Quantitative analysis of TDLUs using adaptive morphological shape techniques

Adrian Rosebrock, Jesus J. Caban, Jonine Figueroa, Gretchen Gierach, Laura Linville, Stephen Hewitt, Mark E. Sherman

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

9 Citations (Scopus)

Abstract

Within the complex branching system of the breast, terminal duct lobular units (TDLUs) are the anatomical location where most cancer originates. With aging, TDLUs undergo physiological involution, reflected in a loss of structural components (acini) and a reduction in total number. Data suggest that women undergoing benign breast biopsies that do not show age appropriate involution are at increased risk of developing breast cancer. To date, TDLU assessments have generally been made by qualitative visual assessment, rather by objective quantitative analysis. This paper introduces a technique to automatically estimate a set of quantitative measurements and use those variables to more objectively describe and classify TDLUs. To validate the accuracy of our system, we compared the computer-based morphological properties of 51 TDLUs in breast tissues donated for research by volunteers in the Susan G. Komen Tissue Bank and compared results to those of a pathologist, demonstrating 70% agreement. Secondly, in order to show that our method is applicable to a wider range of datasets, we analyzed 52 TDLUs from biopsies performed for clinical indications in the National Cancer Institute Breast Radiology and Study of Tissues (BREAST) STAMP project and obtained 82% correlation with visual assessment. Lastly, we demonstrate the ability to uncover novel measures when researching the structural properties of the acini by applying machine learning and clustering techniques. Through our study we found that while the number of acini per TDLU increase exponentially with the TDLU diameter, the average elongation and roundness remain constant.

Original languageEnglish (US)
Title of host publicationMedical Imaging 2013
Subtitle of host publicationDigital Pathology
Volume8676
DOIs
StatePublished - 2013
EventSPIE Medical Imaging Symposium 2013: Digital Pathology - Lake Buena Vista, FL, United States
Duration: Feb 10 2013Feb 11 2013

Other

OtherSPIE Medical Imaging Symposium 2013: Digital Pathology
CountryUnited States
CityLake Buena Vista, FL
Period2/10/132/11/13

Fingerprint

ducts
Ducts
quantitative analysis
Breast
breast
Chemical analysis
Tissue Banks
Breast Neoplasms
Biopsy
National Cancer Institute (U.S.)
Computer Systems
Radiology
Cluster Analysis
Volunteers
cancer
Tissue
Research
machine learning
radiology
Neoplasms

Keywords

  • Acini detection
  • Adaptive morphological shape
  • Breast cancer
  • Clustering
  • Image processing
  • TDLU detection

ASJC Scopus subject areas

  • Atomic and Molecular Physics, and Optics
  • Electronic, Optical and Magnetic Materials
  • Biomaterials
  • Radiology Nuclear Medicine and imaging

Cite this

Rosebrock, A., Caban, J. J., Figueroa, J., Gierach, G., Linville, L., Hewitt, S., & Sherman, M. E. (2013). Quantitative analysis of TDLUs using adaptive morphological shape techniques. In Medical Imaging 2013: Digital Pathology (Vol. 8676). [86760N] https://doi.org/10.1117/12.2006619

Quantitative analysis of TDLUs using adaptive morphological shape techniques. / Rosebrock, Adrian; Caban, Jesus J.; Figueroa, Jonine; Gierach, Gretchen; Linville, Laura; Hewitt, Stephen; Sherman, Mark E.

Medical Imaging 2013: Digital Pathology. Vol. 8676 2013. 86760N.

