Image guidance refers to the use of imaging information to better guide surgical and treatment procedures. Our research spans co-registration of multiple modalities for more targeted biopsies, automated segmentation of structures of interest, as well as focal treatment procedures.
Automated magnetic resonance imaging (MRI) - transrectal ultrasound (TRUS) registration: Left shows a 2D axial plane of MRI (upper left, lower right) and TRUS (upper right, lower left) registered into a common coordinate frame. Prostate delineation for MRI (red) and TRUS (green) are also provided. Right image illustrates a 3D rendering of surface errors between prostate on MRI and TRUS post-registration where the color corresponds to the distance in misalignment between MRI and TRUS prostate surface. Red arrows highlight regions of error near the rectal wall (lower arrow) and near the bladder (upper arrow). Error between corresponding landmarks on MRI and TRUS was 3.39±0.85 mm
Automated segmentation of prostate capsule and prostatic zonal anatomy: Prostate depicted in yellow, CG in red, and PZ in purple, for two different prostate MRI studies. Our automated algorithm can simultaneously segment multiple objects, and makes use of multiple levelsets, rather than anatomical landmarks, to define the shapes. The scheme yielded mean Dice accuracy values of .81, .79 and .68 for the prostate, CG, and PZ, respectively using a leave-one-out cross validation scheme over 40 endorectal, T2-weighted MRI patient studies.
Quantitative Evaluation of Treatment Related Changes on Multi-Parametric MRI after Laser Interstitial Thermal Therapy of Prostate Cancer: This is the first attempt at examining focal treatment-related changes on a per-voxel basis (high resolution) via quantitative evaluation of MR parameters pre- and post-LITT. Preliminary quantitative comparison of the changes in different MR parameters indicated that T2w texture may be highly sensitive as well as specific in identifying changes within the ablation zone pre- and post-LITT. Visual evaluation of the differences in T2w texture features pre- and post-LITT also appeared to provide an indication of LITT-related effects such as edema. Quantitatively combining the ADC and T2w MRI parameters enabled construction of an integrated MP-MRI difference map that was highly indicative of changes specific to the LITT ablation zone.
Quantitative evaluation of multi-parametric MR imaging marker changes post-laser interstitial ablation therapy (LITT) for epilepsy: In this work, we introduce supervised multi-view canonical correlation analysis (sMVCCA), a novel data fusion method that attempts to find a common representation for multiscale, multimodal data where class separation is maximized while noise is minimized. Although this method can be applied to any number of modalities, we demonstrate its application in the context of integrating upto four data streams to predict prostate cancer (CaP) aggressiveness pre- and post- radical prostatectomy (RP) using two datasets. Kaplan-Meier curves generated based on classifier prediction in the sMVCCA joint subspace showed significant (p < 0.05) differences for patients with and without BcR, unlike those generated from classifier prediction in the feature spaces of individual modalities.