Background: Lately, radiomic studies featuring the development of a signature to use in prediction models in diagnosis or prognosis outcomes have been increasingly published. While the results are shown to be promising, these studies still have many pitfalls and limitations. One of the main issues of these studies is that radiomic features depend on how the images are preprocessed before their computation. Since, in widely known and used software for radiomic features calculation, it is possible to set these preprocessing parameters before the calculation of the radiomic feature, there are ongoing studies assessing the stability and repeatability of radiomic features to find the most suitable preprocessing parameters for every used imaging modality. Materials and Methods: We performed a comprehensive literature search using four electronic databases: PubMed, Cochrane Library, Embase, and Scopus. Mesh terms and free text were modeled in search strategies for databases. The inclusion criteria were studies where preprocessing parameters’ influence on feature values and model predictions was addressed. Records lacking information on image acquisition parameters were excluded, and any eligible studies with full-text versions were included in the review process, while conference proceedings and monographs were disregarded. We used the QUADAS-2 (Quality Assessment of Diagnostic Accuracy Studies 2) tool to investigate the risk of bias. We synthesized our data in a table divided by the imaging modalities subgroups. Results: After applying the inclusion and exclusion criteria, we selected 43 works. This review examines the impact of preprocessing parameters on the reproducibility and reliability of radiomic features extracted from multimodality imaging (CT, MRI, CBCT, and PET/CT). Standardized preprocessing is crucial for consistent radiomic feature extraction. Key preprocessing steps include voxel resampling, normalization, and discretization, which influence feature robustness and reproducibility. In total, 44% of the included works studied the effects of an isotropic voxel resampling, and most studies opted to employ a discretization strategy. From 2021, several studies started selecting the best set of preprocessing parameters based on models’ best performance. As for comparison metrics, ICC was the most used in MRI studies in 58% of the screened works. Conclusions: From our work, we highlighted the need to harmonize the use of preprocessing parameters and their values, especially in light of future studies of prospective studies, which are still lacking in the current literature.

Purpose: Currently, no consistent guidelines for CT scans used within PET/CT examinations are available. This systematic review provides an up-to-date overview of studies to answer the following questions: What are the specific CT protocols used in PET/CT? What are the possible purposes of requiring a CT study within a PET/CT scan? Is the CT protocol obtained from a dosimetric optimisation study? Materials and method: PubMed/MEDLINE, Cochrane Library, Embase and Scopus were systematically searched for relevant studies in accordance with the PRISMA statement. The literature search was conducted from January 2007 until June 2019. Data derived from studies were standardized in order to reduce possible biases, and they were divided into clinically homogeneous subgroups (adult, child or phantom). Subsequently, we divided the CT protocol intents into 3 types (anatomic localization only, attenuation correction only and diagnostic purpose). A narrative approach was used to summarise datasets and to investigate their heterogeneity (due to medical prescription methodology) and their combination in multiseries CT protocols. When weighted computed tomography dose index (CTDI_w) was available, we calculated the volumetric computed tomography dose index (CTDI_vol) using the pitch value to make the results uniform. Eventually, the correlation between protocol intents and CTDI_vol values was obtained using a Kruskal–Wallis one-way ANOVA statistical test. Result: Starting from a total of 1440 retrieved records, twenty-four studies were eligible for inclusion in addition to two large multicentric works that we used to compare the results. We analyzed 87 CT protocols. There was a considerable range of variation in the acquisition parameters: tube current–time product revealed to have the most variable range, which was 10–300 mAs for adults and 10–80 mAs for paediatric patients. Seventy percent of datasets presented scans acquired with tube current modulation, 9% used fixed tube current and in 21% of them, this information was not available. Dependence between mean CTDI_vol values and protocol intent was statistically significant (p = 0.002). As expected, in diagnostic protocols, there was a statistically significant difference between CTDI_vol values of with and without contrast acquisitions (11.68 mGy vs 7.99 mGy, p = 0.009). In 13 out of 87 studies, the optimisation aim was not reported; in 2 papers, a clinical protocol was used; and in 11 works, a dose optimisation protocol was applied. Conclusions: According to this review, the dose optimisation in PET/CT exams depends heavily on the correct implementation of the CT protocol. In addition to this, considering the latest technology advances (i.e. iterative algorithms development), we suggest a periodic quality control audit to stay updated on new clinical utility modalities and to achieve a shared standardisation of clinical protocols. In conclusion, this study pointed out the necessity to better identify the specific CT protocol use within PET/CT scans, taking into account the continuous development of new technologies.

