Autonomous Tumor Signature Extraction Applied to Spatially Registered Bi-Parametric MRI to Predict Prostate Tumor Aggressiveness: A Pilot Study.

Simple Summary: The proper management of prostate cancer requires accurate assessment of patients diagnosed with prostate cancer, a common and often lethal cancer. Current conventional prostate cancer diagnosis relies on: (1) needle biopsy, which can result in side effects such as hemorrhage or infection, as well as misplacement of needles resulting in evaluation inaccuracy, (2) prostate serum antigen detection that can lead to overdiagnosis, or (3) MRI interpretations using the Prostate Imaging-Reporting and Data System (PI-RADS), which is a subjective method that depends on the experience of the radiologist's interpretation of the images. Quantitative analysis of MRI can alleviate the limitations of conventional approaches. Artificial intelligence applied to MRI requires big training datasets, and its application is restricted to patients scanned under certain restricted conditions. More recently, spectral/statistical techniques, adapted from remote sensing, have been applied and tested in spatially registered multi-parametric MRI. The new spectral/statistical techniques require limited training, are flexible regarding patient scanning conditions, and perform well relative to other techniques. This study extends spectral/statistical techniques to make them more independent of the individual radiologist by autonomously finding the appropriate tumor signature within a prostate and, therefore, providing an objective, non-invasive, accurate means for determining prostate tumor aggressiveness. Background: Accurate, reliable, non-invasive assessment of patients diagnosed with prostate cancer is essential for proper disease management. Quantitative assessment of multi-parametric MRI, such as through artificial intelligence or spectral/statistical approaches, can provide a non-invasive objective determination of the prostate tumor aggressiveness without side effects or potential poor sampling from needle biopsy or overdiagnosis from prostate serum antigen measurements. To simplify and expedite prostate tumor evaluation, this study examined the efficacy of autonomously extracting tumor spectral signatures for spectral/statistical algorithms for spatially registered bi-parametric MRI. Methods: Spatially registered hypercubes were digitally constructed by resizing, translating, and cropping from the image sequences (Apparent Diffusion Coefficient (ADC), High B-value, T2) from 42 consecutive patients in the bi-parametric MRI PI-CAI dataset. Prostate cancer blobs exceeded a threshold applied to the registered set from normalizing the registered set into an image that maximizes High B-value, but minimizes the ADC and T2 images, appearing "green" in the color composite. Clinically significant blobs were selected based on size, average normalized green value, sliding window statistics within a blob, and position within the hypercube. The center of mass and maximized sliding window statistics within the blobs identified voxels associated with tumor signatures. We used correlation coefficients (R) and p-values, to evaluate the linear regression fits of the z-score and SCR (with processed covariance matrix) to tumor aggressiveness, as well as Area Under the Curves (AUC) for Receiver Operator Curves (ROC) from logistic probability fits to clinically significant prostate cancer. Results: The highest R (R > 0.45), AUC (>0.90), and lowest p-values (<0.01) were achieved using z-score and modified registration applied to the covariance matrix and tumor signatures selected from the "greenest" parts from the selected blob. Conclusions: The first autonomous tumor signature applied to spatially registered bi-parametric MRI shows promise for determining prostate tumor aggressiveness. [ABSTRACT FROM AUTHOR]