Can we predict pathology without surgery? Weighing the added value of multiparametric MRI and whole prostate radiomics in integrative machine learning models.

OBJECTIVE: To test the ability of high-performance machine learning (ML) models employing clinical, radiological, and radiomic variables to improve non-invasive prediction of the pathological status of prostate cancer (PCa) in a large, single-institution cohort. METHODS: Patients who underwent multiparametric MRI and prostatectomy in our institution in 2015-2018 were considered; a total of 949 patients were included. Gradient-boosted decision tree models were separately trained using clinical features alone and in combination with radiological reporting and/or prostate radiomic features to predict pathological T, pathological N, ISUP score, and their change from preclinical assessment. Model behavior was analyzed in terms of performance, feature importance, Shapley additive explanation (SHAP) values, and mean absolute error (MAE). The best model was compared against a naïve model mimicking clinical workflow. RESULTS: The model including all variables was the best performing (AUC values ranging from 0.73 to 0.96 for the six endpoints). Radiomic features brought a small yet measurable boost in performance, with the SHAP values indicating that their contribution can be critical to successful prediction of endpoints for individual patients. MAEs were lower for low-risk patients, suggesting that the models find them easier to classify. The best model outperformed (p ≤ 0.0001) clinical baseline, resulting in significantly fewer false negative predictions and overall was less prone to under-staging. CONCLUSIONS: Our results highlight the potential benefit of integrative ML models for pathological status prediction in PCa. Additional studies regarding clinical integration of such models can provide valuable information for personalizing therapy offering a tool to improve non-invasive prediction of pathological status. CLINICAL RELEVANCE STATEMENT: The best machine learning model was less prone to under-staging of the disease. The improved accuracy of our pathological prediction models could constitute an asset to the clinical workflow by providing clinicians with accurate pathological predictions prior to treatment. KEY POINTS: • Currently, the most common strategies for pre-surgical stratification of prostate cancer (PCa) patients have shown to have suboptimal performances. • The addition of radiological features to the clinical features gave a considerable boost in model performance. Our best model outperforms the naïve model, avoiding under-staging and resulting in a critical advantage in the clinic. •Machine learning models incorporating clinical, radiological, and radiomics features significantly improved accuracy of pathological prediction in prostate cancer, possibly constituting an asset to the clinical workflow.

Patient satisfaction with ultrasound, whole-body CT and whole-body diffusion-weighted MRI for pre-operative ovarian cancer staging: a multicenter prospective cross-sectional survey.

BACKGROUND: In addition to the diagnostic accuracy of imaging methods, patient-reported satisfaction with imaging methods is important. OBJECTIVE: To report a secondary outcome of the prospective international multicenter Imaging Study in Advanced ovArian Cancer (ISAAC Study), detailing patients' experience with abdomino-pelvic ultrasound, whole-body contrast-enhanced computed tomography (CT), and whole-body diffusion-weighted magnetic resonance imaging (WB-DWI/MRI) for pre-operative ovarian cancer work-up. METHODS: In total, 144 patients with suspected ovarian cancer at four institutions in two countries (Italy, Czech Republic) underwent ultrasound, CT, and WB-DWI/MRI for pre-operative work-up between January 2020 and November 2022. After having undergone all three examinations, the patients filled in a questionnaire evaluating their overall experience and experience in five domains: preparation before the examination, duration of examination, noise during the procedure, radiation load of CT, and surrounding space. Pain perception, examination-related patient-perceived unexpected, unpleasant, or dangerous events ('adverse events'), and preferred method were also noted. RESULTS: Ultrasound was the preferred method by 49% (70/144) of responders, followed by CT (38%, 55/144), and WB-DWI/MRI (13%, 19/144) (p<0.001). The poorest experience in all domains was reported for WB-DWI/MRI, which was also associated with the largest number of patients who reported adverse events (eg, dyspnea). Patients reported higher levels of pain during the ultrasound examination than during CT and WB-DWI/MRI (p<0.001): 78% (112/144) reported no pain or mild pain, 19% (27/144) moderate pain, and 3% (5/144) reported severe pain (pain score >7 of 10) during the ultrasound examination. We did not identify any factors related to patients' preferred method. CONCLUSION: Ultrasound was the imaging method preferred by most patients despite being associated with more pain during the examination in comparison with CT and WB-DWI/MRI. TRIAL REGISTRATION NUMBER: NCT03808792.

