Self-adaptive deep learning-based segmentation for universal and functional clinical and preclinical CT image analysis.

ABSTRACT

BACKGROUND: Methods to monitor cardiac functioning non-invasively can accelerate preclinical and clinical research into novel treatment options for heart failure. However, manual image analysis of cardiac substructures is resource-intensive and error-prone. While automated methods exist for clinical CT images, translating these to preclinical µCT data is challenging. We employed deep learning to automate the extraction of quantitative data from both CT and µCT images. METHODS: We collected a public dataset of cardiac CT images of human patients, as well as acquired µCT images of wild-type and accelerated aging mice. The left ventricle, myocardium, and right ventricle were manually segmented in the µCT training set. After template-based heart detection, two separate segmentation neural networks were trained using the nnU-Net framework. RESULTS: The mean Dice score of the CT segmentation results (0.925 ± 0.019, n = 40) was superior to those achieved by state-of-the-art algorithms. Automated and manual segmentations of the µCT training set were nearly identical. The estimated median Dice score (0.940) of the test set results was comparable to existing methods. The automated volume metrics were similar to manual expert observations. In aging mice, ejection fractions had significantly decreased, and myocardial volume increased by age 24 weeks. CONCLUSIONS: With further optimization, automated data extraction expands the application of (µ)CT imaging, while reducing subjectivity and workload. The proposed method efficiently measures the left and right ventricular ejection fraction and myocardial mass. With uniform translation between image types, cardiac functioning in diastolic and systolic phases can be monitored in both animals and humans.