Related Experiment Video
Updated: Jun 14, 2025
Using Retinal Imaging to Study Dementia
Published on: November 6, 2017
SCINet: A Segmentation and Classification Interaction CNN Method for Arteriosclerotic Retinopathy Grading
Xiongwen Quan1, Xingyuan Ou1, Li Gao2
1National Key Laboratory of Intelligent Tracking and Forecasting for Infectious Diseases, Engineering Research Center of Trusted Behavior Intelligence, Ministry of Education, College of Artificial Intelligence, Nankai University, Tianjin, 300000, China.
Insights
This study introduces SCINet, a novel deep learning model for grading arteriosclerotic retinopathy. SCINet improves detection accuracy by integrating vessel segmentation and feature enhancement, offering a more efficient diagnostic tool.
Area of Science:
- Ophthalmology
- Medical Imaging
- Artificial Intelligence
Background:
- Cardiovascular and cerebrovascular diseases are common and dangerous, with high mortality rates.
- Arteriosclerotic retinopathy is a key indicator of disease severity, but manual evaluation is time-consuming and expensive.
- Current deep learning methods lack interpretability in highlighting critical features for arteriosclerosis detection.
Purpose of the Study:
- To develop an automated and interpretable deep learning model for grading arteriosclerotic retinopathy.
- To improve the efficiency and accuracy of arteriosclerotic retinopathy detection.
- To propose a segmentation and classification interaction network (SCINet) for this task.
Main Methods:
- Utilized IterNet for retinal vessel segmentation from fundus images.
- Developed a backbone feature extractor enhanced by a vessel-aware module with an attention mechanism.
- Implemented a classifier module for final arteriosclerotic retinopathy grading.
Main Results:
- SCINet demonstrated superior performance in grading arteriosclerotic retinopathy compared to existing methods.
- The vessel-aware module effectively highlighted crucial vessel features through attention-based information interaction.
- The proposed architecture achieved significant feature enhancement and accurate grading results.
Conclusions:
- SCINet provides an effective and interpretable solution for automated arteriosclerotic retinopathy grading.
- The model's architecture, combining segmentation and classification with attention, enhances diagnostic capabilities.
- The approach is scalable and can be adapted for similar medical imaging tasks using segmented auxiliary information.
Abstract:
As a common disease, cardiovascular and cerebrovascular diseases pose a great harm threat to human wellness. Even using advanced and comprehensive treatment methods, there is still a high mortality rate. Arteriosclerosis, as an important factor reflecting the severity of cardiovascular and cerebrovascular diseases, is imperative to detect the arteriosclerotic retinopathy. However, the detection of arteriosclerosis retinopathy requires expensive and time-consuming manual evaluation, while end-to-end deep learning detection methods also need interpretable design to high light task-related features. Considering the importance of automatic arteriosclerotic retinopathy grading, we propose a segmentation and classification interaction network (SCINet). We propose a segmentation and classification interaction architecture for grading arteriosclerotic retinopathy. After IterNet is used to segment retinal vessel from original fundus images, the backbone feature extractor roughly extracts features from the segmented and original fundus arteriosclerosis images and further enhances them through the vessel aware module. The last classifier module generates fundus arteriosclerosis grading results. Specifically, the vessel aware module is designed to highlight the important areal vessel features segmented from original images by attention mechanism, thereby achieving information interaction. The attention mechanism selectively learns the vessel features of segmentation region information under the proposed interactive architecture, which leads to reweighting the extracted features and enhances significant feature information. Extensive experiments have confirmed the effect of our model. SCINet has the best performance on the task of arteriosclerotic retinopathy grading. Additionally, the CNN method is scalable to similar tasks by incorporating segmented images as auxiliary information.
