Medical Imaging Technology
Permanent URI for this collection
Browse
Recent Submissions
- ItemA comparative study of SAR Distribution in patients undergoing MRI examinations at different field strengths and manufacturers(Al-Quds University, 2024-08-20) Mohammad Jamil Mahmoud Mdallal; محمد جميل محمود مدللThis study aims to assess and compare Specific Absorption Rate (SAR) levels, in patients undergoing MRI scans at 1.5 Tesla (1.5T) and 3 Tesla (3T) using Philips MRI systems. Additionally, it includes a comparison between 1.5 Tesla MRI systems from two industry manufacturers, Philips and Siemens. A cross-sectional prospective descriptive design was employed, involving 180 patients who underwent MRI scans at specified field strengths and manufacturer systems. The study was conducted at Al-Rahma Policlinic, Nablus, and Ibn Rushd Radiology Center, Hebron, West Bank, Palestine, from January to May 2024. SAR values were collected from MRI scan records and analyzed using statistical methods, including Mann-Whitney U tests and multiple regression analysis. The results demonstrated that Philips 3T systems exhibit significantly higher SAR values compared to Philips 1.5T systems, confirming that higher magnetic field strengths result in increased RF energy deposition. Additionally, Siemens 1.5T systems showed significantly higher SAR values than Philips 1.5T systems. differences in pulse sequence parameters, such as repetition time (TR), echo time (TE), and the number of slices, significantly affected SAR values, with longer TR and a higher number of slices associated with higher SAR. Lumbar MRI sequences generally exhibited higher SAR values compared to brain sequences. The study underscores the need for careful monitoring and optimization of MRI protocols to minimize SAR values, especially for high-field strength systems and different manufacturers' equipment. Continuous monitoring of SAR values and adherence to regulatory guidelines are essential to ensure patient safety during MRI scans.
- ItemTowards standardization and development of medical imaging protocols and referral requests in the Palestinian health system(Al-Quds University, 2024-03-18) Laith Abd AL-Fatah Shehdah Jaradat; ليث عبد الفتاح شحدة جرداتIntroduction : Medical imaging plays a pivotal role in healthcare, especially in the field of diagnostic radiology where imaging procedures are used to diagnose monitor, and follow-up diseases. In this process, medical imaging technologists (MIT) play a crucial role in assessing and evaluating patients' conditions, Diagnostic or interventional medical imaging procedures involve interconnected elements, wherein the clinical-anamnestic evaluation and justification for the examination provide essential information for therapy, Assigning protocols for authorized advanced medical imaging (CT, MRI, NM) is a vital but often overlooked task in medical imaging departments workflows, Acquiring additional clinical details, including allergy, laboratory, and medication information, is often complex, requiring multiple interactions across systems, In the Palestinian health system (Public, private, NGOs) hospitals and health centers, various medical imaging protocols are employed. The aim of the study: is to examine and evaluate protocols for advanced medical imaging services within the Palestinian health system due to the lack of a consistent standard across the country, Propose an initial standard criteria for advanced medical imaging procedures Method : In order to address the study's objectives, which highlight the absence of standardization in medical imaging protocols and referral requests within the Palestinian health system, the researcher developed a questionnaire comprising 35 items, The questionnaire items were categorized into three domains: Protocols of medical imaging services, Position of medical imaging technologist, and Referral Requests Protocols, A Quantitative Descriptive and Analytic Methodology used in this research, Following the collection of distributed questionnaires, the researcher processed the data for analysis, Respondents' answers to questionnaire items were recoded into numeric values, with a value of 1 assigned to "Yes," 2 to "No," and 3 to "Don’t know.“ and the target population of this study includes all radiologists and MITs working in the Palestinian health system, The study sample was randomly selected and consisted of 235 radiologists and MITs working in the Palestinian health system, most of whom were male (72.3%), while the percentage of females was (27.7%), Most participants in the study sample were medical imaging technicians (80.9%), only 6.4% were consultant radiologists and 12.8% were radiology residents. Result : The results revealed a deficiency in diagnostic and therapeutic standardized protocols for all procedures by 75.7%, Uniform implementation of protocols was not ensured, and deviations were not monitored, at a rate of 70.6%, No clear job description defining the roles and responsibilities of staff in managing image acquisition, and image quality accounting for 71.9%, The Medical Imaging Department lacks a Radiation Protection