Patient management based on anatomic measurements

A non-transitory computer readable medium embodying a program of instructions executable by machine to perform operations for anatomic measurement, the operations comprising:

• receiving image data of at least a portion of a spine of a patient;
• applying a machine learning technique comprising a deep learning algorithm to determine centroids, vertebra-center coordinate systems or vertebra-specific landmarks of a target vertebra and an adjacent vertebra of the spine in the image data and automatically measuring an anterior shift of the target vertebra of the spine based on the centroids, the vertebra-center coordinate systems or the vertebra-specific landmarks, wherein the anterior shift is automatically measured by identifying first and second front planes of the target vertebra and the adjacent vertebra respectively or first and second back planes of the target vertebra and the adjacent vertebra respectively and determining a distance between the first and second front planes or the first and second back planes, wherein the first and second front planes or the first and second back planes are perpendicular to a spinal disc between the target and the adjacent vertebrae, wherein the anterior shift is an acquired anterior displacement of the target vertebra relative to the adjacent vertebra;
• determining a degree of spondylolisthesis based on the anterior shift;
• and
• presenting the degree of spondylolisthesis in relation to a representative sub-population of patients similar to the patient in a report.