Mantle cell lymphoma (MCL) is a rare lymphoid malignancy with a poor prognosis characterised by frequent relapse and short durations of treatment response. Most patients present with aggressive disease, but there exist indolent subtypes without the need for immediate intervention. The very heterogeneous behaviour of MCL is genetically characterised by the translocation t(11;14)(q13;q32), leading to Cyclin D1 overexpression with distinct clinical and biological characteristics and outcomes. There is still an unfulfilled need for precise MCL prognostication in real-time. Machine learning and deep learning neural networks are rapidly advancing technologies with promising results in numerous fields of application. This study develops and compares the performance of deep learning (DL) algorithms and radiomics-based machine learning (ML) models to predict MCL relapse on baseline CT scans. Five classification algorithms were used, including three deep learning models (3D SEResNet50, 3D DenseNet, and an optimised 3D CNN) and two machine learning models based on K-nearest Neighbor (KNN) and Random Forest (RF). The best performing method, our optimised 3D CNN, predicted MCL relapse with a 70% accuracy, better than the 3D SEResNet50 (62%) and the 3D DenseNet (59%). The second-best performing method was the KNN-based machine learning model (64%) after principal component analysis for improved accuracy. Our optimised CNN developed by ourselves correctly predicted MCL relapse in 70% of the patients on baseline CT imaging. Once prospectively tested in clinical trials with a larger sample size, our proposed 3D deep learning model could facilitate clinical management by precision imaging in MCL.

Merkel cell carcinoma (MCC) is a neuroendocrine skin cancer of the elderly, with high metastatic potential and poor prognosis. In particular, the primary resistance to immune checkpoint inhibitors (ICI) in metastatic (m)MCC patients represents a challenge not yet met by any efficient treatment modality. Herein, we describe a novel therapeutic concept with short-interval, low-dose ¹⁷⁷Lutetium (Lu)-high affinity (HA)-DOTATATE [¹⁷⁷Lu]Lu-HA-DOTATATE peptide receptor radionuclide therapy (SILD-PRRT) in combination with PD-1 ICI to induce remission in patients with ICI-resistant mMCC. We report on the initial refractory response of two immunocompromised mMCC patients to the PD-L1 inhibitor avelumab. After confirming the expression of somatostatin receptors (SSTR) on tumor cells by [⁶⁸Ga]Ga-HA-DOTATATE-PET/CT (PET/CT), we employed low-dose PRRT (up to six treatments, mean activity 3.5 GBq per cycle) at 3–6 weeks intervals in combination with the PD-1 inhibitor pembrolizumab to restore responsiveness to ICI. This combination enabled the synergistic application of PD-1 checkpoint immunotherapy with low-dose PRRT at more frequent intervals, and was very well tolerated by both patients. PET/CTs demonstrated remarkable responses at all metastatic sites (lymph nodes, distant skin, and bones), which were maintained for 3.6 and 4.8 months, respectively. Both patients eventually succumbed with progressive disease after 7.7 and 8 months, respectively, from the start of treatment with SILD-PRRT and pembrolizumab. We demonstrate that SILD-PRRT in combination with pembrolizumab is safe and well-tolerated, even in elderly, immunocompromised mMCC patients. The restoration of clinical responses in ICI-refractory patients as proposed here could potentially be used not only for patients with mMCC, but many other cancer types currently treated with PD-1/PD-L1 inhibitors.

Accurate prediction of lymph node metastasis (LNM) in patients with testicular cancer is highly relevant for treatment decision-making and prognostic evaluation. Our study aimed to develop and validate clinical radiomics models for individual preoperative prediction of LNM in patients with testicular cancer. We enrolled 91 patients with clinicopathologically confirmed early-stage testicular cancer, with disease confined to the testes. We included five significant clinical risk factors (age, preoperative serum tumour markers AFP and B-HCG, histotype and BMI) to build the clinical model. After segmenting 273 retroperitoneal lymph nodes, we then combined the clinical risk factors and lymph node radiomics features to establish combined predictive models using Random Forest (RF), Light Gradient Boosting Machine (LGBM), Support Vector Machine Classifier (SVC), and K-Nearest Neighbours (KNN). Model performance was assessed by the area under the receiver operating characteristic (ROC) curve (AUC). Finally, the decision curve analysis (DCA) was used to evaluate the clinical usefulness. The Random Forest combined clinical lymph node radiomics model with the highest AUC of 0.95 (±0.03 SD; 95% CI) was considered the candidate model with decision curve analysis, demonstrating its usefulness for preoperative prediction in the clinical setting. Our study has identified reliable and predictive machine learning techniques for predicting lymph node metastasis in early-stage testicular cancer. Identifying the most effective machine learning approaches for predictive analysis based on radiomics integrating clinical risk factors can expand the applicability of radiomics in precision oncology and cancer treatment.

