Reference standard for the evaluation of automatic segmentation algorithms: Quantification of inter observer variability of manual delineation of prostate contour on MRI.

PURPOSE: The purpose of this study was to investigate the relationship between inter-reader variability in manual prostate contour segmentation on magnetic resonance imaging (MRI) examinations and determine the optimal number of readers required to establish a reliable reference standard. MATERIALS AND METHODS: Seven radiologists with various experiences independently performed manual segmentation of the prostate contour (whole-gland [WG] and transition zone [TZ]) on 40 prostate MRI examinations obtained in 40 patients. Inter-reader variability in prostate contour delineations was estimated using standard metrics (Dice similarity coefficient [DSC], Hausdorff distance and volume-based metrics). The impact of the number of readers (from two to seven) on segmentation variability was assessed using pairwise metrics (consistency) and metrics with respect to a reference segmentation (conformity), obtained either with majority voting or simultaneous truth and performance level estimation (STAPLE) algorithm. RESULTS: The average segmentation DSC for two readers in pairwise comparison was 0.919 for WG and 0.876 for TZ. Variability decreased with the number of readers: the interquartile ranges of the DSC were 0.076 (WG) / 0.021 (TZ) for configurations with two readers, 0.005 (WG) / 0.012 (TZ) for configurations with three readers, and 0.002 (WG) / 0.0037 (TZ) for configurations with six readers. The interquartile range decreased slightly faster between two and three readers than between three and six readers. When using consensus methods, variability often reached its minimum with three readers (with STAPLE, DSC = 0.96 [range: 0.945-0.971] for WG and DSC = 0.94 [range: 0.912-0.957] for TZ, and interquartile range was minimal for configurations with three readers. CONCLUSION: The number of readers affects the inter-reader variability, in terms of inter-reader consistency and conformity to a reference. Variability is minimal for three readers, or three readers represent a tipping point in the variability evolution, with both pairwise-based metrics or metrics with respect to a reference. Accordingly, three readers may represent an optimal number to determine references for artificial intelligence applications.

Clinical performance of magnetic resonance imaging and biomarkers for prostate cancer diagnosis in men at high genetic risk.

OBJECTIVES: To evaluate different scenarios for the management of early diagnosis of cancer (PCa) in men at high genetic risk, using recently developed blood and urinary molecular biomarkers in combination with clinical information alongside multiparametric magnetic resonance imaging (mpMRI). PATIENTS AND METHODS: A total of 322 patients with a high genetic risk (familial or personal history of cancers or a predisposing germline variant) were included in this study. The primary outcome was the detection rates of PCa (positive biopsy) or clinically significant PCa (biopsy with International Society of Urological Pathology [ISUP] grade >1). Clinical parameters included age, body mass index, ancestry, and germline mutational status, mpMRI, prostate-specific antigen density (PSAD), Prostate Health Index and urinary markers (Prostate Cancer Associated 3, SelectMdx™ and T2:ERG score) were assessed. Sensitivity (Se) and specificity (Sp) for each marker at their recommended cut-off for clinical practice were calculated. Comparison between diagnoses accuracy of each procedure and scenario was computed using mutual information based and direct effect contribution using a supervised Bayesian network approach. RESULTS: A mpMRI Prostate Imaging-Reporting and Data System (PI-RADS) score ≥3 showed higher Se than mpMRI PI-RADS score ≥4 for detection of PCa (82% vs 61%) and for the detection of ISUP grade >1 lesions (96% vs 80%). mpMRI PI-RADS score ≥3 performed better than a PSA level of ≥3 ng/mL (Se 96%, Sp 53% vs Se 91%, Sp 8%) for detection of clinically significant PCa. In case of negative mpMRI results, the supervised Bayesian network approach showed that urinary markers (with the same accuracy for all) and PSAD of ≥0.10 ng/mL/mL were the most useful indicators of decision to biopsy. CONCLUSIONS: We found that screening men at high genetic risk of PCa must be based on mpMRI without pre-screening based on a PSA level of >3 ng/mL, to avoid missing too many ISUP grade >1 tumours and to significantly reduce the number of unnecessary biopsies. However, urinary markers or a PSAD of ≥0.10 ng/mL/mL when mpMRI was negative increased the detection of ISUP grade >1 cancers. We suggest that a baseline mpMRI be discussed for men at high genetic risk from the age of 40 years.

