SegImgNet: Segmentation-Guided Dual-Branch Network for Retinal Disease Diagnoses
This work addresses retinal disease diagnosis for medical imaging applications, presenting an incremental improvement through a novel hybrid method.
The authors tackled the challenge of effectively capturing retinal structural features for disease diagnosis by proposing SegImgNet, a segmentation-guided dual-branch network that integrates segmentation maps with retinal images, and demonstrated its effectiveness by outperforming existing methods on the AIROGS and e-ROP datasets.
Retinal image plays a crucial role in diagnosing various diseases, as retinal structures provide essential diagnostic information. However, effectively capturing structural features while integrating them with contextual information from retinal images remains a challenge. In this work, we propose segmentation-guided dual-branch network for retinal disease diagnosis using retinal images and their segmentation maps, named SegImgNet. SegImgNet incorporates a segmentation module to generate multi-scale retinal structural feature maps from retinal images. The classification module employs two encoders to independently extract features from segmented images and retinal images for disease classification. To further enhance feature extraction, we introduce the Segmentation-Guided Attention (SGA) block, which leverages feature maps from the segmentation module to refine the classification process. We evaluate SegImgNet on the public AIROGS dataset and the private e-ROP dataset. Experimental results demonstrate that SegImgNet consistently outperforms existing methods, underscoring its effectiveness in retinal disease diagnosis. The code is publicly available at https://github.com/hawk-sudo/SegImgNet.