Immunohistochemical analysis of breast tissue microarray images using contextual classifiers
Background: Tissue microarrays (TMAs) are an important tool in translational research for examining multiple cancers for molecular and protein markers. Automatic immunohistochemical (IHC) scoring of breast TMA images remains a challenging problem. Methods: A two-stage approach that involves localiza...
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Elsevier
2013-01-01
|
| Series: | Journal of Pathology Informatics |
| Subjects: | |
| Online Access: | http://www.jpathinformatics.org/article.asp?issn=2153-3539;year=2013;volume=4;issue=2;spage=13;epage=13;aulast=McKenna |
| _version_ | 1818215959310106624 |
|---|---|
| author | Stephen J McKenna Telmo Amaral Shazia Akbar Lee Jordan Alastair Thompson |
| author_facet | Stephen J McKenna Telmo Amaral Shazia Akbar Lee Jordan Alastair Thompson |
| author_sort | Stephen J McKenna |
| collection | DOAJ |
| description | Background: Tissue microarrays (TMAs) are an important tool in translational research for examining multiple cancers for molecular and protein markers. Automatic immunohistochemical (IHC) scoring of breast TMA images remains a challenging problem. Methods: A two-stage approach that involves localization of regions of invasive and in-situ carcinoma followed by ordinal IHC scoring of nuclei in these regions is proposed. The localization stage classifies locations on a grid as tumor or non-tumor based on local image features. These classifications are then refined using an auto-context algorithm called spin-context. Spin-context uses a series of classifiers to integrate image feature information with spatial context information in the form of estimated class probabilities. This is achieved in a rotationally-invariant manner. The second stage estimates ordinal IHC scores in terms of the strength of staining and the proportion of nuclei stained. These estimates take the form of posterior probabilities, enabling images with uncertain scores to be referred for pathologist review. Results: The method was validated against manual pathologist scoring on two nuclear markers, progesterone receptor (PR) and estrogen receptor (ER). Errors for PR data were consistently lower than those achieved with ER data. Scoring was in terms of estimated proportion of cells that were positively stained (scored on an ordinal scale of 0-6) and perceived strength of staining (scored on an ordinal scale of 0-3). Average absolute differences between predicted scores and pathologist-assigned scores were 0.74 for proportion of cells and 0.35 for strength of staining (PR). Conclusions: The use of context information via spin-context improved the precision and recall of tumor localization. The combination of the spin-context localization method with the automated scoring method resulted in reduced IHC scoring errors. |
| first_indexed | 2024-12-12T06:44:22Z |
| format | Article |
| id | doaj.art-571058233c81438f95377e21e2ea4322 |
| institution | Directory Open Access Journal |
| issn | 2153-3539 2153-3539 |
| language | English |
| last_indexed | 2024-12-12T06:44:22Z |
| publishDate | 2013-01-01 |
| publisher | Elsevier |
| record_format | Article |
| series | Journal of Pathology Informatics |
| spelling | doaj.art-571058233c81438f95377e21e2ea43222022-12-22T00:34:14ZengElsevierJournal of Pathology Informatics2153-35392153-35392013-01-0142131310.4103/2153-3539.109871Immunohistochemical analysis of breast tissue microarray images using contextual classifiersStephen J McKennaTelmo AmaralShazia AkbarLee JordanAlastair ThompsonBackground: Tissue microarrays (TMAs) are an important tool in translational research for examining multiple cancers for molecular and protein markers. Automatic immunohistochemical (IHC) scoring of breast TMA images remains a challenging problem. Methods: A two-stage approach that involves localization of regions of invasive and in-situ carcinoma followed by ordinal IHC scoring of nuclei in these regions is proposed. The localization stage classifies locations on a grid as tumor or non-tumor based on local image features. These classifications are then refined using an auto-context algorithm called spin-context. Spin-context uses a series of classifiers to integrate image feature information with spatial context information in the form of estimated class probabilities. This is achieved in a rotationally-invariant manner. The second stage estimates ordinal IHC scores in terms of the strength of staining and the proportion of nuclei stained. These estimates take the form of posterior probabilities, enabling images with uncertain scores to be referred for pathologist review. Results: The method was validated against manual pathologist scoring on two nuclear markers, progesterone receptor (PR) and estrogen receptor (ER). Errors for PR data were consistently lower than those achieved with ER data. Scoring was in terms of estimated proportion of cells that were positively stained (scored on an ordinal scale of 0-6) and perceived strength of staining (scored on an ordinal scale of 0-3). Average absolute differences between predicted scores and pathologist-assigned scores were 0.74 for proportion of cells and 0.35 for strength of staining (PR). Conclusions: The use of context information via spin-context improved the precision and recall of tumor localization. The combination of the spin-context localization method with the automated scoring method resulted in reduced IHC scoring errors.http://www.jpathinformatics.org/article.asp?issn=2153-3539;year=2013;volume=4;issue=2;spage=13;epage=13;aulast=McKennaTissue microarraystumor localizationimmunohistochemical scoring |
| spellingShingle | Stephen J McKenna Telmo Amaral Shazia Akbar Lee Jordan Alastair Thompson Immunohistochemical analysis of breast tissue microarray images using contextual classifiers Journal of Pathology Informatics Tissue microarrays tumor localization immunohistochemical scoring |
| title | Immunohistochemical analysis of breast tissue microarray images using contextual classifiers |
| title_full | Immunohistochemical analysis of breast tissue microarray images using contextual classifiers |
| title_fullStr | Immunohistochemical analysis of breast tissue microarray images using contextual classifiers |
| title_full_unstemmed | Immunohistochemical analysis of breast tissue microarray images using contextual classifiers |
| title_short | Immunohistochemical analysis of breast tissue microarray images using contextual classifiers |
| title_sort | immunohistochemical analysis of breast tissue microarray images using contextual classifiers |
| topic | Tissue microarrays tumor localization immunohistochemical scoring |
| url | http://www.jpathinformatics.org/article.asp?issn=2153-3539;year=2013;volume=4;issue=2;spage=13;epage=13;aulast=McKenna |
| work_keys_str_mv | AT stephenjmckenna immunohistochemicalanalysisofbreasttissuemicroarrayimagesusingcontextualclassifiers AT telmoamaral immunohistochemicalanalysisofbreasttissuemicroarrayimagesusingcontextualclassifiers AT shaziaakbar immunohistochemicalanalysisofbreasttissuemicroarrayimagesusingcontextualclassifiers AT leejordan immunohistochemicalanalysisofbreasttissuemicroarrayimagesusingcontextualclassifiers AT alastairthompson immunohistochemicalanalysisofbreasttissuemicroarrayimagesusingcontextualclassifiers |