Breast Cancer Risk Analysis Based on a Novel Segmentation Framework for Digital Mammograms

Susan Astley; Polina Golland; Nobuhiko Hata; Christian Barillot; Joachim Hornegger; Robert Howe

Breast Cancer Risk Analysis Based on a Novel Segmentation Framework for Digital Mammograms

Susan Astley, Polina Golland (Editor), Nobuhiko Hata (Editor), Christian Barillot (Editor), Joachim Hornegger (Editor), Robert Howe (Editor)

Research output: Chapter in Book/Conference proceeding › Conference contribution › peer-review

Abstract

The radiographic appearance of breast tissue has been established as a strong risk factor for breast cancer. Here we present a complete machine learning framework for automatic estimation of mammographic density (MD) and robust feature extraction for breast cancer risk analysis. Our framework is able to simultaneously classify the breast region, fatty tissue, pectoral muscle, glandular tissue and nipple region. Integral to our method is the extraction of measures of breast density (as the fraction of the breast area occupied by glandular tissue) and mammographic pattern. A novel aspect of the segmentation framework is that a probability map associated with the label mask is provided, which indicates the level of confidence of each pixel being classified as the current label. The Pearson correlation coefficient between the estimated MD value and the ground truth is 0.8012 (p-value

Original language	English
Title of host publication	MICCAI 2014: Lecture Notes in Computer Science 8673
Editors	Polina Golland, Nobuhiko Hata, Christian Barillot, Joachim Hornegger, Robert Howe
Publisher	Springer Nature
Pages	536-543
Number of pages	8
Publication status	Published - Sept 2014
Event	Medical Image Computing and Computer-Assisted Intervention – MICCAI 2014 - Boston, USA Duration: 14 Sept 2014 → 18 Sept 2014

Conference

Conference	Medical Image Computing and Computer-Assisted Intervention – MICCAI 2014
City	Boston, USA
Period	14/09/14 → 18/09/14

Keywords

Breast Cancer
Risk
Mammogram
Density
Segmentation
Machine Learning

UN SDGs

This output contributes to the following UN Sustainable Development Goals (SDGs)

Cite this

@inproceedings{c7c7042139d347cfb6f59a8f20cdad0a,

title = "Breast Cancer Risk Analysis Based on a Novel Segmentation Framework for Digital Mammograms",

abstract = "The radiographic appearance of breast tissue has been established as a strong risk factor for breast cancer. Here we present a complete machine learning framework for automatic estimation of mammographic density (MD) and robust feature extraction for breast cancer risk analysis. Our framework is able to simultaneously classify the breast region, fatty tissue, pectoral muscle, glandular tissue and nipple region. Integral to our method is the extraction of measures of breast density (as the fraction of the breast area occupied by glandular tissue) and mammographic pattern. A novel aspect of the segmentation framework is that a probability map associated with the label mask is provided, which indicates the level of confidence of each pixel being classified as the current label. The Pearson correlation coefficient between the estimated MD value and the ground truth is 0.8012 (p-value",

keywords = "Breast Cancer, Risk, Mammogram, Density, Segmentation, Machine Learning",

author = "Susan Astley and Polina Golland and Nobuhiko Hata and Christian Barillot and Joachim Hornegger and Robert Howe",

year = "2014",

month = sep,

language = "English",

pages = "536--543",

editor = "Polina Golland and Nobuhiko Hata and Christian Barillot and Joachim Hornegger and Robert Howe",

booktitle = "MICCAI 2014: Lecture Notes in Computer Science 8673",

publisher = "Springer Nature",

address = "United States",

note = "Medical Image Computing and Computer-Assisted Intervention – MICCAI 2014 ; Conference date: 14-09-2014 Through 18-09-2014",

}

Astley, S, Golland, P (ed.), Hata, N (ed.), Barillot, C (ed.), Hornegger, J (ed.) & Howe, R (ed.) 2014, Breast Cancer Risk Analysis Based on a Novel Segmentation Framework for Digital Mammograms. in P Golland, N Hata, C Barillot, J Hornegger & R Howe (eds), MICCAI 2014: Lecture Notes in Computer Science 8673. Springer Nature, pp. 536-543, Medical Image Computing and Computer-Assisted Intervention – MICCAI 2014, Boston, USA, 14/09/14.

Breast Cancer Risk Analysis Based on a Novel Segmentation Framework for Digital Mammograms. / Astley, Susan; Golland, Polina (Editor); Hata, Nobuhiko (Editor) et al.
MICCAI 2014: Lecture Notes in Computer Science 8673. ed. / Polina Golland; Nobuhiko Hata; Christian Barillot; Joachim Hornegger; Robert Howe. Springer Nature, 2014. p. 536-543.

Research output: Chapter in Book/Conference proceeding › Conference contribution › peer-review

TY - GEN

T1 - Breast Cancer Risk Analysis Based on a Novel Segmentation Framework for Digital Mammograms

AU - Astley, Susan

A2 - Golland, Polina

A2 - Hata, Nobuhiko

A2 - Barillot, Christian

A2 - Hornegger, Joachim

A2 - Howe, Robert

A2 - Golland, Polina

A2 - Hata, Nobuhiko

A2 - Barillot, Christian

A2 - Hornegger, Joachim

A2 - Howe, Robert

PY - 2014/9

Y1 - 2014/9

N2 - The radiographic appearance of breast tissue has been established as a strong risk factor for breast cancer. Here we present a complete machine learning framework for automatic estimation of mammographic density (MD) and robust feature extraction for breast cancer risk analysis. Our framework is able to simultaneously classify the breast region, fatty tissue, pectoral muscle, glandular tissue and nipple region. Integral to our method is the extraction of measures of breast density (as the fraction of the breast area occupied by glandular tissue) and mammographic pattern. A novel aspect of the segmentation framework is that a probability map associated with the label mask is provided, which indicates the level of confidence of each pixel being classified as the current label. The Pearson correlation coefficient between the estimated MD value and the ground truth is 0.8012 (p-value

AB - The radiographic appearance of breast tissue has been established as a strong risk factor for breast cancer. Here we present a complete machine learning framework for automatic estimation of mammographic density (MD) and robust feature extraction for breast cancer risk analysis. Our framework is able to simultaneously classify the breast region, fatty tissue, pectoral muscle, glandular tissue and nipple region. Integral to our method is the extraction of measures of breast density (as the fraction of the breast area occupied by glandular tissue) and mammographic pattern. A novel aspect of the segmentation framework is that a probability map associated with the label mask is provided, which indicates the level of confidence of each pixel being classified as the current label. The Pearson correlation coefficient between the estimated MD value and the ground truth is 0.8012 (p-value

KW - Breast Cancer

KW - Risk

KW - Mammogram

KW - Density

KW - Segmentation

KW - Machine Learning

M3 - Conference contribution

SP - 536

EP - 543

BT - MICCAI 2014: Lecture Notes in Computer Science 8673

PB - Springer Nature

T2 - Medical Image Computing and Computer-Assisted Intervention – MICCAI 2014

Y2 - 14 September 2014 through 18 September 2014

ER -

Breast Cancer Risk Analysis Based on a Novel Segmentation Framework for Digital Mammograms

Abstract

Conference

Keywords

UN SDGs

Fingerprint

Cite this