|
Week - 1 |
Course Objective and Learning Outcomes; Digital Transformation in Healthcare, Research and Development; Basic Definitions: Computer vision, Medical data analysis, Machine Learning; Course Topics Summary. |
|
Week - 2 |
Computational Model Development Definition; Computational Model Development Tools:
Image processing, Computer Vision, Machine Learning, Probability and Statistics, Python, Anaconda, IDE Spyder; Data Analysis Libraries: NumPy, ScikitLearn, SciPy; Image Processing Libraries; Deep Learning Libraries: Keras, Tensorflow, Pytorch; Python Environment and Library Setup. |
|
Week - 3 |
Computational Model Development Stages; Clinical Problem Definition; Data Curation; Data Annotation; Model Training Strategies: Supervised learning, Conventional learning, Data-driven Approach; Model evaluation and performance metrics. |
|
Week - 4 |
Introduction to Deep Learning; Digital Neuron; Activation Function; Loss Function; Optimization; Deep Learning Software Platforms; Convolutional Neural Networks. |
|
Week - 5 |
Medical Data and Examples; Medical Data Types: Imaging data, Text data, Demographics, Categorical data, Numerical data; PACS- Picture Archiving Communication Systems; Electronic Medical Health Records; DICOM; Publicly Available Dataset Repositories; Data Curation; Missing, Insufficient and Imbalance Data; Data privacy. Suggested Readings and Assignment. |
|
Week - 6 |
Forms of Learning: Supervised learning, Semi-supervised, Transfer learning, Weakly supervised, Federated learning. |
|
Week - 7 |
Deep Learning Model Training; Preparing Data for Model Training: Resizing, Segmentation, Normalization, Split data, Augmentation; Model Creation; Hyperpameters; Overfitting and Underfitting; Overfit Mitigating Techniques; Stop Training. |
|
Week - 8 |
Medical Image Analysis Application: Classification; Example Applications. |
|
Week - 9 |
Medical Image Analysis Application: Segmentation; U-Net; Segmentation Metrics; Example Applications. |
|
Week - 10 |
Medical Image Analysis Application: Clinical Object Detection; Deep Learning Models: R-CNN, Yolo; Example Applications. |
|
Week - 11 |
Medical Image Analysis Application: Advanced Models; 3-Dimensional Data and Video Analysis; Deep Learning Models: Recurrent NN, Long short term memory; Example Applications. |
|
Week - 12 |
Multimodal Data Analysis; Multimodal Model Development; Merging Information from Multiple Sources and Modalities. |
|
Week - 13 |
Medical Model Interpretability; Model Interpretation Techniques: Occlusion, LIME Technique, CAM, Grad-CAM, Shapley Value, Suggested Readings. |
|
Week - 14 |
Course Project Presentations |
Eskisehir Technical University Info Package