3D localization of clustered microcalcifications using cranio-caudal and medio-lateral oblique views

Sheng Chih Yang, Hsian He Hsu, Giu Cheng Hsu, Pau-Choo Chung, Shu-Mei Guo, Chien Shen Lo, Ching Wen Yang, San Kan Lee, Chein I. Chang

Research output: Contribution to journalArticle

8 Citations (Scopus)

Abstract

This paper presents a 3D localization method to register clustered microcalcifications on mammograms from cranio-caudal (CC) and medio-lateral oblique (MLO) views. The method consists of three major components: registration of clustered microcalcifications in CC and MLO views, 3D localization of clustered microcalcifications and 3D visualization of clustered microcalcifications. The registration is performed based on three features, gradient, energy and local entropy codes that are independent of spatial locations of microcalcifications in two different views and are prioritized by discriminability in a binary decision tree. The 3D localization is determined by a sequence of coordinate corrections of calcified pixels using the breast nipple as a controlling point. Finally, the 3D visualization implements a virtual reality modeling language viewer (VRMLV) to view the exact location of the lesion as a guide for needle biopsy. In order to validate our proposed 3D localization system, a set of breast lesions, which appear both in mammograms and in MR Images is used for experiments where the depth of clustered microcalcifications can be verified by the MR images.

Original languageEnglish
Pages (from-to)521-532
Number of pages12
JournalComputerized Medical Imaging and Graphics
Volume29
Issue number7
DOIs
Publication statusPublished - 2005 Oct 1

Fingerprint

Calcinosis
Visualization
Biopsy
Decision trees
Needles
Virtual reality
Entropy
Pixels
Breast
Decision Trees
Nipples
Experiments
Needle Biopsy
Language
Modeling languages

All Science Journal Classification (ASJC) codes

  • Radiological and Ultrasound Technology
  • Radiology Nuclear Medicine and imaging
  • Computer Vision and Pattern Recognition
  • Health Informatics
  • Computer Graphics and Computer-Aided Design

Cite this

Yang, Sheng Chih ; Hsu, Hsian He ; Hsu, Giu Cheng ; Chung, Pau-Choo ; Guo, Shu-Mei ; Lo, Chien Shen ; Yang, Ching Wen ; Lee, San Kan ; Chang, Chein I. / 3D localization of clustered microcalcifications using cranio-caudal and medio-lateral oblique views. In: Computerized Medical Imaging and Graphics. 2005 ; Vol. 29, No. 7. pp. 521-532.
@article{343f2c3a60444420b61df29b209ea23e,
title = "3D localization of clustered microcalcifications using cranio-caudal and medio-lateral oblique views",
abstract = "This paper presents a 3D localization method to register clustered microcalcifications on mammograms from cranio-caudal (CC) and medio-lateral oblique (MLO) views. The method consists of three major components: registration of clustered microcalcifications in CC and MLO views, 3D localization of clustered microcalcifications and 3D visualization of clustered microcalcifications. The registration is performed based on three features, gradient, energy and local entropy codes that are independent of spatial locations of microcalcifications in two different views and are prioritized by discriminability in a binary decision tree. The 3D localization is determined by a sequence of coordinate corrections of calcified pixels using the breast nipple as a controlling point. Finally, the 3D visualization implements a virtual reality modeling language viewer (VRMLV) to view the exact location of the lesion as a guide for needle biopsy. In order to validate our proposed 3D localization system, a set of breast lesions, which appear both in mammograms and in MR Images is used for experiments where the depth of clustered microcalcifications can be verified by the MR images.",
author = "Yang, {Sheng Chih} and Hsu, {Hsian He} and Hsu, {Giu Cheng} and Pau-Choo Chung and Shu-Mei Guo and Lo, {Chien Shen} and Yang, {Ching Wen} and Lee, {San Kan} and Chang, {Chein I.}",
year = "2005",
month = "10",
day = "1",
doi = "10.1016/j.compmedimag.2005.05.001",
language = "English",
volume = "29",
pages = "521--532",
journal = "Computerized Medical Imaging and Graphics",
issn = "0895-6111",
publisher = "Elsevier Limited",
number = "7",

}

3D localization of clustered microcalcifications using cranio-caudal and medio-lateral oblique views. / Yang, Sheng Chih; Hsu, Hsian He; Hsu, Giu Cheng; Chung, Pau-Choo; Guo, Shu-Mei; Lo, Chien Shen; Yang, Ching Wen; Lee, San Kan; Chang, Chein I.

In: Computerized Medical Imaging and Graphics, Vol. 29, No. 7, 01.10.2005, p. 521-532.

Research output: Contribution to journalArticle

TY - JOUR

T1 - 3D localization of clustered microcalcifications using cranio-caudal and medio-lateral oblique views

AU - Yang, Sheng Chih

AU - Hsu, Hsian He

AU - Hsu, Giu Cheng

AU - Chung, Pau-Choo

AU - Guo, Shu-Mei

AU - Lo, Chien Shen

AU - Yang, Ching Wen

AU - Lee, San Kan

AU - Chang, Chein I.

PY - 2005/10/1

Y1 - 2005/10/1

N2 - This paper presents a 3D localization method to register clustered microcalcifications on mammograms from cranio-caudal (CC) and medio-lateral oblique (MLO) views. The method consists of three major components: registration of clustered microcalcifications in CC and MLO views, 3D localization of clustered microcalcifications and 3D visualization of clustered microcalcifications. The registration is performed based on three features, gradient, energy and local entropy codes that are independent of spatial locations of microcalcifications in two different views and are prioritized by discriminability in a binary decision tree. The 3D localization is determined by a sequence of coordinate corrections of calcified pixels using the breast nipple as a controlling point. Finally, the 3D visualization implements a virtual reality modeling language viewer (VRMLV) to view the exact location of the lesion as a guide for needle biopsy. In order to validate our proposed 3D localization system, a set of breast lesions, which appear both in mammograms and in MR Images is used for experiments where the depth of clustered microcalcifications can be verified by the MR images.

AB - This paper presents a 3D localization method to register clustered microcalcifications on mammograms from cranio-caudal (CC) and medio-lateral oblique (MLO) views. The method consists of three major components: registration of clustered microcalcifications in CC and MLO views, 3D localization of clustered microcalcifications and 3D visualization of clustered microcalcifications. The registration is performed based on three features, gradient, energy and local entropy codes that are independent of spatial locations of microcalcifications in two different views and are prioritized by discriminability in a binary decision tree. The 3D localization is determined by a sequence of coordinate corrections of calcified pixels using the breast nipple as a controlling point. Finally, the 3D visualization implements a virtual reality modeling language viewer (VRMLV) to view the exact location of the lesion as a guide for needle biopsy. In order to validate our proposed 3D localization system, a set of breast lesions, which appear both in mammograms and in MR Images is used for experiments where the depth of clustered microcalcifications can be verified by the MR images.

UR - http://www.scopus.com/inward/record.url?scp=27744438085&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=27744438085&partnerID=8YFLogxK

U2 - 10.1016/j.compmedimag.2005.05.001

DO - 10.1016/j.compmedimag.2005.05.001

M3 - Article

C2 - 15996852

AN - SCOPUS:27744438085

VL - 29

SP - 521

EP - 532

JO - Computerized Medical Imaging and Graphics

JF - Computerized Medical Imaging and Graphics

SN - 0895-6111

IS - 7

ER -