echocardiography is the first imaging modality used for assessing cardiac function, and accurate segmentation of cardiac structures is essential for deriving biomarkers. However, t…
Understanding-informed Bias Mitigation for Fair CMR Segmentation
Tiarna Lee, Esther Puyol-Antón, Bram Ruijsink +6
Artificial intelligence (AI) is increasingly being used for medical imaging tasks. However, there can be biases in AI models, particularly when they are trained using imbalanced tr…
DeepSPV: A Deep Learning Pipeline for 3D Spleen Volume Estimation from 2D Ultrasound Images
Zhen Yuan, David Stojanovski, Lei Li +5
Splenomegaly, the enlargement of the spleen, is an important clinical indicator for various associated medical conditions, such as sickle cell disease (SCD). Spleen length measured…
Improving the Scan-rescan Precision of AI-based CMR Biomarker Estimation
Dewmini Hasara Wickremasinghe, Yiyang Xu, Esther Puyol-Antón +3
Quantification of cardiac biomarkers from cine cardiovascular magnetic resonance (CMR) data using deep learning (DL) methods offers many advantages, such as increased accuracy and…
Label Dropout: Improved Deep Learning Echocardiography Segmentation Using Multiple Datasets With Domain Shift and Partial Labelling
Iman Islam, Esther Puyol-Antón, Bram Ruijsink +2
Echocardiography (echo) is the first imaging modality used when assessing cardiac function. The measurement of functional biomarkers from echo relies upon the segmentation of cardi…
Improving Deep Learning Model Calibration for Cardiac Applications using Deterministic Uncertainty Networks and Uncertainty-aware Training
Tareen Dawood, Bram Ruijsink, Reza Razavi +2
Improving calibration performance in deep learning (DL) classification models is important when planning the use of DL in a decision-support setting. In such a scenario, a confiden…