The impact of pre-processing and disease characteristics on reproducibility of T2-weighted MRI radiomics features.

PURPOSE: To evaluate the reproducibility of radiomics features derived via different pre-processing settings from paired T2-weighted imaging (T2WI) prostate lesions acquired within a short interval, to select the setting that yields the highest number of reproducible features, and to evaluate the impact of disease characteristics (i.e., clinical variables) on features reproducibility. MATERIALS AND METHODS: A dataset of 50 patients imaged using T2WI at 2 consecutive examinations was used. The dataset was pre-processed using 48 different settings. A total of 107 radiomics features were extracted from manual delineations of 74 lesions. The inter-scan reproducibility of each feature was measured using the intra-class correlation coefficient (ICC), with ICC values > 0.75 considered good. Statistical differences were assessed using Mann-Whitney U and Kruskal-Wallis tests. RESULTS: The pre-processing parameters strongly influenced the reproducibility of radiomics features of T2WI prostate lesions. The setting that yielded the highest number of features (25 features) with high reproducibility was the relative discretization with a fixed bin number of 64, no signal intensity normalization, and outlier filtering by excluding outliers. Disease characteristics did not significantly impact the reproducibility of radiomics features. CONCLUSION: The reproducibility of T2WI radiomics features was significantly influenced by pre-processing parameters, but not by disease characteristics. The selected pre-processing setting yielded 25 reproducible features.

Pseudo-T2 mapping for normalization of T2-weighted prostate MRI.

OBJECTIVE: Signal intensity normalization is necessary to reduce heterogeneity in T2-weighted (T2W) magnetic resonance imaging (MRI) for quantitative analysis of multicenter data. AutoRef is an automated dual-reference tissue normalization method that normalizes transversal prostate T2W MRI by creating a pseudo-T2 map. The aim of this study was to evaluate the accuracy of pseudo-T2s and multicenter standardization performance for AutoRef with three pairs of reference tissues: fat/muscle (AutoRefF), femoral head/muscle (AutoRefFH) and pelvic bone/muscle (AutoRefPB). MATERIALS AND METHODS: T2s measured by multi-echo spin echo (MESE) were compared to AutoRef pseudo-T2s in the whole prostate (WP) and zones (PZ and TZ/CZ/AFS) for seven asymptomatic volunteers with a paired Wilcoxon signed-rank test. AutoRef normalization was assessed on T2W images from a multicenter evaluation set of 1186 prostate cancer patients. Performance was measured by inter-patient histogram intersections of voxel intensities in the WP before and after normalization in a selected subset of 80 cases. RESULTS: AutoRefFH pseudo-T2s best approached MESE T2s in the volunteer study, with no significant difference shown (WP: p = 0.30, TZ/CZ/AFS: p = 0.22, PZ: p = 0.69). All three AutoRef versions increased inter-patient histogram intersections in the multicenter dataset, with median histogram intersections of 0.505 (original data), 0.738 (AutoRefFH), 0.739 (AutoRefF) and 0.726 (AutoRefPB). DISCUSSION: All AutoRef versions reduced variation in the multicenter data. AutoRefFH pseudo-T2s were closest to experimentally measured T2s.

The Reproducibility of Deep Learning-Based Segmentation of the Prostate Gland and Zones on T2-Weighted MR Images.

