Zoltán Bálint

3D printing enables accurate physical models for surgical planning, education, and research, while computed tomography (CT) remains a primary modality for visualizing internal structures. This study evaluated the fidelity of 3D-printed replicas of a chicken bone. High-resolution CT scans were processed with 3D Slicer and UltiMaker Cura, and six replicas were produced with four printers spanning Fused Deposition Modeling (FDM) and Stereolithography (SLA). Replicas and the original bone were scanned together across eight studies with varied parameters, reconstructed with BONE and STD kernels, and compared through Hounsfield Unit (HU) analysis. A biocompatible ABS closely matched real bone in HU, indicating high radiodensity fidelity, whereas a hollow resin replica approached air-equivalent values. The results confirm 3D printing’s potential for medical training and anatomical models and highlight the importance of careful material and parameter selection.

Objectives: Our aim was to determine imaging-derived parameters from echocardiography associated with the presence of atrial fibrosis in a cohort of atrial fibrillation (AF) patients. Methods: Initially, 123 participants were included in this prospective cross-sectional observational study (clinicaltrials.gov: NCT03584126); after exclusion criteria, 112 full datasets were analyzed. All participants underwent clinical evaluation, echocardiography, and cardiac MRI. Overall, 29 patients with AF and left atrial (LA) fibrosis at MRI, 37 with AF and without LA fibrosis at MRI, and 46 healthy controls were included in the final database. Results: The cardiac structural parameters as assessed by MRI were not significantly different between AF patients with and without fibrosis, apart from LA volume. The area under the curve (AUC) reached a value of 0.69 when using body-surface-area-indexed LA volume (LAVi) determined by echocardiography as a factor associated with LA fibrosis in AF patients. Moreover, when detecting LA fibrosis using LAVi, an optimal cut-off value of 42.7 mL/m² was obtained, resulting in 41.67% specificity and 88.46% sensitivity with a total accuracy of 65.06%. Testing BSA-indexed left ventricular mass (LVMi) as a factor associated with LA fibrosis, the optimal cut-off value was 140.2 g/m², with 76.92% sensitivity, 58.33% specificity and 67.62% total accuracy for the discrimination between AF patients with and without LA fibrosis. A strong association between body-surface-area-indexed left atrial volume (LAVi) and the presence of atrial fibrillation was identified (54.5 mL/m² vs. 29.8 mL/m² in controls, p-value < 0.0001). Conclusion: LA volume indexed to BSA could be a promising tool for the identification of cardiac fibrosis in AF patients.

3D-printed boluses in radiation therapy are of increasing interest for enhancing treatment precision and patient comfort. A comprehensive clinical validation of these boluses remains to be established. This study aims to confirm the effectiveness of a 3D-printed bolus through a proof-of-concept comparative validation, by implementing in a clinical setting a bolus made of PLA and designed to ensure uniform dose coverage for a case in the eye region. In this study the 3D-printed bolus was compared to two commercially available boluses (one thermoplastic and one skin type) by using a refecence where no bolus was present (with the optimal dose distribution scenario). All boluses were placed on an anthropomorphic head phantom and BeOSL detectors were used to measure dose values to determine the level of their effectiveness on delivery. During the scanning process, a thermoplastic mask was used to prevent bolus movement and to accurately reproduce clinical scenarios. Differences in dose values at D_max and D_50% revealed the performance of each bolus. The treatment planning system (TPS) and BeOSL readings for the 3D printed bolus were within 2% (the clinical tolerance), with 0.66% dose difference for the customized 3D-printed bolus. Although the thermoplastic bolus had the closest value to the detector reading, with a score of 0.30%, this result was influenced by improper shaping of the bolus on the phantom and the presence of a wide air gap, which caused lack of eye covering. Whereas, the skin bolus, due to higher volume of air between phantom surface and bolus, showed a 1.29% dose difference between the TPS values and the OSL detector readings. We provide a comparative validation for the use of 3D printed boluses and highlight that proper bolus fitting is essential in clinical settings to avoid air gaps and to maintain dose distribution over multiple treatment sessions.

Introduction: Magnetic resonance imaging (MRI) is conventionally used for the detection and diagnosis of multiple sclerosis (MS), often complemented by lumbar puncture—a highly invasive method—to validate the diagnosis. Additionally, MRI is periodically repeated to monitor disease progression and treatment efficacy. Recent research has focused on the application of artificial intelligence (AI) and radiomics in medical image processing, diagnosis, and treatment planning.Methods: A review of the current literature was conducted, analyzing the use of AI models and texture analysis for MS lesion segmentation and classification. The study emphasizes common models, including U-Net, Support Vector Machine, Random Forest, and K-Nearest Neighbors, alongside their evaluation metrics.Results: The analysis revealed a fragmented research landscape, with significant variation in model architectures and performance. Evaluation metrics such as Accuracy, Dice score, and Sensitivity are commonly employed, with some models demonstrating robustness across multi-center datasets. However, most studies lack validation in clinical scenarios.Discussion: The absence of consensus on the optimal model for MS lesion segmentation highlights the need for standardized methodologies and clinical validation. Future research should prioritize clinical trials to establish the real-world applicability of AI-driven decision support tools. This review provides a comprehensive overview of contemporary advancements in AI and radiomics for analyzing and monitoring emerging MS lesions in MRI.

