Advanced Imaging Analysis in Prostate MRI: Building a Radiomic Signature to Predict Tumor Aggressiveness

Abstract

Radiomics allows the extraction quantitative features from imaging, as imaging biomarkers of disease. The objective of this exploratory study is to implement a reproducible radiomic-pipeline for the extraction of a magnetic resonance imaging (MRI) signature for prostate cancer (PCa) aggressiveness. One hundred and two consecutive patients performing preoperative prostate multiparametric magnetic resonance imaging (mpMRI) and radical prostatectomy were enrolled. Multiparametric images, including T2-weighted (T2w), diffusion-weighted and dynamic contrast-enhanced images, were acquired at 1.5 T. Ninety-three imaging features (Ifs) were extracted from segmentation of index lesion. Ifs were ranked based on a stability rank and redundant Ifs were excluded. Using unsupervised hierarchical clustering, patients were grouped on the basis of similar radiomic patterns, whose association with Gleason Grade Group (GGG), extracapsular extension (ECE), and nodal involvement (pN) was tested. Signatures composed by IFs from T2w-images and Apparent Diffusion Coefficient (ADC) maps were tested for the prediction of GGG, ECE, and pN. T2w radiomic pattern was associated with pN, ECE, and GGG (p = 0.027, 0.05, 0.03) and ADC radiomic pattern was associated with GGG (p = 0.004). The best performance was reached by the signature combing IFs from multiparametric images (0.88, 0.89, and 0.84 accuracy for GGG, pN, and ECE). A reliable multiparametric MRI radiomic signature was extracted, potentially able to predict PCa aggressiveness, to be further validated on an independent sample.

Radiomics for Identification and Prediction in Metastatic Prostate Cancer: A Review of Studies

“…Damascelli et al. ( 93 ) developed a radiomics model for the prediction of LNI on 62 patient mpMRI scans, where features were extracted from T2w images and apparent diffusion coefficient (ADC) maps. Each patient, who had biopsy proven PCa and underwent RP, had their intraprostatic index lesions segmented on each modality by two independent radiologists.…”

“…Radiomics features extracted from each of these modalities will thus characterise the heterogeneity of the tumour in different and potentially complementary ways, which could improve model performance. There is evidence that utilising this approach in mPCa radiomics modelling can yield good results, both in the traditional radiomics methodology ( 93 , 95 , 98 ) and deep radiomics ( 99 ). Particularly in the field of deep radiomics, where the analysis of dual modalities can often be as simple as incorporating an additional channel in the network architecture, this method of analysis should be thoroughly explored.…”

More than Meets the Eye: Using Textural Analysis and Artificial Intelligence as Decision Support Tools in Prostate Cancer Diagnosis—A Systematic Review

“…Regarding the evidence provided by the selected papers, some limitations can be addressed. Firstly, although the total number of subjects respected the chosen inclusion criteria, when divided into testing and training cohorts, 9 studies allocated under 50 cases for testing their developed model, thus raising the question of accuracy of the reported results [ 10 , 13 , 14 , 15 , 20 , 25 , 26 , 27 , 29 ]. In terms of cohorts’ composition, 2 studies designed the training group on a multicentric structure, using different MRI machines or mixing in-house cases with publicly available ones [ 22 , 23 ], while other studies trained, tested and validated the algorithm on patients selected from the same center [ 10 , 30 ].…”

“…However, the number of cases included in the selected papers might be insufficient and the desired variability will not be properly represented by a significant number of cases for decision support tools development. Second, studies focusing on aggressiveness prediction encounter limitations in terms of differentiating each Gleason score, mostly classifying each lesion as below or above a Gleason score of 7 [ 14 , 18 , 27 , 29 , 33 ]. The authors attributed this limitation to the insufficient number of cases required for a subdivision of patients based on Gleason score.…”

Secreted miR-153 Controls Proliferation and Invasion of Higher Gleason Score Prostate Cancer

“…Despite this, in more than 50% of cases, GS obtained by prostate biopsy specimens does not represent the true GS of the tumor, due to both biological cancer heterogeneity and sampling errors [ 3 ]. Recent works were dedicated to explore advanced image processing methodologies, such as radiomics, to predict tumor aggressiveness from advanced quantification of MRI images (e.g., [ 4 ]). Even if the results suggested that reliable radiomic signatures can be evaluated for prediction of PC aggressiveness in terms of Gleason score, extracapsular extension, and nodal stage, the published radiomic approaches have to be standardized and validated in large patient cohorts.…”