CNN-based CP-OCT sensor integrated with a subretinal injector for retinal boundary tracking and injection guidance

Abstract

. Significance: Subretinal injection is an effective way of delivering transplant genes and cells to treat many degenerative retinal diseases. However, the technique requires high-dexterity and microscale precision of experienced surgeons, who have to overcome the physiological hand tremor and limited visualization of the subretinal space. Aim: To automatically guide the axial motion of microsurgical tools (i.e., a subretinal injector) with microscale precision in real time using a fiber-optic common-path swept-source optical coherence tomography distal sensor. Approach: We propose, implement, and study real-time retinal boundary tracking of A-scan optical coherence tomography (OCT) images using a convolutional neural network (CNN) for automatic depth targeting of a selected retinal boundary for accurate subretinal injection guidance. A simplified 1D U-net is used for the retinal layer segmentation on A-scan OCT images. A Kalman filter, combining retinal boundary position measurement by CNN and velocity measurement by cross correlation between consecutive A-scan images, is applied to optimally estimate the retinal boundary position. Unwanted axial motions of the surgical tools are compensated by a piezoelectric linear motor based on the retinal boundary tracking. Results: CNN-based segmentation on A-scan OCT images achieves the mean unsigned error (MUE) of ( ) using an ex vivo bovine retina model. GPU parallel computing allows real-time inference ( ) and thus real-time retinal boundary tracking. Involuntary tremors, which include low-frequency draft in hundreds of micrometers and physiological tremors in tens of micrometers, are compensated effectively. The standard deviations of photoreceptor (PR) and choroid (CH) boundary positions get as low as when the depth targeting is activated. Conclusions: A CNN-based common-path OCT distal sensor successfully tracks retinal boundaries, especially the PR/CH boundary for subretinal injection, and automatically guides the tooltip’s axial position in real time. The microscale depth targeting accuracy of our system shows its promising possibility for clinical application.

Higher-order regression three-dimensional motion-compensation method for real-time optical coherence tomography volumetric imaging of the cornea

“…Note that due to the refractive power of the cornea and crystalline lens, the OCT image of the retina is distorted and does not represent the true curvature of the retina so that additional image processing is required to obtain the true reference image. However, for many applications (including robotic tool guidance that we are pursuing 2 , 28 – 30 ), an optically distorted image is sufficient and only the relative position and the curvature are needed to correctly assess the tool to tissue distance. Therefore, even for retinal imaging, one could still use the same processing methods to obtain motion-free retinal images.…”

Unsupervised out-of-distribution detection for safer robotically guided retinal microsurgery

“…1 . Similar to [ 15 ], the model r is trained by minimizing the standard L2 loss over a training dataset of M-scans and their corresponding ground-truth retinal maps.…”

Artificial Intelligence in Choroid Through Optical Coherence Tomography: A Comprehensive Review

“…This novel concept opens doors for diverse applications. AI aids real-time sensor tracking by tracing boundaries and betters images by eliminating shadows and artifacts [79].…”