raising the digital standard frank a. voelker, dvm, dacvp flagship biosciences pathology visions:...

47
Raising the digital standard Frank A. Voelker, DVM, DACVP Flagship Biosciences Pathology Visions: Approaches to Tissue-based Image Analysis in Pharmaceutical Research and Development

Upload: scarlett-james

Post on 23-Dec-2015

217 views

Category:

Documents


0 download

TRANSCRIPT

Page 1: Raising the digital standard Frank A. Voelker, DVM, DACVP Flagship Biosciences Pathology Visions: Approaches to Tissue-based Image Analysis in Pharmaceutical

Raising the digital standard

Frank A. Voelker, DVM, DACVP

Flagship Biosciences

Pathology Visions: Approaches to Tissue-based Image Analysis in Pharmaceutical Research and Development

Page 2: Raising the digital standard Frank A. Voelker, DVM, DACVP Flagship Biosciences Pathology Visions: Approaches to Tissue-based Image Analysis in Pharmaceutical

www.flagshipbio.com

2

Topics…….

Introduction

Applications and Challenges

Concepts and Approaches

Analytical Strategies

Guidelines and Pitfalls

Various Examples Using Genie™

Summary

Page 3: Raising the digital standard Frank A. Voelker, DVM, DACVP Flagship Biosciences Pathology Visions: Approaches to Tissue-based Image Analysis in Pharmaceutical

www.flagshipbio.com

3

Pharmaceutical Research and Development

Different approaches for each setting are required because of different group sizes, tissue types and tissue heterogeneity. However, segregation of target from nontarget tissue during analysis is a major challenge in all settings

Oncology Clinical Trial

•Samples usually morphologically variable

•Intragroup collection conditions variable

•Target tissue limited to neoplasm, stroma

Early Drug Discovery

Preclinical Safety Testing

•Samples usually morphologically similar

•Intragroup collection conditions adjusted similar

•Target tissue variable depending on project•Samples usually morphologically similar

•Intragroup collection conditions adjusted similar

•Target tissue variable depending on project

Page 4: Raising the digital standard Frank A. Voelker, DVM, DACVP Flagship Biosciences Pathology Visions: Approaches to Tissue-based Image Analysis in Pharmaceutical

www.flagshipbio.com

4

Available Analytical Tools…….

Area Based Analysis

Rare Event AnalysisCell Based Analysis

Pixel CountIHC DeconvolutionCo-localization

Rare EventIHC NuclearMembraneAngiogenesis

Page 5: Raising the digital standard Frank A. Voelker, DVM, DACVP Flagship Biosciences Pathology Visions: Approaches to Tissue-based Image Analysis in Pharmaceutical

www.flagshipbio.com

5

pS6 Ser235 Immunostain of Breast

Carcinoma

Analysis of average cytoplasmic stain intensity using the pixel count tool may be useful in evaluating a neoplasm if there is little background or

nonspecific staining.

Introducing the Concept of “Target Tissue” Analysis

Page 6: Raising the digital standard Frank A. Voelker, DVM, DACVP Flagship Biosciences Pathology Visions: Approaches to Tissue-based Image Analysis in Pharmaceutical

www.flagshipbio.com

6

Analysis of Target Tissue

1. Count and measure simple structures/objects.

2. Measure area of defined regions/stain.

3. Measure intensities of stain as a percentage of defined regions.

4. Combinations of 1, 2 and 3 above.

In it’s Simplest Terms…..

Page 7: Raising the digital standard Frank A. Voelker, DVM, DACVP Flagship Biosciences Pathology Visions: Approaches to Tissue-based Image Analysis in Pharmaceutical

www.flagshipbio.com

7

Two Different Approaches for Analysis

Cellular Hypertrophy/Atrophy

Cell Numbers

Tissue Infiltrates (eg. Fibrosis)

Other Structural Alterations

Cellular Hypertrophy/Atrophy

Cell Numbers

Tissue Infiltrates (eg. Fibrosis)

Other Structural Alterations

Histochemistry

IHC

ISH

Histochemistry

IHC

ISH

Quantify Substances using Special Stains

Usually measuring area or number

Usually measuring area and/or intensity

Quantify Histomorphologic Change

Page 8: Raising the digital standard Frank A. Voelker, DVM, DACVP Flagship Biosciences Pathology Visions: Approaches to Tissue-based Image Analysis in Pharmaceutical

www.flagshipbio.com

8

Morphologic Approach……

Liver: Hepatocellular hypertrophy, bile duct hyperplasia, necrosis, acute and chronic inflammation, extramedullary hematopoiesis, periportal fibrosis, fatty change, glycogen accumulation.

