Over the last decade, there has been a notable and rapid advancement in artificial intelligence (AI), reflecting substantial progress in sophistication and problem-solving capabilities. This evolution has extended across various sectors, encompassing manufacturing, transportation, finance, education, and healthcare. Particularly noteworthy is AI's potential to drive progress in nuclear applications, science, and technology, raising ethical and legal considerations.
This academic paper, titled "AI in Nuclear Medical Applications: Challenges and Opportunities," undertakes a thorough exploration of the intricate relationship between AI and nuclear technology. Moving beyond a simple acknowledgment of AI's current capabilities, the paper delves into the nuanced landscape of challenges and opportunities within the realm of nuclear medical applications. It meticulously examines the ethical and legal dimensions inherent in this symbiotic relationship, emphasizing responsible and accountable utilization of AI in the nuclear domain.
The research focal point is the strategic deployment of AI capabilities in nuclear medicine, highlighting potential positive contributions to address contemporary challenges. From optimizing medical imaging methodologies to facilitating disease theranostics, the paper critically evaluates the transformative impact of AI on nuclear medical applications. By elucidating specific areas where AI has already demonstrated improvements, the research aims to provide a comprehensive understanding of the current landscape. Keywords include Artificial Intelligence, Radiomics, Radiotherapy, Medical Imaging, Radiopharmacy, and Disease Theranostics.

Purpose: Magnetic Resonance Imaging (MRI) can guide the surgical strategy to identify brain tumors and monitor treatment response. It is possible to use transcranial Ultrasound (US) for periodical follow-ups. Ultrasound waves pass through the delicate areas of the skull called acoustic windows. In this study, the efficiency of ultrasound imaging was performed to diagnose glioblastoma brain tumors and the results were compared with MR images.
Materials and Methods: Male Wistar rats were anesthetized by intraperitoneal injection of Ketamine and Xylazine. A stereotaxic device was used to determine the injection coordinates. C6 GBM cell lines were injected into the brains of rats. After two weeks, the formation of a glioblastoma tumor was confirmed histopathologically. The brain of animals was imaged by B-mode ultrasound and MRI. The section with the largest tumor dimensions was selected and the dimensions of the skull and tumor were measured based on the pixel size of each of the imaging methods. Pearson coefficient of correlation and Limits Of Agreement (LOA) were calculated for comparisons of the skull and tumor dimensions.
Results: The skull and the tumor dimensions showed a significant correlation between the B-mode ultrasound and the MRI measurements (R=0.99 and p<0.05). According to the Bland-Altman analysis, the mean difference was 0.31 mm (SD=0.20) for skull and tumor dimensions. The exact shape of the tumor is not completely clear in the ultrasound images, but it can be useful to detect the presence of the tumor and its approximate dimensions.
Conclusion: In conclusion, a glioblastoma tumor was produced in the male Wistar rat. The tumor dimensions were properly assessed by B-mode ultrasound image processing and compared with MR imaging.

Purpose: Independent Component Analysis (ICA) decomposition is a commonly used technique for eye blink artifact detection from Electroencephalogram (EEG) signals. Feature extraction from the decomposed ICs is a prime step for blink detection. This paper presents a new model of eye blink detection for ICA based approach, where the decomposed ICs are projected to their corresponding EEG segments (ReEEG), and feature extraction is performed on the ReEEG instead of the IC. ReEEG represents the eye blink activity more distinctly. Hence, ReEEG-based feature extraction is more potential in detecting eye blink artifacts than the traditional IC-based feature extraction.
Materials and Methods: This paper employs twelve EEG features to substantiate the superiority of ReEEG over IC. Support Vector Machine (SVM) is used as a classifier. A dataset, having 2638 clinical EEG epochs, is employed. All the considered twelve features are extracted from ReEEG and fed to SVM one at a time for blink detection. Then the obtained results are compared with an IC-based model with the same features.
Results: The comparison reveals the success of the proposed ReEEG-based blink detection approach over the traditional IC-based approach. Accuracy, precision, recall, and f1 scores are calculated as performance measuring metrics. For almost all features, ReEEG-based approach achieved up to 12.25% higher accuracy, 24.95% higher precision, 13.49% higher recall, and 12.89% higher f1 score than the IC-based traditional method.
Conclusion: The proposed model will be useful for researchers in dealing with the eye blink artifacts of EEG signals with more efficacy.

