Benchmarking Various Radiomic Toolkit Features While Applying the Image Biomarker Standardization Initiative toward Clinical Translation of Radiomic Analysis.

The image biomarkers standardization initiative (IBSI) was formed to address the standardization of extraction of quantifiable imaging metrics. Despite its effort, there remains a lack of consensus or established guidelines regarding radiomic feature terminology, the underlying mathematics and their implementation across various software programs. This creates a scenario where features extracted using different toolboxes cannot be used to build or validate the same model leading to a non-generalization of radiomic results. In this study, IBSI-established phantom and benchmark values were used to compare the variation of the radiomic features while using 6 publicly available software programs and 1 in-house radiomics pipeline. All IBSI-standardized features (11 classes, 173 in total) were extracted. The relative differences between the extracted feature values from the different software programs and the IBSI benchmark values were calculated to measure the inter-software agreement. To better understand the variations, features are further grouped into 3 categories according to their properties: 1) morphology, 2) statistic/histogram and 3)texture features. While a good agreement was observed for a majority of radiomics features across the various tested programs, relatively poor agreement was observed for morphology features. Significant differences were also found in programs that use different gray-level discretization approaches. Since these software programs do not include all IBSI features, the level of quantitative assessment for each category was analyzed using Venn and UpSet diagrams and quantified using two ad hoc metrics. Morphology features earned lowest scores for both metrics, indicating that morphological features are not consistently evaluated among software programs. We conclude that radiomic features calculated using different software programs may not be interchangeable. Further studies are needed to standardize the workflow of radiomic feature extraction.

Prostate Microstructure in Prostate Cancer Using 3-T MRI with Diffusion-Relaxation Correlation Spectrum Imaging: Validation with Whole-Mount Digital Histopathology.

Background Microstructural MRI has the potential to improve diagnosis and characterization of prostate cancer (PCa), but validation with histopathology is lacking. Purpose To validate ex vivo diffusion-relaxation correlation spectrum imaging (DR-CSI) in the characterization of microstructural tissue compartments in prostate specimens from men with PCa by using registered whole-mount digital histopathology (WMHP) as the reference standard. Materials and Methods Men with PCa who underwent 3-T MRI and robotic-assisted radical prostatectomy between June 2018 and January 2019 were prospectively studied. After prostatectomy, the fresh whole prostate specimens were imaged in patient-specific three-dimensionally printed molds by using 3-T MRI with DR-CSI and were then sliced to create coregistered WMHP slides. The DR-CSI spectral signal component fractions (fA, fB, fC) were compared with epithelial, stromal, and luminal area fractions (fepithelium, fstroma, flumen) quantified in PCa and benign tissue regions. A linear mixed-effects model assessed the correlations between (fA, fB, fC) and (fepithelium, fstroma, flumen), and the strength of correlations was evaluated by using Spearman correlation coefficients. Differences between PCa and benign tissues in terms of DR-CSI signal components and microscopic tissue compartments were assessed using two-sided t tests. Results Prostate specimens from nine men (mean age, 65 years ± 7 [standard deviation]) were evaluated; 20 regions from 17 PCas, along with 20 benign tissue regions of interest, were analyzed. Three DR-CSI spectral signal components (spectral peaks) were consistently identified. The fA, fB, and fC were correlated with fepithelium, fstroma, and flumen (all P < .001), with Spearman correlation coefficients of 0.74 (95% confidence interval [CI]: 0.62, 0.83), 0.80 (95% CI: 0.66, 0.89), and 0.67 (95% CI: 0.51, 0.81), respectively. PCa exhibited differences compared with benign tissues in terms of increased fA (PCa vs benign, 0.37 ± 0.05 vs 0.27 ± 0.06; P < .001), decreased fC (PCa vs benign, 0.18 ± 0.06 vs 0.31 ± 0.13; P = .01), increased fepithelium (PCa vs benign, 0.44 ± 0.13 vs 0.26 ± 0.16; P < .001), and decreased flumen (PCa vs benign, 0.14 ± 0.08 vs 0.27 ± 0.18; P = .004). Conclusion Diffusion-relaxation correlation spectrum imaging signal components correlate with microscopic tissue compartments in the prostate and differ between cancer and benign tissue. © RSNA, 2020 Online supplemental material is available for this article. See also the editorial by Lee and Hectors in this issue.