Kidney: Tubular basophilia, hyaline droplet degeneration, casts, tubular necrosis.

Spleen: Lymphoid hyperplasia/atrophy, extramedullary hematopoiesis

Lung: Alveolar edema, pneumonia, congestion.

Heart: myocardial fibrosis.

Adrenal gland: cortical hypertrophy, cortical vacuolation.

Skin: Acute and chronic inflammation, acanthosis

Liver: Hepatocellular hypertrophy, bile duct hyperplasia, necrosis, acute and chronic inflammation, extramedullary hematopoiesis, periportal fibrosis, fatty change, glycogen accumulation.

Kidney: Tubular basophilia, hyaline droplet degeneration, casts, tubular necrosis.

Spleen: Lymphoid hyperplasia/atrophy, extramedullary hematopoiesis

Lung: Alveolar edema, pneumonia, congestion.

Heart: myocardial fibrosis.

Adrenal gland: cortical hypertrophy, cortical vacuolation.

Skin: Acute and chronic inflammation, acanthosis

Biggest Problem: Distinguishing target from nontarget tissue

Quantifying Common Microscopic ToxPath Changes using H&E or Special Stains

Page 9: Raising the digital standard Frank A. Voelker, DVM, DACVP Flagship Biosciences Pathology Visions: Approaches to Tissue-based Image Analysis in Pharmaceutical

www.flagshipbio.com

9Methods for Defining the Target Tissue for Analysis

1. Define the target tissues for analysis by existing algorithms using common (eg H&E) or special (eg IHC) staining procedures.

2. Define the target tissues for analysis using Genie™

3. Assist in defining target tissues in 1 and 2 above by using the positive and negative pen tools.A high degree of accuracy in target tissue

definition will assure a high degree of accuracy in the final analysis.

Page 10: Raising the digital standard Frank A. Voelker, DVM, DACVP Flagship Biosciences Pathology Visions: Approaches to Tissue-based Image Analysis in Pharmaceutical

www.flagshipbio.com

10

Mouse Liver - Hepatocellular Hypertrophy

Total Hepatocyte Nuclei = 167 Average Nuclear Size = 160 µm² 508 nuclei/mm²

Total Hepatocyte Nuclei = 199 Average Nuclear Size =140 µm² 706 nuclei/mm²

Algorithm: IHC Nuclear (cell-based)

Page 11: Raising the digital standard Frank A. Voelker, DVM, DACVP Flagship Biosciences Pathology Visions: Approaches to Tissue-based Image Analysis in Pharmaceutical

11 Image Analysis in DD / Voelker / 09/12/06

Cyclin D1 Immunostain of Human Breast Carcinoma

Use of the IHC Nuclear Analysis Tool to Determine Percent and Degree of Positivity of Neoplastic Cell Nuclei. Stromal Nuclei are Excluded

from Evaluation.

Page 12: Raising the digital standard Frank A. Voelker, DVM, DACVP Flagship Biosciences Pathology Visions: Approaches to Tissue-based Image Analysis in Pharmaceutical

www.flagshipbio.com

12Quantifying Inflammation in Tissue using the Nuclear Analysis Tool…

Different cell types often can be distinguished from each other in the same tissue based on nuclear diameter. Here lymphocyte nuclei are smaller than mammary carcinoma nuclei.

