Automated Segmentation and Classification of Zebrafish Histology Images for HighThroughput Phenotypi

1
Automated Segmentation and Classification of
Zebrafish Histology Images forHigh-Throughput
Phenotyping

• Brian Canada
• Academic Computing Fellow and PhD Candidate in
  Integrative Biosciences
• Jake Gittlen Cancer Research Institute Penn
  State College of Medicine
• October 22, 2007

2
The zebrafish (danio rerio) A powerful
functional genomics tool

• Vertebrate
• Develop tumors
• Hundreds of eggs per clutch
• Rapid, ex vivo development
• Most organ systems differentiated before 7 days
  post-fertilization
• Transparent embryos
• Reverse genetics
• Morpholinos for gene knock-down

3
Zebrafish histology
Adult zebrafish (sagittal plane view) with
papilloma
Zebrafish larval array
hht mutant 7dpf (days post-fertilization)
4
High-ThroughputZebrafish Histology
Embedding in agarose
Processing into paraffin
Sectioning, staining, mounting onto slides
Fixation
The rate-limiting step
Scanning
Scoring and Annotation
Digitization

• What can be done to improve the speed and
  reliability of scoring images?
• Can we score abnormalities quantitatively?

5
Current efforts in automated zebrafish image
analysis

• Stephen T.C. Wong and colleagues at Harvard
  developed methods for quantitative assessment of
  neuron loss and automated detection of somites
• In principle, such automated methods should be
  scalable to allow high-throughput phenotyping

Retinal cell detection for studying neurogenesis
Detection of Rohon-Beard sensory neurons
Liu T.L., A quantitative zebrafish phenotyping
tool for developmental biology and disease
modeling, IEEE Signal Processing Magazine, Jan
2007.
6
Building on interdisciplinary expertise
Keith Cheng, MD, PhDZebrafish Functional Genomics
James Z. Wang, PhDContent-Based Image
Retrieval,Automatic Image Annotation
7
SHIRAZ System for Histological Image
Retrievaland Annotation for Zoopathology

IPL_Compactness 9.8137 IPL_Eccentricity
0.9019 IPL_Solidity 0.3086 IPL_Contrast
0.9375 IPL_Homogeneity 0.0093 LENS_COMPACTNESS
1.1262 LENS_eccentricity 0.3530
?
?
?
ImagePre-processing
Creation ofVirtual Slides
Extract feature vector for each image
Image segmentation
?
Use feature database to train model for image
classification (K-means clustering,
Classification trees, Support Vector Machine,
etc.)
?
?
Automatically classify and annotate previously
uncharacterized images
Repeat for allimages in database
8
SHIRAZ System for Histological Image
Retrievaland Annotation for Zoopathology

• Prototype implemented in MATLAB for segmentation
  and classification of eye and gut images
• Eye and gut tissues have a polar or directional
  organization that is deformed or disrupted on
  mutation
• To our knowledge, we are the first group to
  publish material on automated zebrafish histology
  image analysis
• Canada, B.A., Thomas, G.K., Cheng ,K.C., Wang,
  J.Z., Automated Segmentation and Classification
  of Zebrafish Histology Images For High-Throughput
  Phenotyping, Proc IEEE-NIH Life Science Systems
  And Applications (LISSA) Workshop 2007

9
Image pre-processing
?
?
?
Manually crop eye and gut images from selected
larvae
Aperio T2 Scanner for Creation ofVirtual
Slides (120 slide capacity)
Take snapshot of selected HE-stained specimens
in ImageScope
?
To reduce computational costs, convert to
grayscale 512 x 512 matrix (pad with white
pixels if needed)
10
Example of wild-typeeye segmentation
11
Example of mutant eye segmentation
12
Eye feature extraction

• Seven moment invariants
• Four gray level co-occurrence features
• Contrast
• Correlation
• Energy
• Homogeneity

• Filled area
• Perimeter
• Compactness
• Eccentricity
• Extent
• Solidity
• Fractal dimension

Yields vector of 92 features per eye image
13
Gut segmentationand feature extraction

• 30 features extracted per gut image, e.g.
• Thickness and shape of the epithelial lining
• Polarity of the epithelial cells (position of
  nuclei relative to basement membrane)
• Number of distinct villi (folds) of the lumen
• Amount and granularity of cellular debris and
  mucous in lumen

Epithelial lining
Lumen
Cell nuclei
14
Classification algorithm CART (Classification
And Regression Trees)

• Advantages
• White-box model
• Helps provide a sense of objectivity and
  direction to histological assessment
• Disadvantages
• May not be as accurate as other classification
  methods (e.g. SVM, GMM, ANN)
• Splits can only be performed on one dimension
  at a time (not really a problem in this case)

15
Preliminary Results
16
Discussion and Conclusions

• Preliminary results are encouraging
• Potential opportunities for improvement
• Analyze different larval ages separately
• Improve segmentation accuracy
• Use color images instead of grayscale
• Experiment with different classifiers (SVM, for
  example)
• Minimize manual preprocessing
• Increase overall size of datasets
• Future
• Direct integration into laboratory pipeline
• Parallel image processing for higher throughput
• Automatic image annotation and retrieval

17
Current collaborators

• Georgia Thomas, Graduate Student
• Keith Cheng, co-PI (Functional Genomics)
• James Z. Wang, co-PI (Info Science Tech)
• Prof. Yanxi Liu (PSU Computer Science dept.)
• Prof. Nancy Hopkins (MIT)