Machine Learning for Medical Image Analysis
Under development
Course Description
This is a senior computer science course that aim to introduce the use of machine learning methods in medical image analysis. The course include theoretical basics that required for deep understanding of machine learning concepts and practical implementation in different medical image applications.
Course outline:
Lecture#01: Basics of machine learning, linear algebra, supervised, unsupervised and reinforcement learning methods
Lecture#02: Bayesian statistics, Maximum likelihood estimation, MAP estimation
Lecture#03: Classifiers, logistic regression, SVM, K-NN
Lecture#04: Medical imaging applications and data representation
Lecture#05: Data representation (2/3/4D) and manupilation
Lecture#06: Principal Component Analysis
Lecture#07: Convolutional Neural Networks
Lecture#08: RNN and LSTM
Lecture#09: Generative Adversarial Networks (GAN)
Lecture#10: Tutorial: AlexNet, ResNet, GoogleNet, DensNet, etc...
Lecture#11: Applications of medical image segmentation
Lecture#12: Applications of tomographic imaging
Lecture#02: Bayesian statistics, Maximum likelihood estimation, MAP estimation
Lecture#03: Classifiers, logistic regression, SVM, K-NN
Lecture#04: Medical imaging applications and data representation
Lecture#05: Data representation (2/3/4D) and manupilation
Lecture#06: Principal Component Analysis
Lecture#07: Convolutional Neural Networks
Lecture#08: RNN and LSTM
Lecture#09: Generative Adversarial Networks (GAN)
Lecture#10: Tutorial: AlexNet, ResNet, GoogleNet, DensNet, etc...
Lecture#11: Applications of medical image segmentation
Lecture#12: Applications of tomographic imaging
Labs are considered four main parts:
- Basics of Python
- Tensorflow and Pytorch
- ImageJ
- Small project for medical image analysis using machine learning
Reference Books
- Goodfellow, I., Bengio, Y., Courville, A., & Bengio, Y. (2016). Deep learning (Vol. 1, p. 2). Cambridge: MIT press. (available online here)
