Search

Abstract Introduction Gadolinium-based T1-weighted MRI sequence is the gold standard for the detection of active multiple sclerosis (MS) lesions. The performance of machine learning (ML) and deep learning (DL) models in the classification of active and non-active MS lesions from the T2-weighted MRI images has been investigated in this study. Methods 107 Features of 75 active and 100 non-active MS lesions were extracted by using SegmentEditor and Radiomics modules of 3D slicer software. Sixteen ML and one sequential DL models were created using the 5-fold cross-validation method and each model with its special optimized parameters trained using the training-validation datasets. Models’ performances in test data set were evaluated by metric parameters of accuracy, precision, sensitivity, specificity, AUC, and F1 score. Results The sequential DL model achieved the highest AUC of 95.60% on the test dataset, demonstrating its superior ability to distinguish between active and non-active plaques. Among traditional ML models, the Hybrid Gradient Boosting Classifier (HGBC) demonstrated a commendable test AUC of 86.75%, while the Gradient Boosting Classifier (GBC) excelled in cross-validation with an AUC of 87.92%. Conclusion The performance of sixteen ML and one sequential DL models in the classification of active and non-active MS lesions was evaluated. The results of the study highlight the effectiveness of sequential DL approach and ensemble methods in achieving robust predictive performance, underscoring their potential applications in classifying MS plaques.

Introduction: Neutron contamination is likely caused by the collision of high-energy photon interactions (γ, ṉ) with heavy metals used in the construction of the accelerator. This study is essential to quantify the excess dose from neutron contamination by Elekta Precis. The main object is to assess the neutron contamination with a gas dosimeter containing He-3. Material and Methods: In this study, neutron contamination was estimated at different points in and out of the treatment room. We used two types of dosimeters: a He-3 gas dosimeter (CRAMAL 31) as a neutron dosimeter and Farmer ionization chambers, and PC-electrometer (Sun Nuclear, USA) which is sensitive to photons measured photo-neutron doses. Both the neutron and Farmer dosimeters were applied in the presence and absence of acrylic plates at the same point. In this study, Monte Carlo (MC) code was utilized to prepare the correct proportion of neutron dose. Results: At different points in and out of the treatment room, neutron contamination was approximately in the range of background dose (D = 0.001 µSv). The neutron dosimeter displayed 48.792 µSv, 25.456 µSv and 28.756 µSv for 6, 10 and 15 MV photon energy, respectively. He-3 gas dosimeter showed that the neutron dose net was negligible under the treatment field. Conclusion: He-3 gas dosimeter detected more than the usual neutron dose in 6 MV photon energy than we expected. Due to the high photon flux under the radiation fields, a He-3 neutron dosimeter reported photo-neutron dose. Nevertheless, the photo-neutron dose was in the range of micro Sievert (µSv). He-3 gas dosimeter was not suitable for neutron dosimetry in places with high photon fluence because of the low energy peak in the detection of neutrons.

Abstract The coronavirus disease 2019 (COVID-19) became the most spread and lethal disease in the last 3 years. Early predictions could optimize the decision-making process, healthcare outcomes, and effective usage of healthcare resources during peaks. This study set out to predict the mortality risk of COVID-19 patients by investigating 14 machine learning (ML) models using extensive clinical, laboratory, and image-based features. Additionally, feature importances in each model and the influences of features in the mortality prediction of ML models have been evaluated in this study. Data from 252 patients during the 5th peak of the COVID-19 pandemic (July 2021-September 2021) with 42 features were used for the training of ML models. Fourteen ML models were created using the fivefold cross-validation method. Each model was trained using a training-validation dataset with its own optimized parameters. The performance of models has been evaluated by metric parameters of accuracy, precision, sensitivity, specificity, AUC, and F1 score. The highest values of accuracy (87.30%), precision (100%), sensitivity (77.27%), specificity (100%), AUC (91.90%), and F1 score (77.99%) were observed for the linear discriminant analysis (LDA), K-Nearest Neighbors (KNN), Gaussian Naive Bayes (GNB), KNN, Passive Aggressive Classifier (PAC), and LDA models, respectively, when training was performed with all 42 features. By using feature selection techniques, the support vector classifier (SVC) model with 10 features showed the most AUC of 93.40%. The features of mechanical ventilation, consolidation, fatigue, malignancy, dry cough, level of consciousness (LOC), gender, diarrhea, O2 therapy, and SpO2 are potential predictors of mortality rates in COVID-19 patients.

