Search

Objective: Interstitial fibrosis/tubular atrophy (IFTA) is a common, irreversible, and progressive form of chronic kidney allograft injury, and it is considered a critical predictor of kidney allograft outcomes. The extent of IFTA is estimated through a graft biopsy, while a non-invasive test is lacking. The aim of this study was to evaluate the feasibility and accuracy of an MRI radiomic-based machine learning (ML) algorithm to estimate the degree of IFTA in a cohort of transplanted patients. Approach: Patients who underwent MRI and renal biopsy within a 6-month interval from 1 January 2012 to 1 March 2021 were included. Stable MRI sequences were selected, and renal parenchyma, renal cortex and medulla were segmented. After image filtering and pre-processing, we computed radiomic features that were subsequently selected through a LASSO algorithm for their highest correlation with the outcome and lowest intercorrelation. Selected features and relevant patients' clinical data were used to produce ML algorithms using 70% of the study cases for feature selection, model training and validation with a 10-fold cross-validation, and 30% for model testing. Performances were evaluated using AUC with 95% confidence interval. Main results: A total of 70 coupled tests (63 patients, 35.4% females, mean age 52.2 years) were included and subdivided into a wider cohort of 50 for training and a smaller cohort of 20 for testing. For IFTA ≥ 25%, the AUCs in test cohort were 0.60, 0.59, and 0.54 for radiomic features only, clinical variables only, and a combined radiomic–clinical model, respectively. For IFTA ≥ 50%, the AUCs in training cohort were 0.89, 0.84, and 0.96, and in the test cohort, they were 0.82, 0.83, and 0.86, for radiomic features only, clinical variables only, and the combined radiomic–clinical model, respectively. Significance: An ML-based MRI radiomic algorithm showed promising discrimination capacity for IFTA > 50%, especially when combined with clinical variables. These results need to be confirmed in larger cohorts. [ABSTRACT FROM AUTHOR]

In Internal Radiotherapy, radiopharmaceutical dosimetry provides an accurate estimation of absorbed radiation doses to organs at risk and tumours. In this paper Velocity Theranostics (Varian Medical Systems), is investigated. Its performances are compared to OLINDA 2.0 in both an anthropomorphic phantom and a group of patients. Velocity Theranostics was evaluated with a cohort of patients (15) treated with 177Lu radiolabelled peptides. The absorbed doses were calculated for the liver, spleen and kidneys, separately with OLINDA 2.0 and Velocity Theranostics using the same set of images. To reduce the contribution of Time-integrated activities (TIAs) on the results and to merely compare the dose calculation algorithms, the OLINDA 2.0 absorbed doses were calculated using the TIA values calculated in Velocity Theranostics. The absorbed doses from Velocity Theranostics were found to be correlated with the doses from OLINDA 2.0 with the TIAs from Theranostics (Lin's coefficient = 0.894 and R2 = 0.9531). Absorbed doses from Velocity Theranostics are reliable at least as reliable as those for OLINDA 2.0, with many advantages regarding accuracy of calculations and robustness. In conclusion, the personalisation of dosimetry may be totally fulfilled by computational systems for absorbed dose in internal radiotherapy, equipped with a complete workflow and borrowed from external radiotherapy. [ABSTRACT FROM AUTHOR]

Aim: Machine learning (ML) and deep learning (DL) predictive models have been employed widely in clinical settings. Their potential support and aid to the clinician of providing an objective measure that can be shared among different centers enables the possibility of building more robust multicentric studies. This study aimed to propose a user-friendly and low-cost tool for COVID-19 mortality prediction using both an ML and a DL approach. Method: We enrolled 2348 patients from several hospitals in the Province of Reggio Emilia. Overall, 19 clinical features were provided by the Radiology Units of Azienda USL-IRCCS of Reggio Emilia, and 5892 radiomic features were extracted from each COVID-19 patient's high-resolution computed tomography. We built and trained two classifiers to predict COVID-19 mortality: a machine learning algorithm, or support vector machine (SVM), and a deep learning model, or feedforward neural network (FNN). In order to evaluate the impact of the different feature sets on the final performance of the classifiers, we repeated the training session three times, first using only clinical features, then employing only radiomic features, and finally combining both information. Results: We obtained similar performances for both the machine learning and deep learning algorithms, with the best area under the receiver operating characteristic (ROC) curve, or AUC, obtained exploiting both clinical and radiomic information: 0.803 for the machine learning model and 0.864 for the deep learning model. Conclusions: Our work, performed on large and heterogeneous datasets (i.e., data from different CT scanners), confirms the results obtained in the recent literature. Such algorithms have the potential to be included in a clinical practice framework since they can not only be applied to COVID-19 mortality prediction but also to other classification problems such as diabetic prediction, asthma prediction, and cancer metastases prediction. Our study proves that the lesion's inhomogeneity depicted by radiomic features combined with clinical information is relevant for COVID-19 mortality prediction. [ABSTRACT FROM AUTHOR]