Comparison of automated segmentation techniques for magnetic resonance images of the prostate.

BACKGROUND: Contouring of anatomical regions is a crucial step in the medical workflow and is both time-consuming and prone to intra- and inter-observer variability. This study compares different strategies for automatic segmentation of the prostate in T2-weighted MRIs. METHODS: This study included 100 patients diagnosed with prostate adenocarcinoma who had undergone multi-parametric MRI and prostatectomy. From the T2-weighted MR images, ground truth segmentation masks were established by consensus from two expert radiologists. The prostate was then automatically contoured with six different methods: (1) a multi-atlas algorithm, (2) a proprietary algorithm in the Syngo.Via medical imaging software, and four deep learning models: (3) a V-net trained from scratch, (4) a pre-trained 2D U-net, (5) a GAN extension of the 2D U-net, and (6) a segmentation-adapted EfficientDet architecture. The resulting segmentations were compared and scored against the ground truth masks with one 70/30 and one 50/50 train/test data split. We also analyzed the association between segmentation performance and clinical variables. RESULTS: The best performing method was the adapted EfficientDet (model 6), achieving a mean Dice coefficient of 0.914, a mean absolute volume difference of 5.9%, a mean surface distance (MSD) of 1.93 pixels, and a mean 95th percentile Hausdorff distance of 3.77 pixels. The deep learning models were less prone to serious errors (0.854 minimum Dice and 4.02 maximum MSD), and no significant relationship was found between segmentation performance and clinical variables. CONCLUSIONS: Deep learning-based segmentation techniques can consistently achieve Dice coefficients of 0.9 or above with as few as 50 training patients, regardless of architectural archetype. The atlas-based and Syngo.via methods found in commercial clinical software performed significantly worse (0.855[Formula: see text]0.887 Dice).

Psychological characteristics and satisfaction for the whole-body MRI in cancer screening.

Whole-body magnetic resonance imaging (WB-MRI) is an all-in-one non-invasive technique that can be used also in early cancer diagnosis in asymptomatic individuals. The aim of this work was to identify the personal characteristics predicting the satisfaction for the WB-MRI in a sample of healthy subjects. Before undergoing a WB-MRI examination, 154 participants completed a questionnaire covering sociodemographics (age, gender, education), personality traits (agreeableness, conscientiousness, emotional stability, extroversion, openness), and expectations about the procedure (expected usefulness, risks, noise, lack of air, duration). After the examination, participants reported their satisfaction with the WB-MRI. Results showed that agreeableness had a significant and positive effect on satisfaction. Expectations about its utility and the possible noise had a positive effect on satisfaction. Expectations of lack of air showed a negative significant effect on satisfaction. Sociodemographics showed no significant effects. Our study confirmed the important impact of individuals' personality and expectations on satisfaction with the procedure. Moreover, it provides useful insights for developing consultations aimed at increasing the acceptability of the procedure.

Repeat MRI during active surveillance: natural history of prostatic lesions and upgrading rates.

OBJECTIVES: To assess upgrading rates in patients on active surveillance (AS) for prostate cancer (PCa) after serial multiparametric magnetic resonance imaging (mpMRI). METHODS: We conducted a retrospective analysis of 558 patients. Five different criteria for mpMRI progression were used: 1) a Prostate Imaging Reporting and Data System (PI-RADS) score increase; 2) a lesion size increase; 3) an extraprostatic extension score increase; 4) overall mpMRI progression; and 5) the number of criteria met for mpMRI progression (0 vs 1 vs 2-3). In addition, two definitions of PCa upgrading were evaluated: 1) International Society of Urological Pathology Grade Group (ISUP GG) ≥2 with >10% of pattern 4 and 2) ISUP GG ≥ 3. Estimated annual percent changes methodology was used to show the temporal trends of mpMRI progression criteria. The sensitivity, specificity, positive predictive value (PPV) and negative predictive value (NPV) of mpMRI progression criteria were also analysed. Multivariable logistic regression models tested PCa upgrading rates. RESULTS: Lower rates over time for all mpMRI progression criteria were observed. The NPV of serial mpMRI scans ranged from 90.5% to 93.5% (ISUP GG≥2 with >10% of pattern 4 PCa upgrading) and from 98% to 99% (ISUP GG≥3 PCa upgrading), depending on the criteria used for mpMRI progression. A prostate-specific antigen density (PSAD) threshold of 0.15 ng/mL/mL was used to substratify those patients who would be able to skip a prostate biopsy. In multivariable logistic regression models assessing PCa upgrading rates, all five mpMRI progression criteria achieved independent predictor status. CONCLUSION: During AS, approximately 27% of patients experience mpMRI progression at first repeat MRI. However, the rates of mpMRI progression decrease over time at subsequent mpMRI scans. Patients with stable mpMRI findings and with PSAD < 0.15 ng/mL/mL could safely skip surveillance biopsies. Conversely, patients who experience mpMRI progression should undergo a prostate biopsy.

