US 2021/0174937 A1 · MACHINE LEARNING ON RAW MEDICAL IMAGING DATA FOR CLINICAL DECISION SUPPORT

Abstract

Various embodiments of the present disclosure are directed to a raw diagnostic machine for a medical diagnosis of raw medical imaging data generated by a medical imaging machine as opposed to a medical diagnosis of a medical image conventionally reconstructed from the raw medical imaging data. In operation, the raw diagnostic engine includes a medical imaging diagnostic controller implementing a dimension reduction pre-processor for selecting or extracting one or more dimension reduced feature vectors from the raw medical imaging data, and further implementing a raw diagnostic artificial intelligence engine for rendering a diagnostic assessment of the raw medical imaging data as represented by the dimension reduced feature vector(s). The medical imaging diagnostic controller may further control a communication of the diagnostic assessment of the raw medical imaging data (e.g., a display, a printing, an emailing, a texting, etc.).

Claims21

Dependent claims

A medical imaging diagnostic system, comprising:

a medical imaging machine for generating raw medical imaging data for a medical image reconstruction engine configured to generate a reconstructed medical image from the raw medical imaging data;
and
a raw diagnostic machine for a medical diagnosis of the raw medical imaging data generated by the medical imaging machine, the raw diagnostic machine including a medical imaging diagnostic controller configured to:
input the raw medical imaging data into a dimension reduction pre-processor—trained to select or extract at least one dimension reduced feature vector from the raw medical imaging data;
input the at least one dimension reduced feature vector into a raw diagnostic artificial intelligence engine trained to render a diagnostic assessment of the raw medical imaging data;
and
control a communication of the diagnostic assessment of the raw medical imaging data.

4 more elements

A non-transitory machine-readable storage medium encoded with instructions for execution by at least one processor for processing raw medical imaging data generated by a medical imaging machine, the raw medical imaging data being arranged for a medical image reconstruction engine configured to generate a reconstructed medical image from the raw medical imaging data, the non-transitory machine-readable storage medium comprising instructions to:

input the raw medical imaging data into a dimension reduction pre-processor—trained to select or extract at least one dimension reduced feature vector from the raw medical imaging data;
and
input the at least one dimension reduced feature vector into a raw diagnostic artificial intelligence engine trained to render a diagnostic assessment of the raw medical imaging data.

A medical imaging diagnostic method for a medical diagnosis by a medical imaging diagnostic controller of raw medical imaging data generated by a medical imaging machine, the raw medical imaging data being arranged for a medical image reconstruction engine configured to generate a reconstructed medical image from the raw medical imaging data, the method comprising:

inputting, by the medical imaging diagnostic controller, the raw medical imaging data into a dimension reduction pre-processor trained to select or extract at least one dimension reduced feature vector from the raw medical imaging data;
and
inputting, by the medical imaging diagnostic controller, the dimension reduced feature vector into a raw diagnostic artificial intelligence engine to render a diagnostic assessment of the raw medical imaging data.

Dependencies are inferred from the claim text.

Machine learning on raw medical imaging data for clinical decision support

Life of this patent

Machine learning on raw medical imaging data for clinical decision support

Life of this patent

Abstract

Claims21