System and method for automated volumetric spinal assessment
Systems, methods, and computer-readable storage media for measuring spinal canal volume in vertebrates, and more specifically to using Artificial Intelligence (AI) to predict how surgical options will affect spinal canal volume. A system configured as disclosed herein can receive two or more pre-operation medical images capturing at least one functional spinal unit, then calculate an initial spinal canal regional volume using the pre-operation medical images for at least a portion of the at least one functional spinal unit. The system can then calculate, using a neural network, a predicted spinal canal regional volume for at least a portion of the at least one functional spinal unit undergoing various spine surgery options separately, resulting in predicted spinal canal regional volumes corresponding to the plurality of spine surgery options. The system or a surgeon can then select, using that data, one or more of the spine surgery options.
1 . A method comprising:
receiving, at a computer system, at least two pre-operation medical images, the at least two pre-operation medical images each capturing at least one functional spinal unit;
generating regional volumetric stenosis measurements of the at least one functional spinal unit;
calculating, via at least one processor of the computer system using the at least two pre-operation medical images and the regional volumetric stenosis measurements, an initial spinal canal regional volume for at least a portion of the at least one functional spinal unit;
identifying a plurality of spine surgery options;
calculating, via the at least one processor executing a neural network wherein the regional volumetric stenosis measurements are inputs to the neural network, a predicted spinal canal regional volume for the at least a portion of the at least one functional spinal unit undergoing each of the plurality of spine surgery options separately, resulting in a plurality of predicted spinal canal regional volumes corresponding to the plurality of spine surgery options; and
selecting, based at least in part on the plurality of predicted spinal canal regional volumes, a selected spine surgery option from the plurality of spine surgery options,
such that the selected spine surgery option is executed on the at least one functional spinal unit.
2 . The method of claim 1 , wherein the at least two pre-operation medical images are part of a pre-operation medical study.
3 . The method of claim 1 , further comprising:
receiving, at the computer system after execution of the selected spine surgery option, at least two post-operation medical images, the at least two post-operation medical images capturing the at least one functional spinal unit;
calculating, via the at least one processor of the computer system using the at least two post-operation medical images, a post-operation spinal canal regional volume;
comparing, via the at least one processor, the post-operation spinal canal regional volume to the initial spinal canal regional volume, resulting in a comparison; and
updating the neural network based on the comparison.
4 . The method of claim 3 , wherein the comparing further comprises comparing the post-operation spinal canal regional volume to at least one predicted spinal canal regional volume of the plurality of predicted spinal canal regional volumes, wherein one predicted spinal canal regional volume within the at least one predicted spinal canal regional volume is based on the selected spine surgery option.
5 . The method of claim 1 , wherein the neural network further predicts, for each of the plurality of spine surgery options, a predicted stenosis resolution, resulting in a plurality of predicted stenosis resolutions; and
wherein the selected spine surgery option is selected, at least in part, based on which of the plurality of spine surgery options is most likely to reduce stenosis symptoms.
6 . The method of claim 1 , wherein each pre-operation medical image in the at least two pre-operation medical images is at least one of a CT, a MRI, an X-ray and an Ultrasound image.
7 . The method of claim 1 , wherein the regional volumetric stenosis measurements comprise:
canal regions comprising: central, lateral recess, and foraminal; and
level regions comprising: disc level, vertebral body level, and pedicle level.
8 . A system comprising:
at least one processor; and
a non-transitory computer-readable storage medium having instructions stored which, when executed by the at least one processor, cause the at least one processor to perform operations comprising:
receiving at least two pre-operation medical images, the at least two pre-operation medical images each capturing at least one functional spinal unit;
generating regional volumetric stenosis measurements of the at least one functional spinal unit;
calculating, using the at least two pre-operation medical images and the regional volumetric stenosis measurements, an initial spinal canal regional volume for at least a portion of the at least one functional spinal unit;
identifying a plurality of spine surgery options;
calculating, by executing a neural network wherein the regional volumetric stenosis measurements are inputs to the neural network, a predicted spinal canal regional volume for the at least a portion of the at least one functional spinal unit undergoing each of the plurality of spine surgery options separately, resulting in a plurality of predicted spinal canal regional volumes corresponding to the plurality of spine surgery options; and
selecting, based at least in part on the plurality of predicted spinal canal regional volumes, a selected spine surgery option from the plurality of spine surgery options,
such that the selected spine surgery option is executed on the at least one functional spinal unit.