Automatic segmentation of prostate zonal anatomy on MRI: a systematic review of the literature.

OBJECTIVES: Accurate zonal segmentation of prostate boundaries on MRI is a critical prerequisite for automated prostate cancer detection based on PI-RADS. Many articles have been published describing deep learning methods offering great promise for fast and accurate segmentation of prostate zonal anatomy. The objective of this review was to provide a detailed analysis and comparison of applicability and efficiency of the published methods for automatic segmentation of prostate zonal anatomy by systematically reviewing the current literature. METHODS: A Preferred Reporting Items for Systematic Reviews and Meta-Analysis (PRISMA) was conducted until June 30, 2021, using PubMed, ScienceDirect, Web of Science and EMBase databases. Risk of bias and applicability based on Quality Assessment of Diagnostic Accuracy Studies 2 (QUADAS-2) criteria adjusted with Checklist for Artificial Intelligence in Medical Imaging (CLAIM) were assessed. RESULTS: A total of 458 articles were identified, and 33 were included and reviewed. Only 2 articles had a low risk of bias for all four QUADAS-2 domains. In the remaining, insufficient details about database constitution and segmentation protocol provided sources of bias (inclusion criteria, MRI acquisition, ground truth). Eighteen different types of terminology for prostate zone segmentation were found, while 4 anatomic zones are described on MRI. Only 2 authors used a blinded reading, and 4 assessed inter-observer variability. CONCLUSIONS: Our review identified numerous methodological flaws and underlined biases precluding us from performing quantitative analysis for this review. This implies low robustness and low applicability in clinical practice of the evaluated methods. Actually, there is not yet consensus on quality criteria for database constitution and zonal segmentation methodology.

Diagnosis of early biochemical recurrence after radical prostatectomy or radiation therapy in patients with prostate cancer: State of the art.

Biochemical recurrence after primary treatment in prostate cancer is not uncommon. A rising serum prostate-specific antigen level represents a first sign of disease relapse. At this time of low disease burden, imaging and particularly magnetic resonance imaging and positron emission tomography/computed tomography (PET/CT) are essential to determine the localization of the recurrence, which may be local, in lymph nodes, and/or metastatic. Imaging results allow best determine modalities of salvage treatment, which can be local by using radiotherapy or other focal treatments or systemic using hormonotherapy. Current evidence suggests that multiparametric magnetic resonance imaging, PET/CT with prostate specific membrane antigen and lympho-magnetic resonance imaging are effective and complementary to detect local recurrences and distant metastases.

Targeting Local Recurrence After Surgery With MRI Imaging for Prostate Cancer in the Setting of Salvage Radiation Therapy.

Magnetic resonance imaging (MRI) is being increasingly used for imaging suspected recurrence in prostate cancer therapy. Functional MRI with diffusion and perfusion imaging has the potential to demonstrate local recurrence even at low PSA value. Detection of recurrence can modify the management of postprostatectomy biochemical recurrence. MRI scan acquired before salvage radiotherapy is useful for the localization of recurrent tumors and also in the delineation of the target volume. The objective of this review is to assess the role and potential impact of MRI in targeting local recurrence after surgery for prostate cancer in the setting of salvage radiation therapy.

Robust Bayesian fusion of continuous segmentation maps.

The fusion of probability maps is required when trying to analyse a collection of image labels or probability maps produced by several segmentation algorithms or human raters. The challenge is to weight the combination of maps correctly, in order to reflect the agreement among raters, the presence of outliers and the spatial uncertainty in the consensus. In this paper, we address several shortcomings of prior work in continuous label fusion. We introduce a novel approach to jointly estimate a reliable consensus map and to assess the presence of outliers and the confidence in each rater. Our robust approach is based on heavy-tailed distributions allowing local estimates of raters performances. In particular, we investigate the Laplace, the Student's t and the generalized double Pareto distributions, and compare them with respect to the classical Gaussian likelihood used in prior works. We unify these distributions into a common tractable inference scheme based on variational calculus and scale mixture representations. Moreover, the introduction of bias and spatial priors leads to proper rater bias estimates and control over the smoothness of the consensus map. Finally, we propose an approach that clusters raters based on variational boosting, and thus may produce several alternative consensus maps. Our approach was successfully tested on MR prostate delineations and on lung nodule segmentations from the LIDC-IDRI dataset.

