Prediction of occult invasive disease in ductal carcinoma in situ using computer-extracted mammographic features

Bibo Shi, Lars J. Grimm, Maciej A. Mazurowski, Jeffrey R. Marks, Lorraine M. King, Carlo Maley, E. Shelley Hwang, Joseph Y. Lo

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

2 Citations (Scopus)

Abstract

Predicting the risk of occult invasive disease in ductal carcinoma in situ (DCIS) is an important task to help address the overdiagnosis and overtreatment problems associated with breast cancer. In this work, we investigated the feasibility of using computer-extracted mammographic features to predict occult invasive disease in patients with biopsy proven DCIS. We proposed a computer-vision algorithm based approach to extract mammographic features from magnification views of full field digital mammography (FFDM) for patients with DCIS. After an expert breast radiologist provided a region of interest (ROI) mask for the DCIS lesion, the proposed approach is able to segment individual microcalcifications (MCs), detect the boundary of the MC cluster (MCC), and extract 113 mammographic features from MCs and MCC within the ROI. In this study, we extracted mammographic features from 99 patients with DCIS (74 pure DCIS; 25 DCIS plus invasive disease). The predictive power of the mammographic features was demonstrated through binary classifications between pure DCIS and DCIS with invasive disease using linear discriminant analysis (LDA). Before classification, the minimum redundancy Maximum Relevance (mRMR) feature selection method was first applied to choose subsets of useful features. The generalization performance was assessed using Leave-One-Out Cross-Validation and Receiver Operating Characteristic (ROC) curve analysis. Using the computer-extracted mammographic features, the proposed model was able to distinguish DCIS with invasive disease from pure DCIS, with an average classification performance of AUC = 0.61 ± 0.05. Overall, the proposed computer-extracted mammographic features are promising for predicting occult invasive disease in DCIS.

Original languageEnglish (US)
Title of host publicationMedical Imaging 2017
Subtitle of host publicationComputer-Aided Diagnosis
PublisherSPIE
Volume10134
ISBN (Electronic)9781510607132
DOIs
StatePublished - 2017
EventMedical Imaging 2017: Computer-Aided Diagnosis - Orlando, United States
Duration: Feb 13 2017Feb 16 2017

Other

OtherMedical Imaging 2017: Computer-Aided Diagnosis
CountryUnited States
CityOrlando
Period2/13/172/16/17

Fingerprint

Carcinoma, Intraductal, Noninfiltrating
cancer
predictions
Calcinosis
Mammography
Biopsy
Discriminant analysis
Computer vision
Redundancy
breast
Feature extraction
Masks
Discriminant Analysis
computer vision
redundancy
ROC Curve
magnification
Area Under Curve
lesions
set theory

Keywords

  • Breast cancer
  • CAD
  • Digital mammogram
  • Ductal carcinoma in situ
  • Microcalcification

ASJC Scopus subject areas

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

Cite this

Shi, B., Grimm, L. J., Mazurowski, M. A., Marks, J. R., King, L. M., Maley, C., ... Lo, J. Y. (2017). Prediction of occult invasive disease in ductal carcinoma in situ using computer-extracted mammographic features. In Medical Imaging 2017: Computer-Aided Diagnosis (Vol. 10134). [101341I] SPIE. https://doi.org/10.1117/12.2255731

Prediction of occult invasive disease in ductal carcinoma in situ using computer-extracted mammographic features. / Shi, Bibo; Grimm, Lars J.; Mazurowski, Maciej A.; Marks, Jeffrey R.; King, Lorraine M.; Maley, Carlo; Hwang, E. Shelley; Lo, Joseph Y.

Medical Imaging 2017: Computer-Aided Diagnosis. Vol. 10134 SPIE, 2017. 101341I.

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

Shi, B, Grimm, LJ, Mazurowski, MA, Marks, JR, King, LM, Maley, C, Hwang, ES & Lo, JY 2017, Prediction of occult invasive disease in ductal carcinoma in situ using computer-extracted mammographic features. in Medical Imaging 2017: Computer-Aided Diagnosis. vol. 10134, 101341I, SPIE, Medical Imaging 2017: Computer-Aided Diagnosis, Orlando, United States, 2/13/17. https://doi.org/10.1117/12.2255731
Shi B, Grimm LJ, Mazurowski MA, Marks JR, King LM, Maley C et al. Prediction of occult invasive disease in ductal carcinoma in situ using computer-extracted mammographic features. In Medical Imaging 2017: Computer-Aided Diagnosis. Vol. 10134. SPIE. 2017. 101341I https://doi.org/10.1117/12.2255731
Shi, Bibo ; Grimm, Lars J. ; Mazurowski, Maciej A. ; Marks, Jeffrey R. ; King, Lorraine M. ; Maley, Carlo ; Hwang, E. Shelley ; Lo, Joseph Y. / Prediction of occult invasive disease in ductal carcinoma in situ using computer-extracted mammographic features. Medical Imaging 2017: Computer-Aided Diagnosis. Vol. 10134 SPIE, 2017.
@inproceedings{1ca640d5a51546afa2ffbb5283fc6c3c,
title = "Prediction of occult invasive disease in ductal carcinoma in situ using computer-extracted mammographic features",
abstract = "Predicting the risk of occult invasive disease in ductal carcinoma in situ (DCIS) is an important task to help address the overdiagnosis and overtreatment problems associated with breast cancer. In this work, we investigated the feasibility of using computer-extracted mammographic features to predict occult invasive disease in patients with biopsy proven DCIS. We proposed a computer-vision algorithm based approach to extract mammographic features from magnification views of full field digital mammography (FFDM) for patients with DCIS. After an expert breast radiologist provided a region of interest (ROI) mask for the DCIS lesion, the proposed approach is able to segment individual microcalcifications (MCs), detect the boundary of the MC cluster (MCC), and extract 113 mammographic features from MCs and MCC within the ROI. In this study, we extracted mammographic features from 99 patients with DCIS (74 pure DCIS; 25 DCIS plus invasive disease). The predictive power of the mammographic features was demonstrated through binary classifications between pure DCIS and DCIS with invasive disease using linear discriminant analysis (LDA). Before classification, the minimum redundancy Maximum Relevance (mRMR) feature selection method was first applied to choose subsets of useful features. The generalization performance was assessed using Leave-One-Out Cross-Validation and Receiver Operating Characteristic (ROC) curve analysis. Using the computer-extracted mammographic features, the proposed model was able to distinguish DCIS with invasive disease from pure DCIS, with an average classification performance of AUC = 0.61 ± 0.05. Overall, the proposed computer-extracted mammographic features are promising for predicting occult invasive disease in DCIS.",
keywords = "Breast cancer, CAD, Digital mammogram, Ductal carcinoma in situ, Microcalcification",
author = "Bibo Shi and Grimm, {Lars J.} and Mazurowski, {Maciej A.} and Marks, {Jeffrey R.} and King, {Lorraine M.} and Carlo Maley and Hwang, {E. Shelley} and Lo, {Joseph Y.}",
year = "2017",
doi = "10.1117/12.2255731",
language = "English (US)",
volume = "10134",
booktitle = "Medical Imaging 2017",
publisher = "SPIE",
address = "United States",

