Learning To Segment Corneal Tissue Interfaces In Oct Images

Abstract

Accurate and repeatable delineation of corneal tissue interfaces is necessary for surgical planning during anterior segment interventions, such as Keratoplasty. Designing an approach to identify interfaces, which generalizes to datasets acquired from different Optical Coherence Tomographic (OCT) scanners, is paramount. In this paper, we present a Convolutional Neural Network (CNN) based framework called CorNet that can accurately segment three corneal interfaces across datasets obtained with different scan settings from different OCT scanners. Extensive validation of the approach was conducted across all imaged datasets. To the best of our knowledge, this is the first deep learning based approach to segment both anterior and posterior corneal tissue interfaces. Our errors are 2× lower than non-proprietary state-of-the-art corneal tissue interface segmentation algorithms, which include image analysis-based and deep learning approaches.

Pathological-Corneas Layer Segmentation and Thickness Measurement in OCT Images

“…However, the corneal OCT images usually have low SNR at the periphery 12 and the segmentation needs to be handled properly in these regions. Methods in References 27 , 29 , and 30 use the U-shape network (e.g., U-Net 32 ) to semantically segment each layer as a region. However, Dos Santos et al .…”

Accurate tissue interface segmentation via adversarial pre-segmentation of anterior segment OCT images

“…Efforts were also made to remove artifacts by using the reference spectrum [11,27], and piezoelectric fiber stretchers [28] in the Fourier domain. However, these methods only work when a fixed type of artifact is encountered, such as the horizontal artifacts in [11,27], and they do not generalize to datasets where the assumption of the artifact presence is violated [29] as seen in Fig. 2.…”

“…However, among all the aforementioned methods, the majority of traditional methods [40,41,[43][44][45][46][47][48][49] and learning-based methods [57][58][59][60][61][62][63]72] are focused on retinal interface segmentation. Corneal interface segmentation algorithms are predominately based on traditional approaches [5,7,11,[64][65][66][67][68][69][70][71], with limited learning-based approaches [29,73] being proposed. Similarly, prior work on limbal interface segmentation is limited to a traditional image analysisbased approach [12].…”

“…But as seen in Fig. 2, this assumption can be violated when the central artifacts are located in different image regions [29]. In such cases, prior approaches failed to accurately segment the tissue interface as shown in Figs.…”

“…Furthermore, there were two independent and concurrently published deep learning-based corneal interface segmentation approaches [29,73]. One of these approaches [73] acquired data from a single OCT scanner, and focused only on the region centered around the corneal apex in these OCT sequences as the drop in SNR was greater when moving away from this region.…”