Classification of tumor histology via morphometric context

Hang Chang, Alexander Borowsky, Paul Spellman, Bahram Parvin

Research output: Chapter in Book/Report/Conference proceedingConference contribution

24 Citations (Scopus)

Abstract

Image-based classification of tissue histology, in terms of different components (e.g., normal signature, categories of aberrant signatures), provides a series of indices for tumor composition. Subsequently, aggregation of these indices in each whole slide image (WSI) from a large cohort can provide predictive models of clinical outcome. However, the performance of the existing techniques is hindered as a result of large technical and biological variations that are always present in a large cohort. In this paper, we propose two algorithms for classification of tissue histology based on robust representations of morphometric context, which are built upon nuclear level morphometric features at various locations and scales within the spatial pyramid matching (SPM) framework. These methods have been evaluated on two distinct datasets of different tumor types collected from The Cancer Genome Atlas (TCGA), and the experimental results indicate that our methods are (i) extensible to different tumor types, (ii) robust in the presence of wide technical and biological variations, (iii) invariant to different nuclear segmentation strategies, and (iv) scalable with varying training sample size. In addition, our experiments suggest that enforcing sparsity, during the construction of morphometric context, further improves the performance of the system.

Original languageEnglish (US)
Title of host publicationProceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition
Pages2203-2210
Number of pages8
DOIs
StatePublished - 2013
Event26th IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2013 - Portland, OR, United States
Duration: Jun 23 2013Jun 28 2013

Other

Other26th IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2013
CountryUnited States
CityPortland, OR
Period6/23/136/28/13

Fingerprint

Histology
Tumors
Tissue
Agglomeration
Genes
Chemical analysis
Experiments

ASJC Scopus subject areas

  • Software
  • Computer Vision and Pattern Recognition

Cite this

Chang, H., Borowsky, A., Spellman, P., & Parvin, B. (2013). Classification of tumor histology via morphometric context. In Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition (pp. 2203-2210). [6619130] https://doi.org/10.1109/CVPR.2013.286

Classification of tumor histology via morphometric context. / Chang, Hang; Borowsky, Alexander; Spellman, Paul; Parvin, Bahram.

Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition. 2013. p. 2203-2210 6619130.

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Chang, H, Borowsky, A, Spellman, P & Parvin, B 2013, Classification of tumor histology via morphometric context. in Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition., 6619130, pp. 2203-2210, 26th IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2013, Portland, OR, United States, 6/23/13. https://doi.org/10.1109/CVPR.2013.286
Chang H, Borowsky A, Spellman P, Parvin B. Classification of tumor histology via morphometric context. In Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition. 2013. p. 2203-2210. 6619130 https://doi.org/10.1109/CVPR.2013.286
Chang, Hang ; Borowsky, Alexander ; Spellman, Paul ; Parvin, Bahram. / Classification of tumor histology via morphometric context. Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition. 2013. pp. 2203-2210
@inproceedings{84ef9a967f934e058919c46f8d71d2d2,
title = "Classification of tumor histology via morphometric context",
abstract = "Image-based classification of tissue histology, in terms of different components (e.g., normal signature, categories of aberrant signatures), provides a series of indices for tumor composition. Subsequently, aggregation of these indices in each whole slide image (WSI) from a large cohort can provide predictive models of clinical outcome. However, the performance of the existing techniques is hindered as a result of large technical and biological variations that are always present in a large cohort. In this paper, we propose two algorithms for classification of tissue histology based on robust representations of morphometric context, which are built upon nuclear level morphometric features at various locations and scales within the spatial pyramid matching (SPM) framework. These methods have been evaluated on two distinct datasets of different tumor types collected from The Cancer Genome Atlas (TCGA), and the experimental results indicate that our methods are (i) extensible to different tumor types, (ii) robust in the presence of wide technical and biological variations, (iii) invariant to different nuclear segmentation strategies, and (iv) scalable with varying training sample size. In addition, our experiments suggest that enforcing sparsity, during the construction of morphometric context, further improves the performance of the system.",
author = "Hang Chang and Alexander Borowsky and Paul Spellman and Bahram Parvin",
year = "2013",
doi = "10.1109/CVPR.2013.286",
language = "English (US)",
pages = "2203--2210",
booktitle = "Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition",

}

TY - GEN

T1 - Classification of tumor histology via morphometric context

AU - Chang, Hang

AU - Borowsky, Alexander

AU - Spellman, Paul

AU - Parvin, Bahram

PY - 2013

Y1 - 2013

N2 - Image-based classification of tissue histology, in terms of different components (e.g., normal signature, categories of aberrant signatures), provides a series of indices for tumor composition. Subsequently, aggregation of these indices in each whole slide image (WSI) from a large cohort can provide predictive models of clinical outcome. However, the performance of the existing techniques is hindered as a result of large technical and biological variations that are always present in a large cohort. In this paper, we propose two algorithms for classification of tissue histology based on robust representations of morphometric context, which are built upon nuclear level morphometric features at various locations and scales within the spatial pyramid matching (SPM) framework. These methods have been evaluated on two distinct datasets of different tumor types collected from The Cancer Genome Atlas (TCGA), and the experimental results indicate that our methods are (i) extensible to different tumor types, (ii) robust in the presence of wide technical and biological variations, (iii) invariant to different nuclear segmentation strategies, and (iv) scalable with varying training sample size. In addition, our experiments suggest that enforcing sparsity, during the construction of morphometric context, further improves the performance of the system.

AB - Image-based classification of tissue histology, in terms of different components (e.g., normal signature, categories of aberrant signatures), provides a series of indices for tumor composition. Subsequently, aggregation of these indices in each whole slide image (WSI) from a large cohort can provide predictive models of clinical outcome. However, the performance of the existing techniques is hindered as a result of large technical and biological variations that are always present in a large cohort. In this paper, we propose two algorithms for classification of tissue histology based on robust representations of morphometric context, which are built upon nuclear level morphometric features at various locations and scales within the spatial pyramid matching (SPM) framework. These methods have been evaluated on two distinct datasets of different tumor types collected from The Cancer Genome Atlas (TCGA), and the experimental results indicate that our methods are (i) extensible to different tumor types, (ii) robust in the presence of wide technical and biological variations, (iii) invariant to different nuclear segmentation strategies, and (iv) scalable with varying training sample size. In addition, our experiments suggest that enforcing sparsity, during the construction of morphometric context, further improves the performance of the system.

UR - http://www.scopus.com/inward/record.url?scp=84887390740&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84887390740&partnerID=8YFLogxK

U2 - 10.1109/CVPR.2013.286

DO - 10.1109/CVPR.2013.286

M3 - Conference contribution

AN - SCOPUS:84887390740

SP - 2203

EP - 2210

BT - Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition

ER -