The segmentation of the liver is a difficult process due to the changes in shape, border, and density that occur in each section in computed tomography (CT) images. In this study, the Adding Inception Module-Unet (AIM-Unet) model, which is a hybridization of convolutional neural networks-based Unet and Inception models, is proposed for computer-assisted automatic segmentation of the liver and liver tumors from CT scans of the abdomen. Experimental studies were carried out on four different liver CT image datasets, one of which was prepared for this study and three of which were open (CHAOS, LIST, and 3DIRCADb). The results obtained using the proposed method and the segmentation results marked by the specialist were compared with the Dice similarity coefficient (DSC), Jaccard similarity coefficient (JSC), and accuracy (ACC) measurement parameters. In this study, we obtained the best DSC, JSC, and ACC liver segmentation performance metrics on the CHAOS dataset as 97.86%, 96.10%, and 99.75%, respectively, of the AIM-Unet model we propose, which is trained separately on three datasets (LiST, CHAOS, and our dataset) containing liver images. Additionally, 75.6% and 65.5% of the DSC tumor segmentation metrics were calculated on the proposed model LiST and 3DIRCADb datasets, respectively. In addition, the segmentation success results on the datasets with the AIM-Unet model were compared with the previous studies. With these results, it has been seen that the method proposed in this study can be used as an auxiliary tool in the decision-making processes of physicians for liver segmentation and detection of liver tumors. This study is useful for medical images, and the developed model can be easily developed for applications in different organs and other medical fields.

The adverse effects of ionizing radiation are well known among researchers today. However, ionizing radiation is commonly used for diagnostic purposes in many medical imaging techniques. One of the most important devices used for diagnostic purposes is computed tomography (CT). It is vital to determine radiation doses, ensure patient safety, and minimize potential health risks.This study aims to determine the doses of radiation to the parotid glands and the spinal cord (C1-C2) region during computed tomography (CT) brain imaging. To achieve this goal, the exposure of these areas to different radiation levels was simulated and measured. This study contributes to the improvement of CT brain imaging procedures and the reduction of patients' radiation exposure risks. The Alderson Rando phantom was used for assessing radiation exposure. TLD-100 dosimeters were strategically placed in the spinal cord (C1/C2) region of the phantom's 6th section. The study was conducted at Istanbul University Cerrahpaşa Nuclear Medicine, and the Alderson Rando phantom was provided by the Department of Radiation Oncology. The evaluation of research findings was performed at the Çekmece Nuclear Research Center. The study revealed average doses of 4.585 mSv for the spinal cord (C1/C2) region, 5.425 mSv for the left parotid, and 5.29 mSv for the right parotid during CT imaging.

Background and Objectives: Quality assurance is an integral part of brachytherapy. Traditionally, radiographic films have been used for source position verification, however, in many clinics, computerized tomography simulators have replaced conventional simulators, and computerized radiography systems have replaced radiographic film processing units. With these advances, the problem of controlling source position verification without traditional radiographic films and conventional simulators has appeared. Materials and Methods: In this study, we investigated an alternative method for source position verification for brachytherapy applications. Source positions were evaluated using Gafchromic™ RTQA2 and EBT3 film and visually compared to exposed RTQA radiochromic film when using a Nucletron Oldelft Simulix HP conventional simulator and a Gammamed 12-i brachytherapy device for performance evaluation. Gafchromic film autoradiography was performed with a linear accelerator (LINAC) on-board imager (OBI). Radiochromic films are very suitable for evaluation by visual inspection with a LINAC OBI. Results: The results showed that this type of low-cost, easy-to-find material can be used for verification purposes under clinical conditions. Conclusions: It can be concluded that source-position quality assurance may be performed through a LINAC OBI device.

Objectives: This study aims to investigate the effect of full- and half-rotation angles on patient radiation dose and quantitative image quality in CBCT imaging of the head and neck region. Methods: A total of 67 TLDs were used for the dosimetry of 16 different regions in the head and neck slices of the anthropometric phantom. The Hyperion X9 Pro (MyRay, Cefla, Imola, Italy) CBCT device was used with a 90 kV pulsed beam and a 13x16e FOV size. Two separate imaging modes (Regular 360 0 and Quick 180 0) were tested, and the mA was determined by the software. Effective doses (EDs) were calculated using the coefficients recommended by ICRP 103 (2007). For the quantitative image quality tests, three VOIs were manually selected for three separate densities in image slices selected from the mandible, maxilla, and paranasal sinus regions of both volumes separately. Pixel values were averaged, and (SNR), contrast-to-noise ratio (CNR), and uniformity tests were conducted. Results: In 360 0, ED was calculated as 1.903 mSv and the highest absorbed dose was found in the oral mucosa (1.566 mSv). In 180 0, ED was calculated as 1.123 mSv and the highest absorbed dose was found in the right temporal squamous region (0.984 mSv). The reduction in ED was found to be 41% for full- and half-rotation angles. Quick/Regular ratios for SNR and CNR were changed between 0.83-0.91. Conclusion: The magnitude of reduction in ED was found to be higher than the quantitative image quality; however, the impact of this change on diagnosis should be analyzed according to the imaging purpose.