Analysis-synthesis model learning with shared features: A new framework for histopathological image classification

Xuelu Li, Vishal Monga, U. K.Arvind Rao

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

Abstract

Automated histopathological image analysis offers exciting opportunities for the early diagnosis of several medical conditions including cancer. There are however stiff practical challenges: 1.) discriminative features from such images for separating diseased vs. healthy classes are not readily apparent, and 2.) distinct classes, e.g. healthy vs. stages of disease continue to share several geometric features. We propose a novel Analysis-synthesis model Learning with Shared Features algorithm (ALSF) for classifying such images more effectively. In ALSF, a joint analysis and synthesis learning model is introduced to learn the classifier and the feature extractor at the same time. In this way, the computation load in patch-level based image classification can be much reduced. Crucially, we integrate into this framework the learning of a low rank shared dictionary and a shared analysis operator, which more accurately represents both similarities and differences in histopathological images from distinct classes. ALSF is evaluated on two challenging databases: (1) kidney tissue images provided by the Animal Diagnosis Lab (ADL) at the Pennsylvania State University and (2) brain tumor images from The Cancer Genome Atlas (TCGA) database. Experimental results confirm that ALSF can offer benefits over state of the art alternatives.

Original languageEnglish (US)
Title of host publication2018 IEEE 15th International Symposium on Biomedical Imaging, ISBI 2018
PublisherIEEE Computer Society
Pages203-206
Number of pages4
ISBN (Electronic)9781538636367
DOIs
StatePublished - May 23 2018
Event15th IEEE International Symposium on Biomedical Imaging, ISBI 2018 - Washington, United States
Duration: Apr 4 2018Apr 7 2018

Publication series

NameProceedings - International Symposium on Biomedical Imaging
Volume2018-April
ISSN (Print)1945-7928
ISSN (Electronic)1945-8452

Other

Other15th IEEE International Symposium on Biomedical Imaging, ISBI 2018
CountryUnited States
CityWashington
Period4/4/184/7/18

Fingerprint

Image classification
Learning
Glossaries
Databases
Image analysis
Tumors
Brain
Animals
Classifiers
Genes
Atlases
Tissue
Brain Neoplasms
Early Diagnosis
Neoplasms
Genome
Kidney

All Science Journal Classification (ASJC) codes

  • Biomedical Engineering
  • Radiology Nuclear Medicine and imaging

Cite this

Li, X., Monga, V., & Rao, U. K. A. (2018). Analysis-synthesis model learning with shared features: A new framework for histopathological image classification. In 2018 IEEE 15th International Symposium on Biomedical Imaging, ISBI 2018 (pp. 203-206). (Proceedings - International Symposium on Biomedical Imaging; Vol. 2018-April). IEEE Computer Society. https://doi.org/10.1109/ISBI.2018.8363555
Li, Xuelu ; Monga, Vishal ; Rao, U. K.Arvind. / Analysis-synthesis model learning with shared features : A new framework for histopathological image classification. 2018 IEEE 15th International Symposium on Biomedical Imaging, ISBI 2018. IEEE Computer Society, 2018. pp. 203-206 (Proceedings - International Symposium on Biomedical Imaging).
@inproceedings{17564117ba1b4729b284c717ca96feda,
title = "Analysis-synthesis model learning with shared features: A new framework for histopathological image classification",
abstract = "Automated histopathological image analysis offers exciting opportunities for the early diagnosis of several medical conditions including cancer. There are however stiff practical challenges: 1.) discriminative features from such images for separating diseased vs. healthy classes are not readily apparent, and 2.) distinct classes, e.g. healthy vs. stages of disease continue to share several geometric features. We propose a novel Analysis-synthesis model Learning with Shared Features algorithm (ALSF) for classifying such images more effectively. In ALSF, a joint analysis and synthesis learning model is introduced to learn the classifier and the feature extractor at the same time. In this way, the computation load in patch-level based image classification can be much reduced. Crucially, we integrate into this framework the learning of a low rank shared dictionary and a shared analysis operator, which more accurately represents both similarities and differences in histopathological images from distinct classes. ALSF is evaluated on two challenging databases: (1) kidney tissue images provided by the Animal Diagnosis Lab (ADL) at the Pennsylvania State University and (2) brain tumor images from The Cancer Genome Atlas (TCGA) database. Experimental results confirm that ALSF can offer benefits over state of the art alternatives.",
author = "Xuelu Li and Vishal Monga and Rao, {U. K.Arvind}",
year = "2018",
month = "5",
day = "23",
doi = "10.1109/ISBI.2018.8363555",
language = "English (US)",
series = "Proceedings - International Symposium on Biomedical Imaging",
publisher = "IEEE Computer Society",
pages = "203--206",
booktitle = "2018 IEEE 15th International Symposium on Biomedical Imaging, ISBI 2018",
address = "United States",

