Biological image temporal stage classification via multi-layer model collaboration

Tao Meng, Mei-Ling Shyu

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

7 Citations (Scopus)

Abstract

In current biological image analysis, the temporal stage information, such as the developmental stage in the Drosophila development in situ hybridization images, is important for biological knowledge discovery. Such information is usually gained through visual inspection by experts. However, as the high-throughput imaging technology becomes increasingly popular, the demand for labor effort on annotating, labeling, and organizing the images for efficient image retrieval has increased tremendously, making manual data processing infeasible. In this paper, a novel multi-layer classification framework is proposed to discover the temporal information of the biological images automatically. Rather than solving the problem directly, the proposed framework uses the idea of "divide and conquer" to create some middle level classes, which are relatively easy to annotate, and to train the proposed subspace-based classifiers on the subsets of data belonging to these categories. Next, the results from these classifiers are integrated to improve the final classification performance. In order to appropriately integrate the outputs from different classifiers, a multi-class based closed form quadratic cost function is defined as the optimization target and the parameters are estimated using the gradient descent algorithm. Our proposed framework is tested on three biological image data sets and compared with other state-of-the-art algorithms. The experimental results demonstrate that the proposed middle-level classes and the proper integration of the results from the corresponding classifiers are promising for mining the temporal stage information of the biological images.

Original languageEnglish
Title of host publicationProceedings - 2013 IEEE International Symposium on Multimedia, ISM 2013
Pages30-37
Number of pages8
DOIs
StatePublished - Dec 1 2013
Event15th IEEE International Symposium on Multimedia, ISM 2013 - Anaheim, CA, United States
Duration: Dec 9 2013Dec 11 2013

Other

Other15th IEEE International Symposium on Multimedia, ISM 2013
CountryUnited States
CityAnaheim, CA
Period12/9/1312/11/13

Fingerprint

Classifiers
Image retrieval
Cost functions
Labeling
Image analysis
Data mining
Inspection
Throughput
Personnel
Imaging techniques

Keywords

  • biological image classification
  • biological image mining
  • model fusion
  • temporal stage information

ASJC Scopus subject areas

  • Computer Graphics and Computer-Aided Design
  • Human-Computer Interaction
  • Software

Cite this

Meng, T., & Shyu, M-L. (2013). Biological image temporal stage classification via multi-layer model collaboration. In Proceedings - 2013 IEEE International Symposium on Multimedia, ISM 2013 (pp. 30-37). [6746466] https://doi.org/10.1109/ISM.2013.15

Biological image temporal stage classification via multi-layer model collaboration. / Meng, Tao; Shyu, Mei-Ling.

Proceedings - 2013 IEEE International Symposium on Multimedia, ISM 2013. 2013. p. 30-37 6746466.

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

Meng, T & Shyu, M-L 2013, Biological image temporal stage classification via multi-layer model collaboration. in Proceedings - 2013 IEEE International Symposium on Multimedia, ISM 2013., 6746466, pp. 30-37, 15th IEEE International Symposium on Multimedia, ISM 2013, Anaheim, CA, United States, 12/9/13. https://doi.org/10.1109/ISM.2013.15
Meng T, Shyu M-L. Biological image temporal stage classification via multi-layer model collaboration. In Proceedings - 2013 IEEE International Symposium on Multimedia, ISM 2013. 2013. p. 30-37. 6746466 https://doi.org/10.1109/ISM.2013.15
Meng, Tao ; Shyu, Mei-Ling. / Biological image temporal stage classification via multi-layer model collaboration. Proceedings - 2013 IEEE International Symposium on Multimedia, ISM 2013. 2013. pp. 30-37
@inproceedings{f75c84f07c9b4f95adbca48ccf4b4538,
title = "Biological image temporal stage classification via multi-layer model collaboration",
abstract = "In current biological image analysis, the temporal stage information, such as the developmental stage in the Drosophila development in situ hybridization images, is important for biological knowledge discovery. Such information is usually gained through visual inspection by experts. However, as the high-throughput imaging technology becomes increasingly popular, the demand for labor effort on annotating, labeling, and organizing the images for efficient image retrieval has increased tremendously, making manual data processing infeasible. In this paper, a novel multi-layer classification framework is proposed to discover the temporal information of the biological images automatically. Rather than solving the problem directly, the proposed framework uses the idea of {"}divide and conquer{"} to create some middle level classes, which are relatively easy to annotate, and to train the proposed subspace-based classifiers on the subsets of data belonging to these categories. Next, the results from these classifiers are integrated to improve the final classification performance. In order to appropriately integrate the outputs from different classifiers, a multi-class based closed form quadratic cost function is defined as the optimization target and the parameters are estimated using the gradient descent algorithm. Our proposed framework is tested on three biological image data sets and compared with other state-of-the-art algorithms. The experimental results demonstrate that the proposed middle-level classes and the proper integration of the results from the corresponding classifiers are promising for mining the temporal stage information of the biological images.",
keywords = "biological image classification, biological image mining, model fusion, temporal stage information",
author = "Tao Meng and Mei-Ling Shyu",
year = "2013",
month = "12",
day = "1",
doi = "10.1109/ISM.2013.15",
language = "English",
isbn = "9780769551401",
pages = "30--37",
booktitle = "Proceedings - 2013 IEEE International Symposium on Multimedia, ISM 2013",