This makes it possible to count lymphocyte numbers per unit area of tissue cross section to determine degree of infiltration.Algorithm: IHC Nuclear (cell-based)

Page 13: Raising the digital standard Frank A. Voelker, DVM, DACVP Flagship Biosciences Pathology Visions: Approaches to Tissue-based Image Analysis in Pharmaceutical

www.flagshipbio.com

13

Sirius Red Stain Depicting Myocardial Fibrosis in a Mouse

Precision in level of section is required for accurately comparing amounts of fibrosis between treatment groups

Analysis Tool: Color Deconvolution (area-based)

Page 14: Raising the digital standard Frank A. Voelker, DVM, DACVP Flagship Biosciences Pathology Visions: Approaches to Tissue-based Image Analysis in Pharmaceutical

www.flagshipbio.com

14

Fibrosis in Livers of Zucker Rats

Control Rat No. 12 Fenofibrate Rat No. 5

Pioglitazone Rat No. 3

Variations in fibrosis (blue) about small portal triad veins (T) as depicted using Masson’s Trichrome stain

C

Compound X Rat No 2

T

T

T

T

0

0.5

1

1.5

2

2.5

3

C F P X

Page 15: Raising the digital standard Frank A. Voelker, DVM, DACVP Flagship Biosciences Pathology Visions: Approaches to Tissue-based Image Analysis in Pharmaceutical

www.flagshipbio.com

15Quantitation of PAS Stain for Glycogen in Livers of DIO Mice Administered XXX Using the Aperio Image Analysis System

PAS-stained Section Aperio Markup Image

Analysis Tool: Color Deconvolution (area-based)

0

5

10

15

20

1 2 3

Page 16: Raising the digital standard Frank A. Voelker, DVM, DACVP Flagship Biosciences Pathology Visions: Approaches to Tissue-based Image Analysis in Pharmaceutical

www.flagshipbio.com

16Three Possible Strategies for Measuring Immunohistochemistry Stains using the Positive

Pixel Count Analysis Tool

1. Quantitate the percentage area of all brown pixels in the section or in selected areas of the section.

2. If the chromagen staining is very extensive in the target cell population, measure only the brownest (darker) pixels in selected areas of the section.

3. If the chromagen staining is uniform in character and very extensive in the target cell population, measure stain intensity as an index of concentration.

1. Quantitate the percentage area of all brown pixels in the section or in selected areas of the section.

2. If the chromagen staining is very extensive in the target cell population, measure only the brownest (darker) pixels in selected areas of the section.

3. If the chromagen staining is uniform in character and very extensive in the target cell population, measure stain intensity as an index of concentration.

Page 17: Raising the digital standard Frank A. Voelker, DVM, DACVP Flagship Biosciences Pathology Visions: Approaches to Tissue-based Image Analysis in Pharmaceutical

www.flagshipbio.com

17Percent of Liver Tissue Staining for Transferrin Receptor(CD71) in Female Mice by

Immunohistochemistry

* p .01 **p .001

0

5

10

15

20

25

1 2 3 4

*

**

Control 100 mg/kg

250 mg/kg1000 mg/kg

%

Measuring all of the brown pixels in the sample area

Page 18: Raising the digital standard Frank A. Voelker, DVM, DACVP Flagship Biosciences Pathology Visions: Approaches to Tissue-based Image Analysis in Pharmaceutical

www.flagshipbio.com

18Cytochrome p450 Reductase Immunostaining of Centrilobular

Hepatocytes

Widespread staining with centrilobular distribution of more intense staining

Page 19: Raising the digital standard Frank A. Voelker, DVM, DACVP Flagship Biosciences Pathology Visions: Approaches to Tissue-based Image Analysis in Pharmaceutical

19 Aperio in TBD / Voelker / 08/24/06

Quantitation of Cytochrome p450 Reductase Immunostaining of Centrilobular Hepatocytes by Aperio

Original Image Markup Image

Measuring only the area of more intense stainColor deconvolution (area-based)

Page 20: Raising the digital standard Frank A. Voelker, DVM, DACVP Flagship Biosciences Pathology Visions: Approaches to Tissue-based Image Analysis in Pharmaceutical

www.flagshipbio.com

20

Quantitation of VEGF Immunostaining in Livers of Mice administered XXX for 52 Weeks

44.00

45.00

46.00

47.00

48.00

49.00

50.00

51.00

Control Males

Control Females

1000 mg/kg Males

1000 mg/kg FemalesComparing stain intensity

Page 21: Raising the digital standard Frank A. Voelker, DVM, DACVP Flagship Biosciences Pathology Visions: Approaches to Tissue-based Image Analysis in Pharmaceutical

www.flagshipbio.com

21

Genie™……..

