Method, system, software and medium for advanced intelligent image analysis and display of medical images and information
Computerized interpretation of medical images for quantitative analysis of multi-modality breast images including analysis of FFDM, 2D/3D ultrasound, MRI, or other breast imaging methods. Real-time characterization of tumors and background tissue, and calculation of image-based biomarkers is provided for breast cancer detection, diagnosis, prognosis, risk assessment, and therapy response. Analysis includes lesion segmentation, and extraction of relevant characteristics (textural/morphological/kinetic features) from lesion-based or voxel-based analyses. Combinations of characteristics in several classification tasks using artificial intelligence is provided. Output in terms of 1D, 2D or 3D distributions in which an unknown case is identified relative to calculations on known or unlabeled cases, which can go through a dimension-reduction technique. Output to 3D shows relationships of the unknown case to a cloud of known or unlabeled cases, in which the cloud demonstrates the structure of the population of patients with and without the disease.
1. A non-transitory computer-readable medium storing thereon executable instructions, that when executed by a computer, cause the computer to execute a process for determining a probability of a disease state of a patient, the process comprising:
obtaining medical data including at least one of a medical image, medical image data, and data representative of a clinical examination of the patient, the medical data including data points for a lesion which are spatially and temporally indexed;
reducing the spatially and temporally indexed data points to remove the temporal indexing and to obtain a kinetic curve for each data point;
extracting kinetic features of the lesion from each kinetic curve; and
displaying the extracted kinetic features.
2. The non-transitory computer-readable medium according to claim 1 , wherein the displaying includes displaying the kinetic features as a color map.
3. The non-transitory computer-readable medium according to claim 2 , wherein the color map is a washout feature map, and the process further includes:
calculating, by a fractal dimension lesion descriptor, an information dimension and a correlation dimension for the color map.
4. The non-transitory computer-readable medium according to claim 3 , the process further comprising:
displaying the information dimension and the correlation dimension for the color map with other information dimensions and correlation dimensions of other labeled lesions using lesion-specific normalization.
5. The non-transitory computer-readable medium according to claim 4 , wherein the correlation dimensions are of fitted time to peak maps.
6. The non-transitory computer-readable medium according to claim 1 , wherein each data point is a voxel, and each voxel has one of the kinetic curves.
7. The non-transitory computer-readable medium according to claim 6 , wherein the extracting includes performing a texture analysis across the voxels, each representing a particular feature from each kinetic curve.
8. The non-transitory computer-readable medium according to claim 1 , the process further comprising:
extracting morphological features of the lesion from the data points;
calculating volumetrics of the lesion from the extracted morphological features; and
displaying the calculated volumetrics together with the extracted kinetic features.
9. The non-transitory computer-readable medium according to claim 8 , wherein:
the data points are voxels which are spatially indexed,
the calculating the volumetrics of the lesion includes segmenting the lesion by identifying the voxels which constitute the lesion, and calculating a volume of the lesion by using volumes of the identified voxels.
10. The non-transitory computer-readable medium according to claim 9 , wherein the calculating the volumetrics further includes calculating a surface area of the lesion using exterior surfaces of the identified voxels.
11. The non-transitory computer-readable medium according to claim 10 , wherein the calculating the volumetrics of the lesion includes utilizing only those voxels which have most enhancing kinetic curves.
12. The non-transitory computer-readable medium according to claim 8 , wherein:
the data points are voxels which are spatially indexed,
the calculating the volumetrics of the lesion includes segmenting the lesion by identifying the voxels which constitute the lesion, and calculating a volume of the lesion by summing volumes of the identified voxels.
13. The non-transitory computer-readable medium according to claim 12 , wherein the calculating the volumetrics further includes calculating a surface area of the lesion by summing exterior surfaces of the identified voxels.
14. The non-transitory computer-readable medium according to claim 1 , the process further comprising:
displaying, together with the extracted kinetic features, an image representing the obtained medical data.