Encoding Structure-Texture Relation with P-Net for Anomaly Detection in Retinal Images

Zhou，Kang1; Xiao，Yuting1; Yang，Jianlong2; Cheng，Jun3; Liu，Wen1; Luo，Weixin1; Gu，Zaiwang3; Liu，Jiang2,4; Gao，Shenghua1,5

10.1007/978-3-030-58565-5_22

2020

0302-9743

1611-3349

LECT NOTES ARTIF INT

12365 LNCS

360-377

Anomaly detection in retinal image refers to the identification of abnormality caused by various retinal diseases/lesions, by only leveraging normal images in training phase. Normal images from healthy subjects often have regular structures (e.g., the structured blood vessels in the fundus image, or structured anatomy in optical coherence tomography image). On the contrary, the diseases and lesions often destroy these structures. Motivated by this, we propose to leverage the relation between the image texture and structure to design a deep neural network for anomaly detection. Specifically, we first extract the structure of the retinal images, then we combine both the structure features and the last layer features extracted from original health image to reconstruct the original input healthy image. The image feature provides the texture information and guarantees the uniqueness of the image recovered from the structure. In the end, we further utilize the reconstructed image to extract the structure and measure the difference between structure extracted from original and the reconstructed image. On the one hand, minimizing the reconstruction difference behaves like a regularizer to guarantee that the image is corrected reconstructed. On the other hand, such structure difference can also be used as a metric for normality measurement. The whole network is termed as P-Net because it has a “P” shape. Extensive experiments on RESC dataset and iSee dataset validate the effectiveness of our approach for anomaly detection in retinal images. Further, our method also generalizes well to novel class discovery in retinal images and anomaly detection in real-world images.

Anomaly detection Novel class discovery Structure-texture relation

其他

英语

EI

20205009616436

Image texture ; Image reconstruction ; Deep neural networks ; Anomaly detection ; Image analysis ; Optical tomography ; Pattern recognition ; Blood vessels ; Medical imaging ; Ophthalmology

Biomedical Engineering:461.1 ; Biological Materials and Tissue Engineering:461.2 ; Ergonomics and Human Factors Engineering:461.4 ; Medicine and Pharmacology:461.6 ; Data Processing and Image Processing:723.2 ; Optical Devices and Systems:741.3 ; Imaging Techniques:746

2-s2.0-85097385403

Scopus

1.School of Information Science and Technology,ShanghaiTech University,Shanghai,China
2.Cixi Institute of Biomedical Engineering,Chinese Academy of Sciences,Beijing,China
3.UBTech Research,Shenzhen,China
4.Southern University of Science and Technology,Shenzhen,China
5.Shanghai Engineering Research Center of Intelligent Vision and Imaging,Shanghai,China

Zhou，Kang,Xiao，Yuting,Yang，Jianlong,et al. Encoding Structure-Texture Relation with P-Net for Anomaly Detection in Retinal Images[C],2020:360-377.