Automatic segmentation of retinal layers in OCT images with intermediate age-related macular degeneration using U-Net and DexiNed

Sousa, Jefferson Alves de; Paiva, Anselmo Cardoso de; Silva, Aristófanes; Almeida, João Dallyson Sousa de; Bráz, Geraldo; Diniz, João Otávio Bandeira; Figueredo, Weslley Kelson Ribeiro; Gattass, Marcelo

doi:10.1371/journal.pone.0251591

Cited by 27 publications

(14 citation statements)

References 21 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…4, respectively. In terms of baseline performance, Table II shows that Proposed w/o L 3 , w/o TPS is superior to the 2D surface prediction methods ReLayNet [11] and BFC-DN [32], and to the multi-step edgedetection method DexiNed [13]. For DexiNed [13] in particular, there are cases where the segmentation fails to provide any positions at certain A-scans (Fig.…”

Section: A Comparison With Baseline and Ablation Studiesmentioning

confidence: 99%

“…A deficiency of this algorithm is that it is not guaranteed to predict a single unique BM position in an A-scan. Sousa et al [13] uses a U-Net to create an initial segmentation followed by a CNN based edge detection network to further refine the results, while predicting one single location per A-scan.…”

Section: A Related Workmentioning

confidence: 99%

“…We compared the performance of our model with adaptions of state-ofthe-art retinal OCT layer segmentation methods, DexiNed [13], ReLayNet [11] and Bayesian Fully Connected Dense Network (BFC-DN) [32]. DexiNed is an edge detection network that produces pixel-wise edge maps.…”

Section: Experiments 1) Comparison With Baseline and Ablation Studiesmentioning

confidence: 99%

“…The segmentation of the retinal layers in OCT scans is a crucial step in order to monitor and quantify the progression of a disease. However, manual layer annotation or correction is very time-consuming and subjective, which has motivated the development of automated accurate and objective methods [10]-- [13].…”

Section: Introductionmentioning

confidence: 99%

See 3 more Smart Citations

Segmentation of Bruch's Membrane in retinal OCT with AMD using anatomical priors and uncertainty quantification

Fazekas¹,

Lachinov²,

Aresta³

et al. 2022

Preprint

View full text Add to dashboard Cite

Bruch's membrane (BM) segmentation on optical coherence tomography (OCT) is a pivotal step for the diagnosis and follow-up of age-related macular degeneration (AMD), one of the leading causes of blindness in the developed world. Automated BM segmentation methods exist, but they usually do not account for the anatomical coherence of the results, neither provide feedback on the confidence of the prediction. These factors limit the applicability of these systems in real-world scenarios. With this in mind, we propose an end-to-end deep learning method for automated BM segmentation in AMD patients. An Attention U-Net is trained to output a probability density function of the BM position, while taking into account the natural curvature of the surface. Besides the surface position, the method also estimates an A-scan wise uncertainty measure of the segmentation output. Subsequently, the A-scans with high uncertainty are interpolated using thin plate splines (TPS). We tested our method with ablation studies on an internal dataset with 138 patients covering all three AMD stages, and achieved a mean absolute localization error of 4.10 µm. In addition, the proposed segmentation method was compared against the state-of-the-art methods and showed a superior performance on an external publicly available dataset from a different patient cohort and OCT device, demonstrating strong generalization ability.

show abstract

Section: A Comparison With Baseline and Ablation Studiesmentioning

confidence: 99%

Section: A Related Workmentioning

confidence: 99%

Section: Experiments 1) Comparison With Baseline and Ablation Studiesmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Segmentation of Bruch's Membrane in retinal OCT with AMD using anatomical priors and uncertainty quantification

Fazekas¹,

Lachinov²,

Aresta³

et al. 2022

Preprint

View full text Add to dashboard Cite

show abstract

“…One of the first DL approaches [13] used a U-Net [12] to classify each pixel of the input image as one of 9 retinal layers, background or possibly fluid-filled pockets, which may lead to segmentation of layers on anatomically implausible locations. This can be circumvented with an edge detection network that predicts only a single location for a layer in an A-scan [16]. However, none of these two approaches accounted for hard anatomical constraints.…”

Section: Introductionmentioning

confidence: 99%

SD-LayerNet: Semi-supervised retinal layer segmentation in OCT using disentangled representation with anatomical priors

Fazekas,

Aresta,

Lachinov

et al. 2022

Preprint

View full text Add to dashboard Cite

Optical coherence tomography (OCT) is a non-invasive 3D modality widely used in ophthalmology for imaging the retina. Achieving automated, anatomically coherent retinal layer segmentation on OCT is important for the detection and monitoring of different retinal diseases, like Age-related Macular Disease (AMD) or Diabetic Retinopathy. However, the majority of state-of-the-art layer segmentation methods are based on purely supervised deep-learning, requiring a large amount of pixel-level annotated data that is expensive and hard to obtain. With this in mind, we introduce a semi-supervised paradigm into the retinal layer segmentation task that makes use of the information present in large-scale unlabeled datasets as well as anatomical priors. In particular, a novel fully differentiable approach is used for converting surface position regression into a pixel-wise structured segmentation, allowing to use both 1D surface and 2D layer representations in a coupled fashion to train the model. In particular, these 2D segmentations are used as anatomical factors that, together with learned style factors, compose disentangled representations used for reconstructing the input image. In parallel, we propose a set of anatomical priors to improve network training when a limited amount of labeled data is available. We demonstrate on the real-world dataset of scans with intermediate and wet-AMD that our method outperforms state-of-the-art when using our full training set, but more importantly largely exceeds state-of-the-art when it is trained with a fraction of the labeled data.

show abstract

Application program interface for automatic segmentation of retinal layers and fluids in Optical Coherence Tomography ‐ Neovascular Age related Macular degeneration retinal images using deep learning models

Jeya Prabha,

Sameera Fathimal,

Meghana

et al. 2023

Int J Imaging Syst Tech

View full text Add to dashboard Cite

Optical coherence tomography is a non‐invasive imaging technique that provides micrometer‐resolution images of retinal structures. These images can assist in identifying changes under the retina's surface, such as edema. This study proposes a novel deep learning model AR U‐Net++ for segmenting retinal layers and fluids. The four retinal layers ILM (Internal Limiting Membrane), IPL (Inner Plexiform Layer), RPE (Retinal Pigment Epithelium), BM (Bruch Membrane), and IRF (Intra Retinal Fluid), SRF (Sub Retinal Fluid), and PED (Pigment Epithelial Detachment) are segmented using AR U‐Net++. The proposed architecture AR U‐Net++ achieves better accuracy (99.67%), mean IoU (0.84), and dice coefficient (0.94) than the existing models of U‐Net, AR U‐Net, and AR W‐Net. The novelty of the suggested model AR U‐Net++ is to identify the exact location and depth of the retinal fluid in between the retinal layers and generating reports that aids the clinicians in the diagnosis of Age related Macular Degeneration.

show abstract

Automatic segmentation of retinal layers in OCT images with intermediate age-related macular degeneration using U-Net and DexiNed

Cited by 27 publications

References 21 publications

Segmentation of Bruch's Membrane in retinal OCT with AMD using anatomical priors and uncertainty quantification

Segmentation of Bruch's Membrane in retinal OCT with AMD using anatomical priors and uncertainty quantification

SD-LayerNet: Semi-supervised retinal layer segmentation in OCT using disentangled representation with anatomical priors

Application program interface for automatic segmentation of retinal layers and fluids in Optical Coherence Tomography ‐ Neovascular Age related Macular degeneration retinal images using deep learning models

Contact Info

Product

Resources

About