Correlation between radiological and biological features and clinical outcomes in early prostate cancer: an exploratory subgroup analysis.

PTEN deletion and Ki-67 expression are two of the most promising biomarkers in prostate cancer (PCa). In the same manner, multiparametric magnetic resonance imaging (mp-MRI) guided core biopsy is a powerful tool for PCa detection and staging. The aim of the study is to assess whether a correlation can be identified between the pathological stage defined by an mp-MRI-guided core biopsy and Ki-67 expression and PTEN deletion. Such correlation might be useful for staging and treatment personalization in PCa. This investigation was conducted in the context of phase II clinical study "Short-term radiotherapy for early prostate cancer with a concomitant boost to the dominant lesion" (AIRC IG-13218), ClinicalTrials.gov identifier: NCT01913717. Nineteen patients underwent a further in-bore MRI-targeted core biopsy (MRI-TBx) on the dominant intraprostatic lesion (DIL); on this basis, an additional Gleason Score (GS) was determined. PTEN loss and Ki-67 expression on these samples were analyzed and correlated with both risk categories modifications and oncological outcomes (overall survival, biochemical and clinical relapse). GS was upgraded in 5 cases, with 4 patients re-classified as intermediate-risk and 1 patient as high-risk. The latter experienced a clinical local relapse. No correlations between up/down-staging, PTEN deletion, and Ki-67 expression were observed in this cohort. Further investigations are needed towards the identification of a pattern in the tumor aggressiveness-response in PCa treated with ultra-hypofractionated radiotherapy. Moreover, a possible relationship between biomarker analysis and imaging textural features could be explored.

MRI-based radiomics signature for localized prostate cancer: a new clinical tool for cancer aggressiveness prediction? Sub-study of prospective phase II trial on ultra-hypofractionated radiotherapy (AIRC IG-13218).

OBJECTIVES: Radiomic involves testing the associations of a large number of quantitative imaging features with clinical characteristics. Our aim was to extract a radiomic signature from axial T2-weighted (T2-W) magnetic resonance imaging (MRI) of the whole prostate able to predict oncological and radiological scores in prostate cancer (PCa). METHODS: This study included 65 patients with localized PCa treated with radiotherapy (RT) between 2014 and 2018. For each patient, the T2-W MRI images were normalized with the histogram intensity scale standardization method. Features were extracted with the IBEX software. The association of each radiomic feature with risk class, T-stage, Gleason score (GS), extracapsular extension (ECE) score, and Prostate Imaging Reporting and Data System (PI-RADS v2) score was assessed by univariate and multivariate analysis. RESULTS: Forty-nine out of 65 patients were eligible. Among the 1702 features extracted, 3 to 6 features with the highest predictive power were selected for each outcome. This analysis showed that texture features were the most predictive for GS, PI-RADS v2 score, and risk class; intensity features were highly associated with T-stage, ECE score, and risk class, with areas under the receiver operating characteristic curve (ROC AUC) ranging from 0.74 to 0.94. CONCLUSIONS: MRI-based radiomics is a promising tool for prediction of PCa characteristics. Although a significant association was found between the selected features and all the mentioned clinical/radiological scores, further validations on larger cohorts are needed before these findings can be applied in the clinical practice. KEY POINTS: • A radiomic model was used to classify PCa aggressiveness. • Radiomic analysis was performed on T2-W magnetic resonance images of the whole prostate gland. • The most predictive features belong to the texture (57%) and intensity (43%) domains.

Whole-body magnetic resonance imaging (WB-MRI) for cancer screening: recommendations for use.