and Safety Officer (RSO) by 72.8%, Explanation and guidance on the imaging procedure were not provided to the service recipient before the procedure (65.1%), Patient safety lacks priority (65.5%), The quality of images is not verified by trained radiology and imaging staff,(65.5%), Safety checks before entering medical imaging procedures not consistently conducted (62.6%), Continuous monitoring of unconscious, or sedated service recipients during the procedure is not ensured (62.6%) and the referral request by the referring physician doesn’t include the relevant clinical information and history (68.5%), there is no a documented procedure for urgent and unexpected emergency patients (68.9%), billing information is not documented, or displayed, prior to the examination (68.1%), the referral request doesn’t include explanation for female safety (66.8%), Medical and treatment information was not linked to previous relevant clinical, laboratory, and radiological details in the referral report (65.1%). Conclusion: The findings of the current study indicate a significantly higher percentage of negative attitudes (No answers) towards referral request protocols in the Public Health sector (Medical Centers or Hospitals) compared to both NGOs, and Private sectors Recommendations : Standardizing medical imaging protocols within the Palestinian health system is recommended, along with ensuring consistent implementation of these protocols and monitoring for any deviations, It is suggested that referral requests include standardized criteria for patient information.
- ItemHybrid Artificial Intelligence Model for Prediction and Classification Across all Stages of Brain Ischemic Stroke in Non-enhanced Computerized Tomography Images(Al-Quds University, 2024-05-26) Ibraheem Bassam Ibraheem Qdaih; إبراهيم بسام إبراهيم قديحStroke is a major global health issue, resulting in significant mortality and disability among approximately 16 million people annually. Rapid response is crucial to mitigate brain damage and improve patient outcomes. Strokes, which are primarily categorized into ischemic and hemorrhagic types, vary in presentation and can be influenced by modifiable risk factors. In regions like Palestine, with limited economic resources, stroke is a prevalent cause of death. Diagnostic challenges are heightened by the limitations of brain non-enhanced CT (B-NECT) scans, which vary in effectiveness based on the stroke's stage. This study introduces a novel artificial intelligence-based framework, the Stroke Precision Enhancement Model (SPEM), which employs image processing, deep learning, and machine learning techniques to enhance the classification of ischemic stroke stages in B-NECT images. This real-time hybrid model integrates Contrast Limited Adaptive Histogram Equalization (CLAHE) for preprocessing, with feature extraction conducted through Densely Connected Convolutional Networks-121 (DenseNet-121). Classification is performed using Support Vector Machine (SVM), Random Forest (RF), and Logistic Regression (LR), with a focus on determining the most effective method based on various performance metrics. The results indicate exceptional performance of the SPEM, especially when combining DenseNet-121 with the LR classifier. Notably, in the hyper-acute stage, the model achieved an accuracy of 0.9957, a precision of 0.9914, and a remarkable Area Under the Receiver Operating Characteristic Curve (AUC) of 0.9999, with a processing time of just 0.04 seconds. Similar high performance was maintained across other stroke stages. These findings highlight the potential of this AI-enhanced model in facilitating faster and more accurate clinical decisions for early-stage stroke treatment. The hybrid model shows promise in predicting and classifying ischemic strokes and could significantly impact clinical practice upon further research, validation on larger datasets, enhanced interpretability, and integration into clinical workflows
- ItemA Hybrid Artificial Intelligence Approach for Early Detection of Breast Cancer and Classification from Mammogram Images in Palestine(Al-Quds University, 2024-05-26) Omar Faiq Sadeq Daraghmeh; عمر فايق صادق دراغمهBreast cancer is a significant global health concern, especially in Palestine, and early and accurate diagnosis is crucial for improving patient outcomes and survival rates. However, despite advancements in medical technology and screening techniques, missed diagnoses remain a persistent challenge in breast cancer detection. This study investigates the use of hybrid artificial intelligence (AI) models that combine deep learning and machine learning techniques to predict benign and malignant breast cancer from mammogram images. The study starts by utilizing pre-trained convolutional neural network models, namely VGG16 and DenseNet121, for feature extraction from mammogram images. These deep learning models have been trained on large datasets and have learned to identify various patterns and features within images. By extracting these features from mammograms, the models can capture important information that is relevant to the classification of