}

Li, X, Monga, V & Rao, UKA 2018, Analysis-synthesis model learning with shared features: A new framework for histopathological image classification. in 2018 IEEE 15th International Symposium on Biomedical Imaging, ISBI 2018. Proceedings - International Symposium on Biomedical Imaging, vol. 2018-April, IEEE Computer Society, pp. 203-206, 15th IEEE International Symposium on Biomedical Imaging, ISBI 2018, Washington, United States, 4/4/18. https://doi.org/10.1109/ISBI.2018.8363555

Analysis-synthesis model learning with shared features : A new framework for histopathological image classification. / Li, Xuelu; Monga, Vishal; Rao, U. K.Arvind.

2018 IEEE 15th International Symposium on Biomedical Imaging, ISBI 2018. IEEE Computer Society, 2018. p. 203-206 (Proceedings - International Symposium on Biomedical Imaging; Vol. 2018-April).

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

TY - GEN

T1 - Analysis-synthesis model learning with shared features

T2 - A new framework for histopathological image classification

AU - Li, Xuelu

AU - Monga, Vishal

AU - Rao, U. K.Arvind

PY - 2018/5/23

Y1 - 2018/5/23

N2 - Automated histopathological image analysis offers exciting opportunities for the early diagnosis of several medical conditions including cancer. There are however stiff practical challenges: 1.) discriminative features from such images for separating diseased vs. healthy classes are not readily apparent, and 2.) distinct classes, e.g. healthy vs. stages of disease continue to share several geometric features. We propose a novel Analysis-synthesis model Learning with Shared Features algorithm (ALSF) for classifying such images more effectively. In ALSF, a joint analysis and synthesis learning model is introduced to learn the classifier and the feature extractor at the same time. In this way, the computation load in patch-level based image classification can be much reduced. Crucially, we integrate into this framework the learning of a low rank shared dictionary and a shared analysis operator, which more accurately represents both similarities and differences in histopathological images from distinct classes. ALSF is evaluated on two challenging databases: (1) kidney tissue images provided by the Animal Diagnosis Lab (ADL) at the Pennsylvania State University and (2) brain tumor images from The Cancer Genome Atlas (TCGA) database. Experimental results confirm that ALSF can offer benefits over state of the art alternatives.

AB - Automated histopathological image analysis offers exciting opportunities for the early diagnosis of several medical conditions including cancer. There are however stiff practical challenges: 1.) discriminative features from such images for separating diseased vs. healthy classes are not readily apparent, and 2.) distinct classes, e.g. healthy vs. stages of disease continue to share several geometric features. We propose a novel Analysis-synthesis model Learning with Shared Features algorithm (ALSF) for classifying such images more effectively. In ALSF, a joint analysis and synthesis learning model is introduced to learn the classifier and the feature extractor at the same time. In this way, the computation load in patch-level based image classification can be much reduced. Crucially, we integrate into this framework the learning of a low rank shared dictionary and a shared analysis operator, which more accurately represents both similarities and differences in histopathological images from distinct classes. ALSF is evaluated on two challenging databases: (1) kidney tissue images provided by the Animal Diagnosis Lab (ADL) at the Pennsylvania State University and (2) brain tumor images from The Cancer Genome Atlas (TCGA) database. Experimental results confirm that ALSF can offer benefits over state of the art alternatives.

UR - http://www.scopus.com/inward/record.url?scp=85048119705&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85048119705&partnerID=8YFLogxK

U2 - 10.1109/ISBI.2018.8363555

DO - 10.1109/ISBI.2018.8363555

M3 - Conference contribution

AN - SCOPUS:85048119705

T3 - Proceedings - International Symposium on Biomedical Imaging

SP - 203

EP - 206

BT - 2018 IEEE 15th International Symposium on Biomedical Imaging, ISBI 2018

PB - IEEE Computer Society

ER -

Li X, Monga V, Rao UKA. Analysis-synthesis model learning with shared features: A new framework for histopathological image classification. In 2018 IEEE 15th International Symposium on Biomedical Imaging, ISBI 2018. IEEE Computer Society. 2018. p. 203-206. (Proceedings - International Symposium on Biomedical Imaging). https://doi.org/10.1109/ISBI.2018.8363555