Automated seeded lesion segmentation on digital mammograms

Matthew A Kupinski, Maryellen L. Giger

Research output: Contribution to journalArticle

225 Citations (Scopus)

Abstract

Segmenting lesions is a vital step in many computerized mass-detection schemes for digital (or digitized) mammograms. We have developed two novel lesion segmentation techniques-one based on a single feature called the radial gradient index (RGI) and one based on simple probabilistic models to segment mass lesions, or other similar nodular structures, from surrounding background. In both methods a series of image partitions is created using gray-level information as well as prior knowledge of the shape of typical mass lesions. With the former method the partition that maximizes the RGI is selected. In the latter method, probability distributions for gray-levels inside and outside the partitions are estimated, and subsequently used to determine the probability that the image occurred for each given partition. The partition that maximizes this probability is selected as the final lesion partition (contour). We tested these methods against a conventional region growing algorithm using a database of biopsy-proven, malignant lesions and found that the new lesion segmentation algorithms more closely match radiologists' outlines of these lesions. At an overlap threshold of 0.30, gray level region growing correctly delineates 62% of the lesions in our database while the RGI and probabilistic segmentation algorithms correctly segment 92% and 96% of the lesions, respectively.

Original languageEnglish (US)
Pages (from-to)510-517
Number of pages8
JournalIEEE Transactions on Medical Imaging
Volume17
Issue number4
StatePublished - 1998
Externally publishedYes

Fingerprint

Biopsy
Databases
Probability distributions
Statistical Models
Radiologists

Keywords

  • Computer-aided diagnosis
  • Digital mammography
  • Lesion segmentation
  • Mass detection

ASJC Scopus subject areas

  • Biomedical Engineering
  • Radiology Nuclear Medicine and imaging
  • Radiological and Ultrasound Technology
  • Electrical and Electronic Engineering
  • Computer Science Applications
  • Computational Theory and Mathematics

Cite this

Automated seeded lesion segmentation on digital mammograms. / Kupinski, Matthew A; Giger, Maryellen L.

In: IEEE Transactions on Medical Imaging, Vol. 17, No. 4, 1998, p. 510-517.

Research output: Contribution to journalArticle

@article{087a252951eb408787cb27faf87a703a,
title = "Automated seeded lesion segmentation on digital mammograms",
abstract = "Segmenting lesions is a vital step in many computerized mass-detection schemes for digital (or digitized) mammograms. We have developed two novel lesion segmentation techniques-one based on a single feature called the radial gradient index (RGI) and one based on simple probabilistic models to segment mass lesions, or other similar nodular structures, from surrounding background. In both methods a series of image partitions is created using gray-level information as well as prior knowledge of the shape of typical mass lesions. With the former method the partition that maximizes the RGI is selected. In the latter method, probability distributions for gray-levels inside and outside the partitions are estimated, and subsequently used to determine the probability that the image occurred for each given partition. The partition that maximizes this probability is selected as the final lesion partition (contour). We tested these methods against a conventional region growing algorithm using a database of biopsy-proven, malignant lesions and found that the new lesion segmentation algorithms more closely match radiologists' outlines of these lesions. At an overlap threshold of 0.30, gray level region growing correctly delineates 62{\%} of the lesions in our database while the RGI and probabilistic segmentation algorithms correctly segment 92{\%} and 96{\%} of the lesions, respectively.",
keywords = "Computer-aided diagnosis, Digital mammography, Lesion segmentation, Mass detection",
author = "Kupinski, {Matthew A} and Giger, {Maryellen L.}",
year = "1998",
language = "English (US)",
volume = "17",
pages = "510--517",
journal = "IEEE Transactions on Medical Imaging",
issn = "0278-0062",
publisher = "Institute of Electrical and Electronics Engineers Inc.",
number = "4",

}

TY - JOUR

T1 - Automated seeded lesion segmentation on digital mammograms

AU - Kupinski, Matthew A

AU - Giger, Maryellen L.

PY - 1998

Y1 - 1998

N2 - Segmenting lesions is a vital step in many computerized mass-detection schemes for digital (or digitized) mammograms. We have developed two novel lesion segmentation techniques-one based on a single feature called the radial gradient index (RGI) and one based on simple probabilistic models to segment mass lesions, or other similar nodular structures, from surrounding background. In both methods a series of image partitions is created using gray-level information as well as prior knowledge of the shape of typical mass lesions. With the former method the partition that maximizes the RGI is selected. In the latter method, probability distributions for gray-levels inside and outside the partitions are estimated, and subsequently used to determine the probability that the image occurred for each given partition. The partition that maximizes this probability is selected as the final lesion partition (contour). We tested these methods against a conventional region growing algorithm using a database of biopsy-proven, malignant lesions and found that the new lesion segmentation algorithms more closely match radiologists' outlines of these lesions. At an overlap threshold of 0.30, gray level region growing correctly delineates 62% of the lesions in our database while the RGI and probabilistic segmentation algorithms correctly segment 92% and 96% of the lesions, respectively.

AB - Segmenting lesions is a vital step in many computerized mass-detection schemes for digital (or digitized) mammograms. We have developed two novel lesion segmentation techniques-one based on a single feature called the radial gradient index (RGI) and one based on simple probabilistic models to segment mass lesions, or other similar nodular structures, from surrounding background. In both methods a series of image partitions is created using gray-level information as well as prior knowledge of the shape of typical mass lesions. With the former method the partition that maximizes the RGI is selected. In the latter method, probability distributions for gray-levels inside and outside the partitions are estimated, and subsequently used to determine the probability that the image occurred for each given partition. The partition that maximizes this probability is selected as the final lesion partition (contour). We tested these methods against a conventional region growing algorithm using a database of biopsy-proven, malignant lesions and found that the new lesion segmentation algorithms more closely match radiologists' outlines of these lesions. At an overlap threshold of 0.30, gray level region growing correctly delineates 62% of the lesions in our database while the RGI and probabilistic segmentation algorithms correctly segment 92% and 96% of the lesions, respectively.

KW - Computer-aided diagnosis

KW - Digital mammography

KW - Lesion segmentation

KW - Mass detection

UR - http://www.scopus.com/inward/record.url?scp=0032129152&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=0032129152&partnerID=8YFLogxK

M3 - Article

C2 - 9845307

AN - SCOPUS:0032129152

VL - 17

SP - 510

EP - 517

JO - IEEE Transactions on Medical Imaging

JF - IEEE Transactions on Medical Imaging

SN - 0278-0062

IS - 4

ER -