Publications by authors named "S Czibor"
Article Synopsis
- The study aimed to validate a deep learning model for predicting treatment outcomes in diffuse large B-cell lymphoma patients across 5 clinical trials, comparing it to the international prognostic index (IPI) and radiomic models.
- The deep learning model, trained on PET/CT scans, demonstrated a higher predictive performance (AUC of 0.66) than IPI (AUC of 0.60) and performed well across all trials.
- While the deep learning and clinical PET models showed similar performance (AUC of 0.69), the PET model achieved the highest AUC (0.71), although the deep learning model provided outcomes without requiring tumor delineation.
Objectives: To investigate the prognostic value of clinical, volumetric, and radiomics-based textural parameters in baseline [ 18 F]FDG-PET/CT scans of diffuse large B-cell lymphoma (DLBCL) patients.
Methods: We retrospectively investigated baseline PET/CT scans and collected clinical data of fifty DLBCL patients. PET images were segmented semiautomatically to determine metabolic tumor volume (MTV), then the largest segmented lymphoma volume of interest (VOI) was used to extract first-, second-, and high-order textural features.
A 76-year-old man with hepatocellular carcinoma was referred for liver radioembolization. Given a prior left hemihepatectomy, it was clinically important to consider potentially irradiated healthy liver at planning. Thus, at the SPECT/CT imaging of the scout dose 166 Ho-microparticles before injected superselectively in the right hepatic artery, 99m Tc-mebrofenin was injected intravenously, and functional volumetry SPECT was performed simultaneously.
View Article and Find Full Text PDFThe staff of the Radiation Protection Service of a European clinical center measured the radiation dose by type-tested thermoluminescent dosemeter systems to which the medical staff was exposed, to assess the effectiveness of current procedures and equipment for optimalisation prompted by the requirements EU Basic Safety Standard 2013. There were three participating sites, the Site 1 was an external hospital, whereas Sites 2 and 3 are part of the same clinical center, who provided data regarding their personnel, from technologists, nurses and medical doctors. In this preliminary study, only a low number of cases were available and used to establish a new, more realistic yearly dose constraint, namely 6 (from two) mSv for whole-body effective dose, 15 (from two) mSv for eye lens dose and 300 (from 50) mSv for extremity dose.
View Article and Find Full Text PDF