9 . The system of claim 8 , wherein the at least two pre-operation medical images are part of a pre-operation medical study.
10 . The system of claim 8 , the non-transitory computer-readable storage medium having additional instructions stored which, when executed by the at least one processor, cause the at least one processor to perform operations comprising:
receiving, after execution of the selected spine surgery option, at least two post-operation medical images, the at least two post-operation medical images capturing the at least one functional spinal unit;
calculating, using the at least two post-operation medical images, a post-operation spinal canal regional volume;
comparing the post-operation spinal canal regional volume to the initial spinal canal regional volume, resulting in a comparison; and
updating the neural network based on the comparison.
11 . The system of claim 10 , wherein the comparing further comprises comparing the post-operation spinal canal regional volume to at least one predicted spinal canal regional volume of the plurality of predicted spinal canal regional volumes, wherein one predicted spinal canal regional volume within the at least one predicted spinal canal regional volume is based on the selected spine surgery option.
12 . The system of claim 8 , wherein the neural network further predicts, for each of the plurality of spine surgery options, a predicted stenosis resolution, resulting in a plurality of predicted stenosis resolutions; and
wherein the selected spine surgery option is selected, at least in part, based on which of the plurality of spine surgery options is most likely to reduce stenosis symptoms.
13 . The system of claim 8 , wherein each pre-operation medical image in the at least two pre-operation medical images is at least one of a CT, a MRI, an X-ray and an Ultrasound image.
14 . The system of claim 8 , wherein the regional volumetric stenosis measurements comprise:
canal regions comprising: central, lateral recess, and foraminal; and
level regions comprising: disc level, vertebral body level, and pedicle level.
15 . A non-transitory computer-readable storage medium having instructions stored which, when executed by at least one processor, cause the at least one processor to perform operations comprising:
receiving at least two pre-operation medical images, the at least two pre-operation medical images each capturing at least one functional spinal unit;
generating regional volumetric stenosis measurements of the at least one functional spinal unit;
calculating, using the at least two pre-operation medical images and the regional volumetric stenosis measurements, an initial spinal canal regional volume for at least a portion of the at least one functional spinal unit;
identifying a plurality of spine surgery options;
calculating, by executing a neural network wherein the regional volumetric stenosis measurements are inputs to the neural network, a predicted spinal canal regional volume for the at least a portion of the at least one functional spinal unit undergoing each of the plurality of spine surgery options separately, resulting in a plurality of predicted spinal canal regional volumes corresponding to the plurality of spine surgery options; and
selecting, based at least in part on the plurality of predicted spinal canal regional volumes, a selected spine surgery option from the plurality of spine surgery options,
such that the selected spine surgery option is executed on the at least one functional spinal unit.
16 . The non-transitory computer-readable storage medium of claim 15 , wherein the at least two pre-operation medical images are part of a pre-operation medical study.
17 . The non-transitory computer-readable storage medium of claim 15 , having additional instructions stored which, when executed by the at least one processor, cause the at least one processor to perform operations comprising:
receiving, after execution of the selected spine surgery option, at least two post-operation medical images, the at least two post-operation medical images capturing the at least one functional spinal unit;
calculating, using the at least two post-operation medical images, a post-operation spinal canal regional volume;
comparing the post-operation spinal canal regional volume to the initial spinal canal regional volume, resulting in a comparison; and
updating the neural network based on the comparison.
18 . The non-transitory computer-readable storage medium of claim 17 , wherein the comparing further comprises comparing the post-operation spinal canal regional volume to at least one predicted spinal canal regional volume of the plurality of predicted spinal canal regional volumes, wherein one predicted spinal canal regional volume within the at least one predicted spinal canal regional volume is based on the selected spine surgery option.