Volume of interest segmentation is an essential step in computer-aided detection and diagnosis (CAD) systems. Deep learning (DL)-based methods provide good performance for prostate segmentation, but little is known about the reproducibility of these methods. In this work, an in-house collected dataset from 244 patients was used to investigate the intra-patient reproducibility of 14 shape features for DL-based segmentation methods of the whole prostate gland (WP), peripheral zone (PZ), and the remaining prostate zones (non-PZ) on T2-weighted (T2W) magnetic resonance (MR) images compared to manual segmentations. The DL-based segmentation was performed using three different convolutional neural networks (CNNs): V-Net, nnU-Net-2D, and nnU-Net-3D. The two-way random, single score intra-class correlation coefficient (ICC) was used to measure the inter-scan reproducibility of each feature for each CNN and the manual segmentation. We found that the reproducibility of the investigated methods is comparable to manual for all CNNs (14/14 features), except for V-Net in PZ (7/14 features). The ICC score for segmentation volume was found to be 0.888, 0.607, 0.819, and 0.903 in PZ; 0.988, 0.967, 0.986, and 0.983 in non-PZ; 0.982, 0.975, 0.973, and 0.984 in WP for manual, V-Net, nnU-Net-2D, and nnU-Net-3D, respectively. The results of this work show the feasibility of embedding DL-based segmentation in CAD systems, based on multiple T2W MR scans of the prostate, which is an important step towards the clinical implementation.

Exploring the diagnostic potential of adding T2 dependence in diffusion-weighted MR imaging of the prostate.

BACKGROUND: Magnetic resonance imaging (MRI) is essential in the detection and staging of prostate cancer. However, improved tools to distinguish between low-risk and high-risk cancer are needed in order to select the appropriate treatment. PURPOSE: To investigate the diagnostic potential of signal fractions estimated from a two-component model using combined T2- and diffusion-weighted imaging (T2-DWI). MATERIAL AND METHODS: 62 patients with prostate cancer and 14 patients with benign prostatic hyperplasia (BPH) underwent combined T2-DWI (TE = 55 and 73 ms, b-values = 50 and 700 s/mm2) following clinical suspicion of cancer, providing a set of 4 measurements per voxel. Cancer was confirmed in post-MRI biopsy, and regions of interest (ROIs) were delineated based on radiology reporting. Signal fractions of the slow component (SFslow) of the proposed two-component model were calculated from a model fit with 2 free parameters, and compared to conventional bi- and mono-exponential apparent diffusion coefficient (ADC) models. RESULTS: All three models showed a significant difference (p<0.0001) between peripheral zone (PZ) tumor and normal tissue ROIs, but not between non-PZ tumor and BPH ROIs. The area under the receiver operating characteristics curve distinguishing tumor from prostate voxels was 0.956, 0.949 and 0.949 for the two-component, bi-exponential and mono-exponential models, respectively. The corresponding Spearman correlation coefficients between tumor values and Gleason Grade Group were fair (0.370, 0.499 and -0.490), but not significant. CONCLUSION: Signal fraction estimates from a two-component model based on combined T2-DWI can differentiate between tumor and normal prostate tissue and show potential for prostate cancer diagnosis. The model performed similarly to conventional diffusion models.

A Quality Control System for Automated Prostate Segmentation on T2-Weighted MRI.

Computer-aided detection and diagnosis (CAD) systems have the potential to improve robustness and efficiency compared to traditional radiological reading of magnetic resonance imaging (MRI). Fully automated segmentation of the prostate is a crucial step of CAD for prostate cancer, but visual inspection is still required to detect poorly segmented cases. The aim of this work was therefore to establish a fully automated quality control (QC) system for prostate segmentation based on T2-weighted MRI. Four different deep learning-based segmentation methods were used to segment the prostate for 585 patients. First order, shape and textural radiomics features were extracted from the segmented prostate masks. A reference quality score (QS) was calculated for each automated segmentation in comparison to a manual segmentation. A least absolute shrinkage and selection operator (LASSO) was trained and optimized on a randomly assigned training dataset (N = 1756, 439 cases from each segmentation method) to build a generalizable linear regression model based on the radiomics features that best estimated the reference QS. Subsequently, the model was used to estimate the QSs for an independent testing dataset (N = 584, 146 cases from each segmentation method). The mean ± standard deviation absolute error between the estimated and reference QSs was 5.47 ± 6.33 on a scale from 0 to 100. In addition, we found a strong correlation between the estimated and reference QSs (rho = 0.70). In conclusion, we developed an automated QC system that may be helpful for evaluating the quality of automated prostate segmentations.