Whole-body magnetic resonance imaging (WB-MRI) is currently recommended for cancer screening in adult and paediatric subjects with cancer predisposition syndromes, representing a substantial aid for prolonging health and survival of these subjects with a high oncological risk. Additionally, the number of studies exploring the use of WB-MRI for cancer screening in asymptomatic subjects from the general population is growing. The primary aim of this review was to analyse the acquisition protocols found in the literature, in order to identify common sequences across published studies and to discuss the need of additional ones for specific populations. The secondary aim of this review was to provide a synthesis of current recommendations regarding the use of WB-MRI for cancer screening.

A novel nomogram to identify candidates for active surveillance amongst patients with International Society of Urological Pathology (ISUP) Grade Group (GG) 1 or ISUP GG2 prostate cancer, according to multiparametric magnetic resonance imaging findings.

OBJECTIVES: To develop a novel nomogram to identify candidates for active surveillance (AS) that combines clinical, biopsy and multiparametric magnetic resonance imaging (mpMRI) findings; and to compare its predictive accuracy to, respectively: (i) Prostate Cancer Research International: Active Surveillance (PRIAS) criteria, (ii) Johns Hopkins (JH) criteria, (iii) European Association of Urology (EAU) low-risk classification, and (iv) EAU low-risk or low-volume with International Society of Urological Pathology (ISUP) Grade Group (GG) 2 classification. PATIENTS AND METHODS: We selected 1837 patients with ISUP GG1 or GG2 prostate cancer (PCa), treated with radical prostatectomy (RP) between 2012 and 2018. The outcome of interest was the presence of unfavourable disease (i.e., clinically significant PCa [csPCa]) at RP, defined as: ISUP GG ≥ 3 and/or pathological T stage (pT) ≥3a and/or pathological N stage (pN) 1. First, logistic regression models including PRIAS, JH, EAU low-risk, and EAU low-risk or low-volume ISUP GG2 binary classifications (not eligible vs eligible) were used. Second, a multivariable logistic regression model including age, prostate-specific antigen density (PSA-D), ISUP GG, and the percentage of positive cores (Model 1) was fitted. Third, Prostate Imaging-Reporting and Data System (PI-RADS) score (Model 2), extracapsular extension (ECE) score (Model 3) and PI-RADS + ECE score (Model 4) were added to Model 1. Only variables associated with higher csPCa rates in Model 4 were retained in the final simplified Model 5. The area under the receiver operating characteristic curve (AUC), calibration plots and decision curve analyses were used. RESULTS: Of the 1837 patients, 775 (42.2%) had csPCa at RP. Overall, 837 (47.5%), 986 (53.7%), 348 (18.9%), and 209 (11.4%) patients were eligible for AS according to, respectively, the EAU low-risk, EAU low-risk or low-volume ISUP GG2, PRIAS, and JH criteria. The proportion of csPCa amongst the EAU low-risk, EAU low-risk or low-volume ISUP GG2, PRIAS and JH candidates was, respectively 28.5%, 29.3%, 25.6% and 17.2%. Model 4 and Model 5 (in which only PSA-D, ISUP GG, PI-RADS and ECE score were retained) had a greater AUC (0.84), compared to the four proposed AS criteria (all P < 0.001). The adoption of a 25% nomogram threshold increased the proportion of AS-eligible patients from 18.9% (PRIAS) and 11.4% (JH) to 44.4%. Moreover, the same 25% nomogram threshold resulted in significantly lower estimated risks of csPCa (11.3%), compared to PRIAS (Δ: -14.3%), JH (Δ: -5.9%), EAU low-risk (Δ: -17.2%), and EAU low-risk or low-volume ISUP GG2 classifications (Δ: -18.0%). CONCLUSION: The novel nomogram combining clinical, biopsy and mpMRI findings was able to increase by ~25% and 35% the absolute frequency of patients suitable for AS, compared to, respectively, the PRIAS or JH criteria. Moreover, this nomogram significantly reduced the estimated frequency of csPCa that would be recommended for AS compared to, respectively, the PRIAS, JH, EAU low-risk, and EAU low-risk or low-volume ISUP GG2 classifications.

Low PI-RADS assessment category excludes extraprostatic extension (≥pT3a) of prostate cancer: a histology-validated study including 301 operated patients.

