Liver tumor detection and classification using content-based image retrieval

Y. Chi, J. Liu, Sudhakar K Venkatesh, J. Zhou, Q. Tian, W. L. Nowinski

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

2 Citations (Scopus)

Abstract

Computer aided liver tumor detection and diagnosis can assist radiologists to interpret abnormal features in liver CT scans. In this paper, a general frame work is proposed to automatically detect liver focal mass lesions, conduct differential diagnosis of liver focal mass lesions based on multiphase CT scans, and provide visually similar case samples for comparisons. The proposed method first detects liver abnormalities by eliminating the normal tissue/organ from the liver region, and in the second step it ranks these abnormalities with respect to spherical symmetry, compactness and size using a tumoroid measure to facilitate fast location of liver focal mass lesions. To differentiate liver focal mass lesions, content-based image retrieval technique is used to query a CT model database with known diagnosis. Multiple-phase encoded texture features are proposed to represent the focal mass lesions. A hypercube indexing structure based method is adopted as the retrieval strategy and the similarity score is calculated to rank the retrieval results. Good performances are obtained from eight clinical CT scans. With the proposed method, the clinician is expected to improve the accuracy of differential diagnosis.

Original languageEnglish (US)
Title of host publicationProgress in Biomedical Optics and Imaging - Proceedings of SPIE
Volume7963
DOIs
StatePublished - 2011
Externally publishedYes
EventMedical Imaging 2011: Computer-Aided Diagnosis - Lake Buena Vista, FL, United States
Duration: Feb 15 2011Feb 17 2011

Other

OtherMedical Imaging 2011: Computer-Aided Diagnosis
CountryUnited States
CityLake Buena Vista, FL
Period2/15/112/17/11

Fingerprint

Image retrieval
liver
Liver
retrieval
Tumors
tumors
lesions
Computerized tomography
Neoplasms
abnormalities
Differential Diagnosis
void ratio
organs
textures
Textures
Databases
Tissue
symmetry

Keywords

  • computer-aided diagnosis
  • content-based image retrieval
  • focal liver mass detection and classification
  • hyper-cube structure indexing
  • multiphase CT scans
  • multiple-phase encoded texture feature

ASJC Scopus subject areas

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

Cite this

Chi, Y., Liu, J., Venkatesh, S. K., Zhou, J., Tian, Q., & Nowinski, W. L. (2011). Liver tumor detection and classification using content-based image retrieval. In Progress in Biomedical Optics and Imaging - Proceedings of SPIE (Vol. 7963). [79632D] https://doi.org/10.1117/12.877919

Liver tumor detection and classification using content-based image retrieval. / Chi, Y.; Liu, J.; Venkatesh, Sudhakar K; Zhou, J.; Tian, Q.; Nowinski, W. L.

Progress in Biomedical Optics and Imaging - Proceedings of SPIE. Vol. 7963 2011. 79632D.

