five

AI Training Data for OCT-SLO Self Calibration and Automation

收藏
IEEE2026-04-17 收录
下载链接:
https://ieee-dataport.org/documents/ai-training-data-oct-slo-self-calibration-and-automation
下载链接
链接失效反馈
官方服务:
资源简介:
Attached Image data set from combined OCT-SLO is used to train AI models and identify features to maximize quality of data set to adjust MZI reference arm, PMT Voltage of Liquid Lens and location of object. Why adjustment is needed is explained below: 1.      Fourier-Domain OCT (FD-OCT), uses a spectrometer that can compensate for wavelength-dependent dispersion. However, residual dispersion mismatch may remain. Fine-tuning the reference arm length may help further minimize dispersion-induced phase errors. Even though the spectrometer compensates for dispersion, thus, MZI arms still need to be optically balanced for efficient interference, time-to-time.2.      In FD-OCT, signal strength decreases with depth. Adjusting the reference arm length can help optimize the depth range and improve the signal-to-noise ratio (SNR).If the optical properties of the sample change significantly (e.g., refractive index variations), or differ than the standard sample adjustment of the reference arm to maintain optimal interference conditions is necessary.3.      Irrespective the integration of spectrometer, the interference fringe contrast may be sub-optimal, adjustment of the reference arm may bring it within the coherence length of light source. This is crucial for sources with a relatively short coherence length (for example, superluminescent diodes, SLDs).4.      If the optical properties of the sample change significantly (dynamic profile etc), default arm settings may not support spectrometer to fulling achive desired dispersion matching. The above listed issues may be attributable to following reasons:1.      Finite spectral resolution of spectrometer,2.      Operational aging of optics affecting the spectral range, resolution, and dispersion properties. What if MZI arms are not adjusted: 1.      If the reference arm position results in an incorrect mapping of k-space frequencies, it can lead to aliasing or artifacts in the depth reconstruction.  Adjusting the reference arm ensures correct spectral calibration and avoids these distortions.
提供机构:
Goswami, Mayank
5,000+
优质数据集
54 个
任务类型
进入经典数据集
二维码
社区交流群

面向社区/商业的数据集话题

二维码
科研交流群

面向高校/科研机构的开源数据集话题

数据驱动未来

携手共赢发展

商业合作