Intelligent shape feature extraction and indexing for efficient content-based medical image retrieval

Phillip A Mlsna, Nikolay M. Sirakov

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

13 Citations (Scopus)

Abstract

We describe the development of novel and efficient approaches and algorithms for a medical image content-based retrieval system capable of extracting and indexing key information about region shape. First, the general structure and the main components of the system are discussed. For grayscale segmentation to locate regions, we have explored a fast active contour approach based on the geometric heat differential equation. Region representation involves a set of extracted shape-based features. A technique for feature organization using N-dimensional feature vectors is employed. The image retrieval process compares similarity of query vectors to the indexed feature vectors. A convex hull model using the heat differential equation is used to organize the index of features to reduce the search space. Some experiments have been performed to test and validate certain portions of our approach. Finally, advantages and disadvantages together with the computational complexity of this system are discussed.

Original languageEnglish (US)
Title of host publicationProceedings of the IEEE Southwest Symposium on Image Analysis and Interpretation
Pages172-176
Number of pages5
Volume6
StatePublished - 2004
Event2004 IEEE Southwest Symposium on Image Analysis and Interpretation - Lake Tahoe, NV, United States
Duration: Mar 28 2004Mar 30 2004

Other

Other2004 IEEE Southwest Symposium on Image Analysis and Interpretation
CountryUnited States
CityLake Tahoe, NV
Period3/28/043/30/04

Fingerprint

Image retrieval
Feature extraction
Differential equations
Content based retrieval
Computational complexity
Experiments
Hot Temperature

ASJC Scopus subject areas

  • Computer Vision and Pattern Recognition

Cite this

Mlsna, P. A., & Sirakov, N. M. (2004). Intelligent shape feature extraction and indexing for efficient content-based medical image retrieval. In Proceedings of the IEEE Southwest Symposium on Image Analysis and Interpretation (Vol. 6, pp. 172-176)

Intelligent shape feature extraction and indexing for efficient content-based medical image retrieval. / Mlsna, Phillip A; Sirakov, Nikolay M.

Proceedings of the IEEE Southwest Symposium on Image Analysis and Interpretation. Vol. 6 2004. p. 172-176.

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

Mlsna, PA & Sirakov, NM 2004, Intelligent shape feature extraction and indexing for efficient content-based medical image retrieval. in Proceedings of the IEEE Southwest Symposium on Image Analysis and Interpretation. vol. 6, pp. 172-176, 2004 IEEE Southwest Symposium on Image Analysis and Interpretation, Lake Tahoe, NV, United States, 3/28/04.
Mlsna PA, Sirakov NM. Intelligent shape feature extraction and indexing for efficient content-based medical image retrieval. In Proceedings of the IEEE Southwest Symposium on Image Analysis and Interpretation. Vol. 6. 2004. p. 172-176
Mlsna, Phillip A ; Sirakov, Nikolay M. / Intelligent shape feature extraction and indexing for efficient content-based medical image retrieval. Proceedings of the IEEE Southwest Symposium on Image Analysis and Interpretation. Vol. 6 2004. pp. 172-176
@inproceedings{19df4f8b2e564ff5943be021ac7f5e56,
title = "Intelligent shape feature extraction and indexing for efficient content-based medical image retrieval",
abstract = "We describe the development of novel and efficient approaches and algorithms for a medical image content-based retrieval system capable of extracting and indexing key information about region shape. First, the general structure and the main components of the system are discussed. For grayscale segmentation to locate regions, we have explored a fast active contour approach based on the geometric heat differential equation. Region representation involves a set of extracted shape-based features. A technique for feature organization using N-dimensional feature vectors is employed. The image retrieval process compares similarity of query vectors to the indexed feature vectors. A convex hull model using the heat differential equation is used to organize the index of features to reduce the search space. Some experiments have been performed to test and validate certain portions of our approach. Finally, advantages and disadvantages together with the computational complexity of this system are discussed.",
author = "Mlsna, {Phillip A} and Sirakov, {Nikolay M.}",
year = "2004",
language = "English (US)",
volume = "6",
pages = "172--176",
booktitle = "Proceedings of the IEEE Southwest Symposium on Image Analysis and Interpretation",

}

TY - GEN

T1 - Intelligent shape feature extraction and indexing for efficient content-based medical image retrieval

AU - Mlsna, Phillip A

AU - Sirakov, Nikolay M.

PY - 2004

Y1 - 2004

N2 - We describe the development of novel and efficient approaches and algorithms for a medical image content-based retrieval system capable of extracting and indexing key information about region shape. First, the general structure and the main components of the system are discussed. For grayscale segmentation to locate regions, we have explored a fast active contour approach based on the geometric heat differential equation. Region representation involves a set of extracted shape-based features. A technique for feature organization using N-dimensional feature vectors is employed. The image retrieval process compares similarity of query vectors to the indexed feature vectors. A convex hull model using the heat differential equation is used to organize the index of features to reduce the search space. Some experiments have been performed to test and validate certain portions of our approach. Finally, advantages and disadvantages together with the computational complexity of this system are discussed.

AB - We describe the development of novel and efficient approaches and algorithms for a medical image content-based retrieval system capable of extracting and indexing key information about region shape. First, the general structure and the main components of the system are discussed. For grayscale segmentation to locate regions, we have explored a fast active contour approach based on the geometric heat differential equation. Region representation involves a set of extracted shape-based features. A technique for feature organization using N-dimensional feature vectors is employed. The image retrieval process compares similarity of query vectors to the indexed feature vectors. A convex hull model using the heat differential equation is used to organize the index of features to reduce the search space. Some experiments have been performed to test and validate certain portions of our approach. Finally, advantages and disadvantages together with the computational complexity of this system are discussed.

UR - http://www.scopus.com/inward/record.url?scp=2942619105&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=2942619105&partnerID=8YFLogxK

M3 - Conference contribution

VL - 6

SP - 172

EP - 176

BT - Proceedings of the IEEE Southwest Symposium on Image Analysis and Interpretation

ER -