OBJECTIVES: To evaluate whether low PI-RADS v2 assessment categories are effective at excluding extraprostatic extension (EPE) of prostate cancer (≥pT3a PCa). METHODS: The local institutional ethics committee approved this retrospective analysis of 301 consecutive PCa patients. Patients were classified as low- or intermediate/high-risk based on clinical parameters and underwent pre-surgical multiparametric magnetic resonance imaging. A PI-RADS v2 assessment category and ESUR EPE score were assigned for each lesion by two readers working in consensus. Histopathologic analysis of the whole-mount radical prostatectomy specimen was the reference standard. Univariate and multivariate analyses were performed to evaluate the association of PI-RADS v2 assessment category with final histology ≥pT3a PCa. RESULTS: For a PI-RADS v2 assessment category threshold of 3, the overall performance for ruling out (sensitivity, negative predictive value, negative likelihood ratio) ≥pT3a PCa was 99%/98%/0.04 and was similar in both the low-risk (96%/97%/0.12; N = 137) and the intermediate/high-risk groups (100%/100%/0.0; N = 164). In univariate analysis, all clinical and tumor characteristics except age were significantly associated with ≥pT3a PCa. In multivariate analysis, PI-RADS v2 assessment categories ≤ 3 had a protective effect relative to categories 4 and 5. The inclusion of ESUR EPE score improved the AUC of ≥pT3a PCa prediction (from 0.73 to 0.86, p = 0.04 in the overall cohort). The impact of PI-RADS v2 assessment category is reflected in a nomogram derived on the basis of our cohort. CONCLUSIONS: In our cohort, low PI-RADS v2 assessment categories of 3 or less confidently ruled out the presence of ≥pT3a PCa irrespective of clinical risk group. KEY POINTS: • Our analysis of 301 mp-MRI and RARP specimens showed that the addition of PI-RADS v2 assessment categories to clinical parameters improves the exclusion of ≥pT3a (extraprostatic) prostate cancer. • PI-RADS v2 assessment categories of 1 to 3 are useful for excluding ≥pT3a prostate cancer with a NPV of 98%; such patients can be considered as candidates for less invasive approaches. • The ability to exclude ≥pT3a prostate cancer may improve confidence in choosing nerve-sparing surgery or in avoiding pelvic nodal dissections, and similarly for patients undergoing radiotherapy, in adopting short-course adjuvant hormonal therapy or foregoing prophylactic nodal irradiation.

Whole-body magnetic resonance imaging (WB-MRI) in oncology: recommendations and key uses.

The past decade has witnessed a growing role and increasing use of whole-body magnetic resonance imaging (WB-MRI). Driving these successes are developments in both hardware and software that have reduced overall examination times and significantly improved MR imaging quality. In addition, radiologists and clinicians have continued to find promising new applications of this innovative imaging technique that brings together morphologic and functional characterization of tissues. In oncology, the role of WB-MRI has expanded to the point of being recommended in international guidelines for the assessment of several cancer histotypes (multiple myeloma, melanoma, prostate cancer) and cancer-prone syndromes (Li-Fraumeni and hereditary paraganglioma-pheochromocytoma syndromes). The literature shows growing use of WB-MRI for the staging and follow-up of other cancer histotypes and cancer-related syndromes (including breast cancer, lymphoma, neurofibromatosis, and von Hippel-Lindau syndromes). The main aim of this review is to examine the current scientific evidence for the use of WB-MRI in oncology.

Multiparametric Magnetic-Resonance to Confirm Eligibility to an Active Surveillance Program for Low-Risk Prostate Cancer: Intermediate Time Results of a Third Referral High Volume Centre Active Surveillance Protocol.

