Quantitative Big Imaging

Kevin Mader
17 March 2016

ETHZ: 227-0966-00L

Analysis of Single Objects

Course Outline

  • 25th February - Introduction and Workflows
  • 3rd March - Image Enhancement (A. Kaestner)
  • 10th March - Basic Segmentation, Discrete Binary Structures
  • 17th March - Advanced Segmentation
  • 24th March - Analyzing Single Objects
  • 7th April - Analyzing Complex Objects
  • 14th April - Spatial Distribution
  • 21st April - Statistics and Reproducibility
  • 28th April - Dynamic Experiments
  • 12th May - Scaling Up / Big Data
  • 19th May - Guest Lecture - High Content Screening
  • 26th May - Guest Lecture - Machine Learning / Deep Learning and More Advanced Approaches
  • 2nd June - Project Presentations

Literature / Useful References

  • Jean Claude, Morphometry with R
  • Online through ETHZ
  • Buy it
  • John C. Russ, β€œThe Image Processing Handbook”,(Boca Raton, CRC Press)
  • Available online within domain ethz.ch (or proxy.ethz.ch / public VPN)
  • Principal Component Analysis
    • Venables, W. N. and B. D. Ripley (2002). Modern Applied Statistics with S, Springer-Verlag
  • Shape Tensors
    • http://www.cs.utah.edu/~gk/papers/vissym04/
    • Doube, M.,et al. (2010). BoneJ: Free and extensible bone image analysis in ImageJ. Bone, 47, 1076–9. doi:10.1016/j.bone.2010.08.023
    • Mader, K. , et al. (2013). A quantitative framework for the 3D characterization of the osteocyte lacunar system. Bone, 57(1), 142–154. doi:10.1016/j.bone.2013.06.026

Previously on QBI ...

  • Image Enhancment
    • Highlighting the contrast of interest in images
    • Minimizing Noise
  • Segmentation
    • Understanding value histograms
    • Dealing with multi-valued data
  • Automatic Methods
    • Hysteresis Method, K-Means Analysis
  • Regions of Interest
    • Contouring
  • Machine Learning

Review of ROC

  • True Positive values in the ring that are classified as Foreground
  • True Negative values outside the ring that are classified as Background
  • False Positive values outside the ring that are classified as Foreground
  • False Negative values in the ring that are classified as Background

ROC Curve

  • Recall (sensitivity)= \( TP/(TP+FN) \)
  • Precision = \( TP/(TP+FP) \)

Reciever Operating Characteristic (first developed for WW2 soldiers detecting objects in battlefields using radar). The ideal is the top-right (identify everything and miss nothing)

Evaluating Models

Practical Example: Calcifications in Breast Tissue

While finding a ring might be didactic, it is not really a relevant problem and these terms are much more meaningful when applied to medical images where every False Positives and False Negative can be mean life-threatening surgery or the lack thereof. (Data courtesy of Zhentian Wang)