Open-Source Pre-Clinical Image Segmentation: Mouse cardiac MRI datasets with a deep learning segmentation framework.
Authors
Affiliations (5)
Affiliations (5)
- UCL Centre for Translational Cardiovascular Imaging, Institute of Cardiovascular Science, University College London, London, UK; UCL Centre for Advanced Biomedical Imaging, University College London, London, UK.
- UCL Centre for Advanced Biomedical Imaging, University College London, London, UK.
- UCL Centre for Translational Cardiovascular Imaging, Institute of Cardiovascular Science, University College London, London, UK.
- Department of Physiology, Anatomy and Genetics, University of Oxford, Oxford, UK.
- UCL Centre for Translational Cardiovascular Imaging, Institute of Cardiovascular Science, University College London, London, UK. Electronic address: [email protected].
Abstract
Longitudinal cardiac MRI in small animal models is essential for studying cardiovascular disease mechanisms and assessing new therapies. However, conventional manual segmentation of ventricular structures from cine short-axis images is slow, labour-intensive, and subject to substantial observer variability, limiting reproducibility in large-scale pre-clinical studies. While deep learning (DL) segmentation has become standard in human cardiac MRI, existing models do not generalize to pre-clinical datasets. Current mouse-specific approaches have been constrained by small private cohorts, where the DL segmentation models are not published. Here, we present the first publicly-available pre-clinical cardiac MRI dataset, along with an open-source DL segmentation model and a web-based interface for easy deployment. The dataset comprises of complete cine short-axis cardiac MRI images from 130 mice with diverse phenotypes, acquired at 9.4T. The dataset also contains expert manual segmentations of left ventricular (LV) blood pool and myocardium at end-diastole, end-systole, as well as additional timeframes with artefacts to improve robustness. Using this resource, we developed an open-source DL segmentation model based on the UNet3+ architecture. The model was evaluated against an independent internal test dataset (9.4T, n = 25 mice), as well as two external test datasets (n = 15 mice at 7T, and n = 10 mice at 11.7T) and compared to expert manual segmentations in terms of Dice and functional parameters. At inference the DL segmentation model took <20 ms per 2D image, enabling complete cine stack segmentation in ~4.6s - over 6,000-fold speed-up over manual analysis. It achieved high segmentation accuracy in both the blood pool and myocardium in all test datasets (overall Dice ≥ 0.91). In addition, functional parameters showed excellent agreement with manual ground-truth measurements (ICC ≥ 0.89 for the internal test dataset, and ICC > 0.85 for the external test datasets), with ICC values comparable to human inter-observer variability. This work provides the first open-access mouse cardiac MRI dataset, an open-source DL segmentation model, and an accessible inference platform. These tools establish a benchmark for pre-clinical cardiac MRI, enabling reproducible, scalable, and community-driven development of DL methods to accelerate cardiovascular research.