Deep-learning based multiclass retinal fluid segmentation and detection in optical coherence tomography images using a fully convolutional neural network

Lu, Donghuan; Heisler, Morgan; Lee, Sieun; Ding, Gavin Weiguang; Navajas, Eduardo V.; Sarunic, Marinko V.; Beg, Mirza Faisal

doi:10.1016/j.media.2019.02.011

Cited by 120 publications

(98 citation statements)

References 40 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…This we see is also the case in the analysis of three fluid labels in the RETOUCH challenge where, in the best performing instances, the approach is to first segment the data, second train a CNN with image data and segmentation as input, and third refine the final result using an additional classifier. 13,29 We see a benefit of having the segmentation element using non-trained data and all of the fluid segmentation within a single CNN, as is reported here. But consensus exists that encoding spatial information about the retinal tissue as an additional channel to the input image data is shown to improve the overall performance of the segmentation algorithm.…”

Section: Discussionsupporting

confidence: 54%

Automated Deep Learning-based Multi-class Fluid Segmentation in Swept-Source Optical Coherence Tomography Images

Oakley¹,

Sodhi

Russakoff³

et al. 2020

Preprint

View full text Add to dashboard Cite

PurposeTo evaluate the performance of a deep learning-based, fully automated, multi-class, macular fluid segmentation algorithm relative to expert annotations in a heterogeneous population of confirmed wet age-related macular degeneration (wAMD) subjects.MethodsTwenty-two swept-source optical coherence tomography (SS-OCT) volumes of the macula from 22 from different individuals with wAMD were manually annotated by two expert graders. These results were compared using cross-validation (CV) to automated segmentations using a deep learning-based algorithm encoding spatial information about retinal tissue as an additional input to the network. The algorithm detects and delineates fluid regions in the OCT data, differentiating between intra- and sub-retinal fluid (IRF, SRF), as well as fluid resulting from in serous pigment epithelial detachments (PED). Standard metrics for fluid detection and quantification were used to evaluate performance.ResultsThe per slice receiver operating characteristic (ROC) area under the curves (AUCs) for each of these fluid types were 0.90, 0.94 and 0.94 for IRF, SRF and PED, respectively. Per volume results were 0.94 and 0.88 for IRF and PED (SRF being present in all cases). The correlation of fluid volume between the expert graders and the algorithm were 0.99 for IRF, 0.99 for SRF and 0.82 for PED.ConclusionsAutomated, deep learning-based segmentation is able to accurately detect and quantify different macular fluid types in SS-OCT data on par with expert graders.

show abstract

Section: Discussionsupporting

confidence: 54%

Automated Deep Learning-based Multi-class Fluid Segmentation in Swept-Source Optical Coherence Tomography Images

Oakley¹,

Sodhi

Russakoff³

et al. 2020

Preprint

View full text Add to dashboard Cite

show abstract

“…Without standardization, images of different sizes, contrast levels, and textures that are not generalizable to a single AI algorithm are obtained. 43,44 Raster pattern dimensions are not consistent between devices, ranging from 128 × 256 to 256 × 768. 40 Different acquisition times and signal-to-noise ratios among devices result in variable image quality.…”

Section: Lack Of a Standardized Acquisition Image Registration And mentioning

confidence: 97%

“…de Sisternes et al 45 created 4 models, each trained using voxel features extracted at 4 different resolutions that correspond to the resolutions of each OCT imaging device. Venhuizen et al 44 combined predictions generated from 3 CNNs at different image scales across entire OCT volumes to segment intraretinal fluid. Lu et al 36 produced individual CNNs for each of the 3 OCT devices separately.…”

Section: Lack Of a Standardized Acquisition Image Registration And mentioning

confidence: 99%

Methodological Challenges of Deep Learning in Optical Coherence Tomography for Retinal Diseases: A Review

Yanagihara

Lee

Ting

et al. 2020

Trans. Vis. Sci. Tech.

View full text Add to dashboard Cite

Artificial intelligence (AI)-based automated classification and segmentation of optical coherence tomography (OCT) features have become increasingly popular. However, its 3-dimensional volumetric nature has made developing an algorithm that generalizes across all patient populations and OCT devices challenging. Several recent studies have reported high diagnostic performances of AI models; however, significant methodological challenges still exist in applying these models in real-world clinical practice. Lack of large-image datasets from multiple OCT devices, nonstandardized imaging or postprocessing protocols between devices, limited graphics processing unit capabilities for exploiting 3-dimensional features, and inconsistency in the reporting metrics are major hurdles in enabling AI for OCT analyses. We discuss these issues and present possible solutions.

show abstract

“…In more recent times, deep learning techniques have also been applied, in works like the ones proposed by Lee et al [19], Venhuizen et al [20], Roy et al [21], Lu et al [22], and Chen et al [23], which aimed too for a precise segmentation and most of them based on the U-Net architecture of Ronnenberger et al [24], an encoder-decoder architecture with skip connections to preserve relevant features from the encoder in the decoder.…”

Section: Introductionmentioning

confidence: 99%

Intraretinal Fluid Pattern Characterization in Optical Coherence Tomography Images

Moura

Vidal

Novo

et al. 2020

Sensors

View full text Add to dashboard Cite

Optical Coherence Tomography (OCT) has become a relevant image modality in the ophthalmological clinical practice, as it offers a detailed representation of the eye fundus. This medical imaging modality is currently one of the main means of identification and characterization of intraretinal cystoid regions, a crucial task in the diagnosis of exudative macular disease or macular edema, among the main causes of blindness in developed countries. This work presents an exhaustive analysis of intensity and texture-based descriptors for its identification and classification, using a complete set of 510 texture features, three state-of-the-art feature selection strategies, and seven representative classifier strategies. The methodology validation and the analysis were performed using an image dataset of 83 OCT scans. From these images, 1609 samples were extracted from both cystoid and non-cystoid regions. The different tested configurations provided satisfactory results, reaching a mean cross-validation test accuracy of 92.69%. The most promising feature categories identified for the issue were the Gabor filters, the Histogram of Oriented Gradients (HOG), the Gray-Level Run-Length matrix (GLRL), and the Laws’ texture filters (LAWS), being consistently and considerably selected along all feature selector algorithms in the top positions of different relevance rankings.

show abstract

Deep-learning based multiclass retinal fluid segmentation and detection in optical coherence tomography images using a fully convolutional neural network

Cited by 120 publications

References 40 publications

Automated Deep Learning-based Multi-class Fluid Segmentation in Swept-Source Optical Coherence Tomography Images

Automated Deep Learning-based Multi-class Fluid Segmentation in Swept-Source Optical Coherence Tomography Images

Methodological Challenges of Deep Learning in Optical Coherence Tomography for Retinal Diseases: A Review

Intraretinal Fluid Pattern Characterization in Optical Coherence Tomography Images

Contact Info

Product

Resources

About