BACKGROUND: To evaluate the role of confirmatory multiparametric magnetic resonance imaging (mpMRI) of the prostate at the time of Active Surveillance (AS) enrollment to reduce disease misclassification. MATERIALS: From 2012 to 2016, 383 patients with low-risk disease respecting Prostate Cancer Research International AS criteria underwent confirmatory 1.5-T mpMRI. AS was proposed to patients with Prostate Imaging and Report and Data System (PI-RADS) score ≤3 and no extraprostatic extension (EPE), whereas patients with PI-RADS score ≥4 and/or EPE were treated actively. Kaplan-Meier analyses quantified progression-free survival (PFS) in patients enrolled in the AS program. Logistic regression analyses tested the association between confirmatory mpMRI and clinically significant prostate cancer (csPCa) at radical prostatectomy (RP). Diagnostic performance of mpMRI was calculated in patients submitted to immediate RP. RESULTS: PFS rate was 99, 90 and 86% at 1, 2 and 3 years respectively. At multivariable analysis, PI-RADS 3, PI-RADS 4, PI-RADS 5 and EPE increased the probability of having csPCa at immediate RP (PI-RADS 3 [OR] 1.2, p = 0.26; PI-RADS 4 [OR] 5.1, p = 0.02; PI-RADS 5 [OR] 6.7; p = 0.009; EPE [OR] 11.8, p < 0.001). Confirmatory mpMRI showed sensibility, specificity, positive predictive value and negative predictive value of 85, 55, 68 and 76% respectively. CONCLUSIONS: MpMRI at the time of AS enrollment reduces the misclassification rate of csPCa. We suggest to perform target biopsies in patients with PI-RADS score 3 and 4 lesions.

Is whole-body magnetic resonance imaging a source of anxiety in oncological patients?

OBJECTIVE: Magnetic resonance often produces feelings of anxiety before, or during, the examination. The aim of this study was to assess anxiety and potential causes of anxiety in cancer patients undergoing whole-body magnetic resonance imaging (WB-MRI). METHODS: This monocentric study recruited 70 cancer patients who were scheduled to undergo WB-MRI for detection, staging or therapy monitoring. At baseline (prior to the WB-MRI), assessments were performed using the State-Trait Anxiety Inventory (STAI-Y 1), Illness Perception Questionnaire (IPQ-R), Big Five Inventory (BIF-10) and Revised Life Orientation Test (LOT-R), while at the end of the WB-MRI examination the patients repeated the STAI-Y 1 questionnaire and were asked to indicate their preference between WB-MRI and computed tomography. RESULTS: We found a positive correlation between pre- and post-examination STAI-Y 1 scores (r = 0.536, p < .0001), with no significant difference between them. Pre-examination STAI-Y 1 scores had a negative correlation with the emotional stability in the BIF-10 questionnaire (r = -0.47, p = .001) and a positive correlation with emotional representation (r = 0.57, p = .001) in IPQ-R. The post-examination STAI-Y 1 had a negative correlation with optimistic orientation (r = -0.59, p = .001). CONCLUSIONS: The anxiety associated with a WB-MRI examination was only in small part associated with the examination itself, and in fact, most patients preferred WB-MRI to computed tomography. Concern with the outcome of the examination was likely a greater source of anxiety.

CT-Based Radiomics and Deep Learning for BRCA Mutation and Progression-Free Survival Prediction in Ovarian Cancer Using a Multicentric Dataset.

PURPOSE: Build predictive radiomic models for early relapse and BRCA mutation based on a multicentric database of high-grade serous ovarian cancer (HGSOC) and validate them in a test set coming from different institutions. METHODS: Preoperative CTs of patients with HGSOC treated at four referral centers were retrospectively acquired and manually segmented. Hand-crafted features and deep radiomics features were extracted respectively by dedicated software (MODDICOM) and a dedicated convolutional neural network (CNN). Features were selected with and without prior harmonization (ComBat harmonization), and models were built using different machine learning algorithms, including clinical variables. RESULTS: We included 218 patients. Radiomic models showed low performance in predicting both BRCA mutation (AUC in test set between 0.46 and 0.59) and 1-year relapse (AUC in test set between 0.46 and 0.56); deep learning models demonstrated similar results (AUC in the test of 0.48 for BRCA and 0.50 for relapse). The inclusion of clinical variables improved the performance of the radiomic models to predict BRCA mutation (AUC in the test set of 0.74). CONCLUSIONS: In our multicentric dataset, representative of a real-life clinical scenario, we could not find a good radiomic predicting model for PFS and BRCA mutational status, with both traditional radiomics and deep learning, but the combination of clinical and radiomic models improved model performance for the prediction of BRCA mutation. These findings highlight the need for standardization through the whole radiomic pipelines and robust multicentric external validations of results.

Ultrahypofractionated radiotherapy for localized prostate cancer with simultaneous boost to the dominant intraprostatic lesion: a plan comparison.