Efficacy of 3T Multiparametric MR Imaging followed by 3T in-Bore MR-Guided Biopsy for Detection of Clinically Significant Prostate Cancer Based on PIRADSv2.1 Score.

PURPOSE: To evaluate the diagnostic yield of 3T in-Bore magnetic resonance-guided biopsy (3T IB-MRGB) for detection of clinically significant prostate cancer (csPCa), based on assessment using the Prostate Imaging Reporting and Data System version 2.1 (PIRADSv2.1). MATERIALS AND METHODS: This single-center study examined individuals who underwent 3T multiparametric prostate magnetic resonance (MR) imaging and subsequent 3T IB-MRGB. The final study cohort included 379 men (with 475 targets) divided into 3 subcohorts: biopsy-naïve men (n = 123), individuals with a history of negative trans-rectal-ultrasonography (TRUS) biopsy results (n = 106), and men with low-grade PCa under active surveillance (n = 150). csPCa was defined as having a Gleason score (GS) ≥3+4. RESULTS: 3T IB-MRGB detected PCa and csPCa in 69.1% (262 of 379) and 50.3% (193 of 379) of patients, respectively. The PCa and csPCa detection rates per target were 64.2% (305 of 475) and 43.8% (208 of 475), respectively. The rate of urosepsis, treated with intravenous antibiotics, was 1% (4 patients). In TRUS biopsy negative results and biopsy-naïve subcohorts, csPCa was found in 36.8% (39 of 106) and 52.8% (65 of 123), respectively. In 50.7% (76 of 150) of the active surveillance subcohort, 3T IB-MRGB upgraded the GS assigned in prior TRUS biopsies. Positive predictive values of PIRADSv2.1 categories 3, 4, and 5 for csPCa detection were 24.8%, 44.4%, and 67.1%, respectively. Higher PIRADSv2.1 categories were significantly associated with PCa (odds ratio [OR], 3.97; 95% confidence interval [CI], 2.98-5.28) and csPCa (OR, 1.41; 95% CI, 1.03-1.94) detection. Of 137 PIRADSv2 category 3 lesions, 28 were downgraded to PIRADSv2.1 category 2, in which there were no occurrences of csPCa in histology. CONCLUSIONS: Use of 3T IB-MRGB resulted in detection of csPCa in 50.9% of individuals. 3T IB-MRGB has a high diagnostic yield in individuals with negative TRUS biopsy results and those under active surveillance. The PIRADSv2.1 category is a strong predictor of PCa and csPCa detection.

Radiomics quality score in renal masses: a systematic assessment on current literature.

OBJECTIVE: To perform a systematic assessment and analyze the quality of radiomics methodology in current literature in the evaluation of renal masses using the Radiomics Quality Score (RQS) approach. METHODS: We systematically reviewed recent radiomics literature in renal masses published in PubMed, EMBASE, Elsevier, and Web of Science. Two reviewers blinded by each other's scores evaluated the quality of radiomics methodology in studies published from 2015 to August 2021 using the RQS approach. Owing to the diversity in the imaging modalities and radiomics applications, a meta-analysis could not be performed. RESULTS: Based on our inclusion/exclusion criteria, a total of 87 published studies were included in our study. The highest RQS was noted in three categories: reporting of clinical utility, gold standard, and feature reduction. The average RQS of the two reviewers ranged from 5 ≤ RQS≤19, with the maximum attainable RQS being 36. Very few (7/87 i.e., 8%) studies received an average RQS that ranged from 17 < RQS≤19, which represents studies with the highest RQS in our study. Many (39/87 i.e., 45%) studies received an average RQS that ranged from 13 < RQS≤15. No significant interreviewer scoring differences were observed. CONCLUSIONS: We report that the overall scientific quality and reporting of radiomics studies in renal masses is suboptimal, and subsequent studies should bolster current deficiencies to improve reporting of radiomics methodologies. ADVANCES IN KNOWLEDGE: The RQS approach is a meaningful quantitative scoring system to assess radiomics methodology quality and supports a comprehensive evaluation of the radiomics approach before its incorporation into clinical practice.

