高级检索
赵文涛, 续欣莹, 谢珺, 程兰, 张喆. 基于深度特征匹配的白内障术中眼球旋转角度检测方法[J]. 计算机辅助设计与图形学学报.
引用本文: 赵文涛, 续欣莹, 谢珺, 程兰, 张喆. 基于深度特征匹配的白内障术中眼球旋转角度检测方法[J]. 计算机辅助设计与图形学学报.
Detection Method of Eye Rotation Angle in Cataract Surgery Based on Depth Feature Matching[J]. Journal of Computer-Aided Design & Computer Graphics.
Citation: Detection Method of Eye Rotation Angle in Cataract Surgery Based on Depth Feature Matching[J]. Journal of Computer-Aided Design & Computer Graphics.

基于深度特征匹配的白内障术中眼球旋转角度检测方法

Detection Method of Eye Rotation Angle in Cataract Surgery Based on Depth Feature Matching

  • 摘要: 为了实现对白内障手术中眼球旋转角度的测量, 提出基于深度特征匹配的白内障术中眼球旋转角度检测方法, 即对术前基准图像与术中图像中角膜缘周围区域的特征点进行提取与匹配以计算术中眼球旋转角度. 针对角膜缘周围纹理特征丰富但相似性高、特征易受手术进程与器械干扰而发生显著变化等问题, 提出一种结合注意力卷积模块(attention convolution block, AttConvBlock)和自适应跳层连接的自监督图像局部特征提取与描述模型. 首先, AttConvBlock利用坐标注意力机制加强模型对于方向和空间位置信息的准确感知, 并通过条件参数化深度卷积提升模型容量以增强对于特征信息的表示能力; 其次, 自适应跳层连接通过融合深层语义信息和浅层结构信息, 获得对特征点更具区分性的描述. 在CATARACT数据集上的实验结果表明, 所提模型在各误差限下的特征点平均匹配精度均优于其他同类模型; 且所提方法的眼球旋转角度测量误差为0.740°, 实时检测速度为36.675 帧/s, 满足白内障手术中眼球旋转角度检测精度和实时性的要求.

     

    Abstract:  In order to measure the eye rotation angle during cataract surgery, a detection method of eye rotation angle in cataract surgery based on depth feature matching is proposed, which extracts and matches the feature points of the preoperative reference image and the intraoperative image around the corneal limbus to calculate the intraoperative eye rotation angle. The texture features around the limbus are rich but their similarity is high, and the features are susceptible to obvious changes due to the interference of the surgical process and instruments. To solve these problems, a self-supervised image local feature extraction and description model is proposed, which combines attention convolution block (AttConvBlock) and adaptive skip connection. First, AttConvBlock enhances the model's accurate perception of orientation and spatial location information by coordinate attention. Besides, AttConvBlock improves the capacity of the model through conditionally parameterized depthwise convolutions, which can enhance the representation ability of the model for feature information. Furthermore, the adaptive skip connection fuses deep semantic information and shallow structural information, which contributes to a more discriminative description of feature points. The experimental results on the CATARACT dataset show that the proposed model has higher mean matching accuracy under each error limit than other compared models. Additionally, the mean rotation error of the proposed method is 0.740°, and the real-time detection speed is 36.675 frames per second, meeting the requirements of accuracy and real-time detection of eye rotation angle in cataract surgery.

     

/

返回文章
返回