A label-free anomaly segmentation method is proposed based on layer-wise grey scale comparisons between the original and the reconstructed images. Abstract.

Experimental results demonstrate the effectiveness of our proposed method for unsupervised anomaly detection, staging and segmentation on both retinal optical ...

Oct 22, 2024 · Experimental results demonstrate the effectiveness of our proposed method for unsupervised anomaly detection, staging and segmentation on both ...

A novel heterogeneous Auto-Encoder (Hetero-AE) is proposed, which utilizes a convolutional neural network as the encoder and a hybrid CNN-Transformer ...

Apr 25, 2024 · Qingbo Kang , Zekun Jiang , Shiyi Du, Shaoting Zhang, Kang Li : Self-supervised anomaly detection, staging and segmentation for retinal images.

A powerful student-teacher framework for the challenging problem of unsupervised anomaly detection and pixel-precise anomaly segmentation in high-resolution ...

在本文中，我们首先提出了一个通用的无监督异常检测框架SSL-AnoVAE ，它利用自监督学习(SSL) 模块根据视网膜图像中待检测的异常提供更细粒度的语义。我们还 ...

Thus, the aim of this study was to identify those common retinal pathologies using novel self-supervised anomaly detection deep learning methods. 2. Methods.

Oct 24, 2023 · We establish an uncertainty-inspired open set (UIOS) model, which is trained with fundus images of 9 retinal conditions.