Journal
IEEE TRANSACTIONS ON BIG DATA
Volume 6, Issue 2, Pages 322-333Publisher
IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
DOI: 10.1109/TBDATA.2016.2573280
Keywords
Feature extraction; Computational modeling; Biological system modeling; Gene expression; Data models; Training; Deep learning; transfer learning; multi-task learning; image analysis; bioinformatics
Funding
- US National Science Foundation [IIS-0953662, DBI1147134, DBI-1350258]
- NIH [R01 LM010730, HG002516-09]
- Direct For Computer & Info Scie & Enginr
- Div Of Information & Intelligent Systems [1538638] Funding Source: National Science Foundation
Ask authors/readers for more resources
A central theme in learning from image data is to develop appropriate representations for the specific task at hand. Thus, a practical challenge is to determine what features are appropriate for specific tasks. For example, in the study of gene expression patterns in Drosophila, texture features were particularly effective for determining the developmental stages from in situ hybridization images. Such image representation is however not suitable for controlled vocabulary term annotation. Here, we developed feature extraction methods to generate hierarchical representations for ISH images. Our approach is based on the deep convolutional neural networks that can act on image pixels directly. To make the extracted features generic, the models were trained using a natural image set with millions of labeled examples. These models were transferred to the ISH image domain. To account for the differences between the source and target domains, we proposed a partial transfer learning scheme in which only part of the source model is transferred. We employed multi-task learning method to fine-tune the pre-trained models with labeled ISH images. Results showed that feature representations computed by deep models based on transfer and multi-task learning significantly outperformed other methods for annotating gene expression patterns at different stage ranges.
Authors
I am an author on this paper
Click your name to claim this paper and add it to your profile.
Reviews
Recommended
No Data Available