EANM guidance document: dosimetry for first-in-human studies and early phase clinical trials.

The numbers of diagnostic and therapeutic nuclear medicine agents under investigation are rapidly increasing. Both novel emitters and novel carrier molecules require careful selection of measurement procedures. This document provides guidance relevant to dosimetry for first-in human and early phase clinical trials of such novel agents. The guideline includes a short introduction to different emitters and carrier molecules, followed by recommendations on the methods for activity measurement, pharmacokinetic analyses, as well as absorbed dose calculations and uncertainty analyses. The optimal use of preclinical information and studies involving diagnostic analogues is discussed. Good practice reporting is emphasised, and relevant dosimetry parameters and method descriptions to be included are listed. Three examples of first-in-human dosimetry studies, both for diagnostic tracers and radionuclide therapies, are given.

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.

The prognostic role of MRI-based radiomics in tongue carcinoma: a multicentric validation study.

PURPOSE: Radiomics is an emerging field that utilizes quantitative features extracted from medical images to predict clinically meaningful outcomes. Validating findings is crucial to assess radiomics applicability. We aimed to validate previously published magnetic resonance imaging (MRI) radiomics models to predict oncological outcomes in oral tongue squamous cell carcinoma (OTSCC). MATERIALS AND METHODS: Retrospective multicentric study on OTSCC surgically treated from 2010 to 2019. All patients performed preoperative MRI, including contrast-enhanced T1-weighted (CE-T1), diffusion-weighted sequences and apparent diffusion coefficient map. We evaluated overall survival (OS), locoregional recurrence-free survival (LRRFS), cause-specific mortality (CSM). We elaborated different models based on clinical and radiomic data. C-indexes assessed the prediction accuracy of the models. RESULTS: We collected 112 consecutive independent patients from three Italian Institutions to validate the previously published MRI radiomic models based on 79 different patients. The C-indexes for the hybrid clinical-radiomic models in the validation cohort were lower than those in the training cohort but remained > 0.5 in most cases. CE-T1 sequence provided the best fit to the models: the C-indexes obtained were 0.61, 0.59, 0.64 (pretreatment model) and 0.65, 0.69, 0.70 (posttreatment model) for OS, LRRFS and CSM, respectively. CONCLUSION: Our clinical-radiomic models retain a potential to predict OS, LRRFS and CSM in heterogeneous cohorts across different centers. These findings encourage further research, aimed at overcoming current limitations, due to the variability of imaging acquisition, processing and tumor volume delineation.

Multi-omics integrative modelling for stereotactic body radiotherapy in early-stage non-small cell lung cancer: clinical trial protocol of the MONDRIAN study.

BACKGROUND: Currently, main treatment strategies for early-stage non-small cell lung cancer (ES-NSCLC) disease are surgery or stereotactic body radiation therapy (SBRT), with successful local control rates for both approaches. However, regional and distant failure remain critical in SBRT, and it is paramount to identify predictive factors of response to identify high-risk patients who may benefit from more aggressive approaches. The main endpoint of the MONDRIAN trial is to identify multi-omic biomarkers of SBRT response integrating information from the individual fields of radiomics, genomics and proteomics. METHODS: MONDRIAN is a prospective observational explorative cohort clinical study, with a data-driven, bottom-up approach. It is expected to enroll 100 ES-NSCLC SBRT candidates treated at an Italian tertiary cancer center with well-recognized expertise in SBRT and thoracic surgery. To identify predictors specific to SBRT, MONDRIAN will include data from 200 patients treated with surgery, in a 1:2 ratio, with comparable clinical characteristics. The project will have an overall expected duration of 60 months, and will be structured into five main tasks: (i) Clinical Study; (ii) Imaging/ Radiomic Study, (iii) Gene Expression Study, (iv) Proteomic Study, (v) Integrative Model Building. DISCUSSION: Thanks to its multi-disciplinary nature, MONDRIAN is expected to provide the opportunity to characterize ES-NSCLC from a multi-omic perspective, with a Radiation Oncology-oriented focus. Other than contributing to a mechanistic understanding of the disease, the study will assist the identification of high-risk patients in a largely unexplored clinical setting. Ultimately, this would orient further clinical research efforts on the combination of SBRT and systemic treatments, such as immunotherapy, with the perspective of improving oncological outcomes in this subset of patients. TRIAL REGISTRATION: The study was prospectively registered at clinicaltrials.gov (NCT05974475).

Implementation of dosimetry for molecular radiotherapy; results from a European survey.

PURPOSE: The use of molecular radiotherapy (MRT) has been rapidly evolving over the last years. The aim of this study was to assess the current implementation of dosimetry for MRTs in Europe. METHODS: A web-based questionnaire was open for treating centres between April and June 2022, and focused on 2020-2022. Questions addressed the application of 16 different MRTs, the availability and involvement of medical physicists, software used, quality assurance, as well as the target regions for dosimetry, whether treatment planning and/or verification were performed, and the dosimetric methods used. RESULTS: A total of 173 responses suitable for analysis was received from centres performing MRT, geographically distributed over 27 European countries. Of these, 146 centres (84 %) indicated to perform some form of dosimetry, and 97 % of these centres had a medical physicist available and almost always involved in dosimetry. The most common MRTs were 131I-based treatments for thyroid diseases and thyroid cancer, and [223Ra]RaCl2 for bone metastases. The implementation of dosimetry varied widely between therapies, from almost all centres performing dosimetry-based planning for microsphere treatments to none for some of the less common treatments (like 32P sodium-phosphate for myeloproliferative disease and [89Sr]SrCl2 for bone metastases). CONCLUSIONS: Over the last years, implementation of dosimetry, both for pre-therapeutic treatment planning and post-therapy absorbed dose verification, increased for several treatments, especially for microsphere treatments. For other treatments that have moved from research to clinical routine, the use of dosimetry decreased in recent years. However, there are still large differences both across and within countries.