Purpose: The present study aims to assess the differences in the condyle position for two skeletal classes using Cone-Beam Computed Tomography (CBCT) reconstructions for both sides and genders.
Materials and Methods: In this cross-sectional descriptive study, the CBCT images of 96 patients (20-60 years) were assessed. The participants were divided according to their Angle malocclusion classifications (Angle Classes I and III). The variables of the Anterior-Posterior position of the Condyle (APC), condylar angle in the axial plane (ACA), the Lateral Position of the Condyle in the axial plane (LPC), the Vertical Position of the Condyle (VPC), condylar angle in coronal dimension (CCA), and the difference of APC and VPC on both sides were measured. The measurements were analyzed using a one‑way ANOVA and Tukey’s post hoc test.
Results: The variables of APC, LPC, ACA, VDC, and the difference of the APC on both sides in the two skeletal classes were similar. The VPC and CCA were greater in Class III than in Class I. All variables representing the 3D position of the condyle were similar in men and women, as well as on the right and left in both skeletal classes, I and III.
Conclusion: Based on the 3D evaluation results of the condylar position, the skeletal classes III and I differed in the VPC and CCA; however, for the rest variables, there were no statistical differences.

Purpose: This study aims to diagnose the severity of important pathological indices, i.e., fibrosis, steatosis, lobular inflammation, and ballooning from the pathological images of the liver tissue based on extracted features by radiomics methods.
Materials and Methods: This research uses the pathological images obtained from liver tissue samples for 258 laboratory mice. After preprocessing the images and data augmentation, a collection of texture feature sets extracted by gray-level-based algorithms, including Global, Gray-level Co-Occurrence Matrix (GLCM), Gray-level Run length Matrix (GLRLM), Gray-level Size Zone Matrix (GLSZM), and Neighboring Gray Tone Difference Matrix (NGTDM) algorithms. Then, advanced methods of classification, namely Support Vector Machine (SVM), Random Forest (RF), Quadratic Discriminant Analysis (QDA), K-Nearest Neighbors (KNN), Logistic Regression (LR), Naïve Bayes (NB), and Multi-layer Perceptrons (MLP) are employed. This procedure is provided separately for each of the four indices of fibrosis level in 6 grading classes, steatosis in 5 grading classes, inflammation in 4 grading classes, and ballooning in 3 grading classes. For a comparison of the output of these algorithms, the accuracy value obtained from the evaluation data is presented for the performance of different methods.
Results: The results showed that, compared to other methods, the Gaussian SVM algorithm provides a better response to the classification of the grading of liver disease among all the indices from the pathological images due to its structural features. This value of accuracy was calculated at 84.30% for fibrosis, 90.55% for steatosis, 81.11% for inflammation, and 95.98% for ballooning.
Conclusion: This fully automatic framework based on advanced radiomics algorithms and machine learning from pathological images can be very useful in clinical procedures and be considered as an assistant or a substitute for pathologists’ diagnoses.

Purpose: Visual-related abilities such as visual memory and visuo-constructional skills are among the cognitive abilities with fundamental importance for normal cognitive function, and its impairment is manifested in many neurological and psychiatric disorders. The present study aimed to generate normative data for the Benson Complex Figure Test (BCFT), a well-known simplified version of the Rey-Osterrieth Complex Figure Test, in Iran and to assess the effect of demographic variables of age, gender, and education on its various measures.
Materials and Methods: The present study was conducted in 2017-2018 as part of the Iranian Brain Imaging Database (IBID) project. The study sample consisted of 300 normal individuals in the age range of 20 to 70 years, with an equal number of participants and an equal proportion of genders in each age decade (# 60). Independent and dependent variables, respectively, were age (classified by five decades including 20-30 year olds, 31-40 year olds, 41-50 year olds, 51-60 year olds, and 61-70 year olds) and performance in the BCFT (defined in terms of 3 scores on copy, recall, and recognition of the geometric figure and 2 scores on time of copy and recall).
Results: The correlation matrix among the variables showed that age and education has a significant correlation with most the BCFT scores, while gender only has a significant correlation with recognition score. Multivariate analysis of variance showed the effect of age, gender, and their interaction on scores, while education did not make a significant difference in the BCFT scores. Also, the t-test showed a significant difference between men and women in recall and recognition, so that women and men showed better  performance in recall and recognition, respectively.
Conclusion: In summary, our results suggest that demographic variables of age, gender, and education affect visual memory and visuospatial abilities, and it is essential to generate normative data for research or clinical settings.

