Scholarlink

Purpose <p>Retinal laser surgery serves as a crucial clinical approach for treating central serous chorioretinopathy (CSCR). However, the preoperative process requires ophthalmologist to manually annotate keypoint on both fundus fluorescein angiography (FFA) and color fundus (CF) images for image registration, which is time-consuming and susceptible to subjective variability. Meanwhile, the existing rigid registration methods are relatively cumbersome in detecting keypoints and establishing their corresponding relationships. Consequently, exploring a new rigid registration method for multi-modal retinal images has potential clinical value and research significance.</p> Methods <p>This paper proposes a novel rigid registration method for multi-modal retinal images based on intelligent matching of keypoint pairs. Concretely, a keypoint pair dataset tailored for clinical CSCR multi-modal retinal images was first constructed to support subsequent research. Then, the YOLOv8-pose based framework for intelligent matching of keypoint pairs was successfully introduced, which unifies keypoint localization and correspondence establishment into a single task. Third, a keypoint re-localization technique was developed to enhance the positional accuracy of keypoints, followed by a keypoint pair selection strategy to optimize the choice of keypoints for affine transformation. Finally, detailed quantitative and qualitative experiments were conducted to investigate the effectiveness of the proposed method.</p> Results <p>The experimental results on the private dataset demonstrate that the relocalized keypoints achieved average reductions of 37.78%, 44.78%, and 40.88% in maximum error (MAE), median error (MEE), and root mean square error (RMSE) respectively, demonstrating that the proposed technique significantly reduces position errors. For multi-modal retinal image registration, the Dice Coefficient (Dice) reached 0.5023 (± 0.1262) and the soft Dice Coefficient (Dice<sub>s</sub>) achieved 0.3940 (± 0.0571), showing higher registration accuracy compared to conventional methods.</p> Conclusion <p>Both quantitative and qualitative results demonstrate that the proposed method achieves precise localization of keypoint pairs and delivers higher registration accuracy compared to conventional approaches.</p>

错误：搜索内容不能为空，请输入英文关键词
错误：关键词超出字数限制，请精简
高级检索

Rigid Registration of Multi-Modal Retinal Images Based on Intelligent Matching of Keypoint Pairs

  • 期刊论文

  • 发表日期：

    2026年2月9日

查看全文
  • Jianguo Xu,
  • Sen Zhang,
  • Jianxin Shen,
  • Jie Pang,
  • Saisai Niu,
  • Fen Zhou,
  • Zhipeng Yan,
  • Jin Yao

摘要

Purpose

Retinal laser surgery serves as a crucial clinical approach for treating central serous chorioretinopathy (CSCR). However, the preoperative process requires ophthalmologist to manually annotate keypoint on both fundus fluorescein angiography (FFA) and color fundus (CF) images for image registration, which is time-consuming and susceptible to subjective variability. Meanwhile, the existing rigid registration methods are relatively cumbersome in detecting keypoints and establishing their corresponding relationships. Consequently, exploring a new rigid registration method for multi-modal retinal images has potential clinical value and research significance.

Methods

This paper proposes a novel rigid registration method for multi-modal retinal images based on intelligent matching of keypoint pairs. Concretely, a keypoint pair dataset tailored for clinical CSCR multi-modal retinal images was first constructed to support subsequent research. Then, the YOLOv8-pose based framework for intelligent matching of keypoint pairs was successfully introduced, which unifies keypoint localization and correspondence establishment into a single task. Third, a keypoint re-localization technique was developed to enhance the positional accuracy of keypoints, followed by a keypoint pair selection strategy to optimize the choice of keypoints for affine transformation. Finally, detailed quantitative and qualitative experiments were conducted to investigate the effectiveness of the proposed method.

Results

The experimental results on the private dataset demonstrate that the relocalized keypoints achieved average reductions of 37.78%, 44.78%, and 40.88% in maximum error (MAE), median error (MEE), and root mean square error (RMSE) respectively, demonstrating that the proposed technique significantly reduces position errors. For multi-modal retinal image registration, the Dice Coefficient (Dice) reached 0.5023 (± 0.1262) and the soft Dice Coefficient (Dices) achieved 0.3940 (± 0.0571), showing higher registration accuracy compared to conventional methods.

Conclusion

Both quantitative and qualitative results demonstrate that the proposed method achieves precise localization of keypoint pairs and delivers higher registration accuracy compared to conventional approaches.