Automated Mouse Organ Segmentation: A Deep Learning Based Solution
This addresses the need for accurate organ identification in animal studies to quantify drug biodistribution, but it is incremental as it applies an existing deep learning method to a specific domain.
The paper tackled the problem of automating organ segmentation in mouse cross-section images for preclinical drug development, achieving high precision with dice coefficients ranging from 0.83 to 0.95 for key organs.
The analysis of animal cross section images, such as cross sections of laboratory mice, is critical in assessing the effect of experimental drugs such as the biodistribution of candidate compounds in preclinical drug development stage. Tissue distribution of radiolabeled candidate therapeutic compounds can be quantified using techniques like Quantitative Whole-Body Autoradiography (QWBA).QWBA relies, among other aspects, on the accurate segmentation or identification of key organs of interest in the animal cross section image such as the brain, spine, heart, liver and others. We present a deep learning based organ segmentation solution to this problem, using which we can achieve automated organ segmentation with high precision (dice coefficient in the 0.83-0.95 range depending on organ) for the key organs of interest.