Biomedical image classification based on a cascade of an SVM with a reject option and subspace analysis

Dongyun Lin, Lei Sun, Kar Ann Toh, Jing Bo Zhang, Zhiping Lin

Research output: Contribution to journalArticle

6 Citations (Scopus)

Abstract

Automated biomedical image classification could confront the challenges of high level noise, image blur, illumination variation and complicated geometric correspondence among various categorical biomedical patterns in practice. To handle these challenges, we propose a cascade method consisting of two stages for biomedical image classification. At stage 1, we propose a confidence score based classification rule with a reject option for a preliminary decision using the support vector machine (SVM). The testing images going through stage 1 are separated into two groups based on their confidence scores. Those testing images with sufficiently high confidence scores are classified at stage 1 while the others with low confidence scores are rejected and fed to stage 2. At stage 2, the rejected images from stage 1 are first processed by a subspace analysis technique called eigenfeature regularization and extraction (ERE), and then classified by another SVM trained in the transformed subspace learned by ERE. At both stages, images are represented based on two types of local features, i.e., SIFT and SURF, respectively. They are encoded using various bag-of-words (BoW) models to handle biomedical patterns with and without geometric correspondence, respectively. Extensive experiments are implemented to evaluate the proposed method on three benchmark real-world biomedical image datasets. The proposed method significantly outperforms several competing state-of-the-art methods in terms of classification accuracy.

Original languageEnglish
Pages (from-to)128-140
Number of pages13
JournalComputers in Biology and Medicine
Volume96
DOIs
Publication statusPublished - 2018 May 1

Fingerprint

Image classification
Support vector machines
Testing
Lighting
Benchmarking
Noise
Experiments
Support Vector Machine

All Science Journal Classification (ASJC) codes

  • Computer Science Applications
  • Health Informatics

Cite this

@article{bfee8be2f684493d8628edd1d34f6b81,
title = "Biomedical image classification based on a cascade of an SVM with a reject option and subspace analysis",
abstract = "Automated biomedical image classification could confront the challenges of high level noise, image blur, illumination variation and complicated geometric correspondence among various categorical biomedical patterns in practice. To handle these challenges, we propose a cascade method consisting of two stages for biomedical image classification. At stage 1, we propose a confidence score based classification rule with a reject option for a preliminary decision using the support vector machine (SVM). The testing images going through stage 1 are separated into two groups based on their confidence scores. Those testing images with sufficiently high confidence scores are classified at stage 1 while the others with low confidence scores are rejected and fed to stage 2. At stage 2, the rejected images from stage 1 are first processed by a subspace analysis technique called eigenfeature regularization and extraction (ERE), and then classified by another SVM trained in the transformed subspace learned by ERE. At both stages, images are represented based on two types of local features, i.e., SIFT and SURF, respectively. They are encoded using various bag-of-words (BoW) models to handle biomedical patterns with and without geometric correspondence, respectively. Extensive experiments are implemented to evaluate the proposed method on three benchmark real-world biomedical image datasets. The proposed method significantly outperforms several competing state-of-the-art methods in terms of classification accuracy.",
author = "Dongyun Lin and Lei Sun and Toh, {Kar Ann} and Zhang, {Jing Bo} and Zhiping Lin",
year = "2018",
month = "5",
day = "1",
doi = "10.1016/j.compbiomed.2018.03.005",
language = "English",
volume = "96",
pages = "128--140",
journal = "Computers in Biology and Medicine",
issn = "0010-4825",
publisher = "Elsevier Limited",

}

Biomedical image classification based on a cascade of an SVM with a reject option and subspace analysis. / Lin, Dongyun; Sun, Lei; Toh, Kar Ann; Zhang, Jing Bo; Lin, Zhiping.

In: Computers in Biology and Medicine, Vol. 96, 01.05.2018, p. 128-140.

Research output: Contribution to journalArticle

TY - JOUR

T1 - Biomedical image classification based on a cascade of an SVM with a reject option and subspace analysis

AU - Lin, Dongyun

AU - Sun, Lei

AU - Toh, Kar Ann

AU - Zhang, Jing Bo

AU - Lin, Zhiping

PY - 2018/5/1

Y1 - 2018/5/1

N2 - Automated biomedical image classification could confront the challenges of high level noise, image blur, illumination variation and complicated geometric correspondence among various categorical biomedical patterns in practice. To handle these challenges, we propose a cascade method consisting of two stages for biomedical image classification. At stage 1, we propose a confidence score based classification rule with a reject option for a preliminary decision using the support vector machine (SVM). The testing images going through stage 1 are separated into two groups based on their confidence scores. Those testing images with sufficiently high confidence scores are classified at stage 1 while the others with low confidence scores are rejected and fed to stage 2. At stage 2, the rejected images from stage 1 are first processed by a subspace analysis technique called eigenfeature regularization and extraction (ERE), and then classified by another SVM trained in the transformed subspace learned by ERE. At both stages, images are represented based on two types of local features, i.e., SIFT and SURF, respectively. They are encoded using various bag-of-words (BoW) models to handle biomedical patterns with and without geometric correspondence, respectively. Extensive experiments are implemented to evaluate the proposed method on three benchmark real-world biomedical image datasets. The proposed method significantly outperforms several competing state-of-the-art methods in terms of classification accuracy.

AB - Automated biomedical image classification could confront the challenges of high level noise, image blur, illumination variation and complicated geometric correspondence among various categorical biomedical patterns in practice. To handle these challenges, we propose a cascade method consisting of two stages for biomedical image classification. At stage 1, we propose a confidence score based classification rule with a reject option for a preliminary decision using the support vector machine (SVM). The testing images going through stage 1 are separated into two groups based on their confidence scores. Those testing images with sufficiently high confidence scores are classified at stage 1 while the others with low confidence scores are rejected and fed to stage 2. At stage 2, the rejected images from stage 1 are first processed by a subspace analysis technique called eigenfeature regularization and extraction (ERE), and then classified by another SVM trained in the transformed subspace learned by ERE. At both stages, images are represented based on two types of local features, i.e., SIFT and SURF, respectively. They are encoded using various bag-of-words (BoW) models to handle biomedical patterns with and without geometric correspondence, respectively. Extensive experiments are implemented to evaluate the proposed method on three benchmark real-world biomedical image datasets. The proposed method significantly outperforms several competing state-of-the-art methods in terms of classification accuracy.

UR - http://www.scopus.com/inward/record.url?scp=85044059402&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85044059402&partnerID=8YFLogxK

U2 - 10.1016/j.compbiomed.2018.03.005

DO - 10.1016/j.compbiomed.2018.03.005

M3 - Article

C2 - 29567484

AN - SCOPUS:85044059402

VL - 96

SP - 128

EP - 140

JO - Computers in Biology and Medicine

JF - Computers in Biology and Medicine

SN - 0010-4825

ER -