Abstract Introduction: Free radicals generated by ionizing radiations, as a powerful cytotoxic agent, can damage DNA and proteins. Thymus vulgaris L (thyme) plant is a rich source of antioxidant phenolic compounds, which makes it a preferable candidate for medical applications. Given this, we set out the present study to investigate the effectiveness of thyme essential oil on human blood mononuclear cells (PBMCs) as a radioprotector agent against ionizing radiations. Materials and Methods: We extracted the thyme essential oil by the conventional Clevenger extraction method. Heparinized peripheral blood samples were also collected from five male volunteers, aged 22-25, without a history of smoking and irradiation. PBMCs were isolated and the maximum nontoxic concentrations (85µg/ml (of thyme essential oil were determined based on the result of the MTT method. In the next step, the PBMCs were cultured in the presence of thyme essential oil before and after X-irradiation with doses of 0.25 and 2.00 Gy. Results: The most radioprotective effect was observed in the dose of 2.00 Gy for thyme-treated cells 24 hours before the irradiation (p-value≤0.001) by a survival enhancement factor of 1.67, compared to the control group. Conclusion: Our results showed that thyme essential oil can be used as an effective radioprotector agent for PBMCs against ionizing radiations. The most radioprotective effect was observed in the presence of thyme essential oil during irradiation.

Introduction: Exquisite soft tissue contrast of magnetic resonance images (MRI) and the new combined radiotherapy system of MR-Linac have been the main impetus for applying MR imaging in radiotherapy. One limitation of MR-based radiotherapy is the geometric distortion of MR images that can generate errors in the contouring and dosimetry stages. This study aimed to evaluate and correct geometric distortion for radiotherapy applications. Material and Methods: A large field of view (FOV) phantom develop using Perspex sheets and 325 plastic pipes. The quantification and correction of MR images' system-related geometric distortion are conducted for HASTE protocol by MATLAB and 3D slicer software in phantom and patient images. The effect of MRI images geometrical distortion was evaluated for ten patients undergoing body radiotherapy treatment. CT images were used as a primary dataset to estimate the distortion map. Results: The phantom investigation results indicate that in radial distances of < 13 cm (or FOVs < 25 cm), the amount of distortion is under 2 mm. Still, at more considerable radial distances, distortion may increase up to about 3.5 cm. MR images of Patients with lateral (LAT) and anterior-posterior (AP) diameters of more than 38 cm and 25 cm respectively, need to be corrected for geometric distortion. Conclusion: MR images' geometric precision in large FOVs is not sufficient for MRI only treatment planning of radiotherapy and further corrections are required. The B-spline deformable registration method can correct the MR geometric distortion until an acceptable range of 2 mm for radiotherapy applications.

The application of nanotechnology in medicine involves using nanomaterials to develop novel therapeutic and diagnostic modalities. Given the unique physiochemical and optical properties of gold nanoparticle (GNP) such as good biocompatibility, nontoxic nature, surface properties and comparative stability, it has been widely studied in medicine, especially as a cancer theranostic agent. This review focuses on recent progresses in the field of gold nanostructures in cancer treatment and diagnosis. As far as cancer detection is concerned, several studies have indicated that GNPs can be used for X-ray, MR and optical imaging. With regard to cancer treatment, most studies have investigated the effect of GNPs in different treatment modalities like photothermal therapy, photodynamic therapy, sonodynamic therapy, drug delivery, and radiotherapy. In this paper, we have focused on reviewing the role of GNPs in improving radiotherapy efficiency as radiosensitizers. For optimization of parameters influencing the radiosensitization of GNPs, several studies have been undertaken in different scientific routes. We categorize these studies into three categories; Monte Carlo simulation, cellular studies and animal studies. Finally, according to findings reported by different researchers, the physical and biological mechanism of GNPs in generating radiosensitizing effect is discussed.

Aim of the study : The 57 Co radioisotope has recently been proposed as a hypothetical brachytherapy source due to its high specific activity, appropriate half-life (272 days) and medium energy photons (114.17 keV on average). In this study, Task Group No. 43 dosimetric parameters were calculated and reported for a hypothetical 57 Co source. Material and methods : A hypothetical 57 Co source was simulated in MCNPX, consisting of an active cylinder with 3.5 mm length and 0.6 mm radius encapsulated in a stainless steel capsule. Three photon energies were utilized (136 keV [10.68%], 122 keV [85.60%], 14 keV [9.16%]) for the 57 Co source. Air kerma strength, dose rate constant, radial dose function, anisotropy function, and isodose curves for the source were calculated and compared to the corresponding data for a 192 Ir source. Results : The results are presented as tables and figures. Air kerma strength per 1 mCi activity for the 57 Co source was 0.46 cGyh–1 cm 2 mCi–1. The dose rate constant for the 57 Co source was determined to be 1.215 cGyh–1U–1. The radial dose function for the 57 Co source has an increasing trend due to multiple scattering of low energy photons. The anisotropy function for the 57 Co source at various distances from the source is more isotropic than the 192 Ir source. Conclusions : The 57 Co source has advantages over 192 Ir due to its lower energy photons, longer half-life, higher dose rate constant and more isotropic anisotropic function. However, the 192 Ir source has a higher initial air kerma strength and more uniform radial dose function. These properties make 57 Co a suitable source for use in brachytherapy applications.