STEP

Spatial-temporal enhancement pattern, for MR-based breast tumor diagnosis

Zheng Yuanjie, Sarah Englander, Mitchell D. Schnall, Dinggang Shen

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

3 Citations (Scopus)

Abstract

This paper demonstrates the importance of capturing SpatialTemporal Enhancement Pattern (STEP) for completely characterizing breast tumor in contrast-enhanced MR images. STEP captures not only the dynamic enhancement and architectural features of tumor, but also the spatial variations of pixel-wise temporal enhancement of tumor. Although the latter has been widely used by radiologist during diagnosis, it is rarely considered as important features for computer-aided tumor diagnosis. Notice that, by regarding serial contrast-enhanced images as a single spatial-temporal image, STEP can capture all types of the features within a single framework. In particular, a Fourier transformation is used to extract various temporal enhancement features, followed by moment invariants to capture spatial patterns of each temporal enhancement feature. Experimental results show the better performance of our designed STEP features than many other features available in the literature. The area under ROC curve can reach 0.96 with our STEP features in tumor diagnosis.

Original languageEnglish
Title of host publication2007 4th IEEE International Symposium on Biomedical Imaging: From Nano to Macro - Proceedings
Pages520-523
Number of pages4
DOIs
Publication statusPublished - 2007 Nov 27
Externally publishedYes
Event2007 4th IEEE International Symposium on Biomedical Imaging: From Nano to Macro; ISBI'07 - Arlington, VA, United States
Duration: 2007 Apr 122007 Apr 15

Other

Other2007 4th IEEE International Symposium on Biomedical Imaging: From Nano to Macro; ISBI'07
CountryUnited States
CityArlington, VA
Period07/4/1207/4/15

Fingerprint

Tumors
Breast Neoplasms
Neoplasms
Image Enhancement
ROC Curve
Image enhancement
Area Under Curve
Pixels

Keywords

  • Breast tumor diagnosis
  • Feature extraction
  • Magnetic resonance imaging

ASJC Scopus subject areas

  • Electrical and Electronic Engineering
  • Medicine(all)

Cite this

Yuanjie, Z., Englander, S., Schnall, M. D., & Shen, D. (2007). STEP: Spatial-temporal enhancement pattern, for MR-based breast tumor diagnosis. In 2007 4th IEEE International Symposium on Biomedical Imaging: From Nano to Macro - Proceedings (pp. 520-523). [4193337] https://doi.org/10.1109/ISBI.2007.356903

STEP : Spatial-temporal enhancement pattern, for MR-based breast tumor diagnosis. / Yuanjie, Zheng; Englander, Sarah; Schnall, Mitchell D.; Shen, Dinggang.

2007 4th IEEE International Symposium on Biomedical Imaging: From Nano to Macro - Proceedings. 2007. p. 520-523 4193337.

