More Web Proxy on the site http://driver.im/

research-article

OCR-based image features for biomedical image and article classification: identifying documents relevant to cis-regulatory elements

Authors:

Ramya Narayanaswamy,

Santosh S. Nagaral,

Gowri Somanath,

Dorothea Blostein,

Chandra KambhamettuAuthors Info & Claims

BCB '12: Proceedings of the ACM Conference on Bioinformatics, Computational Biology and Biomedicine

Pages 98 - 104

https://doi.org/10.1145/2382936.2382949

Published: 07 October 2012 Publication History

Abstract

Images form a significant and useful source of information in published biomedical articles, which is still under-utilized in biomedical document classification and retrieval. Much current work on biomedical image retrieval and classification employs simple, standard image features such as gray scale histograms and edge direction to represent and classify images. We have used such features as well to classify images in our early work [5], where we used image-class-tags to represent and classify articles.

In the work presented here we focus on a different literature classification task, motivated by the need to identify articles discussing cis-regulatory elements and modules in the context of understanding complex gene-networks. The curators who try to identify such articles in the vast literature use as a major cue a certain type of image in which the conserved cis-regulatory region on the DNA is shown. Our experiments show that automatically identifying such images using common image features (like those mentioned above) can be highly error prone. However, using Optical Character Recognition (OCR) to extract alphabet characters from images, calculating character distribution and using the distribution parameters as image features, allows us to form a novel representation of images, and identify DNA-content in images with high precision and recall (over 0.9). Utilizing the occurrence of such DNA-rich images within articles, we train a classifier that identifies articles pertaining to cis-regulatory elements with a similarly high precision and recall. The use of OCR-based image features has much potential beyond the current task, to identify other types of biomedical sequence-based images showing DNA, RNA and proteins. Moreover, the ability to automatically identify such images has much potential to be widely applicable in other important biomedical document classification tasks.

References

[1]

Eppig JT, Bult CA, Kadin JA, Richardson JE and Blake JA. 2005. The Mouse Genome Database (MGD): From Genes to Mice --- A Community Resource for Mouse Biology. Nucleic Acids Research, 33, (Database Issue), D471--D475.

[2]

Smith CM, Finger JH, Hayamizu TF, McCright IJ, Eppig JT, Kadin JA, Richardson JE and Ringwald M. 2007. The Mouse Gene Expression Database (GXD): 2007 Update. Nucleic Acids Res, 35, D618--D623.

[3]

Hersh WR, Cohen A, Yang J, Bhuptiraju RT, Roberts P, Hearst M. 2006. TREC 2005 Genomics Track Overview. Proc. of TREC 2005, NIST Special Publication. 14--25.

[4]

Krallinger M, Vazquez M, Leitner F, et al. 2011. The Protein-Protein Interaction tasks of BioCreative III: classification/ranking of articles and linking bio-ontology concepts to full text. BMC Bioinformatics, 12(Suppl 8):S3.

[5]

Shatkay H, Chen N, Blostein D. 2006. Integrating Image Data into Biomedical Text Categorization. Bioinformatics, 22(11), e446--e453.

Digital Library

[6]

Murphy RF, Velliste M, Yao J, Porreca G. 2001. Searching Online Journals for Fluorescence Microscope Images Depicting Protein Subcellular Location Patterns. Proc. of the 2nd IEEE Int. Symp. on Bio-Informatics and Biomedical Engineering (BIBE'01), 119--128.

Digital Library

[7]

Cohen W, Kou Z, Murphy RF. 2003. Extracting Information from Text and Images for Location Proteomics. Proc. of the 3rd ACM SIGKDD Workshop on Data Mining in Bioinformatics (BIOKDD'03), 2--9.

[8]

Qian Y, Murphy RF. 2008. Improved Recognition of Figures containing Fluorescence Microscope Images in Online Journal Articles using Graphical Models. Bioinformatics 24, 569--576.

Digital Library

[9]

SLIF: Subcellular Localization Image Finder. Carnegie Mellon University. http://slif.cbi.cmu.edu.

[10]

Rafkind B, Lee M, Chang S, Yu H. 2006. Exploring Text and Image Features to Classify Images in Bioscience Literature. Proc. of the BioNLP Workshop on Linking Natural Language Processing and Biology at HLT-NAACL.

Digital Library

[11]

ImageCLEF Medical (since 2007).Cross-Language Image Retrieval Evaluation. http://www.imageclef.org/

[12]

Demner-Fushman D, Antani S, Simpson M and Thoma GR. (2009). Annotation and Retrieval of Clinically Relevant Images. International Journal of Medical Informatics: Special Issue on Mining of Clinical and Biomedical Text and Data, 78(12), e59--e67.