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

Chi, Y, Liu, J, Venkatesh, SK, Zhou, J, Tian, Q & Nowinski, WL 2011, Liver tumor detection and classification using content-based image retrieval. in Progress in Biomedical Optics and Imaging - Proceedings of SPIE. vol. 7963, 79632D, Medical Imaging 2011: Computer-Aided Diagnosis, Lake Buena Vista, FL, United States, 2/15/11. https://doi.org/10.1117/12.877919
Chi Y, Liu J, Venkatesh SK, Zhou J, Tian Q, Nowinski WL. Liver tumor detection and classification using content-based image retrieval. In Progress in Biomedical Optics and Imaging - Proceedings of SPIE. Vol. 7963. 2011. 79632D https://doi.org/10.1117/12.877919
Chi, Y. ; Liu, J. ; Venkatesh, Sudhakar K ; Zhou, J. ; Tian, Q. ; Nowinski, W. L. / Liver tumor detection and classification using content-based image retrieval. Progress in Biomedical Optics and Imaging - Proceedings of SPIE. Vol. 7963 2011.
@inproceedings{86b21ceedc3548709fdf1885c32391e5,
title = "Liver tumor detection and classification using content-based image retrieval",
abstract = "Computer aided liver tumor detection and diagnosis can assist radiologists to interpret abnormal features in liver CT scans. In this paper, a general frame work is proposed to automatically detect liver focal mass lesions, conduct differential diagnosis of liver focal mass lesions based on multiphase CT scans, and provide visually similar case samples for comparisons. The proposed method first detects liver abnormalities by eliminating the normal tissue/organ from the liver region, and in the second step it ranks these abnormalities with respect to spherical symmetry, compactness and size using a tumoroid measure to facilitate fast location of liver focal mass lesions. To differentiate liver focal mass lesions, content-based image retrieval technique is used to query a CT model database with known diagnosis. Multiple-phase encoded texture features are proposed to represent the focal mass lesions. A hypercube indexing structure based method is adopted as the retrieval strategy and the similarity score is calculated to rank the retrieval results. Good performances are obtained from eight clinical CT scans. With the proposed method, the clinician is expected to improve the accuracy of differential diagnosis.",
keywords = "computer-aided diagnosis, content-based image retrieval, focal liver mass detection and classification, hyper-cube structure indexing, multiphase CT scans, multiple-phase encoded texture feature",
author = "Y. Chi and J. Liu and Venkatesh, {Sudhakar K} and J. Zhou and Q. Tian and Nowinski, {W. L.}",
year = "2011",
doi = "10.1117/12.877919",
language = "English (US)",
isbn = "9780819485052",
volume = "7963",
booktitle = "Progress in Biomedical Optics and Imaging - Proceedings of SPIE",

}

TY - GEN

T1 - Liver tumor detection and classification using content-based image retrieval

AU - Chi, Y.

AU - Liu, J.

AU - Venkatesh, Sudhakar K

AU - Zhou, J.

AU - Tian, Q.

AU - Nowinski, W. L.

PY - 2011

Y1 - 2011

N2 - Computer aided liver tumor detection and diagnosis can assist radiologists to interpret abnormal features in liver CT scans. In this paper, a general frame work is proposed to automatically detect liver focal mass lesions, conduct differential diagnosis of liver focal mass lesions based on multiphase CT scans, and provide visually similar case samples for comparisons. The proposed method first detects liver abnormalities by eliminating the normal tissue/organ from the liver region, and in the second step it ranks these abnormalities with respect to spherical symmetry, compactness and size using a tumoroid measure to facilitate fast location of liver focal mass lesions. To differentiate liver focal mass lesions, content-based image retrieval technique is used to query a CT model database with known diagnosis. Multiple-phase encoded texture features are proposed to represent the focal mass lesions. A hypercube indexing structure based method is adopted as the retrieval strategy and the similarity score is calculated to rank the retrieval results. Good performances are obtained from eight clinical CT scans. With the proposed method, the clinician is expected to improve the accuracy of differential diagnosis.

AB - Computer aided liver tumor detection and diagnosis can assist radiologists to interpret abnormal features in liver CT scans. In this paper, a general frame work is proposed to automatically detect liver focal mass lesions, conduct differential diagnosis of liver focal mass lesions based on multiphase CT scans, and provide visually similar case samples for comparisons. The proposed method first detects liver abnormalities by eliminating the normal tissue/organ from the liver region, and in the second step it ranks these abnormalities with respect to spherical symmetry, compactness and size using a tumoroid measure to facilitate fast location of liver focal mass lesions. To differentiate liver focal mass lesions, content-based image retrieval technique is used to query a CT model database with known diagnosis. Multiple-phase encoded texture features are proposed to represent the focal mass lesions. A hypercube indexing structure based method is adopted as the retrieval strategy and the similarity score is calculated to rank the retrieval results. Good performances are obtained from eight clinical CT scans. With the proposed method, the clinician is expected to improve the accuracy of differential diagnosis.

KW - computer-aided diagnosis

KW - content-based image retrieval

KW - focal liver mass detection and classification

KW - hyper-cube structure indexing

KW - multiphase CT scans

KW - multiple-phase encoded texture feature

UR - http://www.scopus.com/inward/record.url?scp=79955759274&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=79955759274&partnerID=8YFLogxK

U2 - 10.1117/12.877919

DO - 10.1117/12.877919

M3 - Conference contribution

AN - SCOPUS:79955759274

SN - 9780819485052

VL - 7963

BT - Progress in Biomedical Optics and Imaging - Proceedings of SPIE

ER -