Effort-free Automated Skeletal Abnormality Detection of Rat Fetuses on Whole-body Micro-CT Scans
This addresses the need for efficient drug safety assessment in animal studies, though it is incremental as it applies existing feature engineering to a new domain.
The paper tackled automated skeletal abnormality detection in rat fetus micro-CT scans, achieving accuracies of 0.900 for skeletal labeling and 0.810 for abnormality detection using limited training data of 49 fetuses.
Machine Learning-based fast and quantitative automated screening plays a key role in analyzing human bones on Computed Tomography (CT) scans. However, despite the requirement in drug safety assessment, such research is rare on animal fetus micro-CT scans due to its laborious data collection and annotation. Therefore, we propose various bone feature engineering techniques to thoroughly automate the skeletal localization/labeling/abnormality detection of rat fetuses on whole-body micro-CT scans with minimum effort. Despite limited training data of 49 fetuses, in skeletal labeling and abnormality detection, we achieve accuracy of 0.900 and 0.810, respectively.