Introducing the concept of using histology pattern recognition software as a preprocessing machine to segregate target from nontarget tissue during analysis

Strategies

Page 22: Raising the digital standard Frank A. Voelker, DVM, DACVP Flagship Biosciences Pathology Visions: Approaches to Tissue-based Image Analysis in Pharmaceutical

www.flagshipbio.com

22Tumor Cell-Specific Biomarker Analysis using Genie Histology Pattern Recognition Software

Pulmonary adenocarcinoma stained for pS6-Ser240 Genie mark-up image. Tumor cells = blue

Positive pixel count analysis of tumor cells IHC nuclear analysis of tumor cells

Page 23: Raising the digital standard Frank A. Voelker, DVM, DACVP Flagship Biosciences Pathology Visions: Approaches to Tissue-based Image Analysis in Pharmaceutical

www.flagshipbio.com

23

Analysis of Study Sample Groups by Genie™

Targeted Tissue Selection and Isolation by Genie™

Subsequent Uniform Analysis of Isolated Target Tissue for area/intensity

Morphologically Variable Samples Trained Individually for Genie Target Tissue Selection

Separate target tissue training of each sample does not affect final target tissue analysis.

Page 24: Raising the digital standard Frank A. Voelker, DVM, DACVP Flagship Biosciences Pathology Visions: Approaches to Tissue-based Image Analysis in Pharmaceutical

www.flagshipbio.com

24Immunostain Analysis of Human Breast Tumor Tissue Micro Arrays

Multiple Genie™ Training Classifiers may be needed in analysis of a TMA slide because of tumor heterogeneity.

Page 25: Raising the digital standard Frank A. Voelker, DVM, DACVP Flagship Biosciences Pathology Visions: Approaches to Tissue-based Image Analysis in Pharmaceutical

www.flagshipbio.com

25Tumor Cell-Specific Biomarker Analysis of TMA Breast Tumor Samples using Genie Histology Pattern Recognition Software

IHC

Genie Mark-up

Positive Pixel Mark-up

Page 26: Raising the digital standard Frank A. Voelker, DVM, DACVP Flagship Biosciences Pathology Visions: Approaches to Tissue-based Image Analysis in Pharmaceutical

www.flagshipbio.com

26Manual Inclusion/Exclusion as a Method of Defining the Target Tissue

1. Usually done when it is difficult to define target tissue components in the image by stain specificity and/or by pattern recognition software.

2. May be laborious and time-consuming to perform manual inclusion or exclusion especially with complex tissue patterns.

3. Potentially introduces subjective evaluation by the operator which may further increase error.

4. However, may be the easiest and most rapid method of helping to define the target tissue.

Use of the Positive and Negative Pen Tools……

Page 27: Raising the digital standard Frank A. Voelker, DVM, DACVP Flagship Biosciences Pathology Visions: Approaches to Tissue-based Image Analysis in Pharmaceutical

www.flagshipbio.com

27Use of Positive and Negative Pen Tools

Similar IHC staining of fibronectin and secretion droplets in this xenograft tumor with subsequent poor differentiation by the Genie™ classifier required the use of the negative pen tool to assist in quantitating fibronectin using the IHC deconvolution algorithm.