}

TY - GEN

T1 - Prediction of occult invasive disease in ductal carcinoma in situ using computer-extracted mammographic features

AU - Shi, Bibo

AU - Grimm, Lars J.

AU - Mazurowski, Maciej A.

AU - Marks, Jeffrey R.

AU - King, Lorraine M.

AU - Maley, Carlo

AU - Hwang, E. Shelley

AU - Lo, Joseph Y.

PY - 2017

Y1 - 2017

N2 - Predicting the risk of occult invasive disease in ductal carcinoma in situ (DCIS) is an important task to help address the overdiagnosis and overtreatment problems associated with breast cancer. In this work, we investigated the feasibility of using computer-extracted mammographic features to predict occult invasive disease in patients with biopsy proven DCIS. We proposed a computer-vision algorithm based approach to extract mammographic features from magnification views of full field digital mammography (FFDM) for patients with DCIS. After an expert breast radiologist provided a region of interest (ROI) mask for the DCIS lesion, the proposed approach is able to segment individual microcalcifications (MCs), detect the boundary of the MC cluster (MCC), and extract 113 mammographic features from MCs and MCC within the ROI. In this study, we extracted mammographic features from 99 patients with DCIS (74 pure DCIS; 25 DCIS plus invasive disease). The predictive power of the mammographic features was demonstrated through binary classifications between pure DCIS and DCIS with invasive disease using linear discriminant analysis (LDA). Before classification, the minimum redundancy Maximum Relevance (mRMR) feature selection method was first applied to choose subsets of useful features. The generalization performance was assessed using Leave-One-Out Cross-Validation and Receiver Operating Characteristic (ROC) curve analysis. Using the computer-extracted mammographic features, the proposed model was able to distinguish DCIS with invasive disease from pure DCIS, with an average classification performance of AUC = 0.61 ± 0.05. Overall, the proposed computer-extracted mammographic features are promising for predicting occult invasive disease in DCIS.

AB - Predicting the risk of occult invasive disease in ductal carcinoma in situ (DCIS) is an important task to help address the overdiagnosis and overtreatment problems associated with breast cancer. In this work, we investigated the feasibility of using computer-extracted mammographic features to predict occult invasive disease in patients with biopsy proven DCIS. We proposed a computer-vision algorithm based approach to extract mammographic features from magnification views of full field digital mammography (FFDM) for patients with DCIS. After an expert breast radiologist provided a region of interest (ROI) mask for the DCIS lesion, the proposed approach is able to segment individual microcalcifications (MCs), detect the boundary of the MC cluster (MCC), and extract 113 mammographic features from MCs and MCC within the ROI. In this study, we extracted mammographic features from 99 patients with DCIS (74 pure DCIS; 25 DCIS plus invasive disease). The predictive power of the mammographic features was demonstrated through binary classifications between pure DCIS and DCIS with invasive disease using linear discriminant analysis (LDA). Before classification, the minimum redundancy Maximum Relevance (mRMR) feature selection method was first applied to choose subsets of useful features. The generalization performance was assessed using Leave-One-Out Cross-Validation and Receiver Operating Characteristic (ROC) curve analysis. Using the computer-extracted mammographic features, the proposed model was able to distinguish DCIS with invasive disease from pure DCIS, with an average classification performance of AUC = 0.61 ± 0.05. Overall, the proposed computer-extracted mammographic features are promising for predicting occult invasive disease in DCIS.

KW - Breast cancer

KW - CAD

KW - Digital mammogram

KW - Ductal carcinoma in situ

KW - Microcalcification

UR - http://www.scopus.com/inward/record.url?scp=85020302741&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85020302741&partnerID=8YFLogxK

U2 - 10.1117/12.2255731

DO - 10.1117/12.2255731

M3 - Conference contribution

VL - 10134

BT - Medical Imaging 2017

PB - SPIE

ER -