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

Rosebrock, A, Caban, JJ, Figueroa, J, Gierach, G, Linville, L, Hewitt, S & Sherman, ME 2013, Quantitative analysis of TDLUs using adaptive morphological shape techniques. in Medical Imaging 2013: Digital Pathology. vol. 8676, 86760N, SPIE Medical Imaging Symposium 2013: Digital Pathology, Lake Buena Vista, FL, United States, 2/10/13. https://doi.org/10.1117/12.2006619
Rosebrock A, Caban JJ, Figueroa J, Gierach G, Linville L, Hewitt S et al. Quantitative analysis of TDLUs using adaptive morphological shape techniques. In Medical Imaging 2013: Digital Pathology. Vol. 8676. 2013. 86760N https://doi.org/10.1117/12.2006619
Rosebrock, Adrian ; Caban, Jesus J. ; Figueroa, Jonine ; Gierach, Gretchen ; Linville, Laura ; Hewitt, Stephen ; Sherman, Mark E. / Quantitative analysis of TDLUs using adaptive morphological shape techniques. Medical Imaging 2013: Digital Pathology. Vol. 8676 2013.
@inproceedings{47805d0c2fc94ce8bf8e87028f937108,
title = "Quantitative analysis of TDLUs using adaptive morphological shape techniques",
abstract = "Within the complex branching system of the breast, terminal duct lobular units (TDLUs) are the anatomical location where most cancer originates. With aging, TDLUs undergo physiological involution, reflected in a loss of structural components (acini) and a reduction in total number. Data suggest that women undergoing benign breast biopsies that do not show age appropriate involution are at increased risk of developing breast cancer. To date, TDLU assessments have generally been made by qualitative visual assessment, rather by objective quantitative analysis. This paper introduces a technique to automatically estimate a set of quantitative measurements and use those variables to more objectively describe and classify TDLUs. To validate the accuracy of our system, we compared the computer-based morphological properties of 51 TDLUs in breast tissues donated for research by volunteers in the Susan G. Komen Tissue Bank and compared results to those of a pathologist, demonstrating 70{\%} agreement. Secondly, in order to show that our method is applicable to a wider range of datasets, we analyzed 52 TDLUs from biopsies performed for clinical indications in the National Cancer Institute Breast Radiology and Study of Tissues (BREAST) STAMP project and obtained 82{\%} correlation with visual assessment. Lastly, we demonstrate the ability to uncover novel measures when researching the structural properties of the acini by applying machine learning and clustering techniques. Through our study we found that while the number of acini per TDLU increase exponentially with the TDLU diameter, the average elongation and roundness remain constant.",
keywords = "Acini detection, Adaptive morphological shape, Breast cancer, Clustering, Image processing, TDLU detection",
author = "Adrian Rosebrock and Caban, {Jesus J.} and Jonine Figueroa and Gretchen Gierach and Laura Linville and Stephen Hewitt and Sherman, {Mark E.}",
year = "2013",
doi = "10.1117/12.2006619",
language = "English (US)",
isbn = "9780819494504",
volume = "8676",
booktitle = "Medical Imaging 2013",

}

TY - GEN

T1 - Quantitative analysis of TDLUs using adaptive morphological shape techniques

AU - Rosebrock, Adrian

AU - Caban, Jesus J.

AU - Figueroa, Jonine

AU - Gierach, Gretchen

AU - Linville, Laura

AU - Hewitt, Stephen

AU - Sherman, Mark E.

PY - 2013

Y1 - 2013

N2 - Within the complex branching system of the breast, terminal duct lobular units (TDLUs) are the anatomical location where most cancer originates. With aging, TDLUs undergo physiological involution, reflected in a loss of structural components (acini) and a reduction in total number. Data suggest that women undergoing benign breast biopsies that do not show age appropriate involution are at increased risk of developing breast cancer. To date, TDLU assessments have generally been made by qualitative visual assessment, rather by objective quantitative analysis. This paper introduces a technique to automatically estimate a set of quantitative measurements and use those variables to more objectively describe and classify TDLUs. To validate the accuracy of our system, we compared the computer-based morphological properties of 51 TDLUs in breast tissues donated for research by volunteers in the Susan G. Komen Tissue Bank and compared results to those of a pathologist, demonstrating 70% agreement. Secondly, in order to show that our method is applicable to a wider range of datasets, we analyzed 52 TDLUs from biopsies performed for clinical indications in the National Cancer Institute Breast Radiology and Study of Tissues (BREAST) STAMP project and obtained 82% correlation with visual assessment. Lastly, we demonstrate the ability to uncover novel measures when researching the structural properties of the acini by applying machine learning and clustering techniques. Through our study we found that while the number of acini per TDLU increase exponentially with the TDLU diameter, the average elongation and roundness remain constant.

AB - Within the complex branching system of the breast, terminal duct lobular units (TDLUs) are the anatomical location where most cancer originates. With aging, TDLUs undergo physiological involution, reflected in a loss of structural components (acini) and a reduction in total number. Data suggest that women undergoing benign breast biopsies that do not show age appropriate involution are at increased risk of developing breast cancer. To date, TDLU assessments have generally been made by qualitative visual assessment, rather by objective quantitative analysis. This paper introduces a technique to automatically estimate a set of quantitative measurements and use those variables to more objectively describe and classify TDLUs. To validate the accuracy of our system, we compared the computer-based morphological properties of 51 TDLUs in breast tissues donated for research by volunteers in the Susan G. Komen Tissue Bank and compared results to those of a pathologist, demonstrating 70% agreement. Secondly, in order to show that our method is applicable to a wider range of datasets, we analyzed 52 TDLUs from biopsies performed for clinical indications in the National Cancer Institute Breast Radiology and Study of Tissues (BREAST) STAMP project and obtained 82% correlation with visual assessment. Lastly, we demonstrate the ability to uncover novel measures when researching the structural properties of the acini by applying machine learning and clustering techniques. Through our study we found that while the number of acini per TDLU increase exponentially with the TDLU diameter, the average elongation and roundness remain constant.

KW - Acini detection

KW - Adaptive morphological shape

KW - Breast cancer

KW - Clustering

KW - Image processing

KW - TDLU detection

UR - http://www.scopus.com/inward/record.url?scp=84878599613&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84878599613&partnerID=8YFLogxK

U2 - 10.1117/12.2006619

DO - 10.1117/12.2006619

M3 - Conference contribution

SN - 9780819494504

VL - 8676

BT - Medical Imaging 2013

ER -