LF-UNet – A novel anatomical-aware dual-branch cascaded deep neural network for segmentation of retinal layers and fluid from optical coherence tomography images

Ma, Da; Lu, Donghuan; Chen, Shuo; Heisler, Morgan; Dabiri, Setareh; Lee, Sieun; Lee, Hyun–Woo; Ding, Gavin Weiguang; Sarunic, Marinko V.; Beg, Mirza Faisal

doi:10.1016/j.compmedimag.2021.101988

Cited by 24 publications

(20 citation statements)

References 24 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Coarsely sampled OCT volumes can even miss certain lesion instances entirely 54 . Also, related work shows possible improvements in segmentation performance when adding 3d context, which we can not reproduce based on the dataset used in this work 55 .…”

Section: Further Limitationsmentioning

confidence: 78%

“…Furthermore, our data is obtained from devices of a single vendor only. Related work has shown strong dependencies of segmentation performance across image data from different vendors [49][50][51]55 . In future work, we will consider image data from different vendors to compare the cross-device generalizability capabilities of ViTs to CNN-based methods.…”

Section: Further Limitationsmentioning

confidence: 99%

See 1 more Smart Citation

A Vision Transformer Architecture for the Automated Segmentation of Retinal Fluids in Spectral Domain Optical Coherence Tomography Images

Philippi

Rothaus

Castelli

2022

Preprint

View full text Add to dashboard Cite

Neovascular age-related macular degeneration (nAMD) is one of the major causes of irreversible blindness and is characterized by accumulations of different fluids inside the retina. An early detection and activity monitoring of predominately three types of fluids, namely intra-retinal fluid (IRF), sub-retinal fluid (SRF), and pigment epithelium detachment (PED), is critical for a successful treatment. Spectral-domain optical coherence tomography (SD-OCT) revolutionized nAMD treatment by providing cross-sectional, high-resolution images of the retina. Automatic segmentation and quantification of IRF, SRF, and PED in SD-OCT images can be extremely useful for clinical decision-making. Despite the use of state-of-the-art convolutional neural network (CNN)-based methods, the task remains challenging due to relevant variations in the location, size, shape, and texture of the fluids. This work is the first to adopt a transformer-based method to automatically segment retinal fluid from SD-OCT images and qualitatively and quantitatively evaluate its performance against CNN-based methods. The method combines the efficient long-range feature extraction and aggregation capabilities of Vision Transformers (ViTs) with data-efficient training of CNNs. The proposed method was tested on a private dataset containing 3842 2-dimensional SD-OCT retina images, manually labeled by experts of the Franziskus-Eye-Hospital. While one of the competitors presents a better performance in terms of Dice score, the proposed method is significantly less computationally expensive. Thus, future research will focus on the proposed network's architecture to increase its segmentation performance while maintaining its computational efficiency.

show abstract

Section: Further Limitationsmentioning

confidence: 78%

Section: Further Limitationsmentioning

confidence: 99%

A Vision Transformer Architecture for the Automated Segmentation of Retinal Fluids in Spectral Domain Optical Coherence Tomography Images

Philippi

Rothaus

Castelli

2022

Preprint

View full text Add to dashboard Cite

show abstract

“…As can be seen from the first lines of the previous figure, in the case of the lesion area close to the edge of the retinal layer, the three models of Li et al., 16 Ma et al., 8 and Hassan et al 30 . have blurred segmentation results for edema regions compared with RLMENet.…”

Section: Resultsmentioning

confidence: 95%

“…As can be seen from the first lines of the previous figure, in the case of the lesion area close to the edge of the retinal layer, the three models of Li et al, 16 Ma et al, 8 and Hassan et al 30 have blurred segmentation results for edema regions compared with RLMENet. The contour of the edema region is not completely segmented, and there are many omissions.Due to the introduction of the DMA module in the RLMENet model, by sharing the features of each layer and expanding the receptive field, the problem of missing boundary details was effectively improved, and the RLMENet produced a segmented image visually like the clinician's manual segmentation results.…”

Section: Subjective Performance Analysismentioning

confidence: 94%

“…Retinal OCT image segmentation methods can be divided into two categories: image processing-based segmentation methods [3][4][5] and deep learning-based semantic segmentation methods. [6][7][8] Traditional image segmentation mainly includes segmentation methods based on image threshold, morphology, active contour, and graph theory. For example, Chiu et al 9 adopted a segmentation framework based on graph theory and dynamic programming and segmented eight retinal layer boundaries; then a random forest retinal OCT image layering algorithm based on principal component analysis was proposed, which used principal component analysis to resample the features collected by random forest.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Joint segmentation of retinal layers and macular edema in optical coherence tomography scans based on RLMENet

Liu

Xiao

et al. 2022

Medical Physics

View full text Add to dashboard Cite

Purpose The segmentation of retinal layers and fluid lesions on retinal optical coherence tomography (OCT) images is an important component of screening and diagnosing retinopathy in clinical ophthalmic treatment. We designed a novel network for accurate segmentation of the seven tissue layers of the retina and lesion areas of diabetic macular edema (DME), which can assist doctors to quantitatively analyze the disease. Methods In this article, we propose the Retinal Layer Macular Edema Network (RLMENet) model to achieve end‐to‐end joint segmentation of retinal layers and fluids. The network employs dense multi‐scale attention to enhance the extraction of retinal layer and fluid detail information and achieve efficient long‐range modeling, which improves the receptive field and obtains multi‐scale features. As the more complex decoder part is designed, which integrates more low‐level feature information on the decoder side, more features are extracted to gradually restore the resolution of the feature map and improve the segmentation accuracy. Results We used part of the OCT2017 dataset to train and verify the model to divide the data into a training set, validation set, and test set and set it to a 7:2:1 ratio. We evaluated our method on the ISIC2017 dataset. Experimental results showed that the RLMENet model designed in this work can accurately segment seven retinal tissue layers and DME lesions on the retinal OCT dataset. Finally, the MIoU value in the test set reached 86.55%. The model can be extended to other medical image segmentation datasets to achieve better segmentation performance. Conclusions The proposed method was superior to the existing segmentation methods, achieved a more refined segmentation effect, and provided an auxiliary analysis tool for clinical diagnosis and treatment.

show abstract

Boundary-Repairing Dual-Path Network for Retinal Layer Segmentation in OCT Image with Pigment Epithelial Detachment

Liu,

Li,

Zhang

et al. 2024

J Digit Imaging. Inform. med.

View full text Add to dashboard Cite

LF-UNet – A novel anatomical-aware dual-branch cascaded deep neural network for segmentation of retinal layers and fluid from optical coherence tomography images

Cited by 24 publications

References 24 publications

A Vision Transformer Architecture for the Automated Segmentation of Retinal Fluids in Spectral Domain Optical Coherence Tomography Images

A Vision Transformer Architecture for the Automated Segmentation of Retinal Fluids in Spectral Domain Optical Coherence Tomography Images

Joint segmentation of retinal layers and macular edema in optical coherence tomography scans based on RLMENet

Boundary-Repairing Dual-Path Network for Retinal Layer Segmentation in OCT Image with Pigment Epithelial Detachment

Contact Info

Product

Resources

About