光学
光学相干层析成像
散斑噪声
斑点图案
降噪
连贯性(哲学赌博策略)
物理
噪音(视频)
图像质量
散斑成像
还原(数学)
图像处理
鬼影成像
信号处理
断层摄影术
信噪比(成像)
空间频率
迭代重建
光学成像
材料科学
激光束
光纤
相干理论
干涉测量
背景噪声
相位噪声
衰减系数
作者
Sivalal Kethavath,Vasundhara Vasundhara,Mohan Kumar Manepalli,Bhaskara Rao Chintada,Phaneendra Kumar Yalavarthy
出处
期刊:Optics Letters
[Optica Publishing Group]
日期:2026-08-19
卷期号:51 (17): 4793-4793
摘要
Optical Coherence Tomography (OCT) speckle degrades the contrast and impairs automated analysis. Classical speckle suppression methods blur boundaries, supervised deep learning requires clinically impractical training pairs, and existing self-supervised approaches, such as S2SNet, tend to over-smooth retinal layers. To address these limitations, this study proposes a novel, to the best of our knowledge, energy-based regularization term that penalizes overly smooth, low-energy reconstructions, yielding an Energy-regularized Self-Supervised Network (E-S2SNet). Evaluation of the 18 B-scan SD-OCT dataset and the NR206 dataset demonstrated that E-S2SNet achieves a superior balance between speckle suppression and structural preservation, outperforming both classical and deep learning baselines without requiring clean reference (ground truth/training) data. Furthermore, improved downstream retinal layer segmentation indicates the practical utility of the proposed approach, showing promise for future integration into automated OCT analysis.
科研通智能强力驱动
Strongly Powered by AbleSci AI