Prostate cancer radiomics and the promise of radiogenomics

Abstract

Prostate cancer exhibits intra-tumoral heterogeneity that we hypothesize to be the leading confounding factor contributing to the underperformance of the current pre-treatment clinicalpathological and genomic assessment. These limitations impose an urgent need to develop better computational tools to identify men with low risk of prostate cancer versus others that may be at risk for developing metastatic cancer. The patient stratification will directly translate to patient treatments, wherein decisions regarding active surveillance or intensified therapy are made. Multiparametric MRI (mpMRI) provides the platform to investigate tumor heterogeneity by mapping the individual tumor habitats. We hypothesize that quantitative assessment (radiomics) of these habitats results in distinct combinations of descriptors that reveal regions with different physiologies and phenotypes. Radiogenomics, a discipline connecting tumor morphology described by radiomic and its genome described by the genomic data, has the potential to derive "radio phenotypes" that both correlate to and complement existing validated genomic risk stratification biomarkers. In this article we first describe the radiomic pipeline, tailored for analysis of prostate mpMRI, and in the process we introduce our particular implementations of radiomics modules. We also summarize the efforts in the radiomics field related to prostate cancer diagnosis and assessment of aggressiveness. Finally, we describe our results from radiogenomic analysis, based on mpMRI-Ultrasound (MRI-US) biopsies and discuss the potential of future applications of this technique. The mpMRI radiomics data indicate that the platform would significantly improve the biopsy targeting of prostate habitats through better recognition of indolent versus aggressive disease, thereby facilitating a more personalized approach to prostate cancer management. The expectation to non-invasively identify habitats with high probability of housing Author Manuscript aggressive cancers would result in directed biopsies that are more informative and actionable. Conversely, providing evidence for lack of disease would reduce the incidence of non-informative biopsies. In radiotherapy of prostate cancer, dose escalation has been shown to reduce biochemical failure. Dose escalation only to determinate prostate habitats has the potential to improve tumor control with less toxicity than when the entire prostate is dose escalated. HHS Public Access

Machine and deep learning methods for radiomics

“…The radiomics approach of combining the extraction of radiomic features with machine learning, can be used either to detect/diagnose cancer or to automatically contour the tumor lesion. Methods for radiomics‐driven automatic prostate tumor detection typically use a supervised method trained on a set of features calculated from multimodality images . For detection of prostate cancer, features were computed in a 3 × 3 pixels sliding window in multimodal MRI of prostate.…”

Repeatability of radiomics and machine learning for DWI: Short‐term repeatability study of 112 patients with prostate cancer

“…Adoption of these methods in routine clinical practice has been limited by concerns related to poor repeatability and reproducibility because of different degree of noise in the imaging data sets obtained from different imaging sessions . An increasing number of research groups are applying radiomics for prostate cancer (PCa) imaging …”

“…9 An increasing number of research groups are applying radiomics for prostate cancer (PCa) imaging. [10][11][12][13][14][15][16][17][18] Prostate cancer is the most common solid cancer among men in the western world. 19 Development of methods for accurate patient-tailored diagnostic process and treatment planning could have a major impact on improved PCa detection, characterization, and treatment planning, ultimately leading to improved outcomes of men with suspected or diagnosed PCa.…”

Efficient data management infrastructure for the integration of imaging and omics data in life science research

“…Here, we propose a solution based on principles of Service Oriented Architecture (SOA) design (Josuttis 2007) , to integrate an interoperable image management system to accommodate data from microscopy and medical imaging studies in qPortal and thereby facilitate the integrated analysis of imaging and omics data, which is an increasingly deployed strategy in biology and medical studies (Stoyanova et al 2016;Disselhorst et al 2018;Hériché et al 2019) . Given the limited imaging support offered by OpenBIS, we suggest using an OMERO server as a backend component, which is required to work in conjunction with the OpenBIS server that conventionally builds the backbone for qPortal compatible setups.…”