Background: Prostate cancer (PCa) is the most frequent neoplasia in the male population. According to the International Society of Urological Pathology (ISUP), PCa can be divided into two major groups, based on their prognosis and treatment options. Multiparametric magnetic resonance imaging (mpMRI) holds a central role in PCa assessment; however, it does not have a one-to-one correspondence with the histopathological grading of tumors. Recently, artificial intelligence (AI)-based algorithms and textural analysis, a subdivision of radiomics, have shown potential in bridging this gap. Objectives: We aimed to develop a machine-learning algorithm that predicts the ISUP grade of manually contoured prostate nodules on T2-weighted images and classifies them into clinically significant and indolent ones. Materials and Methods: We included 55 patients with 76 lesions. All patients were examined on the same 1.5 Tesla mpMRI scanner. Each nodule was manually segmented using the open-source 3D Slicer platform, and textural features were extracted using the PyRadiomics (version 3.0.1) library. The software was based on machine-learning classifiers. The accuracy was calculated based on precision, recall, and F1 scores. Results: The median age of the study group was 64 years (IQR 61–68), and the mean PSA value was 11.14 ng/mL. A total of 85.52% of the nodules were graded PI-RADS 4 or higher. Overall, the algorithm classified indolent and clinically significant PCas with an accuracy of 87.2%. Further, when trained to differentiate each ISUP group, the accuracy was 80.3%. Conclusions: We developed an AI-based decision-support system that accurately differentiates between the two PCa prognostic groups using only T2 MRI acquisitions by employing radiomics with a robust machine-learning architecture.

Introduction: Prostate magnetic resonance imaging (MRI) has been recently integrated into the pathway of diagnosis of prostate cancer (PCa). However, the lack of an optimal contrast-to-noise ratio hinders automatic recognition of suspicious lesions, thus developing a solution for proper delimitation of the tumour and its separation from the healthy parenchyma, which is of primordial importance. Methods: As a solution to this unmet medical need, we aimed to develop a decision support system based on artificial intelligence, which automatically segments the prostate and any suspect area from the 3D MRI images. : We assessed retrospective data from all patients diagnosed with PCa by MRI-US fusion prostate biopsy, who underwent prostate MRI in our department due to a clinical or biochemical suspicion of PCa (n=33). All examinations were performed using a 1.5 Tesla MRI scanner. All images were reviewed by two radiologists, who performed manual segmentation of the prostate and all lesions. A total of 145 augmented datasets were generated. The performance of our fully automated end-to-end segmentation model based on a 3D UNet architecture and trained in two learning scenarios (on 14 or 28 patient datasets) was evaluated by two loss functions. Results: Our model had an accuracy of over 90% for automatic segmentation of prostate and PCa nodules, as compared to manual segmentation. We have shown low complexity networks, UNet architecture with less than five layers, as feasible and to show good performance for automatic 3D MRI image segmentation. A larger training dataset could further improve the results. Conclusion: Therefore, herein, we propose a less complex network, a slim 3D UNet with superior performance, being faster than the original five-layer UNet architecture.

(1): Background: With the recent introduction of vesical imaging reporting and data system (VI-RADS), magnetic resonance imaging (MRI) has become the main imaging method used for the preoperative local staging of bladder cancer (BCa). However, the VI-RADS score is subject to interobserver variability and cannot provide information about tumor cellularity. These limitations may be overcome by using a quantitative approach, such as the new emerging domain of radiomics. (2) Aim: To systematically review published studies on the use of MRI-based radiomics in bladder cancer. (3) Materials and Methods: We performed literature research using the PubMed MEDLINE, Scopus, and Web of Science databases using PRISMA principles. A total of 1092 papers that addressed the use of radiomics for BC staging, grading, and treatment response were retrieved using the keywords “bladder cancer”, “magnetic resonance imaging”, “radiomics”, and “textural analysis”. (4) Results: 26 papers met the eligibility criteria and were included in the final review. The principal applications of radiomics were preoperative tumor staging (n = 13), preoperative prediction of tumor grade or molecular correlates (n = 9), and prediction of prognosis/response to neoadjuvant therapy (n = 4). Most of the developed radiomics models included second-order features mainly derived from filtered images. These models were validated in 16 studies. The average radiomics quality score was 11.7, ranging between 8.33% and 52.77%. (5) Conclusions: MRI-based radiomics holds promise as a quantitative imaging biomarker of BCa characterization and prognosis. However, there is still need for improving the standardization of image preprocessing, feature extraction, and external validation before applying radiomics models in the clinical setting.