Intraoperative cell salvage reduces the need for allogeneic blood transfusion in complex cancer surgery, but concerns about the possibility of it re-infusing cancer cells have hindered its application in oncology. We monitored the presence of cancer cells on patient-salvaged blood by means of flow cytometry; next, we simulated cell salvage, followed by leucodepletion and irradiation on blood contaminated with a known amount of EpCAM-expressing cancer cells, assessing also residual cancer cell proliferation as well as the quality of salvaged red blood cell concentrates (RBCs). We observed a significant reduction of EpCAM-positive cells in both cancer patients and contaminated blood, which was comparable to the negative control after leucodepletion. The washing, leucodepletion and leucodepletion plus irradiation steps of cell salvage were shown to preserve the quality of RBCs in terms of haemolysis, membrane integrity and osmotic resistance. Finally, cancer cells isolated from salvaged blood lose their ability to proliferate. Our results confirm that cell salvage does not concentrate proliferating cancer cells, and that leucodepletion allows for the reduction of residual nucleated cells, making irradiation unnecessary. Our study gathers pieces of evidence on the feasibility of this procedure in complex cancer surgery. Nevertheless, it highlights the necessity of finding a definitive consensus through prospective trials. [ABSTRACT FROM AUTHOR]

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. [ABSTRACT FROM AUTHOR]

Featured Application: This paper presents a deformable image registration-based method for the quality assurance of head and neck adaptive radiotherapy using digitally post-processed anthropomorphic phantom image datasets. One of the main findings of this work is that spatial and dose errors are a function of the magnitude of the deformation and of the gradient of the dose distribution. This emphasizes the importance of performing patient-specific deformable image registration verification and, consequently, the need to develop and make available tools that are for this purpose. Despite the availability of national and international guidelines, an accurate and efficient, patient-specific, deformable image registration (DIR) validation methodology is not yet established, and several groups have found an incompatibility of the various digital phantoms with the commercial systems. To evaluate the quality of the computed tomography (CT) and on-board cone-beam CT (CBCT) DIRs, a novel methodology was developed and tested on 10 head and neck (HN) patients, using CT and CBCT anthropomorphic HN phantom images, digitally reprocessed to include the common organs at risk. Reference DVFs (refDVFs) were generated from the clinical patient CT-CBCT fused images using an independent registration software. The phantom CT images were artificially deformed, using the refDVFs, and registered with the phantom CBCT images, using the clinical registration software, generating a test DVF (testDVF) dataset. The clinical plans were recalculated on the daily patient 'deformed' CTs, and the dose maps transferred to the patient-planning CT, using both the refDVF and testDVF. The spatial and dosimetric errors were quantified and the DIR performance evaluated using an established operative tolerance level. The method showed the ability to quantify the DIR spatial errors and assess their dose impact at the voxel level and could be applied to patient-specific DIR evaluation during adaptive HN radiotherapy in routine practice. [ABSTRACT FROM AUTHOR]