Page 28: Raising the digital standard Frank A. Voelker, DVM, DACVP Flagship Biosciences Pathology Visions: Approaches to Tissue-based Image Analysis in Pharmaceutical

www.flagshipbio.com

28

pS6 Ser235 Immunostain of Squamous Cell Carcinoma in Human Lung

Estimation of Average stain intensity should take into account negative-staining regions of target tissue as well as positive-

staining regions

“H Score”: A Convention for the Simultaneous Assessment of Both Area and Intensity of Stain

Page 29: Raising the digital standard Frank A. Voelker, DVM, DACVP Flagship Biosciences Pathology Visions: Approaches to Tissue-based Image Analysis in Pharmaceutical

www.flagshipbio.com

29 Scoring is a Convention for Determining Average Stain Intensity of Target Tissue

Now “H” Score evaluation is automatically calculated in Aperio’s IHC Deconvolution Algorithm using attribute outputs in the following similar formula:

(Nwp/Ntotal)x(100) + Np/Ntotal)x(200) + Nsp/Ntotal)x(300) = “H” Score  Where:Nwp = Number of weakly positive pixelsNp = Number of moderately positive pixelsNsp = Number of strongly positive pixelsNtotal = Total number negative + positive pixels

With the old subjective scoring method, the pathologist visually scored staining features of cells (eg. cytoplasmic, nuclear, or membranous staining) by intensity of stain according to grades 0, 1+ , 2+ or 3+ using the following formula:

(1)x(%1+)x(%Area) + (2)x(%2+) x (%Area) + (3)x(%3+)x(%Area) = “H” Score

Not available with IHC Nuclear and Membrane Algorithms

(For a maximum of 300)

Page 30: Raising the digital standard Frank A. Voelker, DVM, DACVP Flagship Biosciences Pathology Visions: Approaches to Tissue-based Image Analysis in Pharmaceutical

www.flagshipbio.com

30Some Guidelines for Analysis of Slides from Experimental Studies

Take care to assure immediate optimal fixation for all tissue samples. Uniformity of handling as well as fixation time is important.

Staining procedures for all slides in a study need to be performed simultaneously in a single batch to assure uniformity of stain.

Sampling must be strictly representational as well as consistent. Care must be taken to assure exact uniformity of analysis with respect to anatomical location (eg. Tissue trimming, sectioning)

A preliminary evaluation of image analysis tools between some slides of varying stain intensities will help assure that analysis values are established optimally for all slides in the study.

Take care to assure immediate optimal fixation for all tissue samples. Uniformity of handling as well as fixation time is important.

Staining procedures for all slides in a study need to be performed simultaneously in a single batch to assure uniformity of stain.

Sampling must be strictly representational as well as consistent. Care must be taken to assure exact uniformity of analysis with respect to anatomical location (eg. Tissue trimming, sectioning)

A preliminary evaluation of image analysis tools between some slides of varying stain intensities will help assure that analysis values are established optimally for all slides in the study.

Page 31: Raising the digital standard Frank A. Voelker, DVM, DACVP Flagship Biosciences Pathology Visions: Approaches to Tissue-based Image Analysis in Pharmaceutical

www.flagshipbio.com

31Consistency of Study Conditions can Affect Morphometric Analysis

Variations in duration of fasting prior to necropsy can result in large differences in hepatocellular glycogen thus leading to

inaccurate analysis

Mouse Liver263 nuclei/mm²

212 nuclei/mm²

Page 32: Raising the digital standard Frank A. Voelker, DVM, DACVP Flagship Biosciences Pathology Visions: Approaches to Tissue-based Image Analysis in Pharmaceutical

www.flagshipbio.com

32Consistency of Necropsy Conditions Can Affect Morphometric Analysis

Variations in exsanguination during necropsy may result in differences in sinusoidal dilatation thus leading to inaccurate

analysis

Mouse Liver

Page 33: Raising the digital standard Frank A. Voelker, DVM, DACVP Flagship Biosciences Pathology Visions: Approaches to Tissue-based Image Analysis in Pharmaceutical

www.flagshipbio.com

33Consistency of Sample Area Selection for Morphometric Analysis within the Median Lobe of the

Mouse Liver

1 2 3

Select samples within approximately the same region of the same lobe of the liver for consistency of analysis. As an assurance of sampling homogeneity, areas should have roughly similar pixel count values.

