Create spatially registered, mosaicked multiparametric (T1, T2, Dynamic Contrast Enhanced, Diffusion) MRI of prostate cancer patients.
Identify and generate seven component prostate tumor and Gleason score signatures or image-based biomarkers.
Insert transformed (“whitening-dewhitening”) and untransformed signatures into supervised target detection algorithms and create target detection maps.
Apply, describe, and test a novel application of supervised target detection algorithms to spatially registered multiparametric MR images in order to non-invasively detect, locate, and score prostate cancer at the voxel level (6 mm3).
The Gleason scoring and volume measurements were quantitatively validated by comparing the results from 10 patients to the pathologist’s assessment of the histology and performed well (p<0.02).
Assigning red, green, and blue colors to the registered hypercubes effectively highlight tumors relative to normal prostate.
This technique may assist those interpreting prostate cancer MRI and help manage patients.
Advanced Algorithm and Image-Based Biomarkers for Cancer Detection, Scoring and Tumor Volume Measurements and Color Display