Simple Summary: Glioblastoma multiforme (GBM) is the most frequent primary malignant brain tumor, and despite advances in imaging techniques and treatment options, the outcome remains poor and recurrence is inevitable. Salvage therapy presents a challenge, and re-irradiation can be a therapeutic option in recurrent GBM. The decision-making process for re-irradiation is a challenge for radiation oncologists due to the expected toxicity of a second course of radiotherapy and the limited radiation tolerance of normal tissue; nevertheless, it is being increasingly used, as several studies have demonstrated its feasibility. The current study aimed to investigate the safety of moderate–high-voxel-based dose escalation radiotherapy in recurrent GBM patients after conventional concurrent chemoradiation. Twelve patients were enrolled in this prospective single-center study. Retreatment consisted of re-irradiation with a total dose range of 30–50 Gy over 5 days using the IMRT (arc VMAT) technique using dose painting planning. The treatment was well tolerated. No toxicities greater than 3 were recorded; only one patient had severe G3 acute toxicity, characterized by muscle weakness and fatigue. Median overall survival (OS2) and progression-free survival (PFS2) from the time of re-irradiation were 10.4 months and 5.7 months, respectively. Our phase I study demonstrated an acceptable tolerance profile of this approach, and the future prospective phase II study will analyze the efficacy in terms of PFS and OS. Glioblastoma multiforme (GBM) is the most aggressive astrocytic primary brain tumor, and concurrent temozolomide (TMZ) and radiotherapy (RT) followed by maintenance of adjuvant TMZ is the current standard of care. Despite advances in imaging techniques and multi-modal treatment options, the median overall survival (OS) remains poor. As an alternative to surgery, re-irradiation (re-RT) can be a therapeutic option in recurrent GBM. Re-irradiation for brain tumors is increasingly used today, and several studies have demonstrated its feasibility. Besides differing techniques, the published data include a wide range of doses, emphasizing that no standard approach exists. The current study aimed to investigate the safety of moderate–high-voxel-based dose escalation in recurrent GBM. From 2016 to 2019, 12 patients met the inclusion criteria and were enrolled in this prospective single-center study. Retreatment consisted of re-irradiation with a total dose of 30 Gy (up to 50 Gy) over 5 days using the IMRT (arc VMAT) technique. A dose painting by numbers (DPBN)/dose escalation plan were performed, and a continuous relation between the voxel intensity of the functional image set and the risk of recurrence in that voxel were used to define target and dose distribution. Re-irradiation was well tolerated in all treated patients. No toxicities greater than G3 were recorded; only one patient had severe G3 acute toxicity, characterized by muscle weakness and fatigue. Median overall survival (OS2) and progression-free survival (PFS2) from the time of re-irradiation were 10.4 months and 5.7 months, respectively; 3-, 6-, and 12-month OS2 were 92%, 75%, and 42%, respectively; and 3-, 6-, and 12-month PFS2 were 83%, 42%, and 8%, respectively. Our work demonstrated a tolerable tolerance profile of this approach, and the future prospective phase II study will analyze the efficacy in terms of PFS and OS. [ABSTRACT FROM AUTHOR]

The purpose of this multi-centric work was to investigate the relationship between radiomic features extracted from pre-treatment computed tomography (CT), positron emission tomography (PET) imaging, and clinical outcomes for stereotactic body radiation therapy (SBRT) in early-stage non-small cell lung cancer (NSCLC). One-hundred and seventeen patients who received SBRT for early-stage NSCLC were retrospectively identified from seven Italian centers. The tumor was identified on pre-treatment free-breathing CT and PET images, from which we extracted 3004 quantitative radiomic features. The primary outcome was 24-month progression-free-survival (PFS) based on cancer recurrence (local/non-local) following SBRT. A harmonization technique was proposed for CT features considering lesion and contralateral healthy lung tissues using the LASSO algorithm as a feature selector. Models with harmonized CT features (B models) demonstrated better performances compared to the ones using only original CT features (C models). A linear support vector machine (SVM) with harmonized CT and PET features (A1 model) showed an area under the curve (AUC) of 0.77 (0.63–0.85) for predicting the primary outcome in an external validation cohort. The addition of clinical features did not enhance the model performance. This study provided the basis for validating our novel CT data harmonization strategy, involving delta radiomics. The harmonized radiomic models demonstrated the capability to properly predict patient prognosis. [ABSTRACT FROM AUTHOR]

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. [ABSTRACT FROM AUTHOR]

Artificial intelligence (AI) is a branch of computer science dedicated to giving machines or computers the ability to perform human-like cognitive functions, such as learning, problem-solving, and decision making. Since it is showing superior performance than well-trained human beings in many areas, such as image classification, object detection, speech recognition, and decision-making, AI is expected to change profoundly every area of science, including healthcare and the clinical application of physics to healthcare, referred to as medical physics. As a result, the Italian Association of Medical Physics (AIFM) has created the "AI for Medical Physics" (AI4MP) group with the aims of coordinating the efforts, facilitating the communication, and sharing of the knowledge on AI of the medical physicists (MPs) in Italy. The purpose of this review is to summarize the main applications of AI in medical physics, describe the skills of the MPs in research and clinical applications of AI, and define the major challenges of AI in healthcare. [ABSTRACT FROM AUTHOR]