System and methods for classifying magnetic resonance imaging (MRI) image characteristics

A system for classifying magnetic resonance imaging (MRI) pulse sequences, the system comprising:

• one or more processors;
• and
• one or more memories storing processor-executable instructions that, when executed by the one or more processors, cause the one or more processors to perform operations comprising:
• receiving first medical imaging data associated with an MRI scan;
• determining a plurality of pulse sequence characteristics for the first medical imaging data using a machine learning model, wherein the first medical imaging data is provided as an input to the machine learning model, wherein the machine learning model outputs a plurality of binary classifications that includes a binary classification for each characteristic of the plurality of pulse sequence characteristics, and wherein the plurality of pulse sequence characteristics includes at least two of (i) whether fat suppression is present, (ii) an echo type of the MRI scan, (iii) whether fluid is bright, (iv) whether contrast is present, (v) whether chemical shift is present, (vi) whether cerebral spinal fluid (CFS) is bright, or (vii) whether grey matter is bright;
• updating a database to include the plurality of binary classifications in association with the first medical imaging data;
• generating a pulse sequence identifier for the first medical imaging data, at least in part by:
• determining, based on the plurality of binary classifications, whether other medical imaging data in the database has pulse sequence characteristics similar to the plurality of pulse sequence characteristics;
• and
• either:
• setting the pulse sequence identifier of the first medical imaging data to be a pulse sequence identifier of second medical imaging data in the database when determining, based on the plurality of binary classifications, that the second medical imaging data has pulse sequence characteristics similar to the plurality of pulse sequence characteristics;
• or
• generating a new pulse sequence identifier for use as the pulse sequence identifier of the first medical imaging data when determining, based on the plurality of binary classifications, that no other medical imaging data in the database has pulse sequence characteristics similar to the plurality of pulse sequence characteristics;
• and
• retrieving, responsive to a user request, and based on the plurality of pulse sequence characteristics, third medical imaging data from the database, the third medical imaging data including related MRI scans captured using pulse sequence characteristics similar to the plurality of pulse sequence characteristics.

One or more non-transitory computer readable media storing processor-executable instructions that, when executed by one or more processors, cause the one or more processors to perform operations comprising:

• receiving first medical imaging data associated with an MRI scan;
• determining a plurality of pulse sequence characteristics for the first medical imaging data using a machine learning model, wherein the first medical imaging data is provided as an input to the machine learning model, wherein the machine learning model outputs a plurality of binary classifications that includes a binary classification for each characteristic of the plurality of pulse sequence characteristics, and wherein the plurality of pulse sequence characteristics includes at least two of (i) whether fat suppression is present, (ii) an echo type of the MRI scan, (iii) whether fluid is bright, (iv) whether contrast is present, (v) whether chemical shift is present, (vi) whether cerebral spinal fluid (CFS) is bright, or (vii) whether grey matter is bright;
• updating a database to include the plurality of binary classifications in association with the first medical imaging data;
• generating a pulse sequence identifier for the first medical imaging data, at least in part by:
• determining, based on the plurality of binary classifications, whether other medical imaging data in the database has pulse sequence characteristics similar to the plurality of pulse sequence characteristics;
• and
• either:
• setting the pulse sequence identifier of the first medical imaging data to be a pulse sequence identifier of second medical imaging data in the database when determining, based on the plurality of binary classifications, that the second medical imaging data has pulse sequence characteristics similar to the plurality of pulse sequence characteristics;
• or
• generating a new pulse sequence identifier for use as the pulse sequence identifier of the first medical imaging data when determining, based on the plurality of binary classifications, that no other medical imaging data in the database has pulse sequence characteristics similar to the plurality of pulse sequence characteristics;
• and
• retrieving, responsive to a user request, and based on the plurality of pulse sequence characteristics, third medical imaging data from the database, the third medical imaging data including related MRI scans captured using pulse sequence characteristics similar to the plurality of pulse sequence characteristics.