Efficient Semantic Diffusion Architectures for Model Training on Synthetic Echocardiograms

We investigate the utility of diffusion generative models to efficiently synthesise datasets that effectively train deep learning models for image analysis. Specifically, we propose novel $\Gamma$-distribution Latent Denoising Diffusion Models (LDMs) designed to generate semantically guided synthetic cardiac ultrasound images with improved computational efficiency. We also investigate the potential of using these synthetic images as a replacement for real data in training deep networks for left-ventricular segmentation and binary echocardiogram view classification tasks. We compared six diffusion models in terms of the computational cost of generating synthetic 2D echo data, the visual realism of the resulting images, and the performance, on real data, of downstream tasks (segmentation and classification) trained using these synthetic echoes. We compare various diffusion strategies and ODE solvers for their impact on segmentation and classification performance. The results show that our propose architectures significantly reduce computational costs while maintaining or improving downstream task performance compared to state-of-the-art methods. While other diffusion models generated more realistic-looking echo images at higher computational cost, our research suggests that for model training, visual realism is not necessarily related to model performance, and considerable compute costs can be saved by using more efficient models.

Multi-Site Class-Incremental Learning with Weighted Experts in Echocardiography

Building an echocardiography view classifier that maintains performance in real-life cases requires diverse multi-site data, and frequent updates with newly available data to mitigate model drift. Simply fine-tuning on new datasets results in "catastrophic forgetting", and cannot adapt to variations of view labels between sites. Alternatively, collecting all data on a single server and re-training may not be feasible as data sharing agreements may restrict image transfer, or datasets may only become available at different times. Furthermore, time and cost associated with re-training grows with every new dataset. We propose a class-incremental learning method which learns an expert network for each dataset, and combines all expert networks with a score fusion model. The influence of ``unqualified experts'' is minimised by weighting each contribution with a learnt in-distribution score. These weights promote transparency as the contribution of each expert is known during inference. Instead of using the original images, we use learned features from each dataset, which are easier to share and raise fewer licensing and privacy concerns. We validate our work on six datasets from multiple sites, demonstrating significant reductions in training time while improving view classification performance.

BackMix: Mitigating Shortcut Learning in Echocardiography with Minimal Supervision

Neural networks can learn spurious correlations that lead to the correct prediction in a validation set, but generalise poorly because the predictions are right for the wrong reason. This undesired learning of naive shortcuts (Clever Hans effect) can happen for example in echocardiogram view classification when background cues (e.g. metadata) are biased towards a class and the model learns to focus on those background features instead of on the image content. We propose a simple, yet effective random background augmentation method called BackMix, which samples random backgrounds from other examples in the training set. By enforcing the background to be uncorrelated with the outcome, the model learns to focus on the data within the ultrasound sector and becomes invariant to the regions outside this. We extend our method in a semi-supervised setting, finding that the positive effects of BackMix are maintained with as few as 5% of segmentation labels. A loss weighting mechanism, wBackMix, is also proposed to increase the contribution of the augmented examples. We validate our method on both in-distribution and out-of-distribution datasets, demonstrating significant improvements in classification accuracy, region focus and generalisability. Our source code is available at: https://github.com/kitbransby/BackMix

EchoNet-Synthetic: Privacy-preserving Video Generation for Safe Medical Data Sharing

To make medical datasets accessible without sharing sensitive patient information, we introduce a novel end-to-end approach for generative de-identification of dynamic medical imaging data. Until now, generative methods have faced constraints in terms of fidelity, spatio-temporal coherence, and the length of generation, failing to capture the complete details of dataset distributions. We present a model designed to produce high-fidelity, long and complete data samples with near-real-time efficiency and explore our approach on a challenging task: generating echocardiogram videos. We develop our generation method based on diffusion models and introduce a protocol for medical video dataset anonymization. As an exemplar, we present EchoNet-Synthetic, a fully synthetic, privacy-compliant echocardiogram dataset with paired ejection fraction labels. As part of our de-identification protocol, we evaluate the quality of the generated dataset and propose to use clinical downstream tasks as a measurement on top of widely used but potentially biased image quality metrics. Experimental outcomes demonstrate that EchoNet-Synthetic achieves comparable dataset fidelity to the actual dataset, effectively supporting the ejection fraction regression task. Code, weights and dataset are available at https://github.com/HReynaud/EchoNet-Synthetic.

Fourier-Net+: Leveraging Band-Limited Representation for Efficient 3D Medical Image Registration

U-Net style networks are commonly utilized in unsupervised image registration to predict dense displacement fields, which for high-resolution volumetric image data is a resource-intensive and time-consuming task. To tackle this challenge, we first propose Fourier-Net, which replaces the costly U-Net style expansive path with a parameter-free model-driven decoder. Instead of directly predicting a full-resolution displacement field, our Fourier-Net learns a low-dimensional representation of the displacement field in the band-limited Fourier domain which our model-driven decoder converts to a full-resolution displacement field in the spatial domain. Expanding upon Fourier-Net, we then introduce Fourier-Net+, which additionally takes the band-limited spatial representation of the images as input and further reduces the number of convolutional layers in the U-Net style network's contracting path. Finally, to enhance the registration performance, we propose a cascaded version of Fourier-Net+. We evaluate our proposed methods on three datasets, on which our proposed Fourier-Net and its variants achieve comparable results with current state-of-the art methods, while exhibiting faster inference speeds, lower memory footprint, and fewer multiply-add operations. With such small computational cost, our Fourier-Net+ enables the efficient training of large-scale 3D registration on low-VRAM GPUs. Our code is publicly available at \url{https://github.com/xi-jia/Fourier-Net}.

