Go to login Go to sub menu Go to text

Course summary

  • Type MOOC course
  • Period Always open
  • Learning Time Study freely
  • Course approval method Automatic approval
  • Certificate Issue Online
http://www.edwith.org/medical-20200327
둘러보기
Thumb up 615 Learner 1598

Instructor Introduction

  • DGIST 박상현 교수

    - DGIST 로봇공학과 조교수 (2017.02~)
    - 스탠포드연구센터 (SRI International) 포닥 (2016.03~2017.02) 
    - 노스캐롤라이나 대학 (UNC at Chapel Hill) 포닥 (2014.03~2016.02) 
    - 서울대학교 전기컴퓨터공학부 박사 (2008.03~2014.02)

    https://sites.google.com/view/mispl/members/professor

Lecture plan

강의목록
  1. 1. Introduction to medical image analysis
    1. 1.Overview
    1. 2.Introduction to medical image analysis 1
    1. 3.Introduction to medical image analysis 2
    1. 4.PACS/DICOM/Visualization
    1. 5.Image acquisition
    1. 6.X-ray / CT / PET
    1. 7.Magnetic Resonance Imaging (MRI)
    1. Quiz 1
  2. 2. Medical image classification(1)
    1. 1.Introduction to medical image classification
    1. 2.Linear Regression
    1. 3.Logistic Regression
    1. 4.Neural Network
    1. 5.Image Classification
    1. 6.Medical image classification
    1. 7.Classification with demographic scores
    1. Quiz 2
  3. 3. Medical image classification(2)
    1. 1.Property of Deep Neural Network
    1. 2.Convolution
    1. 3.Convolutional Neural Network (CNN)
    1. 4.Advanced CNNs (LeNet, AlexNet, VGG)
    1. 5.Advanced CNNs (ResNet, InceptionNet, DenseNet)
    1. 6.3D CNN with demographic scores
    1. Quiz 3
  4. 4. Medical image classification(3)
    1. 1.Overall procedure
    1. 2.Validation
    1. 3.Overfitting / Regularization
    1. 4.Transfer Learning
    1. 5.Data Augmentation
    1. 6.Evaluation of classification model
    1. 7.Evaluation of classification model (Multi-label)
    1. Quiz 4
  5. 5. Medical image classification(4)
    1. 1.Feature selection using L1 regularization
    1. 2.Feature selection using Entropy / Mutual information
    1. 3.Feature extraction using Deep Learning
    1. 4.Class Activation Map
    1. 5.Weekly supervised learning
    1. 6.Multiple instance learning
    1. Quiz 5
  6. 6. Medical image segmentation(1)
    1. 1.Introduction to medical image segmentation
    1. 2.Otsu thresholding
    1. 3.Morphological processing
    1. 4.Region growing / Watershed algorithm
    1. 5.Segmentation using graph model
    1. 6.Graph cut optimization
    1. Quiz 6
  7. 7. Medical image segmentation(2)
    1. 1.Active Contour Model
    1. 2.Atlas based method / Label fusion
    1. 3.Segmentation via learning based method
    1. 4.Principle Component Analysis (PCA)
    1. 5.Active shape model
    1. 6.Segmentation using classifier
    1. Quiz 7
  8. 8. Medical image segmentation(3)
    1. 1.Fully Convolution Network(FCN)
    1. 2.U-net
    1. 3.Dilated Convolution
    1. 4.DeepLab V3+
    1. 5.Segmentation using 3D CNN
    1. 6.Loss Function
    1. 7.Segmentation Metric
    1. Quiz 8
  9. 9. Medical image Enhancement(1)
    1. 1.Introduction to medical image enhancement
    1. 2.Intensity normalization
    1. 3.Histogram equalization
    1. 4.Histogram Matching
    1. 5.Spatial Filtering
    1. 6.Anisotropic diffusion filtering
    1. 7.Vessel enhancement filtering
    1. Quiz 9
  10. 10. Medical image Enhancement(2)
    1. 1.Filtering in frequency domain
    1. 2.Filtering in 2D frequency domain
    1. 3.Spatial domain vs Frequency domain
    1. 4.Non-Local Mean denoising
    1. 5.Denoising with Dictionary
    1. 6.Dictionary Learning
    1. 7.Super-resolution via dictionary learning
    1. Quiz 10
  11. 11. Medical image Enhancement(3)
    1. 1.SRCNN
    1. 2.Upsampling strategy
    1. 3.Deep networks for super resolution
    1. 4.Generative Adversarial Network(GAN)
    1. 5.SRGAN
    1. 6.CNN for medical image enhancement
    1. 7.Enhancement metric
    1. Quiz 11
  12. 12. Medical image registration(1)
    1. 1.Introduction to medical image registration
    1. 2.Overview
    1. 3.Transformation Matrix in 2D
    1. 4.Transformation Matrix in 3D
    1. 5.Backward warping
    1. 6.Interpolation
    1. 7.Similarity measure – SSD, SAD, NCC
    1. 8.Similarity measure – Mutual information
    1. Quiz 12
  13. 13. Medical image registration(2)
    1. 1.Registration types
    1. 2.Registration using main axis
    1. 3.Iterative Closest Point (ICP)
    1. 4.Nonrigid registration via ICP
    1. 5.Nonrigid registration via B-spline
    1. 6.Nonrigid registration via deformable model
    1. Quiz 13
  14. 14. Medical image registration(3)
    1. 1.Optical flow / FlowNet
    1. 2.Data augmentation for optical flow
    1. 3.3D image registration via CNN
    1. 4.Spatial Transformer Network
    1. 5.3D image registration via unsupervised learning
    1. 6.Registration metric
    1. Quiz 14
  15. 강의평가
    1. 강의평가