BME 5210 - Medical Imaging Systems

• Demonstrate an understanding of fundamental multi-dimensional systems and signals concepts
• Demonstrate an understanding of general image characteristics across various imaging modalities
• Demonstrate an understanding of physics fundamentals of various imaging modalities
• Demonstrate an understanding of how a basic x-ray radiography system works, and how images are created and analyzed
• Demonstrate an understanding of how a basic CT system works, and how images are created and analyzed
• Demonstrate an understanding of how a basic MRI system works, and how images are created and analyzed
• Demonstrate an understanding of how a basic ultrasound system works, and how images are created and analyzed
• Demonstrate an understanding of how basic nuclear medicine systems (e.g., PET and SPECT) work, and how images are created and analyzed.
• Demonstrate an understanding of fundamental image processing methodologies
• Proficiently apply fundamental image processing methodologies to medical images
• Proficiently apply MATLAB and Anatomage Table (or other modern computer-aided tools) to perform image analysis and visualization
• Critically evaluate published research in AI, machine learning, or data science applied to medical imaging, and communicate findings through written summaries and formal oral presentations
• Explain the foundational concepts of deep learning and convolutional neural network (CNN) architectures, as they apply to medical image analysis
• Select appropriate AI-enabled models for medical imaging tasks based on the characteristics of the imaging dataset and the intended application
• Implement AI-enabled image processing models on medical imaging datasets and document relevant model parameters, training configurations, and output metrics for quantitative performance assessment
• Evaluate the performance of AI models applied to medical images using appropriate metrics, and interpret results in terms of model accuracy, limitations, and fitness for a specific clinical application
• Assess the trustworthiness of AI-enabled medical imaging solutions by examining model explainability, transparency of decision-making, potential sources of bias, and the broader implications for clinical reliability and patient safety

• Linear and time-invariant systems
• Signal transformations
• Impulse response function and convolution
• Medical imaging phantom design

• Introduction to medical imaging systems and their development
• Fundamentals of multi-dimensional systems and signals
• Image characteristics and medical imaging data standards (DICOM and NIfTI)
• Fundamentals of image processing
• Medical imaging phantoms and their role in system evaluation
• X-ray radiography and angiography systems
• Computed tomography (CT) systems
• Magnetic resonance imaging (MRI) systems
• Ultrasound imaging systems
• Deep learning fundamentals
• AI-enabled applications in medical imaging

• Medical image visualization, display, and quantification
• Image processing and spatial-frequency analysis
• Image reconstruction and acquisition, including optical CT systems
• Image classification and segmentation
• AI-enabled medical image analysis and deep learning applications
• Phantom design, fabrication, and imaging-based quantification