Sharif Digital Repository

Small animal SPECT imaging systems have a broad application in developing new diagnostic or therapeutic radiopharmaceutical and biomedical researches. The main goal of this imaging method is to determine distribution tendency and amount of radio pharmaceutics in body. In this study we have developed a reconstruction technique along with photon attenuation correction so as to obtain a high quality image and the finding a relationship between image matrix and absorbed radioisotope in tissues in order to quantify SPECT images with acceptable error range. In this research we have used MLEM method for image reconstruction and the obtained images were evaluated from quantitative and qualitative... 

Cerebral palsy is a disorder and a condition that occurs before, during or after birth. According to reports, in developing countries, out of every 1,000 births, 3.5 cases develop cerebral palsy. One of the consequences of cerebral palsy is unusual walking due to nerve disorders, including severe spasm of the lower muscles of the trunk. Drugs, therapies, and orthopedic surgeries are used to help patients with cerebral palsy. Improper orthopedic surgeries have severe effects on the patient's function. You can partially solve these problems by using the gateway category. The common patterns of cerebral palsy gait help decide the treatment method. In recent years, the use of gait analysis has... 

Question Answering (QA) systems have reached human-level accuracy; however, these systems are vulnerable to adversarial examples. Recently, adversarial attacks have been widely investigated in text classification. However, there have been few research efforts on this topic in QA systems. In this thesis our approach is improving the robustness of QA systems using deep neural networks. In this thesis, as the first proposed approach, the knowledge distillation method is introduced to create a student model to improve the robustness of QA systems. In this regard, the pre-trained BERT model was used as a teacher, and its impact on the robustness of the student models on the Adversarial SQuAD... 

Objective: Accurate quantification in PET imaging is essential for proper evaluation and requires attenuation and scatter correction. Typically, this correction is performed using CT; however, the propagation of CT image errors to PET, the additional radiation dose in PET/CT, especially in pediatric cases and repeated scans, as well as challenges associated with standalone PET and PET/MRI, highlight the need for alternative approaches. This study investigates the capability of deep learning in jointly correcting attenuation and scatter for PET images with different radiotracers. Methods: Various neural network models, including ResNet, U-Net, and swin UNETR, were trained for direct...