Simultaneous 18F-fluciclovine Positron Emission Tomography and Magnetic Resonance Spectroscopic Imaging of Prostate Cancer.

Purpose: To investigate the associations of metabolite levels derived from magnetic resonance spectroscopic imaging (MRSI) and 18F-fluciclovine positron emission tomography (PET) with prostate tissue characteristics. Methods: In a cohort of 19 high-risk prostate cancer patients that underwent simultaneous PET/MRI, we evaluated the diagnostic performance of MRSI and PET for discrimination of aggressive cancer lesions from healthy tissue and benign lesions. Data analysis comprised calculations of correlations of mean standardized uptake values (SUVmean), maximum SUV (SUVmax), and the MRSI-derived ratio of (total choline + spermine + creatine) to citrate (CSC/C). Whole-mount histopathology was used as gold standard. Results: The results showed a moderate significant correlation between both SUVmean and SUVmax with CSC/C ratio. Conclusions: We demonstrated that the simultaneous acquisition of 18F-fluciclovine PET and MRSI with an integrated PET/MRI system is feasible and a combination of these imaging modalities has potential to improve the diagnostic sensitivity and specificity of prostate cancer lesions.

Ex vivo metabolic fingerprinting identifies biomarkers predictive of prostate cancer recurrence following radical prostatectomy.

This corrects the article DOI: 10.1038/bjc.2017.346.

18F-Fluciclovine PET/MRI for preoperative lymph node staging in high-risk prostate cancer patients.

OBJECTIVE: To investigate the diagnostic potential of simultaneous 18F-fluciclovine PET/MRI for pelvic lymph node (LN) staging in patients with high-risk prostate cancer. METHODS: High-risk prostate cancer patients (n=28) underwent simultaneous 18F-fluciclovine PET/MRI prior to surgery. LNs were removed according to a predefined template of eight regions. PET and MR images were evaluated for presence of LN metastases according to these regions. Sensitivity/specificity for detection of LN metastases were calculated on patient and region basis. Sizes of LN metastases in regions with positive and negative imaging findings were compared with linear mixed models. Clinical parameters of PET-positive and -negative stage N1 patients were compared with the Mann-Whitney U test. RESULTS: Patient- and region-based sensitivity/specificity for detection of pelvic LN metastases was 40 %/87.5 % and 35 %/95.7 %, respectively, for MRI and 40 %/100 % and 30 %/100 %, respectively, for PET. LN metastases in true-positive regions were significantly larger than metastases in false-negative regions. PET-positive stage N1 patients had higher metastatic burden than PET-negative N1 patients. CONCLUSION: Simultaneous 18F-fluciclovine PET/MRI provides high specificity but low sensitivity for detection of LN metastases in high-risk prostate cancer patients. 18F-Fluciclovine PET/MRI scan positive for LN metastases indicates higher metastatic burden than negative scan. KEY POINTS: • 18F-Fluciclovine PET/MRI has high specificity for detection of lymph node metastasis. • 18F-Fluciclovine PET/MRI lacks sensitivity to replace ePLND. • 18F-Fluciclovine PET/MRI may be used to aid surgery and select adjuvant therapy. • 18F-Fluciclovine PET-positive patients have more extensive disease than PET-negative patients. • Size of metastatic lymph nodes is an important factor for detection.

Geometric distortion correction in prostate diffusion-weighted MRI and its effect on quantitative apparent diffusion coefficient analysis.