Automatic zonal segmentation of the prostate from 2D and 3D T2-weighted MRI and evaluation for clinical use.

Purpose: An accurate zonal segmentation of the prostate is required for prostate cancer (PCa) management with MRI. Approach: The aim of this work is to present UFNet, a deep learning-based method for automatic zonal segmentation of the prostate from T2-weighted (T2w) MRI. It takes into account the image anisotropy, includes both spatial and channelwise attention mechanisms and uses loss functions to enforce prostate partition. The method was applied on a private multicentric three-dimensional T2w MRI dataset and on the public two-dimensional T2w MRI dataset ProstateX. To assess the model performance, the structures segmented by the algorithm on the private dataset were compared with those obtained by seven radiologists of various experience levels. Results: On the private dataset, we obtained a Dice score (DSC) of 93.90 ± 2.85 for the whole gland (WG), 91.00 ± 4.34 for the transition zone (TZ), and 79.08 ± 7.08 for the peripheral zone (PZ). Results were significantly better than other compared networks' ( p - value < 0.05 ). On ProstateX, we obtained a DSC of 90.90 ± 2.94 for WG, 86.84 ± 4.33 for TZ, and 78.40 ± 7.31 for PZ. These results are similar to state-of-the art results and, on the private dataset, are coherent with those obtained by radiologists. Zonal locations and sectorial positions of lesions annotated by radiologists were also preserved. Conclusions: Deep learning-based methods can provide an accurate zonal segmentation of the prostate leading to a consistent zonal location and sectorial position of lesions, and therefore can be used as a helping tool for PCa diagnosis.

Regulatory Flexibilities and Guidances for Addressing the Challenges of COVID-19 in the EU: What Can We Learn from Company Experiences?

The COVID-19 pandemic required urgency in the development and delivery of effective vaccines and therapeutics; meanwhile, ongoing clinical research, regulation and supply for other much-needed therapeutics and vaccines needed to be sustained. In Europe, the European Commission, the European Medicines Agency (EMA) and the national regulatory agencies (NRAs) responded by issuing guidance outlining regulatory flexibilities mainly directed at COVID-19 vaccines and, belatedly, therapeutics. Using a survey methodology, this study gathered the views of the R&D based pharmaceutical industry in May-June 2021 on the value of these flexibilities for continued use in the post-pandemic era as well as for future use in health emergency situations. Findings indicate that many flexibilities were foreseen to have value beyond the pandemic, particularly where EU and Member States aligned closely to provide a singular, streamlined regulatory environment. Digitalization was a notable driver of these flexibilities, but innovations in regulatory process (e.g. rolling reviews, flexible Scientific Advice) improved the process and outcomes measurably. Finally, the rapid reaction of the EU regulatory system and extensive efforts by all involved in providing innovative therapeutics and vaccines to patients in need provides learnings for the upcoming overhaul of the pharmaceutical acquis.

Prostate volume prediction on MRI: tools, accuracy and variability.

