Machine-learning based segmentation of the optic nerve head using multi-contrast Jones matrix optical coherence tomography with semi-automatic training dataset generation

Kasaragod, Deepa; Makita, Shuichi; Hong, Young-Joo; Yasuno, Yoshiaki

doi:10.1364/boe.9.003220

Cited by 10 publications

(9 citation statements)

References 53 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Machine learning techniques have been explored to segment microvasculature, 166 non-perfusion areas, 167 optical nerve head. 168 A support vector machine (SVM) classifier was recently demonstrated for supervised machine learning based OCTA classification of SCR 35 and DR. 39 Six OCTA features, i.e. BVD, BVC, BVT, VPI, FAZ-A, and FAZ-CI, were used to train the SVM classifier for identifying control, mild, and severe SCR subjects.…”

Section: Discussionmentioning

confidence: 99%

Quantitative optical coherence tomography angiography: A review

Yao

Alam

et al. 2020

Exp Biol Med (Maywood)

View full text Add to dashboard Cite

As a new optical coherence tomography (OCT) modality, OCT angiography (OCTA) provides a noninvasive method to detect microvascular distortions correlated with eye conditions. By providing unparalleled capability to differentiate individual plexus layers in the retina, OCTA has demonstrated its excellence in clinical management of diabetic retinopathy, glaucoma, sickle cell retinopathy, diabetic macular edema, and other eye diseases. Quantitative OCTA analysis of retinal and choroidal vasculatures is essential to standardize objective interpretations of clinical outcome. Quantitative features, including blood vessel tortuosity, blood vessel caliber, blood vessel density, vessel perimeter index, fovea avascular zone area, fovea avascular zone contour irregularity, vessel branching coefficient, vessel branching angle, branching width ratio, and choroidal vascular analysis have been established for objective OCTA assessment. Moreover, differential artery–vein analysis has been recently demonstrated to improve OCTA performance for objective detection and classification of eye diseases. In this review, technical rationales and clinical applications of these quantitative OCTA features are summarized, and future prospects for using these quantitative OCTA features for artificial intelligence classification of eye conditions are discussed. Impact statement OCT angiography (OCTA) provides a noninvasive method to detect microvascular distortions correlated with eye conditions. Quantitative analysis of OCTA is essential to standardize objective interpretations of clinical outcome. This review summarizes technical rationales and clinical applications of quantitative OCTA features.

show abstract

Section: Discussionmentioning

confidence: 99%

Quantitative optical coherence tomography angiography: A review

Yao

Alam

et al. 2020

Exp Biol Med (Maywood)

View full text Add to dashboard Cite

show abstract

“…Machine learning, and other advanced computational techniques have begun to dramatically reduce the time taken to convert an imaged volume to discrete and quantifiable structures within the volume (Januszewski et al, 2018; Berning et al, 2015; Lucchi et al, 2010; Meijs et al, 2017; Camacho et al, 2018; Kasaragod et al, 2018).…”

Section: Introductionmentioning

confidence: 99%

Semi-automated 3D segmentation of human skeletal muscle using Focused Ion Beam-Scanning Electron Microscopic images

Caffrey

Maltsev

González-Freire

et al. 2019

Journal of Structural Biology

View full text Add to dashboard Cite

Focused Ion Beam Scanning Electron Microscopy (FIB-SEM) is an imaging approach that enables analysis of the 3D architecture of cells and tissues at resolutions that are 1–2 orders of magnitude higher than that possible with light microscopy. The slow speeds of data collection and manual segmentation are two critical problems that limit the more extensive use of FIB-SEM technology. Here, we present an easily accessible robust method that enables rapid, large-scale acquisition of data from tissue specimens, combined with an approach for semi-automated data segmentation using the open-source machine learning Weka segmentation software, which dramatically increases the speed of image analysis. We demonstrate the feasibility of these methods through the 3D analysis of human muscle tissue by showing that our process results in an improvement in speed of up to three orders of magnitude as compared to manual approaches for data segmentation. All programs and scripts we use are open source and are immediately available for use by others.

show abstract

“…Both collagen beams and neural tissues are highly scattering, and previous studies have shown that collagen beams are more scattering than neural tissues. 23 The neural tissues appear to have similar properties to white matter, which has weak absorption and the collagen tissues were also reported to have weak absorption. 24,25 To compare the performance of SPLM on thick tissues with regular PLM on thin sections, we fixed and cryosectioned coronally (transversely) a sheep ONH starting from the anterior side.…”

Section: Sample Preparation and Mountingmentioning

confidence: 99%

Structured polarized light microscopy for collagen fiber structure and orientation quantification in thick ocular tissues

et al. 2018

View full text Add to dashboard Cite

Collagen is a major constituent of the eye and understanding its architecture and biomechanics is critical to preserve and restore vision. We, recently, demonstrated polarized light microscopy (PLM) as a powerful technique for measuring properties of the collagen fibers of the eye, such as spatial distribution and orientation. Our implementation of PLM, however, required sectioning the tissues for imaging using transmitted light. This is problematic because it limits analysis to thin sections. This is not only slow, but precludes study of dynamic events such as pressure-induced deformations, which are central to the role of collagen. We introduce structured polarized light microscopy (SPLM), an imaging technique that combines structured light illumination with PLM to allow imaging and measurement of collagen fiber properties in thick ocular tissues. Using pig and sheep eyes, we show that SPLM rejects diffuse background light effectively in thick tissues, significantly enhancing visualization of optic nerve head (ONH) structures, such as the lamina cribrosa, and improving the accuracy of the collagen fiber orientation measurements. Further, we demonstrate the integration of SPLM with an inflation device to enable direct visualization, deformation tracking, and quantification of collagen fibers in ONHs while under controlled pressure.

show abstract

Machine-learning based segmentation of the optic nerve head using multi-contrast Jones matrix optical coherence tomography with semi-automatic training dataset generation

Cited by 10 publications

References 53 publications

Quantitative optical coherence tomography angiography: A review

Quantitative optical coherence tomography angiography: A review

Semi-automated 3D segmentation of human skeletal muscle using Focused Ion Beam-Scanning Electron Microscopic images

Structured polarized light microscopy for collagen fiber structure and orientation quantification in thick ocular tissues

Contact Info

Product

Resources

About