[13]

Yu H, Liu FF, Ramesh BP. 2010. Automatic Figure Ranking and User Interfacing for Intelligent Figure Search. PLoS One 5(10), e12983.

[14]

Chen N, Shatkay H, Blostein D. 2006. Exploring a new space of features for document classification: figure clustering. Proc. of the 2006 Conference of the IBM Center for Advanced Studies on Collaborative research. (CASCON'06).

Digital Library

[15]

Xu S, McCusker J, Krauthammer M. 2008. Exploring the use of image text for biomedical literature retrieval. Proc. of the AMIA Annu Symp, 2008, 1186.

[16]

Rodriguez-Esteban R, Iossifov I. 2009. Figure Mining for Biomedical research. Bioinformatics, 25(16), 2082--2084.

Digital Library

[17]

Gonzalez RC, Woods RE. 2002. Digital Image Processing. Prentice-Hall.

Digital Library

[18]

Haralick RM, Shanmugam K, Dinstein I. 1973. Texture features for image classification. IEEE Trans. On Systems, Man and Cybernetics, SMC-3(6), 610--621.

[19]

Jain AK, Vailaya A. 1998. Shape-based retrieval: a case study with trademark image databases. Pattern Recognition, 31(9), 1369--1390.

[20]

Istrail S, Tarpine R, Schutter K, and Aguiar D. 2010. Practical Computational Methods for Regulatory Genomics: A cisGRN-Lexicon and cisGRN-Browser for Gene Regulatory Networks. Methods in Molecular Biology 1, 674, Computational Biology of Transcription Factor Binding, 369--399.

[21]

CYRENE=http://www.brown.edu/Research/Istrail_Lab/pages/cyrene.html

[22]

Annicotte JS, Fayard E, Swift GH et al. 2003. Pancreatic-duodenal homeobox 1 regulates expression of liver receptor homolog 1 during pancreas development. Mol Cell Biol, 23(19), 6713--6724. 12972592

[23]

Regev Y, et al. 2002. Rule-Based Extraction of Experimental Evidence in the Biomedical Domain - the KDD Cup (Task 1). SIGKDD Explorations, 4(2), 90--91.

Digital Library

[24]

Xerox Rossinante=https://pdf2epub.services.open.xerox.com/

[25]

ABBYY Finereader for OCR. The website is at http://finereader.abbyy.com/

[26]

Puppina C, Ivan Prestab I, D'Elia AV et al. 2004. Functional interaction among thyroid-specific transcription factors: Pax8 regulates the activity of Hex promoter. Mol Cell Endocrinol, 224(1--2), 117--125. 15062550

[27]

Nishi H, Nakada T, Kyo S et al. 2004. Hypoxia-inducible factor 1 mediates upregulation of telomerase (hTERT). Mol Cell Biol, 24(13), 6076--6083. 15199161

[28]

Witten IH, Frank E. 2005. Data Mining: Practical machine learning tools and techniques. Morgan Kaufmann. (Describes Weka: The Waikato Environment for Knowledge Analysis. http://www.cs.waikato.ac.nz/ml/weka.)

Digital Library

[29]

Brady S, Shatkay H. 2008. EpiLoc: a (working) text-based system for predicting protein subcellular location. Proc. of the Pacific Symposium on Biocomputing (PSB'08), 604--615.

[30]

Denroche R, Madupu R, Yooseph S, Sutton G, Shatkay H. 2010. Toward Computer-Assisted Text Curation: Classification Is Easy (Choosing Training Data Can Be Hard...) Linking Literature, Information, and Knowledge for Biology, Lecture Notes in Computer Science, 6004, 33--42.

Digital Library

[31]

Porter MF. 1997. An Algorithm for Suffix Stripping (Reprint). Readings in Information Retrieval, Morgan Kaufmann. http://www.tartarus.org/~martin/PorterStemmer/.

Digital Library

Cited By

Jiang XLi PKadin JBlake JRingwald MShatkay H(2020)Integrating image caption information into biomedical document classification in support of biocurationDatabase10.1093/database/baaa0242020Online publication date: 15-Apr-2020
https://doi.org/10.1093/database/baaa024
Jiang XRingwald MBlake JArighi CZhang GShatkay H(2019)An effective biomedical document classification scheme in support of biocuration: addressing class imbalanceDatabase10.1093/database/baz0452019Online publication date: 25-Apr-2019
https://doi.org/10.1093/database/baz045
Genc EShin HSik Park JSong J(2018)Number Recognition of Parts Book Schematics using Convolutional Recurrent Neural Network2018 International Conference on Information and Communication Technology Robotics (ICT-ROBOT)10.1109/ICT-ROBOT.2018.8549859(1-3)Online publication date: Sep-2018
https://doi.org/10.1109/ICT-ROBOT.2018.8549859
Show More Cited By

