Synthesizing New Retinal Symptom Images by Multiple Generative Models
License
http://creativecommons.org/licenses/by-nc-sa/4.0/Type
Conference PaperAuthors
Liu, Yi ChiehYang, Hao Hsiang
Huck Yang, C. H.
Huang, Jia-Hong
Tian, Meng
Morikawa, Hiromasa
Tsai, Yi Chang James
Tegner, Jesper
KAUST Department
Biological and Environmental Sciences and Engineering (BESE) DivisionBioscience
Bioscience Program
Earth Science and Engineering
Earth Science and Engineering Program
Preprint Posting Date
2019-02-11Online Publication Date
2019-06-19Print Publication Date
2019Date
2019-06-19Abstract
Age-Related Macular Degeneration (AMD) is an asymptomatic retinal disease which may result in loss of vision. There is limited access to high-quality relevant retinal images and poor understanding of the features defining sub-classes of this disease. Motivated by recent advances in machine learning we specifically explore the potential of generative modeling, using Generative Adversarial Networks (GANs) and style transferring, to facilitate clinical diagnosis and disease understanding by feature extraction. We design an analytic pipeline which first generates synthetic retinal images from clinical images; a subsequent verification step is applied. In the synthesizing step we merge GANs (DCGANs and WGANs architectures) and style transferring for the image generation, whereas the verified step controls the accuracy of the generated images. We find that the generated images contain sufficient pathological details to facilitate ophthalmologists’ task of disease classification and in discovery of disease relevant features. In particular, our system predicts the drusen and geographic atrophy sub-classes of AMD. Furthermore, the performance using CFP images for GANs outperforms the classification based on using only the original clinical dataset. Our results are evaluated using existing classifier of retinal diseases and class activated maps, supporting the predictive power of the synthetic images and their utility for feature extraction. Our code examples are available online. (https://github.com/huckiyang/EyeNet-GANs).Citation
Liu, Y.-C., Yang, H.-H., Huck Yang, C.-H., Huang, J.-H., Tian, M., Morikawa, H., … Tegnèr, J. (2019). Synthesizing New Retinal Symptom Images by Multiple Generative Models. Lecture Notes in Computer Science, 235–250. doi:10.1007/978-3-030-21074-8_19Publisher
Springer NatureConference/Event Name
14th Asian Conference on Computer Vision, ACCV 2018DOI
10.1007/978-3-030-21074-8_19arXiv
1902.04147Additional Links
http://pubs.acs.org/doi/10.1021/acs.iecr.9b00527Relations
Is Supplemented By:- [Software]
Title: huckiyang/EyeNet-GANs: ACCV'18 workshop - Synthesizing New Retinal Symptom Images by Multiple Generative Models. Publication Date: 2018-12-03. github: huckiyang/EyeNet-GANs Handle: 10754/668079