One paper has been accepted by IEEE TMI 🎉

Title: Semantic Augmentation Variational Autoencoder for Unsupervised Anomaly Detection in Retinal OCT Images

Our paper on unsupervised anomaly detection in retinal OCT images has been accepted by IEEE Transactions on Medical Imaging (Zhou et al., 2026). This work proposes SeAugVAE, a semantic augmentation variational autoencoder that improves anomaly sensitivity by enforcing dual distribution consistency in both image and feature spaces during VAE training. It further develops structural-semantic anomaly attention maps to localize retinal anomalies from local and global perspectives.

References

IEEE TMI, IF 12.4

Semantic Augmentation Variational Autoencoder for Unsupervised Anomaly Detection in Retinal OCT Images

Xueying Zhou, Sijie Niu^*, Xiangmin Han, Xiaohui Li, Xizhan Gao, Guang Feng, and Jun Shi

IEEE Transactions on Medical Imaging, Jun 2026

DOI Bib HTML

@article{zhou2026semantic,
  title = {Semantic Augmentation Variational Autoencoder for Unsupervised Anomaly Detection in Retinal OCT Images},
  author = {Zhou, Xueying and Niu, Sijie and Han, Xiangmin and Li, Xiaohui and Gao, Xizhan and Feng, Guang and Shi, Jun},
  journal = {IEEE Transactions on Medical Imaging},
  year = {2026},
  month = jun,
  volume = {45},
  number = {6},
  pages = {2961--2977},
  doi = {10.1109/TMI.2026.3667146},
}