Imaging of the temporal bone and middle ear is challenging for radiologists due to the abundance of distinct anatomical structures and the plethora of possible pathologies. The basis for a precise diagnosis is knowledge of the underlying anatomy as well as the clinical presentation and the individual patient’s otological status. In this article, we aimed to summarize the most common inflammatory lesions of the temporal bone and middle ear, describe their specific imaging characteristics, and highlight their differential diagnoses. First, we introduce anatomical and imaging fundamentals. Additionally, a point-to-point comparison of the radiological and histological features of the wide spectrum of inflammatory diseases of the temporal bone and middle ear in context with a review of the current literature and current trends is given.

Recent improvements in alveolar echinococcosis (AE) therapy can provide long-term disease control, and even allow structured treatment interruption in selected cases. Imaging has a pivotal role in monitoring disease activity, with 18-fluoro-deoxyglucose positron emission and computed tomography (18F-FDG-PET/CT) in particular having proven beneficial for assessing disease activity. Repetitive regular examinations to monitor therapy response, however, can lead to substantial radiation burden. Therefore, by combining metabolic information and excellent tissue contrast in magnetic resonance imaging (MRI), PET/MR appears ideally suited for this task. Here, we retrospectively analyzed 51 AE patients that underwent 18F-FDG-PET/MR. Patients had a ‘confirmed/probable’ diagnosis in 22/29 cases according to the WHO classification. FDG uptake, diffusion restriction, and MRI morphology were evaluated. We found significant differences in FDG uptake between responders to benzimidazole therapy and progressive manifestations (SUVavg 2.7 ± 1.3 vs. 5.4 ± 2.2, p < 0.001) as well as between Kodama Types 1 and 3 (F = 9.9, p < 0.003). No significant differences were detected for ADC values or MRI morphology concerning response and no correlations were present between FDG uptake and ADC values. The mean radiation dose was 5.9–6.5 mSv. We conclude that the combination of metabolic information and MRI morphology at a low radiation dose proposes PET/MR as a suitable imaging modality for AE assessment. Longitudinal studies are needed to define the role of this imaging modality.

Castration resistant prostate cancer (CRPC) is characterized by an aggressive biological behavior with a relatively short survival time, especially in progressive tumors pretreated with new hormonal agents and taxane chemotherapy. [177Lu]-Lutetium-PSMA (Lu-PSMA) treatment has proven efficacy in these patients. However, around 30% of the CRPC patients do not benefit from Lu-PSMA treatment, and little is known about predictive factors for treatment success if Lu-PSMA is offered in an individualized approach based on clinical and laboratory features. In this monocentric retrospective study, 86 CRPC patients receiving Lu-PSMA treatment were evaluated. The focus of the study was to describe clinical factors at baseline and during early treatment that are related to overall survival (OS). In addition, PSMA PET/CT-, PSA-response, and safety and tolerability (CTCAE adverse event reporting) were assessed. Efficacy endpoints were calculated using stratified Kaplan–Meier methods and Cox regression models. Mean applied dose was 17.7 GBq (mean 5.3 ± 1.1 GBq per cycle) with an average of 3.6 (range 1–8) therapy cycles. Patients were followed up for a mean of 12.4 months (range 1–39). The median OS was 15 months (95% CI 12.8–17.2). The best overall response rate in patients assessed with PSMA PET/CT and PSA response was 27.9%, and 50.0% had at least stable disease. Nine patients had a ≥grade 3 adverse event with anemia being the most frequent adverse event. Positive predictors for prolonged OS from baseline parameters were pre-treatment hemoglobin level of ≥10 g/dL and a lower PSA values at treatment start, while the presence of visceral or liver metastases were not significantly associated with worse prognoses in this cohort. With careful patient selection, an individualized Lu-PSMA treatment approach is feasible and patients with dose-limiting factors or visceral metastases should be included in prospective trials.