A novel approach was used to assess radiomic software agreement based on Italian multicenter Shared Understanding of Radiomic Extractors phantoms and a systematic feature extraction, finding that d... Background The translation of radiomic models into clinical practice is hindered by the limited reproducibility of features across software and studies. Standardization is needed to accelerate this...

In recent decades, artificial intelligence (AI) tools have been applied in many medical fields, opening the possibility of finding novel solutions for managing very complex and multifactorial problems, such as those commonly encountered in radiotherapy (RT). We conducted a PubMed and Scopus search to identify the AI application field in RT limited to the last four years. In total, 1824 original papers were identified, and 921 were analyzed by considering the phase of the RT workflow according to the applied AI approaches. AI permits the processing of large quantities of information, data, and images stored in RT oncology information systems, a process that is not manageable for individuals or groups. AI allows the iterative application of complex tasks in large datasets (e.g., delineating normal tissues or finding optimal planning solutions) and might support the entire community working in the various sectors of RT, as summarized in this overview. AI-based tools are now on the roadmap for RT and have been applied to the entire workflow, mainly for segmentation, the generation of synthetic images, and outcome prediction. Several concerns were raised, including the need for harmonization while overcoming ethical, legal, and skill barriers.

Sarcopenia (SP) is a syndrome characterized by age-associated loss of skeletal muscle mass and function. SP worsens both acute and late radiation-induced toxicity, prognosis, and quality of life. Myosteatosis is a pathological infiltration of muscle tissue by adipose tissue which often precedes SP and has a proven correlation with prognosis in cancer patients. Sarcopenic obesity is considered a “hidden form” of SP (due to large fat mass) and is independently related to higher mortality and worse complications after surgery and systemic treatments with worse prognostic impact compared to SP alone. The evaluation of SP is commonly based on CT images at the level of the middle of the third lumbar vertebra. On this scan, all muscle structures are contoured and then the outlined surface area is calculated. Several studies reported a negative impact of SP on overall survival in patients undergoing RT for tumors of the head and neck, esophagus, rectum, pancreas, cervix, and lung. Furthermore, several appetite-reducing side effects of RT, along with more complex radiation-induced mechanisms, can lead to SP through, but not limited to, reduced nutrition. In particular, in pediatric patients, total body irradiation was associated with the onset of SP and other changes in body composition leading to an increased risk of cardiometabolic morbidity in surviving adults. Finally, some preliminary studies showed the possibility of effectively treating SP and preventing the worsening of SP during RT. Future studies should be able to provide information on how to prevent and manage SP before, during, or after RT, in both adult and pediatric patients.

This proof-of-concept study lays the foundations for the development of a delivery strategy for radioactive lanthanides, such as Yttrium-90, against recurrent glioblastoma. Our appealing hypothesis is that by taking advantage of the combination of biocompatible polyvinyl alcohol (PVA) microbubbles (MBs) and endovascular radiopharmaceutical infusion, a minimally invasive selective radioembolization can be achieved, which can lead to personalized treatments limiting off-target toxicities for the normal brain. The results show the successful formulation strategy that turns the ultrasound contrast PVA-shelled microbubbles into a microdevice, exhibiting good loading efficiency of Yttrium cargo by complexation with a bifunctional chelator. The selective targeting of Yttrium-loaded MBs on the glioblastoma-associated tumor endothelial cells can be unlocked by the biorecognition between the overexpressed α_Vβ₃ integrin and the ligand Cyclo(Arg-Gly-Asp-D-Phe-Lys) at the PVA microbubble surface. Hence, we show the suitability of PVA MBs as selective Y-microdevices for in situ injection via the smallest (i.e., 1.2F) neurointerventional microcatheter available on the market and the accumulation of PVA MBs on the HUVEC cell line model of integrin overexpression, thereby providing ~6 × 10⁻¹⁵ moles of Y90 per HUVEC cell. We further discuss the potential impact of using such versatile PVA MBs as a new therapeutic chance for treating glioblastoma multiforme recurrence.

Background: Radiomics is a field of research medicine and data science in which quantitative imaging features are extracted from medical images and successively analyzed to develop models for providing diagnostic, prognostic, and predictive information. The purpose of this work was to develop a machine learning model to predict the survival probability of 85 cervical cancer patients using PET and CT radiomic features as predictors. Methods: Initially, the patients were divided into two mutually exclusive sets: a training set containing 80% of the data and a testing set containing the remaining 20%. The entire analysis was separately conducted for CT and PET features. Genetic algorithms and LASSO regression were used to perform feature selection on the initial PET and CT feature sets. Two different survival models were employed: the Cox proportional hazard model and random survival forest. The Cox model was built using the subset of features obtained with the feature selection process, while all the available features were used for the random survival forest model. The models were trained on the training set; cross-validation was used to fine-tune the models and to obtain a preliminary measurement of the performance. The models were then validated on the test set, using the concordance index as the metric. In addition, alternative versions of the models were developed using tumor recurrence as an adjunct feature to evaluate its impact on predictive performance. Finally, the selected CT and PET features were combined to build a further Cox model. Results: The genetic algorithm was superior to the LASSO regression for feature selection. The best performing model was the Cox model, which was built using the selected CT features; it achieved a concordance index score of 0.707. With the addition of tumor recurrence as a predictive feature, the Cox CT model reached a concordance index score of 0.776. PET features, however, proved to be inadequate for survival prediction. The CT model performed better than the model with combined PET and CT features. Conclusions: The results showed that radiomic features can be used to successfully predict survival probability in cervical cancer patients. In particular, CT radiomic features proved to be better predictors than PET radiomic features in this specific case.