Kenneth T Gao1,2,3, Radhika Tibrewala1,2, Madeline Hess1,2, Upasana Bharadwaj1,2, Gaurav Inamdar1,2, Cynthia T Chin1, Valentina Pedoia1,2, and Sharmila Majumdar1,2
1Department of Radiology and Biomedical Imaging, University of California, San Francisco, San Francisco, CA, United States, 2Center for Intelligent Imaging, Department of Radiology and Biomedical Imaging, University of California, San Francisco, San Francisco, CA, United States, 3University of California, Berkeley-University of California San Francisco Graduate Program in Bioengineering, San Francisco, CA, United States
1Department of Radiology and Biomedical Imaging, University of California, San Francisco, San Francisco, CA, United States, 2Center for Intelligent Imaging, Department of Radiology and Biomedical Imaging, University of California, San Francisco, San Francisco, CA, United States, 3University of California, Berkeley-University of California San Francisco Graduate Program in Bioengineering, San Francisco, CA, United States
Vertebral Modic changes are strongly linked to low back pain. We present a deep learning approach that detects Modic changes with 85.7% identification rate and performs voxel-wise mapping to visualize local, granular pathologies.
Fig. 5. Representative examples of the model inputs (T1 and T2 images), radiologist-annotated ground truth segmentations, and the predicted Modic maps. The mapping technique is advantageous for visualizing heterogeneity and transitional pathology.
Fig. 1. Schematic of the full Modic mapping approach. Vertebral bodies are first segmented and extracted from T1-weighted MRI, allowing extraction of the bodies on the T1 and registered T2 images. Next, a binary segmentation network localizes and detects regions of Modic changes. Lastly, each voxel of the detected regions is classified to a Modic type using a nearest neighbor algorithm and T1 and T2 z-scores to form a Modic map.
