A multimodal deep learning model combining echocardiography and cardiac magnetic resonance features predicted cardiac resynchronisation therapy response with 77.38% accuracy, outperforming a baseline approach using only 2D echocardiography.
Does a multimodal deep learning model combining echocardiography and CMR data improve the accuracy of predicting response to cardiac resynchronisation therapy compared to echocardiography alone?
A novel multimodal deep learning framework combining echocardiography and CMR data significantly improves the accuracy of predicting volumetric response to cardiac resynchronisation therapy.
We present a novel multimodal deep learning framework for cardiac resynchronisation therapy (CRT) response prediction from 2D echocardiography and cardiac magnetic resonance (CMR) data. The proposed method first uses the 'nnU-Net' segmentation model to extract segmentations of the heart over the full cardiac cycle from the two modalities. Next, a multimodal deep learning classifier is used for CRT response prediction, which combines the latent spaces of the segmentation models of the two modalities. At test time, this framework can be used with 2D echocardiography data only, whilst taking advantage of the implicit relationship between CMR and echocardiography features learnt from the model. We evaluate our pipeline on a cohort of 50 CRT patients for whom paired echocardiography/CMR data were available, and results show that the proposed multimodal classifier results in a statistically significant improvement in accuracy compared to the baseline approach that uses only 2D echocardiography data. The combination of multimodal data enables CRT response to be predicted with 77.38% accuracy (83.33% sensitivity and 71.43% specificity), which is comparable with the current state-of-the-art in machine learning-based CRT response prediction. Our work represents the first multimodal deep learning approach for CRT response prediction.
Puyol‐Antón et al. (Wed,) conducted a other in Heart failure requiring cardiac resynchronisation therapy (n=50). Multimodal deep learning (MMDL) model vs. Single-modality 2D echocardiography model was evaluated on Accuracy of CRT response prediction. A multimodal deep learning model combining echocardiography and cardiac magnetic resonance features predicted cardiac resynchronisation therapy response with 77.38% accuracy, outperforming a baseline approach using only 2D echocardiography.