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

Yuanjie, Z, Englander, S, Schnall, MD & Shen, D 2007, STEP: Spatial-temporal enhancement pattern, for MR-based breast tumor diagnosis. in 2007 4th IEEE International Symposium on Biomedical Imaging: From Nano to Macro - Proceedings., 4193337, pp. 520-523, 2007 4th IEEE International Symposium on Biomedical Imaging: From Nano to Macro; ISBI'07, Arlington, VA, United States, 07/4/12. https://doi.org/10.1109/ISBI.2007.356903
Yuanjie Z, Englander S, Schnall MD, Shen D. STEP: Spatial-temporal enhancement pattern, for MR-based breast tumor diagnosis. In 2007 4th IEEE International Symposium on Biomedical Imaging: From Nano to Macro - Proceedings. 2007. p. 520-523. 4193337 https://doi.org/10.1109/ISBI.2007.356903
Yuanjie, Zheng ; Englander, Sarah ; Schnall, Mitchell D. ; Shen, Dinggang. / STEP : Spatial-temporal enhancement pattern, for MR-based breast tumor diagnosis. 2007 4th IEEE International Symposium on Biomedical Imaging: From Nano to Macro - Proceedings. 2007. pp. 520-523
@inproceedings{20441fe1e27640149071f3238a026543,
title = "STEP: Spatial-temporal enhancement pattern, for MR-based breast tumor diagnosis",
abstract = "This paper demonstrates the importance of capturing SpatialTemporal Enhancement Pattern (STEP) for completely characterizing breast tumor in contrast-enhanced MR images. STEP captures not only the dynamic enhancement and architectural features of tumor, but also the spatial variations of pixel-wise temporal enhancement of tumor. Although the latter has been widely used by radiologist during diagnosis, it is rarely considered as important features for computer-aided tumor diagnosis. Notice that, by regarding serial contrast-enhanced images as a single spatial-temporal image, STEP can capture all types of the features within a single framework. In particular, a Fourier transformation is used to extract various temporal enhancement features, followed by moment invariants to capture spatial patterns of each temporal enhancement feature. Experimental results show the better performance of our designed STEP features than many other features available in the literature. The area under ROC curve can reach 0.96 with our STEP features in tumor diagnosis.",
keywords = "Breast tumor diagnosis, Feature extraction, Magnetic resonance imaging",
author = "Zheng Yuanjie and Sarah Englander and Schnall, {Mitchell D.} and Dinggang Shen",
year = "2007",
month = "11",
day = "27",
doi = "10.1109/ISBI.2007.356903",
language = "English",
isbn = "1424406722",
pages = "520--523",
booktitle = "2007 4th IEEE International Symposium on Biomedical Imaging: From Nano to Macro - Proceedings",

}

TY - GEN

T1 - STEP

T2 - Spatial-temporal enhancement pattern, for MR-based breast tumor diagnosis

AU - Yuanjie, Zheng

AU - Englander, Sarah

AU - Schnall, Mitchell D.

AU - Shen, Dinggang

PY - 2007/11/27

Y1 - 2007/11/27

N2 - This paper demonstrates the importance of capturing SpatialTemporal Enhancement Pattern (STEP) for completely characterizing breast tumor in contrast-enhanced MR images. STEP captures not only the dynamic enhancement and architectural features of tumor, but also the spatial variations of pixel-wise temporal enhancement of tumor. Although the latter has been widely used by radiologist during diagnosis, it is rarely considered as important features for computer-aided tumor diagnosis. Notice that, by regarding serial contrast-enhanced images as a single spatial-temporal image, STEP can capture all types of the features within a single framework. In particular, a Fourier transformation is used to extract various temporal enhancement features, followed by moment invariants to capture spatial patterns of each temporal enhancement feature. Experimental results show the better performance of our designed STEP features than many other features available in the literature. The area under ROC curve can reach 0.96 with our STEP features in tumor diagnosis.

AB - This paper demonstrates the importance of capturing SpatialTemporal Enhancement Pattern (STEP) for completely characterizing breast tumor in contrast-enhanced MR images. STEP captures not only the dynamic enhancement and architectural features of tumor, but also the spatial variations of pixel-wise temporal enhancement of tumor. Although the latter has been widely used by radiologist during diagnosis, it is rarely considered as important features for computer-aided tumor diagnosis. Notice that, by regarding serial contrast-enhanced images as a single spatial-temporal image, STEP can capture all types of the features within a single framework. In particular, a Fourier transformation is used to extract various temporal enhancement features, followed by moment invariants to capture spatial patterns of each temporal enhancement feature. Experimental results show the better performance of our designed STEP features than many other features available in the literature. The area under ROC curve can reach 0.96 with our STEP features in tumor diagnosis.

KW - Breast tumor diagnosis

KW - Feature extraction

KW - Magnetic resonance imaging

UR - http://www.scopus.com/inward/record.url?scp=36349015390&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=36349015390&partnerID=8YFLogxK

U2 - 10.1109/ISBI.2007.356903

DO - 10.1109/ISBI.2007.356903

M3 - Conference contribution

SN - 1424406722

SN - 9781424406722

SP - 520

EP - 523

BT - 2007 4th IEEE International Symposium on Biomedical Imaging: From Nano to Macro - Proceedings

ER -