Page 34: Raising the digital standard Frank A. Voelker, DVM, DACVP Flagship Biosciences Pathology Visions: Approaches to Tissue-based Image Analysis in Pharmaceutical

www.flagshipbio.com

34Quantitation of Periarteriolar Lymphoid Tissue in a Mouse Spleen using Genie and the Aperio Positive Pixel Count Tool

Aperio Positive Pixel Markup Image

H&E Stain

Genie Markup Image

Result: Lymphoid tissue comprises 30.1% of positive pixels in splenic cross-sectional area

Extrapolating to an entire tissue section demands more robust training than for a simple image.

Page 35: Raising the digital standard Frank A. Voelker, DVM, DACVP Flagship Biosciences Pathology Visions: Approaches to Tissue-based Image Analysis in Pharmaceutical

www.flagshipbio.com

35Quantitation of Splenic Erythropoiesis in a Mouse using Genie™ and Aperio Algorithms

Original H&E Stain Genie™ EMH Classifier

Counting Erythroid Nuclei Using Nuclear Algorithm

Measuring Erythroid Nuclear Area Using Hematoxylin Channel of Deconvolution Algorithm

Page 36: Raising the digital standard Frank A. Voelker, DVM, DACVP Flagship Biosciences Pathology Visions: Approaches to Tissue-based Image Analysis in Pharmaceutical

www.flagshipbio.com

36

Quantitation of Hepatocellular Necrosis

Use of Genie™ as a preprocessing utility to identify regions of hepatic necrosis (red) and areas of normal liver (grey)

Subsequent quantitation of necrotic area to allow precise grading

Page 37: Raising the digital standard Frank A. Voelker, DVM, DACVP Flagship Biosciences Pathology Visions: Approaches to Tissue-based Image Analysis in Pharmaceutical

www.flagshipbio.com

37Using the Microvessel Analysis Algorithm to Assess Angiogenesis in a Xenograft Neoplasm

Use of the microvessel analysis algorithm to assess angiogenesis in a xenograft neoplasm in a mouse

Microvessel analysis provides important information regarding potential antineoplastic effects of pharmaceutical compounds

Page 38: Raising the digital standard Frank A. Voelker, DVM, DACVP Flagship Biosciences Pathology Visions: Approaches to Tissue-based Image Analysis in Pharmaceutical

www.flagshipbio.com

38Using the Microvessel Analysis Algorithm to Count Cells

Use of the microvessel analysis algorithm to assess macrophage populations in mouse xenograft neoplasms

Threshold algorithm parameters are modified to accommodate the smaller size and shape characteristics of the macrophages

Page 39: Raising the digital standard Frank A. Voelker, DVM, DACVP Flagship Biosciences Pathology Visions: Approaches to Tissue-based Image Analysis in Pharmaceutical

www.flagshipbio.com

39Using the Microvessel Analysis Algorithm to Count Cells

Algorithm Output Provides Valuable Cell Population Data

•Total Number of Cells

•Total Area of Analysis

•Total Cell Area

•Cell Density/Unit Area

•Average Stain Density

•Mean Cell Area

•Histogram of Cell Areas

Page 40: Raising the digital standard Frank A. Voelker, DVM, DACVP Flagship Biosciences Pathology Visions: Approaches to Tissue-based Image Analysis in Pharmaceutical

www.flagshipbio.com

40Quantitating Dog Thyroid Gland Tissue Components

Use of Genie™ as a preprocessing utility to identify thyroid gland follicular epithelium (green), colloid (red) and C-cells (blue)

Then quantitate as part of the Genie™ utility to determine area and relative percentage of each separate tissue component.

Page 41: Raising the digital standard Frank A. Voelker, DVM, DACVP Flagship Biosciences Pathology Visions: Approaches to Tissue-based Image Analysis in Pharmaceutical

www.flagshipbio.com

41Measuring Follicular Cell Hypertrophy in Dog Thyroid Gland

Use of Genie™ to segregate the thyroid gland follicular epithelium (green) as an intended target tissue for analysis

Then apply the nuclear algorithm counting total nuclear numbers in the target tissue.