Purpose: In premenopausal women, abdominopelvic radiotherapy may have a direct and profound effect on ovarian function. Stabilized selenium Nanoparticles (NPs) with some natural materials have been demonstrated to have high antioxidant activity and reduce radiation damage as a radioprotector. This study was done to compare the ability for the biosynthesis of selenium NPs by Gum Arabic (Se-GA) and Polyanionic Cellulose (Se-PAC) in the protection of Chinese Hamster Ovary (CHO) cells against radiation damage.
Materials and Methods: First, Selenium Nanoparticles (SeNPs) were synthesized in the presence of GA and PAC. Then, CHO cells were cultured in-vitro and were randomly divided into six groups in different concentrations of Se-GA and Se-PAC to measure the biocompatibility of NPs. Finally, cells were treated with NPs and radiation (6MV, 2Gy), and the percentage of cell survival was determined by MTT assay. Both NPs with an average size of 20-30 nm and an absorption absorbance peak at about 300 nm using Ultraviolet-Visible (UV–Vis) spectroscopy.
Results: According to the parametric t-test analysis, Se-GA nanoparticles with a concentration higher than 0.4 ppm significantly increased the radioprotective effect on CHO cells compared to the control group (P<0.05). However, Se-PAC showed no significant increase in radioprotection in contrast to the control group (P>0.05).
Conclusion: Se-GA nanoparticles have antioxidant properties, and the radiation protection properties of Se-GA nanoparticles are significantly higher than control. Consequently, Se-GA nanoparticles showed promising results and may be able to play the role of a radioprotector.

Introduction: SPECT is reconstructed using iterative techniques incorporating photon attenuation correction based on the X ray transmission map and scatter correction. Since the quality of image in SPECT scans depends on the imaging parameters that are determined experimentally in the field of nuclear medicine, designing a dedicated scanning method for 99mTc/SPECT is need to improve the accuracy of disease diagnostic. Therefore, in this study with the aims of assessment and evaluation the effect of different filters on image quality, assessment of quality criteria on image before and after optimization and determine optimum algorithm for reconstruction on liver scanning using ^99m Tc for SPECT studies.
Material and Method: Filtered Back-projection reconstruction method had been used in liver scanning using ^99m Tc/EDDA/HYNIC-TOC for SPECT image and effect of different filters on SPECT imaging have been evaluated.
Results and Conclusion: Based on results, we suggest the Hamming filter to be used for visual analysis of Liver SPECT because of its ability to produce the high-quality image. Instead, the Butterworth filter is suggested for quantitative analysis because of its ability to balance between image quality and noise.

Purpose: Atrial Fibrillation (AF) is one of the most common types of heart arrhythmias observed in clinical practice. AF can be detected using an Electrocardiogram (ECG). ECG signals are time-varying and nonlinear in nature. Hence, it is very difficult for a physician to manually perform accurate and rapid classification of different heart rhythms.
Materials and Methods: In this paper, we propose a method using Discrete Wavelet Transform (DWT) with db6 as the basis function for denoising ECG signal.
Results: The denoised ECG is smoothened using the Savitzky- Golay filter. Deep learning methods, such as a combination of Convolutional Neural Network (CNN) and Long Short Term Memory (LSTM) (CNN-LSTM) and ResNet18 are used for the accurate classification of ECG signals using Physionet Challenge 2017 database.
Conclusion: With a 10-fold cross-validation method the model provided overall accuracy of 98.25% with the CNN-LSTM classifier.

