Radiomics is an emerging field of image analysis with potential applications in patient risk stratification. This study developed and evaluated machine learning models using quantitative radiomic features extracted from multiparametric magnetic resonance imaging (mpMRI) to detect and classify prostate cancer (PCa). In total, 191 patients that underwent prostatic mpMRI and combined targeted and systematic fusion biopsy were retrospectively included. Segmentations of the whole prostate glands and index lesions were performed manually in apparent diffusion coefficient (ADC) maps and T2-weighted MRI. Radiomic features were extracted from regions corresponding to the whole prostate gland and index lesion. The best performing combination of feature setup and classifier was selected to compare its predictive ability of the radiologist’s evaluation (PI-RADS), mean ADC, prostate specific antigen density (PSAD) and digital rectal examination (DRE) using receiver operating characteristic (ROC) analysis. Models were evaluated using repeated 5-fold cross-validation and a separate independent test cohort. In the test cohort, an ensemble model combining a radiomics model, with models for PI-RADS, PSAD and DRE achieved high predictive AUCs for the differentiation of (i) malignant from benign prostatic lesions (AUC = 0.889) and of (ii) clinically significant (csPCa) from clinically insignificant PCa (cisPCa) (AUC = 0.844). Our combined model was numerically superior to PI-RADS for cancer detection (AUC = 0.779; p = 0.054) as well as for clinical significance prediction (AUC = 0.688; p = 0.209) and showed a significantly better performance compared to mADC for csPCa prediction (AUC = 0.571; p = 0.022). In our study, radiomics accurately characterizes prostatic index lesions and shows performance comparable to radiologists for PCa characterization. Quantitative image data represent a potential biomarker, which, when combined with PI-RADS, PSAD and DRE, predicts csPCa more accurately than mADC. Prognostic machine learning models could assist in csPCa detection and patient selection for MRI-guided biopsy.

Original Article Performance variability of radiomics machine learning models for the detection of clinically significant prostate cancer in heterogeneous MRI datasets Eva Gresser, Balthasar Schachtner, Anna Theresa Stüber, Olga Solyanik, Andrea Schreier, Thomas Huber, Matthias Frank Froelich, Giuseppe Magistro, Alexander Kretschmer, Christian Stief, Jens Ricke, Michael Ingrisch, Dominik Nörenberg

(1) Background: To evaluate radiomics features as well as a combined model with clinical parameters for predicting overall survival in patients with bladder cancer (BCa). (2) Methods: This retrospective study included 301 BCa patients who received radical cystectomy (RC) and pelvic lymphadenectomy. Radiomics features were extracted from the regions of the primary tumor and pelvic lymph nodes as well as the peritumoral regions in preoperative CT scans. Cross-validation was performed in the training cohort, and a Cox regression model with an elastic net penalty was trained using radiomics features and clinical parameters. The models were evaluated with the time-dependent area under the ROC curve (AUC), Brier score and calibration curves. (3) Results: The median follow-up time was 56 months (95% CI: 48–74 months). In the follow-up period from 1 to 7 years after RC, radiomics models achieved comparable predictive performance to validated clinical parameters with an integrated AUC of 0.771 (95% CI: 0.657–0.869) compared to an integrated AUC of 0.761 (95% CI: 0.617–0.874) for the prediction of overall survival (p = 0.98). A combined clinical and radiomics model stratified patients into high-risk and low-risk groups with significantly different overall survival (p < 0.001). (4) Conclusions: Radiomics features based on preoperative CT scans have prognostic value in predicting overall survival before RC. Therefore, radiomics may guide early clinical decision-making.

Fusion imaging depicts an innovative technique that facilitates combining assets and reducing restrictions of advanced ultrasound and cross-sectional imaging. The purpose of the present retrospective study was to evaluate the role of fusion imaging for assessing hepatic and renal lesions. Between 02/2011–08/2020, 92 patients in total were included in the study, of which 32 patients had hepatic lesions, 60 patients had renal lesions. Fusion imaging was technically successful in all patients. No adverse side effects upon intravenous (i.v.) application of SonoVue^® (Bracco, Milan, Italy) were registered. Fusion imaging could clarify all 11 (100%) initially as indeterminate described hepatic lesions by computed tomography/magnetic resonance imaging (CT/MRI). Moreover, 5/14 (36%) initially suspicious hepatic lesions could be validated by fusion imaging, whereas in 8/14 (57%), malignant morphology was disproved. Moreover, fusion imaging allowed for the clarification of 29/30 (97%) renal lesions initially characterized as suspicious by CT/MRI, of which 19/30 (63%) underwent renal surgery, histopathology revealed malignancy in 16/19 (84%), and benignity in 3/19 (16%). Indeterminate findings could be elucidated by fusion imaging in 20/20 (100%) renal lesions. Its accessibility and repeatability, even during pregnancy and in childhood, its cost-effectiveness, and its excellent safety profile, make fusion imaging a promising instrument for the thorough evaluation of hepatic and renal lesions in the future.

Neuroendocrine tumors (NETs) are relatively rare neoplasms arising from the hormone-producing neuroendocrine system that can occur in various organs such as pancreas, small bowel, stomach and lung. As the majority of these tumors express somatostatin receptors (SSR) on their cell membrane, utilization of SSR analogs in nuclear medicine is a promising, but relatively costly approach for detection and localization. The aim of this study was to analyze the cost-effectiveness of ⁶⁸Ga-DOTA-TATE PET/CT (Gallium-68 DOTA-TATE Positron emission tomography/computed tomography) compared to ¹¹¹In-pentetreotide SPECT/CT (Indium-111 pentetreotide Single Photon emission computed tomography/computed tomography) and to CT (computed tomography) alone in detection of NETs. A decision model on the basis of Markov simulations evaluated lifetime costs and quality-adjusted life years (QALYs) related to either a CT, SPECT/CT or PET/CT. Model input parameters were obtained from publicized research projects. The analysis is grounded on the US healthcare system. Deterministic sensitivity analysis of diagnostic parameters and probabilistic sensitivity analysis predicated on a Monte Carlo simulation with 30,000 reiterations was executed. The willingness-to-pay (WTP) was determined to be $ 100,000/QALY. In the base-case investigation, PET/CT ended up with total costs of $88,003.07 with an efficacy of 4.179, whereas CT ended up with total costs of $88,894.71 with an efficacy of 4.165. SPECT/CT ended up with total costs of $89,973.34 with an efficacy of 4.158. Therefore, the strategies CT and SPECT/CT were dominated by PET/CT in the base-case scenario. In the sensitivity analyses, PET/CT remained a cost-effective strategy. This result was due to reduced therapy costs of timely detection. The additional costs of ⁶⁸Ga-DOTA-TATE PET/CT when compared to CT alone are justified in the light of potential savings in therapy costs and better outcomes.