Towards large-scale histopathological image analysis: Hashing-based image retrieval

Xiaofan Zhang, Wei Liu, Murat Dundar, Sunil Badve, Shaoting Zhang

Research output: Contribution to journalArticle

123 Citations (Scopus)

Abstract

Automatic analysis of histopathological images has been widely utilized leveraging computational image-processing methods and modern machine learning techniques. Both computer-aided diagnosis (CAD) and content-based image-retrieval (CBIR) systems have been successfully developed for diagnosis, disease detection, and decision support in this area. Recently, with the ever-increasing amount of annotated medical data, large-scale and data-driven methods have emerged to offer a promise of bridging the semantic gap between images and diagnostic information. In this paper, we focus on developing scalable image-retrieval techniques to cope intelligently with massive histopathological images. Specifically, we present a supervised kernel hashing technique which leverages a small amount of supervised information in learning to compress a 10 000-dimensional image feature vector into only tens of binary bits with the informative signatures preserved. These binary codes are then indexed into a hash table that enables real-time retrieval of images in a large database. Critically, the supervised information is employed to bridge the semantic gap between low-level image features and high-level diagnostic information. We build a scalable image-retrieval framework based on the supervised hashing technique and validate its performance on several thousand histopathological images acquired from breast microscopic tissues. Extensive evaluations are carried out in terms of image classification (i.e., benign versus actionable categorization) and retrieval tests. Our framework achieves about 88.1% classification accuracy as well as promising time efficiency. For example, the framework can execute around 800 queries in only 0.01 s, comparing favorably with other commonly used dimensionality reduction and feature selection methods.

Original languageEnglish
Article number6919336
Pages (from-to)496-506
Number of pages11
JournalIEEE Transactions on Medical Imaging
Volume34
Issue number2
DOIs
StatePublished - Feb 1 2015

Fingerprint

Image retrieval
Image analysis
Semantics
Computer aided diagnosis
Binary codes
Image classification
Learning systems
Feature extraction
Image processing
Breast
Learning
Databases
Tissue
Efficiency

Keywords

  • Breast lesion
  • hashing
  • high dimension
  • histopathological image analysis
  • large-scale image retrieval
  • supervised learning

ASJC Scopus subject areas

  • Electrical and Electronic Engineering
  • Computer Science Applications
  • Radiological and Ultrasound Technology
  • Software
  • Medicine(all)

Cite this

Towards large-scale histopathological image analysis : Hashing-based image retrieval. / Zhang, Xiaofan; Liu, Wei; Dundar, Murat; Badve, Sunil; Zhang, Shaoting.

In: IEEE Transactions on Medical Imaging, Vol. 34, No. 2, 6919336, 01.02.2015, p. 496-506.

Research output: Contribution to journalArticle

Zhang, Xiaofan ; Liu, Wei ; Dundar, Murat ; Badve, Sunil ; Zhang, Shaoting. / Towards large-scale histopathological image analysis : Hashing-based image retrieval. In: IEEE Transactions on Medical Imaging. 2015 ; Vol. 34, No. 2. pp. 496-506.
@article{a34214ac3cfa47c8bba3428cf5383ce9,
title = "Towards large-scale histopathological image analysis: Hashing-based image retrieval",
abstract = "Automatic analysis of histopathological images has been widely utilized leveraging computational image-processing methods and modern machine learning techniques. Both computer-aided diagnosis (CAD) and content-based image-retrieval (CBIR) systems have been successfully developed for diagnosis, disease detection, and decision support in this area. Recently, with the ever-increasing amount of annotated medical data, large-scale and data-driven methods have emerged to offer a promise of bridging the semantic gap between images and diagnostic information. In this paper, we focus on developing scalable image-retrieval techniques to cope intelligently with massive histopathological images. Specifically, we present a supervised kernel hashing technique which leverages a small amount of supervised information in learning to compress a 10 000-dimensional image feature vector into only tens of binary bits with the informative signatures preserved. These binary codes are then indexed into a hash table that enables real-time retrieval of images in a large database. Critically, the supervised information is employed to bridge the semantic gap between low-level image features and high-level diagnostic information. We build a scalable image-retrieval framework based on the supervised hashing technique and validate its performance on several thousand histopathological images acquired from breast microscopic tissues. Extensive evaluations are carried out in terms of image classification (i.e., benign versus actionable categorization) and retrieval tests. Our framework achieves about 88.1{\%} classification accuracy as well as promising time efficiency. For example, the framework can execute around 800 queries in only 0.01 s, comparing favorably with other commonly used dimensionality reduction and feature selection methods.",
keywords = "Breast lesion, hashing, high dimension, histopathological image analysis, large-scale image retrieval, supervised learning",
author = "Xiaofan Zhang and Wei Liu and Murat Dundar and Sunil Badve and Shaoting Zhang",
year = "2015",
month = "2",
day = "1",
doi = "10.1109/TMI.2014.2361481",
language = "English",
volume = "34",
pages = "496--506",
journal = "IEEE Transactions on Medical Imaging",
issn = "0278-0062",
publisher = "Institute of Electrical and Electronics Engineers Inc.",
number = "2",

