Deep learning-based Segmentation of Rabbit fetal skull with limited and sub-optimal annotations

TL;DR

This paper introduces a deep learning method for segmenting rabbit fetal skull bones in micro-CT images using limited and sub-optimal annotations, aiding in developmental toxicology studies.

Contribution

It presents a novel approach that leverages weakly labeled data to train a CNN model for skeletal segmentation in micro-CT images.

Findings

Achieved an average DSC of 0.89 across all skull bones.

14 bones reached an average DSC >0.93.

Demonstrated effective segmentation with limited annotations.

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.