Supervised machine learning enables non-invasive lesion characterization in primary prostate cancer with [68Ga]Ga-PSMA-11 PET/MRI.

PURPOSE: Risk classification of primary prostate cancer in clinical routine is mainly based on prostate-specific antigen (PSA) levels, Gleason scores from biopsy samples, and tumor-nodes-metastasis (TNM) staging. This study aimed to investigate the diagnostic performance of positron emission tomography/magnetic resonance imaging (PET/MRI) in vivo models for predicting low-vs-high lesion risk (LH) as well as biochemical recurrence (BCR) and overall patient risk (OPR) with machine learning. METHODS: Fifty-two patients who underwent multi-parametric dual-tracer [18F]FMC and [68Ga]Ga-PSMA-11 PET/MRI as well as radical prostatectomy between 2014 and 2015 were included as part of a single-center pilot to a randomized prospective trial (NCT02659527). Radiomics in combination with ensemble machine learning was applied including the [68Ga]Ga-PSMA-11 PET, the apparent diffusion coefficient, and the transverse relaxation time-weighted MRI scans of each patient to establish a low-vs-high risk lesion prediction model (MLH). Furthermore, MBCR and MOPR predictive model schemes were built by combining MLH, PSA, and clinical stage values of patients. Performance evaluation of the established models was performed with 1000-fold Monte Carlo (MC) cross-validation. Results were additionally compared to conventional [68Ga]Ga-PSMA-11 standardized uptake value (SUV) analyses. RESULTS: The area under the receiver operator characteristic curve (AUC) of the MLH model (0.86) was higher than the AUC of the [68Ga]Ga-PSMA-11 SUVmax analysis (0.80). MC cross-validation revealed 89% and 91% accuracies with 0.90 and 0.94 AUCs for the MBCR and MOPR models respectively, while standard routine analysis based on PSA, biopsy Gleason score, and TNM staging resulted in 69% and 70% accuracies to predict BCR and OPR respectively. CONCLUSION: Our results demonstrate the potential to enhance risk classification in primary prostate cancer patients built on PET/MRI radiomics and machine learning without biopsy sampling.

Osteoarthritis in morbidly obese children and adolescents, an age-matched controlled study.

PURPOSE: Main objective of this study was to investigate the association of pain and early cartilage lesions in morbidly obese children and adolescents. METHODS: A total of 57 subjects were included in the study. Morbidly obese patients (n = 39) were subdivided into two groups: Group A: (11 males and 9 females, 14.2 ± 2.7 years) with permanent knee pain; and Group B: (10 males and 9 females, 14.4 ± 2.2 years) without permanent or without any knee pain. Group C (8 males and 10 females, 15.0 ± 2.9 years) included age-matched children and adolescents of normal weight. MRI examinations were performed in all subjects, and an extensive analysis of the images was conducted according to the condition of the cartilage surface and the meniscus. Patients' subjective health was assessed by means of four well-known knee scores (IKDC, KOOS, Tegner/Lysholm, and VAS). Nonparametric Jonckheere-Terpstra test was used to test the trend of the natural order between the three groups. RESULTS: In 38 of 39 morbidly obese children and adolescents, in at least one region of the knee, a marked cartilage lesion could be shown by MRI. Group A showed significantly (p < 0.001) more cartilage lesions (mean 3.7) compared to Group B (mean 2.8) and Group C (mean 0.8). IKDC, and all the KOOS subunits, showed significantly (p < 0.001, p Bonferroni < 0.001) increasing scores from Group A to B to C, in addition to KOOS symptoms. CONCLUSIONS: Morbid obesity causes early lesions of the knee cartilage, even in young patients. Significantly, more patients with reported pain show more severe damages.