Index Terms

OCR-based image features for biomedical image and article classification: identifying documents relevant to cis-regulatory elements
1. Computing methodologies
  1. Artificial intelligence
    1. Computer vision
      1. Computer vision problems
      2. Computer vision representations
        Image representations
  2. Computer graphics
    1. Image manipulation
      1. Image processing
2. Information systems
  1. Information retrieval

Recommendations

Prediction of OCR accuracy using simple image features
ICDAR '95: Proceedings of the Third International Conference on Document Analysis and Recognition (Volume 1) - Volume 1

A classifier for predicting the character accuracy achieved by any Optical Character Recognition (OCR) system on a given page is presented. This classifier is based on measuring the amount of white speckle, the amount of character fragments, and overall ...
Symmetry features for license plate classification

Achieving high recognition rate for license plate images is challenging due to multi‐type images. We present new symmetry features based on stroke width for classifying each input license image as private, taxi, cursive text, when they expand the symbols ...
Hybrid model for Chinese character recognition based on Tesseract-OCR

Optical character recognition (OCR) is an important way to input information into a computer. And text information can be extracted by OCR from an image. Currently, the accuracy rate of Chinese OCR can also be improved. This study proposes a hybrid ...

Comments

Please enable JavaScript to view thecomments powered by Disqus.

Information & Contributors

Information

Published In

cover image ACM Conferences

BCB '12: Proceedings of the ACM Conference on Bioinformatics, Computational Biology and Biomedicine

October 2012

725 pages

ISBN:9781450316705

DOI:10.1145/2382936

General Chair:
Sanjay Ranka
University of Florida
,
Program Chairs:
Tamer Kahveci
University of Florida
,
Mona Singh
Princeton University

Copyright © 2012 ACM.

Permission to make digital or hard copies of all or part of this work for personal or classroom use is granted without fee provided that copies are not made or distributed for profit or commercial advantage and that copies bear this notice and the full citation on the first page. Copyrights for components of this work owned by others than ACM must be honored. Abstracting with credit is permitted. To copy otherwise, or republish, to post on servers or to redistribute to lists, requires prior specific permission and/or a fee. Request permissions from [email protected]

Sponsors

SIGBio: ACM Special Interest Group on Bioinformatics

Publisher

Association for Computing Machinery

New York, NY, United States

Publication History

Published: 07 October 2012

Permissions

Request permissions for this article.

Request Permissions

Check for updates

Author Tags

Qualifiers

Research-article

Funding Sources

National Science Foundation

Conference

BCB' 12

Sponsor:

SIGBio

BCB' 12: ACM International Conference on Bioinformatics, Computational Biology and Biomedicine

October 7 - 10, 2012

Florida, Orlando

Acceptance Rates

BCB '12 Paper Acceptance Rate 33 of 159 submissions, 21%;

Overall Acceptance Rate 254 of 885 submissions, 29%

Contributors

Other Metrics

View Article Metrics

Bibliometrics & Citations

Bibliometrics

Article Metrics

4
Total Citations
View Citations
148
Total Downloads

Downloads (Last 12 months)0
Downloads (Last 6 weeks)0

Reflects downloads up to 21 Dec 2024

Other Metrics

View Author Metrics

Citations

Cited By

Jiang XLi PKadin JBlake JRingwald MShatkay H(2020)Integrating image caption information into biomedical document classification in support of biocurationDatabase10.1093/database/baaa0242020Online publication date: 15-Apr-2020
https://doi.org/10.1093/database/baaa024
Jiang XRingwald MBlake JArighi CZhang GShatkay H(2019)An effective biomedical document classification scheme in support of biocuration: addressing class imbalanceDatabase10.1093/database/baz0452019Online publication date: 25-Apr-2019
https://doi.org/10.1093/database/baz045
Genc EShin HSik Park JSong J(2018)Number Recognition of Parts Book Schematics using Convolutional Recurrent Neural Network2018 International Conference on Information and Communication Technology Robotics (ICT-ROBOT)10.1109/ICT-ROBOT.2018.8549859(1-3)Online publication date: Sep-2018
https://doi.org/10.1109/ICT-ROBOT.2018.8549859
Ma KJeong HRohith MSomanath GTarpine RSchutter KBlostein DIstrail SKambhamettu CShatkay H(2015)Utilizing image-based features in biomedical document classification2015 IEEE International Conference on Image Processing (ICIP)10.1109/ICIP.2015.7351648(4451-4455)Online publication date: Sep-2015
https://doi.org/10.1109/ICIP.2015.7351648

View Options

Login options

Check if you have access through your login credentials or your institution to get full access on this article.

Full Access

Get this Publication

View options

PDF

View or Download as a PDF file.

eReader

View online with eReader.

Media

Figures

Other

Tables

View Table of Contents