OBJECTIVE: To compare different stereotactic body techniques-intensity-modulated radiotherapy with photons and protons, applied to radiotherapy of prostatic cancer-with simultaneous integrated boost (SIB) on the dominant intraprostatic lesion (DIL). METHODS: Ten patients were selected for this planning study. Dosimetric results were compared between volumetric modulated arc therapy, intensity-modulated radiation therapy (IMRT), and intensity-modulated proton therapy both with two (IMPT 2F) and five fields (IMPT 5F) planning while applying the prescription schemes of 7.25 Gy/fraction to the prostate gland and 7.5 Gy/fraction to the DIL in 5 fractions. RESULTS: Comparison of the coverages of the planning target volumes showed that small differences exist. The IMPT-2F-5F techniques allowed higher doses in the targets; conformal indexes resulted similar; homogeneity was better in the photon techniques (2%-5%). Regarding the organs at risk, all the techniques were able to maintain the dose well below the prescribed constraints: in the rectum, the IMPT-2F-5F and IMRT were more efficient in lowering the intermediate doses; in the bladder, the median dose was significantly better in the case of IMPT (2F-5F). In the urethra, the best sparing was achieved only by IMPT-5F. CONCLUSIONS: Stereotactic radiotherapy with SIB for localized prostate cancer is feasible with all the investigated techniques. Concerning IMPT, the two-beam technique does not seem to have a greater advantage compared to the standard techniques; the 5-beam technique seems more promising also accounting for the range uncertainty.

MRI- and Histologic-Molecular-Based Radio-Genomics Nomogram for Preoperative Assessment of Risk Classes in Endometrial Cancer.

High- and low-risk endometrial carcinoma (EC) differ in whether or not a lymphadenectomy is performed. We aimed to develop MRI-based radio-genomic models able to preoperatively assess lymph-vascular space invasion (LVSI) and discriminate between low- and high-risk EC according to the ESMO-ESGO-ESTRO 2020 guidelines, which include molecular risk classification proposed by "ProMisE". This is a retrospective, multicentric study that included 64 women with EC who underwent 3T-MRI before a hysterectomy. Radiomics features were extracted from T2WI images and apparent diffusion coefficient maps (ADC) after manual segmentation of the gross tumor volume. We constructed a multiple logistic regression approach from the most relevant radiomic features to distinguish between low- and high-risk classes under the ESMO-ESGO-ESTRO 2020 guidelines. A similar approach was taken to assess LVSI. Model diagnostic performance was assessed via ROC curves, accuracy, sensitivity and specificity on training and test sets. The LVSI predictive model used a single feature from ADC as a predictor; the risk class model used two features as predictors from both ADC and T2WI. The low-risk predictive model showed an AUC of 0.74 with an accuracy, sensitivity, and specificity of 0.74, 0.76, 0.94; the LVSI model showed an AUC of 0.59 with an accuracy, sensitivity, and specificity of 0.60, 0.50, 0.61. MRI-based radio-genomic models are useful for preoperative EC risk stratification and may facilitate therapeutic management.

Quality assurance for automatically generated contours with additional deep learning.

OBJECTIVE: Deploying an automatic segmentation model in practice should require rigorous quality assurance (QA) and continuous monitoring of the model's use and performance, particularly in high-stakes scenarios such as healthcare. Currently, however, tools to assist with QA for such models are not available to AI researchers. In this work, we build a deep learning model that estimates the quality of automatically generated contours. METHODS: The model was trained to predict the segmentation quality by outputting an estimate of the Dice similarity coefficient given an image contour pair as input. Our dataset contained 60 axial T2-weighted MRI images of prostates with ground truth segmentations along with 80 automatically generated segmentation masks. The model we used was a 3D version of the EfficientDet architecture with a custom regression head. For validation, we used a fivefold cross-validation. To counteract the limitation of the small dataset, we used an extensive data augmentation scheme capable of producing virtually infinite training samples from a single ground truth label mask. In addition, we compared the results against a baseline model that only uses clinical variables for its predictions. RESULTS: Our model achieved a mean absolute error of 0.020 ± 0.026 (2.2% mean percentage error) in estimating the Dice score, with a rank correlation of 0.42. Furthermore, the model managed to correctly identify incorrect segmentations (defined in terms of acceptable/unacceptable) 99.6% of the time. CONCLUSION: We believe that the trained model can be used alongside automatic segmentation tools to ensure quality and thus allow intervention to prevent undesired segmentation behavior.

Value Attribution in the Decision to Use of Whole Body MRI for Early Cancer Diagnosis.

