Learning Retinal Patterns from Multimodal Images

Proceedings

Novo, Jorge¹  Hervella, Álvaro S.²  Rouco, José³  Ortega, Marcos⁴ 

[1] Author to whom correspondence should be addressed.;CITIC—Research Center of Information and Communication Technologies, University of A Coruña, 17051 A Coruña, Spain;Department of Computer Science, University of A Coruña, 17051 A Coruña, Spain;Presented at the XoveTIC Congress, A Coruña, Spain, 27–28 September 2018.

关键词: self-supervised;    multimodal;    retinography;    angiography;   

DOI  :  10.3390/proceedings2181195

学科分类：社会科学、人文和艺术（综合）

来源: mdpi

【 摘 要 】

The training of deep neural networks usually requires a vast amount of annotated data, which is expensive to obtain in clinical environments. In this work, we propose the use of complementary medical image modalities as an alternative to reduce the required annotated data. The self-supervised training of a reconstruction task between paired multimodal images can be used to learn about the image contents without using any label. Experiments performed with the multimodal setting formed by retinography and fluorescein angiography demonstrate that the proposed task produces the recognition of relevant retinal structures.

【 授权许可】

CC BY