Retinal layer parcellation of optical coherence tomography images: Data resource for multiple sclerosis and healthy controls

He, Yufan; Carass, Aaron; Solomon, Sharon D.; Saidha, Shiv; Calabresi, Peter A.; Prince, Jerry L.

doi:10.1016/j.dib.2018.12.073

Cited by 62 publications

(32 citation statements)

References 11 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The proposed method was validated on two publicly available data sets. The first data set [8] contains 35 (14 healthy controls (HC) and 21 subjects with multiple sclerosis (MS)) macula Spectralis OCT scans, of which nine surfaces are manually delineated. Each scan has 49 Bscans of size 496 × 1024.…”

Section: Methodsmentioning

confidence: 99%

Fully Convolutional Boundary Regression for Retina OCT Segmentation

Carass

Liu

et al. 2019

Lecture Notes in Computer Science

Self Cite

View full text Add to dashboard Cite

A major goal of analyzing retinal optical coherence tomography (OCT) images is retinal layer segmentation. Accurate automated algorithms for segmenting smooth continuous layer surfaces, with correct hierarchy (topology) are desired for monitoring disease progression. State-of-the-art methods use a trained classifier to label each pixel into background, layer, or surface pixels. The final step of extracting the desired smooth surfaces with correct topology are mostly performed by graph methods (e.g. shortest path, graph cut). However, manually building a graph with varying constraints by retinal region and pathology and solving the minimization with specialized algorithms will degrade the flexibility and time efficiency of the whole framework. In this paper, we directly model the distribution of surface positions using a deep network with a fully differentiable soft argmax to obtain smooth, continuous surfaces in a single feed forward operation. A special topology module is used in the deep network both in the training and testing stages to guarantee the surface topology. An extra deep network output branch is also used for predicting lesion and layers in a pixel-wise labeling scheme. The proposed method was evaluated on two publicly available data sets of healthy controls, subjects with multiple sclerosis, and diabetic macular edema; it achieves state-of-the art sub-pixel results.

show abstract

Section: Methodsmentioning

confidence: 99%

Fully Convolutional Boundary Regression for Retina OCT Segmentation

Carass

Liu

et al. 2019

Lecture Notes in Computer Science

Self Cite

View full text Add to dashboard Cite

show abstract

“…Our first data set includes 35 macular OCT scans, publicly available from [42], acquired from a Spectralis OCT system (Heidelberg Engineering, Heidelberg, Germany). Twenty-one of the scans are diagnosed with multiple sclerosis (MS) and the remaining fourteen are healthy controls (HC).…”

Section: Retina Layer Surface Evaluationmentioning

confidence: 99%

Deep learning based topology guaranteed surface and MME segmentation of multiple sclerosis subjects from retinal OCT

He¹,

Carass²,

Liu³

et al. 2019

Biomed. Opt. Express

Self Cite

View full text Add to dashboard Cite

Optical coherence tomography (OCT) is a noninvasive imaging modality that can be used to obtain depth images of the retina. Patients with multiple sclerosis (MS) have thinning retinal nerve fiber and ganglion cell layers, and approximately 5% of MS patients will develop microcystic macular edema (MME) within the retina. Segmentation of both the retinal layers and MME can provide important information to help monitor MS progression. Graph-based segmentation with machine learning preprocessing is the leading method for retinal layer segmentation, providing accurate surface delineations with the correct topological ordering. However, graph methods are time-consuming and they do not optimally incorporate joint MME segmentation. This paper presents a deep network that extracts continuous, smooth, and topology-guaranteed surfaces and MMEs. The network learns shape priors automatically during training rather than being hard-coded as in graph methods. In this new approach, retinal surfaces and MMEs are segmented together with two cascaded deep networks in a single feed forward propagation. The proposed framework obtains retinal surfaces (separating the layers) with sub-pixel surface accuracy comparable to the best existing graph methods and MMEs with better accuracy than the state-of-the-art method. The full segmentation operation takes only ten seconds for a 3D volume.

show abstract

“…The advantages and disadvantages of these approaches have been described elsewhere. [38][39][40] Some of the main technical challenges in these algorithms have been managing corrections for blood vessels within the layers and irregular boundaries across the quadrants sampled in the macular tissue. 40 Of all the retinal layers, the combined GCL/IPL has had overall strongest performance for identifying pathology of interest in MS. 38,41 These OCT observations of the GCL/IPL are consistent with postmortem analysis of RGC loss in the retinal tissue of MS patients.…”

Section: Segmentation and The Retinal Ganglion Cell Layermentioning

confidence: 99%

Optical Coherence Tomography in Multiple Sclerosis

Graves

2019

Semin Neurol

View full text Add to dashboard Cite

Optical coherence tomography (OCT) grew out of a convergence of rapid advancements in femtoseconds optics research and fiber optic commercial technology. The basic concept of OCT is to “see” into tissues using light echoes, analogous to the sound echoes of ultrasonography. Multiple A-scans are assembled into a B-scan two-dimensional image of the tissue of interest. Retina is an ideal tissue for evaluation by OCT, since the eye is designed to minimize light scattering through the anterior chamber and vitreous. OCT has had a significant impact on the field of multiple sclerosis, where it has allowed direct imaging of the myelin-free segments of axons and cell bodies of retinal ganglion cells. Together with precise functional measurements of the afferent visual system, the addition of robust structural measurements of retinal injury has allowed for an unprecedented ability to correlate clinical effects with the degree of neuronal loss. In addition, OCT has proven helpful to distinguish different forms of demyelinating disease, such as multiple sclerosis (MS) and neuromyelitis optica, and has provided ideal outcome measures in remyelination and neuroprotection trials.

show abstract

Retinal layer parcellation of optical coherence tomography images: Data resource for multiple sclerosis and healthy controls

Cited by 62 publications

References 11 publications

Fully Convolutional Boundary Regression for Retina OCT Segmentation

Fully Convolutional Boundary Regression for Retina OCT Segmentation

Deep learning based topology guaranteed surface and MME segmentation of multiple sclerosis subjects from retinal OCT

Optical Coherence Tomography in Multiple Sclerosis

Contact Info

Product

Resources

About