In Journal of applied physiology (Bethesda, Md. : 1985) ; h5-index 0.0
The loss of skeletal muscle mass is recognized as a complication of several chronic diseases and is associated with increased mortality and a decreased quality of life. Relevant and reliable animal models in which muscle wasting can be monitored non-invasively over time are instrumental to investigate and develop new therapies. In this work, we developed a fully automatic deep learning algorithm for segmentation of micro cone beam CT (µCBCT) images of the lower limb muscle complex in mice, and subsequent muscle mass calculation. A deep learning algorithm was trained on manually segmented data from 32 mice. Muscle wet mass measurements were obtained of 47 mice and served as a dataset for model validation and the reverse model validation. The automatic algorithm performance was approximately 150 times faster than manual segmentation. Reverse validation of the algorithm showed high quantitative metrics substantiating the robustness and accuracy of the model, i.e. a Dice Similarity Coefficient of 0.93, a Hausdorff distance of 0.4 mm, and a center-of-mass displacement of 0.1 mm. A high correlation (R2=0.92) was obtained between the CT-derived muscle mass measurements and the muscle wet masses. Longitudinal follow-up revealed time-dependent changes in muscle mass that separated control from lung tumor bearing mice, which was confirmed as cachexia. In conclusion, this deep learning model for automated assessment of the lower limb muscle complex provides highly accurate non-invasive longitudinal evaluation of skeletal muscle mass. Furthermore, it facilitates the workflow and increases the amount of data derived from mouse studies, while reducing the animal numbers.
van der Heyden Brent, van de Worp Wouter R P H, van Helvoort Ardy, Theys Jan, Schols Annemie M W J, Langen Ramon C J, Verhaegen Frank
artificial intelligence, muscle segmentation, µCBCT