PURPOSE: To evaluate the effect of correction for B0 inhomogeneity-induced geometric distortion in echo-planar diffusion-weighted imaging on quantitative apparent diffusion coefficient (ADC) analysis in multiparametric prostate MRI. METHODS: Geometric distortion correction was performed in echo-planar diffusion-weighted images (b = 0, 50, 400, 800 s/mm2 ) of 28 patients, using two b0 scans with opposing phase-encoding polarities. Histology-matched tumor and healthy tissue volumes of interest delineated on T2 -weighted images were mapped to the nondistortion-corrected and distortion-corrected data sets by resampling with and without spatial coregistration. The ADC values were calculated on the volume and voxel level. The effect of distortion correction on ADC quantification and tissue classification was evaluated using linear-mixed models and logistic regression, respectively. RESULTS: Without coregistration, the absolute differences in tumor ADC (range: 0.0002-0.189 mm2 /s×10-3 (volume level); 0.014-0.493 mm2 /s×10-3 (voxel level)) between the nondistortion-corrected and distortion-corrected were significantly associated (P < 0.05) with distortion distance (mean: 1.4 ± 1.3 mm; range: 0.3-5.3 mm). No significant associations were found upon coregistration; however, in patients with high rectal gas residue, distortion correction resulted in improved spatial representation and significantly better classification of healthy versus tumor voxels (P < 0.05). CONCLUSIONS: Geometric distortion correction in DWI could improve quantitative ADC analysis in multiparametric prostate MRI. Magn Reson Med 79:2524-2532, 2018. © 2017 International Society for Magnetic Resonance in Medicine.

Combined 18F-Fluciclovine PET/MRI Shows Potential for Detection and Characterization of High-Risk Prostate Cancer.

The objective of this study was to investigate whether quantitative imaging features derived from combined 18F-fluciclovine PET/multiparametric MRI show potential for detection and characterization of primary prostate cancer. Methods: Twenty-eight patients diagnosed with high-risk prostate cancer underwent simultaneous 18F-fluciclovine PET/MRI before radical prostatectomy. Volumes of interest (VOIs) for prostate tumors, benign prostatic hyperplasia (BPH) nodules, prostatitis, and healthy tissue were delineated on T2-weighted images, using histology as a reference. Tumor VOIs were marked as high-grade (≥Gleason grade group 3) or not. MRI and PET features were extracted on the voxel and VOI levels. Partial least-squared discriminant analysis (PLS-DA) with double leave-one-patient-out cross-validation was performed to distinguish tumors from benign tissue (BPH, prostatitis, or healthy tissue) and high-grade tumors from other tissue (low-grade tumors or benign tissue). The performance levels of PET, MRI, and combined PET/MRI features were compared using the area under the receiver-operating-characteristic curve (AUC). Results: Voxel and VOI features were extracted from 40 tumor VOIs (26 high-grade), 36 BPH VOIs, 6 prostatitis VOIs, and 37 healthy-tissue VOIs. PET/MRI performed better than MRI and PET alone for distinguishing tumors from benign tissue (AUCs of 87%, 81%, and 83%, respectively, at the voxel level and 96%, 93%, and 93%, respectively, at the VOI level) and high-grade tumors from other tissue (AUCs of 85%, 79%, and 81%, respectively, at the voxel level and 93%, 93%, and 91%, respectively, at the VOI level). T2-weighted MRI, diffusion-weighted MRI, and PET features were the most important for classification. Conclusion: Combined 18F-fluciclovine PET/multiparametric MRI shows potential for improving detection and characterization of high-risk prostate cancer, in comparison to MRI and PET alone.

Ex vivo metabolic fingerprinting identifies biomarkers predictive of prostate cancer recurrence following radical prostatectomy.

