Abstract
With the rampant explosion of the information in biomedical literature, text-mining tools have become popular. A drawback of these tools is that they are unable to capture visual representations (images). We propose an idea to tackle this challenge, by using image classification and meta-information extraction using machine learning algorithm. To enable image classification, we pre-process the image to extract its pixel values in the form of a histogram. This histogram is the basis for training a logistic regression with a one-vs-rest approach. At the end of classification, the image and its meta-information is stored in a database that is accessible via an API call. Additionally, we combine these individual components into a command-line application and a web application (hosted at www.bolzano.ml).
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Similar content being viewed by others
References
N. I. of Health: Imagej (2018). [Online] https://imagej.nih.gov/ij/
Sonka, M., Boyle, R., Hlavac, V.: Image Processing, Analysis and Machine Vision book. CL Engineering (1993)
Kanan, C., Cottrell, G.W.: Color-to-grayscale: Does the method matter in image recognition? PLOS One 7 (2012). [Online]. https://doi.org/10.1371/journal.pone.0029740
Anitha, S., Rsdha, Dr.V.: Comparison of image pre-processing techniques for textile texture images. Int. J. Eng. Sci. Technol. 2, 7619–7625 (2010)
Deserno, T.M.E.: Biomedical Image Processing. Springer (2011)
Nocedal, J., Wright, S.J.: Introduction, pp. 1–9. Springer New York, New York, NY (2006). https://doi.org/10.1007/978-0-387-40065-5_1
Initializr, S., Services, P.W.: Spring initializr (2020). https://start.spring.io
Schmidt, M., Le Roux, N., Bach, F.: Minimizing finite sums with the stochastic average gradient. Math. Progr. B 162(1–2), 83–112 (2017). Revision from January 2015 submission. Major changes: updated literature follow and discussion of subsequent work, additional Lemma showing the validity of one of the formulas, somewhat simplified presentation of Lyapunov bound, included code needed for checking proofs rather than the polynomials generated by the code, added error regions to the numerical experiments. [Online]. https://hal.inria.fr/hal-00860051/file/sagMP.pdf
Haifengl: Statistical machine intelligence & learning engine (smile) (2020)
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2022 The Author(s), under exclusive license to Springer Nature Switzerland AG
About this chapter
Cite this chapter
Alawathurage, T.M., Vinay, B., Yojana, G. (2022). Classification of Images from Biomedical Literature. In: Dörpinghaus, J., Weil, V., Schaaf, S., Apke, A. (eds) Computational Life Sciences. Studies in Big Data, vol 112. Springer, Cham. https://doi.org/10.1007/978-3-031-08411-9_21
Download citation
DOI: https://doi.org/10.1007/978-3-031-08411-9_21
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-031-08410-2
Online ISBN: 978-3-031-08411-9
eBook Packages: Mathematics and StatisticsMathematics and Statistics (R0)