}

TY - JOUR

T1 - Towards large-scale histopathological image analysis

T2 - Hashing-based image retrieval

AU - Zhang, Xiaofan

AU - Liu, Wei

AU - Dundar, Murat

AU - Badve, Sunil

AU - Zhang, Shaoting

PY - 2015/2/1

Y1 - 2015/2/1

N2 - Automatic analysis of histopathological images has been widely utilized leveraging computational image-processing methods and modern machine learning techniques. Both computer-aided diagnosis (CAD) and content-based image-retrieval (CBIR) systems have been successfully developed for diagnosis, disease detection, and decision support in this area. Recently, with the ever-increasing amount of annotated medical data, large-scale and data-driven methods have emerged to offer a promise of bridging the semantic gap between images and diagnostic information. In this paper, we focus on developing scalable image-retrieval techniques to cope intelligently with massive histopathological images. Specifically, we present a supervised kernel hashing technique which leverages a small amount of supervised information in learning to compress a 10 000-dimensional image feature vector into only tens of binary bits with the informative signatures preserved. These binary codes are then indexed into a hash table that enables real-time retrieval of images in a large database. Critically, the supervised information is employed to bridge the semantic gap between low-level image features and high-level diagnostic information. We build a scalable image-retrieval framework based on the supervised hashing technique and validate its performance on several thousand histopathological images acquired from breast microscopic tissues. Extensive evaluations are carried out in terms of image classification (i.e., benign versus actionable categorization) and retrieval tests. Our framework achieves about 88.1% classification accuracy as well as promising time efficiency. For example, the framework can execute around 800 queries in only 0.01 s, comparing favorably with other commonly used dimensionality reduction and feature selection methods.

AB - Automatic analysis of histopathological images has been widely utilized leveraging computational image-processing methods and modern machine learning techniques. Both computer-aided diagnosis (CAD) and content-based image-retrieval (CBIR) systems have been successfully developed for diagnosis, disease detection, and decision support in this area. Recently, with the ever-increasing amount of annotated medical data, large-scale and data-driven methods have emerged to offer a promise of bridging the semantic gap between images and diagnostic information. In this paper, we focus on developing scalable image-retrieval techniques to cope intelligently with massive histopathological images. Specifically, we present a supervised kernel hashing technique which leverages a small amount of supervised information in learning to compress a 10 000-dimensional image feature vector into only tens of binary bits with the informative signatures preserved. These binary codes are then indexed into a hash table that enables real-time retrieval of images in a large database. Critically, the supervised information is employed to bridge the semantic gap between low-level image features and high-level diagnostic information. We build a scalable image-retrieval framework based on the supervised hashing technique and validate its performance on several thousand histopathological images acquired from breast microscopic tissues. Extensive evaluations are carried out in terms of image classification (i.e., benign versus actionable categorization) and retrieval tests. Our framework achieves about 88.1% classification accuracy as well as promising time efficiency. For example, the framework can execute around 800 queries in only 0.01 s, comparing favorably with other commonly used dimensionality reduction and feature selection methods.

KW - Breast lesion

KW - hashing

KW - high dimension

KW - histopathological image analysis

KW - large-scale image retrieval

KW - supervised learning

UR - http://www.scopus.com/inward/record.url?scp=84922344423&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84922344423&partnerID=8YFLogxK

U2 - 10.1109/TMI.2014.2361481

DO - 10.1109/TMI.2014.2361481

M3 - Article

C2 - 25314696

AN - SCOPUS:84922344423

VL - 34

SP - 496

EP - 506

JO - IEEE Transactions on Medical Imaging

JF - IEEE Transactions on Medical Imaging

SN - 0278-0062

IS - 2

M1 - 6919336

ER -