Purpose: Designing an automated emotion recognition system using biosignals has become a hot and challenging issue in many fields, including human-computer interferences, robotics, and affective computing. Several algorithms have been proposed to characterize the internal and external behaviors of the subjects in confronting emotional events/stimuli. Eye movements, as an external behavior, are habitually analyzed in a multi-modality system using classic statistical measures, and the evaluation of its dynamics has been neglected so far.
Materials and Methods: This experiment intended to provide an innovative single-modality scheme for emotion classification using eye-blinking data. The dynamics of eye-blinking data have been characterized by weighted visibility graph-based indices. The extracted measures were then fed to the different classifiers, including support vector machine, decision tree, k-Nearest neighbor, Adaptive Boosting, and random subset to complete the process of classifying sad, happy, neutral, and fearful affective states. The scheme has been evaluated utilizing the available signals in the SEED-IV database.
Results: The proposed framework provided significant performance in terms of recognition rates. The highest average recognition rates of  > 90% were achieved using the decision tree.
Conclusion: In brief, our results showed that eye-blinking data has the potential for emotion recognition. The present system can be extended for designing future affect recognition systems.

Purpose: Generated free radicals by ionizing radiations, as powerful cytotoxic agents, 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 Peripheral 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.

Purpose: Parotidectomy is usually suggested for many persons with parotid gland tumors. Facial nerve weakening is the most concerning of the potential consequences related to parotidectomy, resulting in a significantly reduced patient quality of life. With preoperative preparation and surgical training and simulation, a three-dimensional (3D) printed human face anatomical model has just been designed and fabricated.
Materials and Methods: Fifteen surgeons from Iraqi teaching hospitals evaluated the simulator model by using a Likert scale survey. The model is composed of a silicon based human face replica with an incorporated parotid gland replica and a closed electrical circuit of the facial nerve course to show when contact is made between the surgical instrument and the nerve to provide feedback.
Results and Conclusion: All participants gave favorable feedback. Significant levels of satisfaction with the designed simulator have been relatively achieved. In comparison to experts, novice surgeons scored less for skin realism and handling. Such a difference suggests that the proposed simulator appears to have the potential to contribute to the advancement of surgical simulation, education, and planning.

Purpose: This study aimed to evaluate the lumbar annular tears prevalence regarding the patient’s history factors, and Magnetic Resonance Imaging (MRI) recorded data.
Materials and Methods: In this study, 218 patients (106 men and 112 women) were evaluated; 136 cases (63 men and 73 women, 20-80 years, mean: 45.4±14.8 years) with Lower Back Pain (LBP) and High-Intensity Zone (HIZ) were diagnosed based on MR images. The diagnosed annular tears from the MRI data, Body Mass Index (BMI, kg/m²), and physical activity of the patients were recorded, and the prevalence of lumbar annular tears was evaluated regarding the mentioned parameters.
Results: The prevalence of annular tears was 31.6% at L5/S1 (43/136 patients), 43.4% at L4/L5 (59/136 patients), 16.9% at L3/L4 (23/136 patients), 4.4% at L2/L3 (6/136 patients), and 3.7% at L1/L2 spinal disc space (5/136 patients). Most patients with annular tears had LBP (>60%). Based on the patient's history, 25% of patients had BMI above 30, 8.8% had post-traumatic history, 15.4% had a history of falling down, 19.1% had slipped down history, 16.2% were athletes, and 15.4% performed heavy work.
Conclusion: The prevalence of lumbar annular tears was higher in patients having LBP and a BMI over 30, which should be considered possible risk factors. This study demonstrated that annular tears are more likely to occur in lower lumbar discs, especially in L4/L5 and L5/S1 discs.

Purpose: The present study was designed to evaluate the potential efficacy of Multiparametric-Magnetic Resonance Imaging (MP-MRI) in the detection of prostate cancer locations compared to Transrectal Ultrasound (TRUS) guided biopsy, as the gold standard method.
Materials and Methods: A total of 66 subjects participated in this cross-sectional study. All individuals underwent MP-MRI imaging before the prostate TRUS. The findings of either method have been investigated and the comparison had been made using the Chi-squared test.
Results: The sensitivity and specificity of the MP-MRI in the diagnosis of prostate cancer were 81.8% and 93.9%, respectively. The positive and negative predictive values were 93.1% and 83.8%, respectively.
Conclusion: The current study indicates that the MP-MRI imaging method has sufficient sensitivity and specificity for detecting the location of prostate cancer and can potentially be employed as a clue-providing method prior to the TRUS-guided biopsy.