Total Nuclei/Total Target Tissue Area = Mean Follicular Cell Area

Page 42: Raising the digital standard Frank A. Voelker, DVM, DACVP Flagship Biosciences Pathology Visions: Approaches to Tissue-based Image Analysis in Pharmaceutical

www.flagshipbio.com

42

Islet Cell Mass of Mouse Pancreas

Measurement of Pancreatic Islet Cell Mass using Genie™ Followed by the Colocalization Algorithm

(A/B)C=Islet Cell MassA=Total Islet Area in Section

B=Total Pancreas Area in SectionC=Pancreatic Weight

Page 43: Raising the digital standard Frank A. Voelker, DVM, DACVP Flagship Biosciences Pathology Visions: Approaches to Tissue-based Image Analysis in Pharmaceutical

www.flagshipbio.com

43

Bile Duct Hyperplasia in Rat Liver

Hyperplastic Bile Ducts = GreenHepatic Parenchyma = RedPeriportal Inflammatory Cells = BluePeriductal Collagen = BrownBile Duct Lumena + Sinusoids = Yellow

First pass Genie histology pattern identification with minimal training. Genie™ can simultaneously analyze three or more tissue areas

Then analyze up to three tissue areas using colocalization tool

Page 44: Raising the digital standard Frank A. Voelker, DVM, DACVP Flagship Biosciences Pathology Visions: Approaches to Tissue-based Image Analysis in Pharmaceutical

www.flagshipbio.com

44

Cynomolgus Monkey Lung

Use of Genie™ as a preprocessing utility to identify regions of bronchiolar epithelium (green)

Subsequent isolation and analysis of only bronchiolar epithelium using the positive pixel count or other analysis tool

Page 45: Raising the digital standard Frank A. Voelker, DVM, DACVP Flagship Biosciences Pathology Visions: Approaches to Tissue-based Image Analysis in Pharmaceutical

www.flagshipbio.com

45

Summary The ability to digitize entire slides and perform morphometric analysis

on images has been valuable in allowing the rapid and practical measurement of tissue biomarkers for pharmaceutical research and development.

A number of strategies and examples have been presented for using various image analysis algorithms in the measurement of tissue changes and tissue biomarkers. Image analysis of specific target tissues can be particularly challenging in cases with large and morphologically intricate areas of tissue, or when tissue staining is nonspecific.

Genie™, a histology pattern recognition tool, has been introduced as a preprocessing utility capable of identifying and categorizing specific histologic tissue types, thus allowing subsequent analysis of target regions by standard image analysis tools.

Significant challenges remain in developing practical procedures and methods appropriate for the analysis of oncology and toxicology specimens. Recent object recognition advancements may assist in this effort.

Page 46: Raising the digital standard Frank A. Voelker, DVM, DACVP Flagship Biosciences Pathology Visions: Approaches to Tissue-based Image Analysis in Pharmaceutical

www.flagshipbio.com

46

Acknowledgements

Ms. Kimberly Merriam, TBG, BMD Novartis Pharmaceuticals Ms. Jeanette Rheinhardt, TBG, BMD Novartis Pharmaceuticals Dr. Allen Olson, Aperio Technologies, Inc. Dr. Kate Lillard-Wetherell, Aperio Technologies, Inc. Mr. James Deeds, Oncology Research, Novartis Pharmaceuticals Ms. Veronica Travaglione, Pharmacology, Infinity Pharmaceuticals Mr. Igor Deyneko, Pharmacology, Infinity Pharmaceuticals Dr. Humphrey Gardner, TBG, BMD, Novartis Pharmaceuticals Dr. Steve Potts, Aperio Technologies, Inc Dr. Reginald Valdez, Novartis Pharmaceuticals Dr Oliver Turner, Novartis Pharmaceuticals Mr. Trevor Johnson, Aperio Technologies, Inc. Others

Page 47: Raising the digital standard Frank A. Voelker, DVM, DACVP Flagship Biosciences Pathology Visions: Approaches to Tissue-based Image Analysis in Pharmaceutical

www.flagshipbio.com

47

Frank VoelkerDVM  MS Diplomate ACVPKey bio points / specialties

Flagship Biosciences LLC provides biotech, pharmaceutical, and medical device companies with quantitative pathology services.

Contact us: www.flagshipbio.com