Automatic retrieval of corresponding US views in longitudinal examinations

Skeletal muscle atrophy is a common occurrence in critically ill patients in the intensive care unit (ICU) who spend long periods in bed. Muscle mass must be recovered through physiotherapy before patient discharge and ultrasound imaging is frequently used to assess the recovery process by measuring the muscle size over time. However, these manual measurements are subject to large variability, particularly since the scans are typically acquired on different days and potentially by different operators. In this paper, we propose a self-supervised contrastive learning approach to automatically retrieve similar ultrasound muscle views at different scan times. Three different models were compared using data from 67 patients acquired in the ICU. Results indicate that our contrastive model outperformed a supervised baseline model in the task of view retrieval with an AUC of 73.52% and when combined with an automatic segmentation model achieved 5.7%+/-0.24% error in cross-sectional area. Furthermore, a user study survey confirmed the efficacy of our model for muscle view retrieval.

Echo from noise: synthetic ultrasound image generation using diffusion models for real image segmentation

We propose a novel pipeline for the generation of synthetic images via Denoising Diffusion Probabilistic Models (DDPMs) guided by cardiac ultrasound semantic label maps. We show that these synthetic images can serve as a viable substitute for real data in the training of deep-learning models for medical image analysis tasks such as image segmentation. To demonstrate the effectiveness of this approach, we generated synthetic 2D echocardiography images and trained a neural network for segmentation of the left ventricle and left atrium. The performance of the network trained on exclusively synthetic images was evaluated on an unseen dataset of real images and yielded mean Dice scores of 88.5 $\pm 6.0$ , 92.3 $\pm 3.9$, 86.3 $\pm 10.7$ \% for left ventricular endocardial, epicardial and left atrial segmentation respectively. This represents an increase of $9.09$, $3.7$ and $15.0$ \% in Dice scores compared to the previous state-of-the-art. The proposed pipeline has the potential for application to a wide range of other tasks across various medical imaging modalities.

Feature-Conditioned Cascaded Video Diffusion Models for Precise Echocardiogram Synthesis

Image synthesis is expected to provide value for the translation of machine learning methods into clinical practice. Fundamental problems like model robustness, domain transfer, causal modelling, and operator training become approachable through synthetic data. Especially, heavily operator-dependant modalities like Ultrasound imaging require robust frameworks for image and video generation. So far, video generation has only been possible by providing input data that is as rich as the output data, e.g., image sequence plus conditioning in, video out. However, clinical documentation is usually scarce and only single images are reported and stored, thus retrospective patient-specific analysis or the generation of rich training data becomes impossible with current approaches. In this paper, we extend elucidated diffusion models for video modelling to generate plausible video sequences from single images and arbitrary conditioning with clinical parameters. We explore this idea within the context of echocardiograms by looking into the variation of the Left Ventricle Ejection Fraction, the most essential clinical metric gained from these examinations. We use the publicly available EchoNet-Dynamic dataset for all our experiments. Our image to sequence approach achieves an $R^2$ score of 93%, which is 38 points higher than recently proposed sequence to sequence generation methods. Code and models will be available at: https://github.com/HReynaud/EchoDiffusion.

Efficient Pix2Vox++ for 3D Cardiac Reconstruction from 2D echo views

Accurate geometric quantification of the human heart is a key step in the diagnosis of numerous cardiac diseases, and in the management of cardiac patients. Ultrasound imaging is the primary modality for cardiac imaging, however acquisition requires high operator skill, and its interpretation and analysis is difficult due to artifacts. Reconstructing cardiac anatomy in 3D can enable discovery of new biomarkers and make imaging less dependent on operator expertise, however most ultrasound systems only have 2D imaging capabilities. We propose both a simple alteration to the Pix2Vox++ networks for a sizeable reduction in memory usage and computational complexity, and a pipeline to perform reconstruction of 3D anatomy from 2D standard cardiac views, effectively enabling 3D anatomical reconstruction from limited 2D data. We evaluate our pipeline using synthetically generated data achieving accurate 3D whole-heart reconstructions (peak intersection over union score > 0.88) from just two standard anatomical 2D views of the heart. We also show preliminary results using real echo images.

Left Ventricle Contouring of Apical Three-Chamber Views on 2D Echocardiography

We propose a new method to automatically contour the left ventricle on 2D echocardiographic images. Unlike most existing segmentation methods, which are based on predicting segmentation masks, we focus at predicting the endocardial contour and the key landmark points within this contour (basal points and apex). This provides a representation that is closer to how experts perform manual annotations and hence produce results that are physiologically more plausible. Our proposed method uses a two-headed network based on the U-Net architecture. One head predicts the 7 contour points, and the other head predicts a distance map to the contour. This approach was compared to the U-Net and to a point based approach, achieving performance gains of up to 30\% in terms of landmark localisation (<4.5mm) and distance to the ground truth contour (<3.5mm).