This study aimed to identify the main factors that asymptomatic individuals considered when deciding to undergo self-referred Whole-body MRI (WB-MRI) for early cancer diagnosis and the subjective values attributed to each mentioned factor in a Decision tree analysis. Personal characteristics such as risk perception and personality were investigated as possible factors affecting value attribution. Seventy-four volunteers (mean age 56.4; male = 47) filled a simplified decision tree by expressing the expected factors and related subjective values associated with two screening options for early cancer diagnosis (standard procedures vs. WB-MRI+standard procedures) while waiting for a WB-MRI examination. Questionnaires on risk perception and personality traits were also administered. Expected factors were summarized in 5 clusters: diagnostic certainty, psychological well-being, safety, test validity and time/cost. Test validity and time/cost were evaluated as potential losses in both procedures. Diagnostic Certainty and safety were evaluated as losses in standard screening, and as an advantage when considering WB-MRI+standard screening. Forty-five percent of participants considered WB-MRI+standard screening as beneficial for their psychological well-being. Finally, personal absolute and comparative risk to get cancer was associated with a positive value attribution to WB-MRI (p < 0.05). Our results showed the addition of WB-MRI to be generally considered a good option to increase individuals' perceptions of diagnostic certainty and the safety of the exam, and to increase psychological well-being. The positive value of such a screening option increased with the individual's cancer risk perception.

Whole-body magnetic resonance imaging: technique, guidelines and key applications.

Whole-body magnetic resonance imaging (WB-MRI) is an imaging method without ionising radiation that can provide WB coverage with a core protocol of essential imaging contrasts in less than 40 minutes, and it can be complemented with sequences to evaluate specific body regions as needed. In many cases, WB-MRI surpasses bone scintigraphy and computed tomography in detecting and characterising lesions, evaluating their response to therapy and in screening of high-risk patients. Consequently, international guidelines now recommend the use of WB-MRI in the management of patients with multiple myeloma, prostate cancer, melanoma and individuals with certain cancer predisposition syndromes. The use of WB-MRI is also growing for metastatic breast cancer, ovarian cancer and lymphoma as well as for cancer screening amongst the general population. In light of the increasing interest from clinicians and patients in WB-MRI as a radiation-free technique for guiding the management of cancer and for cancer screening, we review its technical basis, current international guidelines for its use and key applications.

Preliminary observations regarding the expectations, acceptability and satisfaction of whole-body MRI in self-referring asymptomatic subjects.

OBJECTIVE: To evaluate the satisfaction of asymptomatic subjects who self-referring Whole-Body Magnetic Resonance Imaging (WB-MRI) for early cancer diagnosis. METHODS: Subjects completed a pre-examination questionnaire, while waiting for their WB-MRI examination, recording demographics, expected discomfort, perceived knowledge and usefulness of the procedure and health risk perceptions, as well as a post-examination questionnaire, measuring discomfort experienced, acceptability and satisfaction with WB-MRI. We examined which factors influenced discomfort and satisfaction associated with WB-MRI. RESULTS: 65 asymptomatic subjects (median age 51; 29 females) completed the questionnaire. Before WB-MRI, 29% of subjects expected discomfort of some form with claustrophobia (27.7%) and exam duration (24.6%) being the most common concerns. Experienced discomfort due to shortness of breath was significantly lower than expected. This difference was significantly associated with the personal risk perception to get a disease (p = 0.01) and educational level (p = 0.002). More specifically, higher level of perceived personal risk of getting a disease and lower level of education were associated with higher expected than experienced discomfort. Similarly, experiencing less claustrophobia than expected was significantly associated with gender (p = 0.005) and more pronounced among females. A majority (83%) of subjects expressed high levels of satisfaction with WB-MRI for early cancer diagnosis and judged it more acceptable than other diagnostic exams. CONCLUSIONS: Asymptomatic subjects self-referring to WB-MRI for early cancer diagnosis showed high levels of satisfaction and acceptability with the examination. Nevertheless, a relevant proportion of participants reported some form of discomfort. Interestingly, participants with higher perceived personal risk to get a disease, lower education and females showed to expect higher discomfort than experienced. ADVANCES IN KNOWLEDGE: Scope exists for measures to assess expected feelings and develop personalized interventions to reduce the stress anticipated by individuals deciding to undergo WB-MRI for early cancer diagnosis.