BACKGROUND: Robust biomarkers that identify prostate cancer patients with high risk of recurrence will improve personalised cancer care. In this study, we investigated whether tissue metabolites detectable by high-resolution magic angle spinning magnetic resonance spectroscopy (HR-MAS MRS) were associated with recurrence following radical prostatectomy. METHODS: We performed a retrospective ex vivo study using HR-MAS MRS on tissue samples from 110 radical prostatectomy specimens obtained from three different Norwegian cohorts collected between 2002 and 2010. At the time of analysis, 50 patients had experienced prostate cancer recurrence. Associations between metabolites, clinicopathological variables, and recurrence-free survival were evaluated using Cox proportional hazards regression modelling, Kaplan-Meier survival analyses and concordance index (C-index). RESULTS: High intratumoural spermine and citrate concentrations were associated with longer recurrence-free survival, whereas high (total-choline+creatine)/spermine (tChoCre/Spm) and higher (total-choline+creatine)/citrate (tChoCre/Cit) ratios were associated with shorter time to recurrence. Spermine concentration and tChoCre/Spm were independently associated with recurrence in multivariate Cox proportional hazards modelling after adjusting for clinically relevant risk factors (C-index: 0.769; HR: 0.72; P=0.016 and C-index: 0.765; HR: 1.43; P=0.014, respectively). CONCLUSIONS: Spermine concentration and tChoCre/Spm ratio in prostatectomy specimens were independent prognostic markers of recurrence. These metabolites can be noninvasively measured in vivo and may thus offer predictive value to establish preoperative risk assessment nomograms.

SFRP4 gene expression is increased in aggressive prostate cancer.

Increased knowledge of the molecular differences between indolent and aggressive prostate cancer is needed for improved risk stratification and treatment selection. Secreted frizzled-related protein 4 (SFRP4) is a modulator of the cancer-associated Wnt pathway, and previously suggested as a potential marker for prostate cancer aggressiveness. In this study, we investigated and validated the association between SFRP4 gene expression and aggressiveness in nine independent cohorts (n = 2157). By differential expression and combined meta-analysis of all cohorts, we detected significantly higher SFRP4 expression in cancer compared with normal samples, and in high (3-5) compared with low (1-2) Grade Group samples. SFRP4 expression was a significant predictor of biochemical recurrence in six of seven cohorts and in the overall analysis, and was a significant predictor of metastatic event in one cohort. In our study cohort, where metabolic information was available, SFRP4 expression correlated significantly with the concentrations of citrate and spermine, two previously suggested biomarkers for aggressive prostate cancer. SFRP4 immunohistochemistry in an independent cohort (n = 33) was not associated with aggressiveness. To conclude, high SFRP4 gene expression is associated with high Grade Group and recurrent prostate cancer after surgery. Future studies investigating the mechanistic and clinical usefulness of SFRP4 in prostate cancer are warranted.

A novel non-canonical Wnt signature for prostate cancer aggressiveness.

Activation of the Canonical Wnt pathway (CWP) has been linked to advanced and metastatic prostate cancer, whereas the Wnt5a-induced non-canonical Wnt pathway (NCWP) has been associated with both good and poor prognosis. A newly discovered NCWP, Wnt5/Fzd2, has been shown to induce epithelial-to-mesenchymal transition (EMT) in cancers, but has not been investigated in prostate cancer. The aim of this study was to investigate if the CWP and NCWP, in combination with EMT, are associated with metabolic alterations, aggressive disease and biochemical recurrence in prostate cancer. An initial analysis was performed using integrated transcriptomics, ex vivo and in vivo metabolomics, and histopathology of prostatectomy samples (n=129), combined with at least five-year follow-up. This analysis detected increased activation of NCWP through Wnt5a/ Fzd2 as the most common mode of Wnt activation in prostate cancer. This activation was associated with increased expression of EMT markers and higher Gleason score. The transcriptional association between NCWP and EMT was confirmed in five other publicly available patient cohorts (1519 samples in total). A novel gene expression signature of concordant activation of NCWP and EMT (NCWP-EMT) was developed, and this signature was significantly associated with metastasis and shown to be a significant predictor of biochemical recurrence. The NCWP-EMT signature was also associated with decreased concentrations of the metabolites citrate and spermine, which have previously been linked to aggressive prostate cancer. Our results demonstrate the importance of NCWP and EMT in prostate cancer aggressiveness, suggest a novel gene signature for improved risk stratification, and give new molecular insight.