Purpose: Noise in brain Single Photon Emission Computed Tomography (SPECT) images limits an early diagnosis of Parkinson's Disease (PD). To overcome the limitation, as an image processing approach, wavelet transformation was used to denoising the images also with a segmentation method to differentiate the basal ganglia in brain SPECT.
Materials and Methods: The brain scans of the human XCAT phantom through the Simulating Medical Imaging Nuclear Detectors (SIMIND) simulated SPECT system were imported to the MATLAB toolkit for image processing. The reconstructed brain images by iterative reconstruction were de-noised through 9 methods of wavelet transformation at different levels, and then six segmentation methods were applied to differentiate the caudate and putamen. The Dice coefficient, Specificity, and Sensitivity evaluation criteria were calculated based on the adaptive thresholding of the selected images from segmentation. A ground truth image was manually marked by a clinical nuclear medicine specialist.
Results: The dice coefficient was obtained in a range from 0.3979 to 0.6299, as well as the specificity criterion from 0.7682 to 0.8168 and the sensitivity from 0.9049 to 0.9871.The results from adaptive threshold
segmentation and the evaluation criteria showed that the best levels of the nucleuses detectability were provided by level 7 of Biorthogonal, levels 4 and 7 of Coiflet, level 6 of Daubechies, level 5 of Haar, level 6 of Morlet and level 6 of Symlet methods.
Conclusion: Parkinson’s disease may be diagnosed in the early stage by an image processing approach to improve the quality of brain SPECT images.

Purpose: Medical professionals throughout the world prefer to use conventional stethoscopes to listen to respiratory sounds. Listening to respiratory sounds through stethoscopes is a subjective matter, and proper diagnosis of the disease depends on the skills and ability of the doctor. Computerized analysis of respiratory sounds can help doctors and researchers to characterize different abnormal respiratory patterns and make informed decisions.
Materials and Methods: This study includes previously reported work in different normal and abnormal respiratory sounds. The IEEE, PubMed, Google Scholar and Elsevier databases were searched and studies with the keywords of lung sound analysis, respiratory sound analysis, and respiratory sound classification were included. Detailed characteristics of normal and abnormal respiratory sounds are mentioned. In addition, Time-amplitude characteristics of different respiratory sound plots are obtained using MATLAB and ICBHI database. This study systematically discusses different approaches for respiratory sound analysis like visual analysis of the time-amplitude signals, frequency analysis, and spectral analysis using fast Fourier transform, statistical analysis, and machine learning approach. A list of relevant datasets is mentioned that can help researchers to do further analysis in this domain.
Results: The careful observations and analysis show the possibility of predicting respiratory diseases by extracting suitable parameters such as the frequency response and spectral characteristics of the signal. Power spectral density can help us to calculate the maximum, median frequency over an extended period. Using machine learning we can estimate the energy, entropy, spectral features, and wavelets of the signals.
Conclusion: Computer-based respiratory sound analysis can help medical professionals in making informed decisions. This will help in early diagnosis and devise effective treatment plans for the patients.

Purpose: Although ionizing radiation is useful in diagnosing various diseases, it can cause potential biological damage such as cancer, cataracts, and fetal damage for patients and staff working in radiology departments. Therefore, awareness and practice about the application of radiation protection are essential. This research aims to investigate radiology personnel's knowledge, attitude, and performance in the north and northeast of Iran regarding radiation protection.
Methods: This descriptive-analytical cross-sectional study was conducted using a 30-question questionnaire among 435 radiology personnel in North Khorasan, Razavi Khorasan, Golestan, and Mazandaran provinces. This questionnaire included questions related to demographic information and the level of knowledge, attitude, and performance of radiology personnel regarding radiation protection. Data analysis was also analyzed using SPSS-19 software.
Result: The participation rate of radiology personnel was 80.55%, and the mean and standard deviation of their knowledge, attitude, and performance regarding radiation protection were 45.9907±1.294, 78.1531±4.707, and 44.9368±6.88, respectively. Based on the results of the study, there is no significant relationship between gender and knowledge, attitude and performance of personnel (P=0.781, P=0.156, and P=0.87), but between education degree and attitude of personnel, between working years and expertise of personnel, and also between job title and philosophy, a significant relationship was observed between personnel (P=0.026, P=0.019, and P=0.003, respectively)
Conclusion: Based on the results of this study, it is suggested that employees with fewer years of work be encouraged to participate in radiation protection courses and workshops. It is also better to periodically consider training programs on radiation protection in in-service training for personnel.