Deep Radiomic Analysis to Predict Gleason Score in Prostate Cancer

Abstract

Convolutional neural networks (CNNs) require large amounts of data for training, beyond what can be acquired for current radiomics models. We hypothesize that deep entropy features (DEFs) derived from existing CNNs can be applied to MRI images of prostate cancers (PCa) to reliably predict the Gleason score (GS) of PCa lesions. In this study, we analyzed 112 lesions acquired from 99 PCa patients, either pre-biopsy or pre-treatment, their associated GS, and multi-parametric MRI (mpMRI) sequences. Our approach is based on the extraction of DEF features produced in individual layers of 9 pre-trained CNN models. We first analyze DEFs from separate CNNs using the Wilcoxon test and Spearman correlation to find significant features associated with GS. In a multivariate analysis, we then use the combined DEFs of all CNNs as input to a random forest (RF) classifier for predicting the Gleason grade group of patients. Among the 9 pre-trained CNNs, the NASNet-mobile architecture offered the features most correlated to GS (ρ=0.47; p<0.05). From the 7,857 combined features, 11 DEFs could differentiate GS < 8 from GS ≥ 8 (corrected p < 0.05). Moreover, the RF classifier discerned GS of 6, 3+4, 4+3, 8 and ≥ 9 with an AUC (%) of 80.08, 85.77, 97.30, 98.20, and 86.51, respectively. Our results suggest that the DEFs can be used to differentiate GS of PCa lesions with the highest accuracy of GS ≥ 8 based on mpMRI. DEFs could improve diagnosis accuracy, reduce the risks of misclassification, help to better assess prognosis, and individualize patient care approaches.

Magnetic Resonance Imaging Based Radiomic Models of Prostate Cancer: A Narrative Review

“…MRI radiomics have demonstrated the potential to discern the PCa grade [ 23 , 24 , 86 , 87 , 88 ] or guide management approaches [ 45 , 89 ] from the abundance of clinical data acquired at each scan. However, reproducibility is a significant issue at different stages of the radiomics pipeline, with few studies investigating this question [ 41 , 78 ].…”

“…The ability to generate a multitude of features increases the likelihood of discovering imaging characteristics representative of the GS. This pipeline model was expanded by Chaddad et al, adapting multiple 2D CNN models to generate deep texture features in prostatic mpMRIs, generating a robust model for predicting the GS [ 88 ].…”

“…An approach to circumvent this limitation has been proposed to construct CNNs pretrained in other settings and then apply them to the clinical setting of interest [ 118 , 129 , 130 , 131 , 132 ]. In PCa specifically, Chaddad et al used this approach to predict the GS with robust outcomes albeit with a smaller publicly available data set [ 88 ]. The established CNNs were trained on brain MRI data and used to generate multiscale texture of PCa images.…”

“…Table 2 reports on the recently published works utilizing mpMRI to predict the GS. The inclusion of more classifying options by Jesen et al [ 133 ] and Chaddad et al [ 88 ] may be associated with the seemingly greater area under the ROC curve (AUC) values, implying some value to this approach. Common to many studies, frequent radiomic features used in GS predictions were based on texture (e.g., histogram, GLCM, NGTDM, and GLSZM), shape/morphological (e.g., volume and surface), and clinical markers (e.g., age and treatment modality).…”

“…Given the present state-of-the-art, such a study is unlikely to suggest that radiomic models are ready for clinical implementation to be positive. To advance the radiomics field, the study would need to discover novel radiomic features that remain stable between serial assessments—a feasible outcome given the success of CNNs in this role [ 88 ]. If sufficient stable features were identified, this would lead organically to a multicenter validation study that could demonstrate intra- and interpatient radiomic feature stability.…”