Systems and methods for integrated magnetic resonance imaging and magnetic resonance fingerprinting radiomics analysis
Automated processing and radiomic analysis of magnetic resonance imaging (“MRI”), such as multi-contrast MR images, and magnetic resonance fingerprinting (“MRF”) data, such as quantitative parameter maps, are integrated into a single workflow.
1 . A method for generating radiomic feature data from magnetic resonance images and magnetic resonance fingerprinting maps, the method comprising:
(a) accessing with a computer system, magnetic resonance imaging (MRI) data acquired from a subject with an MRI system;
(b) accessing with the computer system, magnetic resonance fingerprinting (MRF) data acquired from the subject, wherein the MRF data comprise quantitative parameter maps;
(c) preprocessing the MRI data and the MRF data with the computer system;
(d) performing an integrated radiomic analysis on the preprocessed MRI data and the preprocessed MRF data with the computer system to generate output as radiomic feature data, wherein the integrated radiomic analysis extracts radiomic features from coregistered MRI and MRF data within regions-of-interest, where the radiomic features comprise at least shape features, first-order statistical features, and second-order statistical features computed from the quantitative parameter maps of the MRF data; and
(e) generating a report based on the radiomic feature data using the computer system.
2 . The method of claim 1 , wherein preprocessing the MRI data and the MRF data comprises:
denoising and bias correcting the MRI data, generating output as denoised MRI data;
segmenting the denoised MRI data and the MRF data, generating output as segmented MRI data and segmented MRF data;
coregistering the segmented MRI data and the segmented MRF data.
3 . The method of claim 2 , wherein the segmented MRI data are coregistered with the segmented MRF data using one of the quantitative parameter maps contained in the segmented MRF data as a reference.
4 . The method of claim 3 , wherein the reference comprises a longitudinal relaxation time (T1) map.
5 . The method of claim 2 , wherein the MRI data comprise multi-contrast MRI data including magnetic resonance images having different contrast weightings.
6 . The method of claim 5 , wherein one of the different contrast weightings comprises T2-weighted images.
7 . The method of claim 6 , wherein segmenting the denoised MRI data comprises affinely registering the denoised MRI data to one of the T2-weighted images.
8 . The method of claim 1 , wherein the radiomic feature data comprise at least one of shape data, first-order statistical feature data, or second-order statistical feature data.
9 . The method of claim 8 , wherein the shape data comprise at least one of volume or surface area of regions-of-interest in the MRI data and the MRF data.
10 . The method of claim 8 , wherein the first-order statistical feature data comprise at least one of mean or variance of image values within regions-of-interest in the MRI data and the MRF data.
11 . The method of claim 8 , wherein the second-order statistical feature data comprise at least one of gray-level co-occurrence matrix-based features, gray-level run length matrix-based features, gray-level size zone matrix-based features, neighborhood gray tone difference matrix-based features, or gray level dependence matrix-based features computed for image values within one or more regions-of-interest in the MRI data and the MRF data.
12 . The method of claim 1 , wherein generating the report comprises computing statistical features of the radiomic feature data and displaying the statistical features to a user using the computer system.
13 . The method of claim 1 , wherein preprocessing the MRI data and the MRF data comprises coregistering the MRI data and the MRF data.
14 . The method of claim 13 , wherein the MRI data and the MRF data are coregistered based on an affine transformation.
15 . The method of claim 13 , wherein the MRI data comprise T2-weighted images and images with other contrast weightings, wherein the images with other contrast weightings are coregistered to the T2-weighted images.
16 . The method of claim 15 , wherein the MRF data are coregistered to the MRI data using an affine registration using a maximization of normalized mutual information (NMI).
17 . The method of claim 16 , wherein the MRF data comprise longitudinal relaxation time (T1) maps and other quantitative parameter maps, wherein the MRF data are coregistered with the MRI data using the T1 maps as a reference for the affine registration using the maximization of NMI.