breast cancer. The extracted features are then used to train several machine learning classifiers, including logistic regression, support vector machines, random forests, and gradient boosting models. These classifiers learn to recognize patterns and make predictions based on the extracted features. To evaluate the performance of the hybrid AI models, the study is conducted in three stages. In the first stage, the original mammogram images are used for classification. In the second stage, the mammogram images are enhanced using various image preprocessing and enhancement techniques. Finally, in the third stage, the models are tested on new mammogram images to assess their generalization capabilities. To enhance the mammogram images, several image processing techniques are applied. These include morphological erosion preprocessing, Contrast-Limited Adaptive Histogram Equalization (CLAHE), Laplacian of Gaussian (LoG) edge enhancement, and unsharp masking. These techniques aim to improve the visibility of important structures and features within the images, making it easier for the AI models to make accurate predictions. In the second stage, when predicting benign cases from the enhanced mammogram images, the logistic regression classifier with DenseNet121 features achieves remarkable performance. It achieves the highest accuracy of 0.991, precision of 0.996, F1-score of 0.989, and an AUC of 0.999. The support vector machine with DenseNet121 features also performs well, with an accuracy of 0.986 and an AUC of 0.999. The logistic regression model with VGG16 features demonstrates the fastest predictive time, requiring only 0.13 seconds. Similarly, in predicting malignant cases from the enhanced images, the logistic regression classifier with DenseNet121 features excels with the highest accuracy of 0.995, precision of 0.995, recall of 0.995, F1-score of 0.995, and an AUC of 0.999. The support vector machine with DenseNet121 features follows closely with an accuracy of 0.992 and an AUC of 0.998. The logistic regression model with VGG16 features maintains its fast predictive time, taking only 0.08 seconds. The study demonstrates that the enhanced mammogram images in the second stage consistently outperform the original and new test images in the first and third stages, respectively. This emphasizes the significant impact of image preprocessing and enhancement techniques on the predictive capabilities of the hybrid AI models. The findings highlight the potential of combining deep learning for feature extraction and machine learning for classification in achieving high accuracy, precision, recall, F1-scores, and AUC values for predicting breast cancer malignancy from mammogram images. In conclusion, the study demonstrates the potential of hybrid AI models that combine deep learning and machine learning techniques for the prediction of benign and malignant breast cancer from mammogram images. The integration of deep learning for feature extraction and machine learning for classification, along with image preprocessing and enhancement, results in improved accuracy and performance. These advancements have the potential to enhance breast cancer detection, ultimately leading to better patient outcomes and survival rates.
- ItemEvaluation of Radiation Dose for Pediatric Patients On Brain CT Scans as A Function of Protocol Used and Type of CT Device in The Palestinian Governmental Hospitals(Al-Quds University, 2024-01-06) Asala Mohamed Mahmoud Khalil; أصالة محمد محمود خليلMedical imaging, specifically computed tomography scans, plays a vital role in diagnosing and treating various medical conditions, such as brain tumors, lesions, and strokes. This is particularly beneficial in pediatric cases where it can aid in diagnosis and potentially save lives. However, its use also raises concerns about unnecessary radiation exposure. The purpose of this study is to evaluate the existence of local Diagnostic reference levels in Palestine, and to contribute to national efforts in building national DRLs. A multi-center retrospective cross-sectional analytical design was carefully chosen for achieving the study’s objectives. A suitable protocol data and dose reports contain information from Picture Archiving and Communication System (PACS) and Hospital Information System (HIS) were used to collect data in different hospitals of Palestine. A Microsoft Excel spreadsheet was used to analyze the collected data. Regarding the effect of types of protocols on the amount of patient dose, the results showed that all protocols were affected with the amount of patient dose but insignificant at the Dose Length Product. While regarding the effect of Equipment on the amount of patient dose, the results showed that all equipment models were insignificant with the amount of patient Computed Tomography Dose Index, Dose Length Product, (mAs and KVP). The findings showed that CT Dose Index vol and Dose Length Product values in the governmental hospitals were much higher than European Dose Length Product values, which proves that the governmental hospitals do not use a standardized pediatric brain CT protocol