Pathology-centric medical image retrieval with hierarchical contextual spatial descriptor

Yang Song; Weidong Cai; Yun Zhou; Lingfeng Wen; David Dagan Feng

doi:10.1109/ISBI.2013.6556446

Pathology-centric medical image retrieval with hierarchical contextual spatial descriptor

Yang Song, Weidong Cai, Yun Zhou, Lingfeng Wen, David Dagan Feng

School of Medicine

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

12 Scopus citations

Abstract

Content-based image retrieval has been suggested as an aid to medical diagnosis. Techniques based on standard feature descriptors, however, might not represent optimally the pathological characteristics in medical images. In this paper, we propose a new approach for medical image retrieval based on pathology-centric feature extraction and representation; and patch-based local feature extraction and hierarchical contextual spatial descriptor are designed. The proposed method is evaluated on positron emission tomography - computed tomography (PET-CT) images from subjects with non-small cell lung cancer (NSCLC), showing promising performance improvements over the other benchmarked techniques.

Original language	English (US)
Title of host publication	Proceedings - International Symposium on Biomedical Imaging
Pages	198-201
Number of pages	4
DOIs	https://doi.org/10.1109/ISBI.2013.6556446
State	Published - 2013
Event	2013 IEEE 10th International Symposium on Biomedical Imaging: From Nano to Macro, ISBI 2013 - San Francisco, CA, United States Duration: Apr 7 2013 → Apr 11 2013

Other

Other	2013 IEEE 10th International Symposium on Biomedical Imaging: From Nano to Macro, ISBI 2013
Country/Territory	United States
City	San Francisco, CA
Period	4/7/13 → 4/11/13

Keywords

context
local
Retrieval
spatial
tumor

ASJC Scopus subject areas

Biomedical Engineering
Radiology Nuclear Medicine and imaging

Access to Document

10.1109/ISBI.2013.6556446

Cite this

Song, Y, Cai, W, Zhou, Y, Wen, L & Feng, DD 2013, Pathology-centric medical image retrieval with hierarchical contextual spatial descriptor. in Proceedings - International Symposium on Biomedical Imaging., 6556446, pp. 198-201, 2013 IEEE 10th International Symposium on Biomedical Imaging: From Nano to Macro, ISBI 2013, San Francisco, CA, United States, 4/7/13. https://doi.org/10.1109/ISBI.2013.6556446

@inproceedings{a963d334257442a48c04d94421f524f0,

title = "Pathology-centric medical image retrieval with hierarchical contextual spatial descriptor",

abstract = "Content-based image retrieval has been suggested as an aid to medical diagnosis. Techniques based on standard feature descriptors, however, might not represent optimally the pathological characteristics in medical images. In this paper, we propose a new approach for medical image retrieval based on pathology-centric feature extraction and representation; and patch-based local feature extraction and hierarchical contextual spatial descriptor are designed. The proposed method is evaluated on positron emission tomography - computed tomography (PET-CT) images from subjects with non-small cell lung cancer (NSCLC), showing promising performance improvements over the other benchmarked techniques.",

keywords = "context, local, Retrieval, spatial, tumor",

author = "Yang Song and Weidong Cai and Yun Zhou and Lingfeng Wen and Feng, {David Dagan}",

year = "2013",

doi = "10.1109/ISBI.2013.6556446",

language = "English (US)",

isbn = "9781467364546",

pages = "198--201",

booktitle = "Proceedings - International Symposium on Biomedical Imaging",

note = "2013 IEEE 10th International Symposium on Biomedical Imaging: From Nano to Macro, ISBI 2013 ; Conference date: 07-04-2013 Through 11-04-2013",

}

TY - GEN

T1 - Pathology-centric medical image retrieval with hierarchical contextual spatial descriptor

AU - Song, Yang

AU - Cai, Weidong

AU - Zhou, Yun

AU - Wen, Lingfeng

AU - Feng, David Dagan

PY - 2013

Y1 - 2013

N2 - Content-based image retrieval has been suggested as an aid to medical diagnosis. Techniques based on standard feature descriptors, however, might not represent optimally the pathological characteristics in medical images. In this paper, we propose a new approach for medical image retrieval based on pathology-centric feature extraction and representation; and patch-based local feature extraction and hierarchical contextual spatial descriptor are designed. The proposed method is evaluated on positron emission tomography - computed tomography (PET-CT) images from subjects with non-small cell lung cancer (NSCLC), showing promising performance improvements over the other benchmarked techniques.

AB - Content-based image retrieval has been suggested as an aid to medical diagnosis. Techniques based on standard feature descriptors, however, might not represent optimally the pathological characteristics in medical images. In this paper, we propose a new approach for medical image retrieval based on pathology-centric feature extraction and representation; and patch-based local feature extraction and hierarchical contextual spatial descriptor are designed. The proposed method is evaluated on positron emission tomography - computed tomography (PET-CT) images from subjects with non-small cell lung cancer (NSCLC), showing promising performance improvements over the other benchmarked techniques.

KW - context

KW - local

KW - Retrieval

KW - spatial

KW - tumor

UR - http://www.scopus.com/inward/record.url?scp=84881627189&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84881627189&partnerID=8YFLogxK

U2 - 10.1109/ISBI.2013.6556446

DO - 10.1109/ISBI.2013.6556446

M3 - Conference contribution

AN - SCOPUS:84881627189

SN - 9781467364546

SP - 198

EP - 201

BT - Proceedings - International Symposium on Biomedical Imaging

T2 - 2013 IEEE 10th International Symposium on Biomedical Imaging: From Nano to Macro, ISBI 2013

Y2 - 7 April 2013 through 11 April 2013

ER -

Pathology-centric medical image retrieval with hierarchical contextual spatial descriptor

Abstract

Other

Keywords

ASJC Scopus subject areas

Access to Document

Other files and links

Fingerprint

Cite this