Title: Automated Segmentation and Classification of Zebrafish Histology Images for HighThroughput Phenotypi
1Automated 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
2The 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
3Zebrafish histology
Adult zebrafish (sagittal plane view) with
papilloma
Zebrafish larval array
hht mutant 7dpf (days post-fertilization)
4High-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?
5Current 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.
6Building on interdisciplinary expertise
Keith Cheng, MD, PhDZebrafish Functional Genomics
James Z. Wang, PhDContent-Based Image
Retrieval,Automatic Image Annotation
7SHIRAZ 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
8SHIRAZ 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
9Image 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)
10Example of wild-typeeye segmentation
11Example of mutant eye segmentation
12Eye 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
13Gut 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
14Classification 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)
15Preliminary Results
16Discussion 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
17Current 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)