}

TY - GEN

T1 - Biological image temporal stage classification via multi-layer model collaboration

AU - Meng, Tao

AU - Shyu, Mei-Ling

PY - 2013/12/1

Y1 - 2013/12/1

N2 - In current biological image analysis, the temporal stage information, such as the developmental stage in the Drosophila development in situ hybridization images, is important for biological knowledge discovery. Such information is usually gained through visual inspection by experts. However, as the high-throughput imaging technology becomes increasingly popular, the demand for labor effort on annotating, labeling, and organizing the images for efficient image retrieval has increased tremendously, making manual data processing infeasible. In this paper, a novel multi-layer classification framework is proposed to discover the temporal information of the biological images automatically. Rather than solving the problem directly, the proposed framework uses the idea of "divide and conquer" to create some middle level classes, which are relatively easy to annotate, and to train the proposed subspace-based classifiers on the subsets of data belonging to these categories. Next, the results from these classifiers are integrated to improve the final classification performance. In order to appropriately integrate the outputs from different classifiers, a multi-class based closed form quadratic cost function is defined as the optimization target and the parameters are estimated using the gradient descent algorithm. Our proposed framework is tested on three biological image data sets and compared with other state-of-the-art algorithms. The experimental results demonstrate that the proposed middle-level classes and the proper integration of the results from the corresponding classifiers are promising for mining the temporal stage information of the biological images.

AB - In current biological image analysis, the temporal stage information, such as the developmental stage in the Drosophila development in situ hybridization images, is important for biological knowledge discovery. Such information is usually gained through visual inspection by experts. However, as the high-throughput imaging technology becomes increasingly popular, the demand for labor effort on annotating, labeling, and organizing the images for efficient image retrieval has increased tremendously, making manual data processing infeasible. In this paper, a novel multi-layer classification framework is proposed to discover the temporal information of the biological images automatically. Rather than solving the problem directly, the proposed framework uses the idea of "divide and conquer" to create some middle level classes, which are relatively easy to annotate, and to train the proposed subspace-based classifiers on the subsets of data belonging to these categories. Next, the results from these classifiers are integrated to improve the final classification performance. In order to appropriately integrate the outputs from different classifiers, a multi-class based closed form quadratic cost function is defined as the optimization target and the parameters are estimated using the gradient descent algorithm. Our proposed framework is tested on three biological image data sets and compared with other state-of-the-art algorithms. The experimental results demonstrate that the proposed middle-level classes and the proper integration of the results from the corresponding classifiers are promising for mining the temporal stage information of the biological images.

KW - biological image classification

KW - biological image mining

KW - model fusion

KW - temporal stage information

UR - http://www.scopus.com/inward/record.url?scp=84900586913&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84900586913&partnerID=8YFLogxK

U2 - 10.1109/ISM.2013.15

DO - 10.1109/ISM.2013.15

M3 - Conference contribution

SN - 9780769551401

SP - 30

EP - 37

BT - Proceedings - 2013 IEEE International Symposium on Multimedia, ISM 2013

ER -