Read-out Segmented Echo Planar Imaging with Two-Dimensional Navigator Correction (RESOLVE): An Alternative Sequence to Improve Image Quality on Diffusion-Weighted Imaging of Prostate.

OBJECTIVE: We aimed to investigate if the use of read-out segmented echoplanar imaging with additional two-dimensional navigator correction (Readout Segmentation of Long Variable Echo, RESOLVE) for acquiring prostate diffusion-weighted imaging (DWI) improves image quality, compared to single-shot echoplanar imaging (ss-EPI). METHODS: This single-center prospective study cohort included 162 males with suspected prostate cancer, who underwent 3 Tesla multiparametric MRI (3T-mpMRI). Two abdominal radiologists, blinded to the clinical information, separately reviewed each 3T-mpMRI study to rank geometrical distortion, degree of rectal distention, lesion conspicuity, and anatomic details delineation first on ss-EPI-DWI and later on RESOLVE-DWI using 5-point scales (1 = excellent, 5 = poor). The average of the ranking scores given by two readers was generated and used as the final score. RESULTS: There was good-to-excellent interreader agreement for scoring image quality parameters on both ss-EPI and RESOLVE. Geometrical distortion scores > 3 was seen in 12.3% (20/162) of ss-EPI images, with all having geometrical distortion score <3 on RESOLVE (p < .001). The mean image distortion score was significantly less on RESOLVE than ss-EPI (1.16 vs 1.61, p < .01 regardless of rectal gas, p< .05 when stratified by the degree of rectal distention ). RESOLVE was superior to ss-EPI for lesion conspicuity (mean 1.35 vs 1.53, p< .002) and anatomic delineation (2.60 vs 2.68, p< .001) of prostate on DWI. CONCLUSION: Compared to conventional ss-EPI, the use of RESOLVE for acquisition of prostate DWI resulted in significantly enhanced image quality and reduced geometrical distortion. ADVANCES IN KNOWLEDGE: RESOLVE could be an alternative or replacement of ss-EPI for acquiring prostate DWI with significantly less geometrical distortion and significantly improved lesion conspicuity and anatomic delineation.

Exploring Uncertainty Measures in Bayesian Deep Attentive Neural Networks for Prostate Zonal Segmentation.

Automatic segmentation of prostatic zones on multiparametric MRI (mpMRI) can improve the diagnostic workflow of prostate cancer. We designed a spatial attentive Bayesian deep learning network for the automatic segmentation of the peripheral zone (PZ) and transition zone (TZ) of the prostate with uncertainty estimation. The proposed method was evaluated by using internal and external independent testing datasets, and overall uncertainties of the proposed model were calculated at different prostate locations (apex, middle, and base). The study cohort included 351 MRI scans, of which 304 scans were retrieved from a de-identified publicly available datasets (PROSTATEX) and 47 scans were extracted from a large U.S. tertiary referral center (external testing dataset; ETD)). All the PZ and TZ contours were drawn by research fellows under the supervision of expert genitourinary radiologists. Within the PROSTATEX dataset, 259 and 45 patients (internal testing dataset; ITD) were used to develop and validate the model. Then, the model was tested independently using the ETD only. The segmentation performance was evaluated using the Dice Similarity Coefficient (DSC). For PZ and TZ segmentation, the proposed method achieved mean DSCs of 0.80±0.05 and 0.89±0.04 on ITD, as well as 0.79±0.06 and 0.87±0.07 on ETD. For both PZ and TZ, there was no significant difference between ITD and ETD for the proposed method. This DL-based method enabled the accuracy of the PZ and TZ segmentation, which outperformed the state-of-art methods (Deeplab V3+, Attention U-Net, R2U-Net, USE-Net and U-Net). We observed that segmentation uncertainty peaked at the junction between PZ, TZ and AFS. Also, the overall uncertainties were highly consistent with the actual model performance between PZ and TZ at three clinically relevant locations of the prostate.