OBJECTIVE: A reliable estimation of prostate volume (PV) is essential to prostate cancer management. The objective of our multi-rater study was to compare intra- and inter-rater variability of PV from manual planimetry and ellipsoid formulas. METHODS: Forty treatment-naive patients who underwent prostate MRI were selected from a local database. PV and corresponding PSA density (PSAd) were estimated on 3D T2-weighted MRI (3 T) by 7 independent radiologists using the traditional ellipsoid formula (TEF), the newer biproximate ellipsoid formula (BPEF), and the manual planimetry method (MPM) used as ground truth. Intra- and inter-rater variability was calculated using the mixed model-based intraclass correlation coefficient (ICC). RESULTS: Mean volumes were 67.00 (± 36.61), 66.07 (± 35.03), and 64.77 (± 38.27) cm3 with the TEF, BPEF, and MPM methods, respectively. Both TEF and BPEF overestimated PV relative to MPM, with the former presenting significant differences (+ 1.91 cm3, IQ = [- 0.33 cm3, 5.07 cm3], p val = 0.03). Both intra- (ICC > 0.90) and inter-rater (ICC > 0.90) reproducibility were excellent. MPM had the highest inter-rater reproducibility (ICC = 0.999). Inter-rater PV variation led to discrepancies in classification according to the clinical criterion of PSAd > 0.15 ng/mL for 2 patients (5%), 7 patients (17.5%), and 9 patients (22.5%) when using MPM, TEF, and BPEF, respectively. CONCLUSION: PV measurements using ellipsoid formulas and MPM are highly reproducible. MPM is a robust method for PV assessment and PSAd calculation, with the lowest variability. TEF showed a high degree of concordance with MPM but a slight overestimation of PV. Precise anatomic landmarks as defined with the BPEF led to a more accurate PV estimation, but also to a higher variability. KEY POINTS: • Manual planimetry used for prostate volume estimation is robust and reproducible, with the lowest variability between readers. • Ellipsoid formulas are accurate and reproducible but with higher variability between readers. • The traditional ellipsoid formula tends to overestimate prostate volume.

Zonal anatomy of the prostate using magnetic resonance imaging, morphometrics, and radiomic features: impact of age-related changes.

OBJECTIVE: To evaluate the impact of age on the zonal anatomy of the prostate by MRI using morphometric and textural analysis. METHODS: A total of 154 men (mean age: 63 years) who underwent MRI due to a high prostate-specific antigen (PSA) level were included retrospectively. At each MRI examination the following variables were measured: overall dimensions of the prostate (whole gland (WG), transitional zone (TZ), and peripheral zone (PZ)), and thickness of the anterior fibromuscular stroma (AFMS) and the periprostatic venous plexus (PPVP) on T2 weighted images. Identical regions of interest (ROIs) were delineated on the apparent diffusion coefficient (ADC) map on the anterior (horn) and posterior part of the PZ. Textural (TexRAD®) parameter differences between TZ and PZ ROIs on T2 weighted images were analyzed by linear regression. Results were correlated with age (distributed into five decades from 22 to 89 years). RESULTS: Age was positively correlated with PSA level and glandular volumes (WG, TZ, and TZ/WG ratio; p < 0.0001) and was negatively correlated with AFSM and PPVP thickness (p < 0.0001). There was a positive correlation between ADC values of the PZ and age (p = 0.003) and between entropy of the TZ and PZ and age (p < 0.001). CONCLUSION: Gradual variations in morphologic and textural features of the prostate were observed with age, mainly due to the increase in TZ volume while PZ volume tended to decrease. These modifications resulted in textural changes mainly at the expense of entropy. ADVANCES IN KNOWLEDGE: Entropy could be relevant for studying the process of aging of the prostate.

Challenge of prostate MRI segmentation on T2-weighted images: inter-observer variability and impact of prostate morphology.

BACKGROUND: Accurate prostate zonal segmentation on magnetic resonance images (MRI) is a critical prerequisite for automated prostate cancer detection. We aimed to assess the variability of manual prostate zonal segmentation by radiologists on T2-weighted (T2W) images, and to study factors that may influence it. METHODS: Seven radiologists of varying levels of experience segmented the whole prostate gland (WG) and the transition zone (TZ) on 40 axial T2W prostate MRI images (3D T2W images for all patients, and both 3D and 2D images for a subgroup of 12 patients). Segmentation variabilities were evaluated based on: anatomical and morphological variation of the prostate (volume, retro-urethral lobe, intensity contrast between zones, presence of a PI-RADS ≥ 3 lesion), variation in image acquisition (3D vs 2D T2W images), and reader's experience. Several metrics including Dice Score (DSC) and Hausdorff Distance were used to evaluate differences, with both a pairwise and a consensus (STAPLE reference) comparison. RESULTS: DSC was 0.92 (± 0.02) and 0.94 (± 0.03) for WG, 0.88 (± 0.05) and 0.91 (± 0.05) for TZ respectively with pairwise comparison and consensus reference. Variability was significantly (p < 0.05) lower for the mid-gland (DSC 0.95 (± 0.02)), higher for the apex (0.90 (± 0.06)) and the base (0.87 (± 0.06)), and higher for smaller prostates (p < 0.001) and when contrast between zones was low (p < 0.05). Impact of the other studied factors was non-significant. CONCLUSIONS: Variability is higher in the extreme parts of the gland, is influenced by changes in prostate morphology (volume, zone intensity ratio), and is relatively unaffected by the radiologist's level of expertise.

