Multi-field-of-view strategy for image-based outcome prediction of multi-parametric estrogen receptor-positive breast cancer histopathology: Comparison to Oncotype DX
In this paper, we attempt to quantify the prognostic information embedded in multi-parametric histologic biopsy images to predict disease aggressiveness in estrogen receptor-positive (ER+) breast cancers (BCa). The novel methodological contribution is in the use of a multi-field-of-view (multi-FOV)...
| Main Authors: | , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Elsevier
2011-01-01
|
| Series: | Journal of Pathology Informatics |
| Subjects: | |
| Online Access: | http://www.jpathinformatics.org/article.asp?issn=2153-3539;year=2011;volume=2;issue=2;spage=1;epage=1;aulast=Basavanhally |
| _version_ | 1811340454359203840 |
|---|---|
| author | Ajay Basavanhally Michael Feldman Natalie Shih Carolyn Mies John Tomaszewski Shridar Ganesan Anant Madabhushi |
| author_facet | Ajay Basavanhally Michael Feldman Natalie Shih Carolyn Mies John Tomaszewski Shridar Ganesan Anant Madabhushi |
| author_sort | Ajay Basavanhally |
| collection | DOAJ |
| description | In this paper, we attempt to quantify the prognostic information embedded in multi-parametric histologic biopsy images to predict disease aggressiveness in estrogen receptor-positive (ER+) breast cancers (BCa). The novel methodological contribution is in the use of a multi-field-of-view (multi-FOV) framework for integrating image-based information from differently stained histopathology slides. The multi-FOV approach involves a fixed image resolution while simultaneously integrating image descriptors from many FOVs corresponding to different sizes. For each study, the corresponding risk score (high scores reflecting aggressive disease and vice versa), predicted by a molecular assay (Oncotype DX), is available and serves as the surrogate ground truth for long-term patient outcome. Using the risk scores, a trained classifier is used to identify disease aggressiveness for each FOV size. The predictions for each FOV are then combined to yield the final prediction of disease aggressiveness (good, intermediate, or poor outcome). Independent multi-FOV classifiers are constructed for (1) 50 image features describing the spatial arrangement of cancer nuclei (via Voronoi diagram, Delaunay triangulation, and minimum spanning tree graphs) in H and E stained histopathology and (2) one image feature describing the vascular density in CD34 IHC stained histopathology. In a cohort of 29 patients, the multi-FOV classifiers obtained by combining information from the H and E and CD34 IHC stained channels were able to distinguish low- and high-risk patients with an accuracy of 0.91 ± 0.02 and a positive predictive value of 0.94 ± 0.10, suggesting that a purely image-based assay could potentially replace more expensive molecular assays for making disease prognostic predictions. |
| first_indexed | 2024-04-13T18:42:07Z |
| format | Article |
| id | doaj.art-f342ce3fa14842f28728f79f4d30fc54 |
| institution | Directory Open Access Journal |
| issn | 2153-3539 2153-3539 |
| language | English |
| last_indexed | 2024-04-13T18:42:07Z |
| publishDate | 2011-01-01 |
| publisher | Elsevier |
| record_format | Article |
| series | Journal of Pathology Informatics |
| spelling | doaj.art-f342ce3fa14842f28728f79f4d30fc542022-12-22T02:34:42ZengElsevierJournal of Pathology Informatics2153-35392153-35392011-01-01221110.4103/2153-3539.92027Multi-field-of-view strategy for image-based outcome prediction of multi-parametric estrogen receptor-positive breast cancer histopathology: Comparison to Oncotype DXAjay BasavanhallyMichael FeldmanNatalie ShihCarolyn MiesJohn TomaszewskiShridar GanesanAnant MadabhushiIn this paper, we attempt to quantify the prognostic information embedded in multi-parametric histologic biopsy images to predict disease aggressiveness in estrogen receptor-positive (ER+) breast cancers (BCa). The novel methodological contribution is in the use of a multi-field-of-view (multi-FOV) framework for integrating image-based information from differently stained histopathology slides. The multi-FOV approach involves a fixed image resolution while simultaneously integrating image descriptors from many FOVs corresponding to different sizes. For each study, the corresponding risk score (high scores reflecting aggressive disease and vice versa), predicted by a molecular assay (Oncotype DX), is available and serves as the surrogate ground truth for long-term patient outcome. Using the risk scores, a trained classifier is used to identify disease aggressiveness for each FOV size. The predictions for each FOV are then combined to yield the final prediction of disease aggressiveness (good, intermediate, or poor outcome). Independent multi-FOV classifiers are constructed for (1) 50 image features describing the spatial arrangement of cancer nuclei (via Voronoi diagram, Delaunay triangulation, and minimum spanning tree graphs) in H and E stained histopathology and (2) one image feature describing the vascular density in CD34 IHC stained histopathology. In a cohort of 29 patients, the multi-FOV classifiers obtained by combining information from the H and E and CD34 IHC stained channels were able to distinguish low- and high-risk patients with an accuracy of 0.91 ± 0.02 and a positive predictive value of 0.94 ± 0.10, suggesting that a purely image-based assay could potentially replace more expensive molecular assays for making disease prognostic predictions.http://www.jpathinformatics.org/article.asp?issn=2153-3539;year=2011;volume=2;issue=2;spage=1;epage=1;aulast=BasavanhallyImage-based risk scorebreast cancerestrogen receptor positivecomputerized prognosisoutcome predictionmulti-variate histologyH and ECD34 immunohistochemistry |
| spellingShingle | Ajay Basavanhally Michael Feldman Natalie Shih Carolyn Mies John Tomaszewski Shridar Ganesan Anant Madabhushi Multi-field-of-view strategy for image-based outcome prediction of multi-parametric estrogen receptor-positive breast cancer histopathology: Comparison to Oncotype DX Journal of Pathology Informatics Image-based risk score breast cancer estrogen receptor positive computerized prognosis outcome prediction multi-variate histology H and E CD34 immunohistochemistry |
| title | Multi-field-of-view strategy for image-based outcome prediction of multi-parametric estrogen receptor-positive breast cancer histopathology: Comparison to Oncotype DX |
| title_full | Multi-field-of-view strategy for image-based outcome prediction of multi-parametric estrogen receptor-positive breast cancer histopathology: Comparison to Oncotype DX |
| title_fullStr | Multi-field-of-view strategy for image-based outcome prediction of multi-parametric estrogen receptor-positive breast cancer histopathology: Comparison to Oncotype DX |
| title_full_unstemmed | Multi-field-of-view strategy for image-based outcome prediction of multi-parametric estrogen receptor-positive breast cancer histopathology: Comparison to Oncotype DX |
| title_short | Multi-field-of-view strategy for image-based outcome prediction of multi-parametric estrogen receptor-positive breast cancer histopathology: Comparison to Oncotype DX |
| title_sort | multi field of view strategy for image based outcome prediction of multi parametric estrogen receptor positive breast cancer histopathology comparison to oncotype dx |
| topic | Image-based risk score breast cancer estrogen receptor positive computerized prognosis outcome prediction multi-variate histology H and E CD34 immunohistochemistry |
| url | http://www.jpathinformatics.org/article.asp?issn=2153-3539;year=2011;volume=2;issue=2;spage=1;epage=1;aulast=Basavanhally |
| work_keys_str_mv | AT ajaybasavanhally multifieldofviewstrategyforimagebasedoutcomepredictionofmultiparametricestrogenreceptorpositivebreastcancerhistopathologycomparisontooncotypedx AT michaelfeldman multifieldofviewstrategyforimagebasedoutcomepredictionofmultiparametricestrogenreceptorpositivebreastcancerhistopathologycomparisontooncotypedx AT natalieshih multifieldofviewstrategyforimagebasedoutcomepredictionofmultiparametricestrogenreceptorpositivebreastcancerhistopathologycomparisontooncotypedx AT carolynmies multifieldofviewstrategyforimagebasedoutcomepredictionofmultiparametricestrogenreceptorpositivebreastcancerhistopathologycomparisontooncotypedx AT johntomaszewski multifieldofviewstrategyforimagebasedoutcomepredictionofmultiparametricestrogenreceptorpositivebreastcancerhistopathologycomparisontooncotypedx AT shridarganesan multifieldofviewstrategyforimagebasedoutcomepredictionofmultiparametricestrogenreceptorpositivebreastcancerhistopathologycomparisontooncotypedx AT anantmadabhushi multifieldofviewstrategyforimagebasedoutcomepredictionofmultiparametricestrogenreceptorpositivebreastcancerhistopathologycomparisontooncotypedx |