A PET/MRI study towards finding the optimal [18F]Fluciclovine PET protocol for detection and characterisation of primary prostate cancer.

PURPOSE: [18F]Fluciclovine PET imaging shows promise for the assessment of prostate cancer. The purpose of this PET/MRI study is to optimise the PET imaging protocol for detection and characterisation of primary prostate cancer, by quantitative evaluation of the dynamic uptake of [18F]Fluciclovine in cancerous and benign tissue. METHODS: Patients diagnosed with high-risk primary prostate cancer underwent an integrated [18F]Fluciclovine PET/MRI exam before robot-assisted radical prostatectomy with extended pelvic lymph node dissection. Volumes-of-interest (VOIs) of selected organs (prostate, bladder, blood pool) and sub-glandular prostate structures (tumour, benign prostatic hyperplasia (BPH), inflammation, healthy tissue) were delineated on T2-weighted MR images, using whole-mount histology samples as a reference. Three candidate windows for optimal PET imaging were identified based on the dynamic curves of the mean and maximum standardised uptake value (SUVmean and SUVmax, respectively). The statistical significance of differences in SUV between VOIs were analysed using Wilcoxon rank sum tests (p<0.05, adjusted for multiple testing). RESULTS: Twenty-eight (28) patients [median (range) age: 66 (55-72) years] were included. An early (W1: 5-10 minutes post-injection) and two late candidate windows (W2: 18-23; W3: 33-38 minutes post-injection) were selected. Late compared with early imaging was better able to distinguish between malignant and benign tissue [W3, SUVmean: tumour vs. BPH 2.5 vs. 2.0 (p<0.001), tumour vs. inflammation 2.5 vs. 1.7 (p<0.001), tumour vs. healthy tissue 2.5 vs. 2.0 (p<0.001); W1, SUVmean: tumour vs. BPH 3.1 vs. 3.1 (p=0.771), tumour vs inflammation 3.1 vs. 2.2 (p=0.021), tumour vs. healthy tissue 3.1 vs. 2.5 (p<0.001)] as well as between high-grade and low/intermediate-grade tumours (W3, SUVmean: 2.6 vs. 2.1 (p=0.040); W1, SUVmean: 3.1 vs. 2.8 (p=0.173)). These differences were relevant to the peripheral zone, but not the central gland. CONCLUSION: Late-window [18F]Fluciclovine PET imaging shows promise for distinguishing between prostate tumours and benign tissue and for assessment of tumour aggressiveness.

Presence of TMPRSS2-ERG is associated with alterations of the metabolic profile in human prostate cancer.

TMPRSS2-ERG has been proposed to be a prognostic marker for prostate cancer. The aim of this study was to identify changes in metabolism, genes and biochemical recurrence related to TMPRSS2-ERG by using an integrated approach, combining metabolomics, transcriptomics, histopathology and clinical data in a cohort of 129 human prostate samples (41 patients). Metabolic analyses revealed lower concentrations of citrate and spermine comparing ERGhigh to ERGlow samples, suggesting an increased cancer aggressiveness of ERGhigh compared to ERGlow. These results could be validated in a separate cohort, consisting of 40 samples (40 patients), and magnetic resonance spectroscopy imaging (MRSI) indicated an in vivo translational potential. Alterations of gene expression levels associated with key enzymes in the metabolism of citrate and polyamines were in consistence with the metabolic results. Furthermore, the metabolic alterations between ERGhigh and ERGlow were more pronounced in low Gleason samples than in high Gleason samples, suggesting it as a potential tool for risk stratification. However, no significant difference in biochemical recurrence was detected, although a trend towards significance was detected for low Gleason samples. Using an integrated approach, this study suggests TMPRSS2-ERG as a potential risk stratification tool for inclusion of active surveillance patients.