Aim: The aim of this study was to develop robust prognostic models for mortality prediction of COVID-19 patients, applicable to different sets of real scenarios, using radiomic and neural network features extracted from chest X-rays (CXRs) with a certified and commercially available software. Methods: 1816 patients from 5 different hospitals in the Province of Reggio Emilia were included in the study. Overall, 201 radiomic features and 16 neural network features were extracted from each COVID-19 patient’s radiography. The initial dataset was balanced to train the classifiers with the same number of dead and survived patients, randomly selected. The pipeline had three main parts: balancing procedure; three-step feature selection; and mortality prediction with radiomic features through three machine learning (ML) classification models: AdaBoost (ADA), Quadratic Discriminant Analysis (QDA) and Random Forest (RF). Five evaluation metrics were computed on the test samples. The performance for death prediction was validated on both a balanced dataset (Case 1) and an imbalanced dataset (Case 2). Results: accuracy (ACC), area under the ROC-curve (AUC) and sensitivity (SENS) for the best classifier were, respectively, 0.72 ± 0.01, 0.82 ± 0.02 and 0.84 ± 0.04 for Case 1 and 0.70 ± 0.04, 0.79 ± 0.03 and 0.76 ± 0.06 for Case 2. These results show that the prediction of COVID-19 mortality is robust in a different set of scenarios. Conclusions: Our large and varied dataset made it possible to train ML algorithms to predict COVID-19 mortality using radiomic and neural network features of CXRs.

Breast cancer represents the second leading cause of cancer-related death in the female population, despite continuing advances in treatment options that have significantly accelerated in recent years. Conservative treatments have radically changed the concept of healing, also focusing on the psychological aspect of oncological treatments. In this scenario, radiotherapy plays a key role. Brachytherapy is an extremely versatile radiation technique that can be used in various settings for breast cancer treatment. Although it is invasive, technically complex, and requires a long learning curve, the dosimetric advantages and sparing of organs at risk are unequivocal. Literature data support muticatheter interstitial brachytherapy as the only method with strong scientific evidence to perform partial breast irradiation and reirradiation after previous conservative surgery and external beam radiotherapy, with longer follow-up than new, emerging radiation techniques, whose effectiveness is proven by over 20 years of experience. The aim of our work is to provide a comprehensive view of the use of interstitial brachytherapy to perform breast lumpectomy boost, breast-conserving accelerated partial breast irradiation, and salvage reirradiation for ipsilateral breast recurrence, with particular focus on the implant description, limits, and advantages of the technique.

Anterior segment optical coherence tomography (AS-OCT) allows the explore not only the anterior chamber but also the front part of the vitreous cavity. Our cross-sectional single-centre study investigated whether AS-OCT can distinguish between vitreous involvement due to vitreoretinal lymphoma (VRL) and vitritis in uveitis. We studied AS-OCT images from 28 patients (11 with biopsy-proven VRL and 17 with differential diagnosis uveitis) using publicly available radiomics software written in MATLAB. Patients were divided into two balanced groups: training and testing. Overall, 3260/3705 (88%) AS-OCT images met our defined quality criteria, making them eligible for analysis. We studied five different sets of grey-level samplings (16, 32, 64, 128, and 256 levels), finding that 128 grey levels performed the best. We selected the five most effective radiomic features ranked by the ability to predict the class (VRL or uveitis). We built a classification model using the xgboost python function; through our model, 87% of eyes were correctly diagnosed as VRL or uveitis, regardless of exam technique or lens status. Areas under the receiver operating characteristic curves (AUC) in the 128 grey-level model were 0.95 [CI 0.94, 0.96] and 0.84 for training and testing datasets, respectively. This preliminary retrospective study highlights how AS-OCT can support ophthalmologists when there is clinical suspicion of VRL.

Background: among cardiac arrhythmias, ventricular tachycardia (VT) is one that can lead to cardiac death, although significant progress has been made in its treatment, including the use of implantable cardioverter-defibrillators (ICD) and radiofrequency catheter ablation. Nevertheless, long-term recurrence rates remain in about half of patients and drastically impact the patient’s quality of life. Moreover, recurrent ICD shocks are painful and are associated with higher mortality and worsening of heart failure. Recently, more and more experiences are demonstrating potential efficacy in the use of stereotactic body radiotherapy (SBRT) (also called cardiac radio-ablation) to treat this condition. In this paper, we report our experience in the use of cardiac radio-ablation for the treatment of refractory ventricular tachycardia with a focus on the technique used, along with a review of the literature and technical notes. Case presentation: an 81-year-old male patient with a long history of non-ischemic dilated cardiomyopathy and mechanical mitral prosthesis underwent a biventricular cardioverter defibrillator implant after atrial ventricular node ablation. At the end of 2021, the number of tachycardias increased significantly to about 10 episodes per day. After failure of medical treatment and conventional RT catheter ablation, the patient was treated with SBRT for a total dose of 25 Gy in a single session at the site of the ectopic focus. No acute toxicity was recorded. After SBRT (follow-up 7 months) no other VT episodes were recorded. Conclusion: SBRT appears to be safe and leads to a rapid reduction in arrhythmic storms as treatment for VT without acute toxicity, representing one of the most promising methods for treating VT storms.