Deep learning-based segmentation of rabbit fetal skull with limited and sub-optimal training labels

Rajath Soans, Alexa Gleason, Tosha Shah, Corey Miller, Barbara Robinson, Kimberly Brannen, Antong Chen

Keywords: U-Net, non-clinical drug safety assessment, DART, micro-CT, rabbit fetus, sub-optimal ground truth training label, sparse label map

TL;DR: We propose a deep learning-based method to segment the skeletal structures in the micro-CT images of rabbit fetuses which can assist in the assessment of drug-induced skeletal abnormalities in developmental and reproductive toxicology (DART).

Abstract: In this paper, we propose a deep learning-based method to segment the skeletal structures in the micro-CT images of Dutch-Belted rabbit fetuses which can assist in the assessment of drug-induced skeletal abnormalities as a required study in developmental and reproductive toxicology (DART). Our strategy leverages sub-optimal segmentation labels of 22 skull bones from 26 micro-CT volumes and maps them to 250 unlabeled volumes on which a deep CNN-based segmentation model is trained. In the experiments, our model was able to achieve an average Dice Similarity Coefficient (DSC) of 0.89 across all bones on the testing set, and 14 out of the 26 skull bones reached average DSC >0.93. Our next steps are segmenting the whole body followed by developing a model to classify abnormalities.