Prostate cancer local staging using biparametric MRI: assessment and comparison with multiparametric MRI.

PURPOSE: The value of adding dynamic contrast-enhanced (DCE) imaging to T2-weighted (T2W) magnetic resonance imaging (MRI) and diffusion-weighted imaging (DWI) to improve the detection and staging of prostate cancer (PCa) is unclear. The aim of this retrospective study was to compare the diagnostic performance of non-contrast biparametric MRI (bpMRI) with multiparametric MRI (mpMRI), for local staging of PCa. METHODS: Ninety-two patients who underwent prostate MRI on a 3-Tesla MRI system before radical prostatectomy for PCa were included retrospectively. Four readers independently assigned a Likert score (ranging from 1 to 5) for predicting extra-prostatic extension (EPE) on T2W + DWI (bpMRI) and then on T2W + DWI + DCE imaging (mpMRI). MRI-based staging results were compared with radical prostatectomy histology. A prediction of EPE generalized linear mixed model was used to assess the added-value of DCE and discriminative power of staging accuracy by area under the receiver-operating curve (AUC ROC). RESULTS: AUC was not significantly improved by DCE (mpMRI, AUC = 0.73 [95%CI: 0.655‒0.827] vs. bpMRI, AUC = 0.76 [95%CI: 0.681‒0.846]). After applying a selection procedure, only MRI criteria were retained in a multivariate model. The following criteria were significantly associated with local extension: localization in the peripheral zone (p < 0.001), maximal diameter of the lesion (<0.0001), curvilinear capsular contact on T2W (p < 0.0001), capsular irregularity on T2W (p < 0.0001), bulging on T2W (p < 0.001) and seminal vesicle hypo-signal (p < 0.001). CONCLUSION: Use of bpMRI did not result in a decrease in local staging accuracy.

MRI for prostate cancer: can computed high b-value DWI replace native acquisitions?

OBJECTIVE: To compare computed high b-value diffusion-weighted images (c-DWI) derived from low b-value DWI images and acquired high b-value DWI (a-DWI), in overall image quality and prostate cancer detection rate. MATERIALS AND METHODS: A total of 124 consecutive men with suspected prostate cancer (PCa) underwent diagnosis prostate MRI on a 3.0 T MR system using a 32-channel phased-array torso coil. Among them, 63 underwent prostate biopsy. MRI protocol included 3DT2w images, high resolution Fov Optimized and Constrained Undistorted Single-Shot (FOCUS™) DWI images with b-values of 100, 400, 800, and 2000 s/mm2 and dynamic contrast enhanced images. C-DWI images (2000 and 2500 s/mm2) were derived from the three lower acquired b-value DWI images using a mono-exponential diffusion decay. C-DWI and acquired high b-value DWI (a-DWI) (2000 s/mm2) were compared for image quality (background signal suppression, anatomic clarity, ghosting, distortion) and tumor conspicuity by four radiologists. RESULTS: C-DWIs demonstrated higher rating than a-DWIs for overall image quality despite worsened ghosting. In patients with a biopsy, similar detection rate was observed while conspicuity was better with c-DWI (p < 0.001). Non-acquisition of high b-value a-DWI reduced total acquisition time by 220 s per patient. CONCLUSION: C-DWI provides a substantial reduction in acquisition time while maintaining comparable prostate cancer detection rate and improving global image quality. KEY POINTS: • Computed DWI improves global quality of prostate MRI. • Computed DWI improves analysis of DWI images with decrease acquisition time. • Computed DWI provides greater background suppression of parenchyma and improves conspicuity of suspicious lesion.