Intelligent Systems in Medical Imaging

Lecturer: Francesco Ciompi

Contents:

W1: Basic Techniques

W2: Segmentation (old techniques)

Suggested paper: Comparative study of retinal vessel segmentation methods on a new publicly available database

Paper:

W3: Introduction supervised learning

TODO Suggested reading: Lecun et al. - Gradient-Based Learning Applied to Document Recognition (only first pages)

ISMI-3a-Supervised_learning

W4: Convolutional Networks Basic Techniques

Suggested paper: ImageNet Classification with Deep Convolutional Neural Networks

W5: Convolutional networks (for segmentation)

Suggested papers:

W6: Object Detection using CNNs

Suggested papers:

Exam preparation

TODO: read some papers?

  • Be able to recognize different types of medical imaging problems
  • For those problems, be able to select appropriate techniques
  • Be able to name the amount of parameters for common layers, such as a convolution layer or dense layer.
  • Be able to quickly determine the output dimensions after common operations, such as convolution with a type of padding and stride
  • Understand which CNN parameters are data-driven and which are design choices