|
| 融合下补偿结构的眼底血管图像分割网络研究 |
| Research on fundus vascular images segmentation network combined with low compensation structure |
| 投稿时间：2022-09-16 |
| DOI：10.3969/j.issn.1005-5630.2023.003.003 |
| 中文关键词: 医学图像分割 神经网络 空间注意力 下补偿结构 |
| 英文关键词:medical image segmentation neural network spatial attention low compensation structure |
| 基金项目:国家自然科学基金民航联合重点项目（U2033218） |
|
| 摘要点击次数: 1529 |
| 全文下载次数: 1330 |
| 中文摘要: |
| 眼底血管图像在临床中通常被用于眼部疾病的诊断及监测，其中血管的形态结构能够反映疾病的重要特征，因此，眼底血管图像的分割处理对眼部疾病的诊断和预防具有十分重要的医学意义。针对目前人工智能主流算法中卷积和池化操作会导致很多特征丢失，提取特征时会忽视图像中的空间信息，图像中的细小血管很难分割出来等问题，基于U-net模型进行了相关研究，结合空间注意力模块对空间特征进行细化，同时提出了一种下补偿结构LC-SAnet。该结构能够减少网络提取特征信息过程中的特征损失，从而提高分割精度。研究实验在DRIVE数据集上完成，LC-SAnet的分割准确率达到96.97%，F1值达到74.36%。结果证明，LC-SAnet表现出更好的分割性能，对细小血管的结构识别更加准确。 |
| 英文摘要: |
| Fundus vascular images are commonly used in clinical practice for the diagnosis and monitoring of eye diseases. The morphology and structure of blood vessels could reflect the essential features of the disease. Therefore, the segmentation of fundus vascular images is of great medical significance for the diagnosis and prevention of eye diseases. Current mainstream artificial intelligence algorithms, due to convolution and pooling operation, often neglect the extracted features of the spatial information in the images, making it difficult to segment fine blood vessels and other details. This study conducted research based on the U-net model, combining a spatial attention module to refine the spatial features. It also proposed a low compensation structure to reduce the feature loss during the feature extraction process of network, thereby improving the segmentation accuracy. Experiments were conducted on the DRIVE open dataset, and the algorithm achieved a segmentation accuracy of 96.97% and an F1 value of 74.36%. The results demonstrate that the proposed network structure exhibits better segmentation performance and more accurate identification of fine blood vessels structures. |
| HTML 查看全文 查看/发表评论 下载PDF阅读器 |
| 关闭 |
