Transformer and convolutional based dual branch network for retinal vessel segmentation in OCTA images

Liu, Xiaoming; Zhang, Di; Yao, Junping

doi:10.1016/j.bspc.2023.104604

Cited by 37 publications

(4 citation statements)

References 25 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…DS-TransUNet [ 62 ] adopts the Swin Transformer block [ 58 ] to both the encoder and the decoder and achieve competitive performance. Liu et al [ 63 ] proposed a network which consists of a transformer-based branch and a convolution-based branch, and the information is exchanged between the inner layers. However, all the above-mentioned medical segmentation methods fails to take full advantage of the spatial detail information from the transformer-based network since the medical training images are insufficient, which greatly increases the difficulty of transformer network training.…”

Section: Related Workmentioning

confidence: 99%

Self-supervised pre-training for joint optic disc and cup segmentation via attention-aware network

Zhou,

Zheng,

Zhou

et al. 2024

BMC Ophthalmol

View full text Add to dashboard Cite

Image segmentation is a fundamental task in deep learning, which is able to analyse the essence of the images for further development. However, for the supervised learning segmentation method, collecting pixel-level labels is very time-consuming and labour-intensive. In the medical image processing area for optic disc and cup segmentation, we consider there are two challenging problems that remain unsolved. One is how to design an efficient network to capture the global field of the medical image and execute fast in real applications. The other is how to train the deep segmentation network using a few training data due to some medical privacy issues. In this paper, to conquer such issues, we first design a novel attention-aware segmentation model equipped with the multi-scale attention module in the pyramid structure-like encoder-decoder network, which can efficiently learn the global semantics and the long-range dependencies of the input images. Furthermore, we also inject the prior knowledge that the optic cup lies inside the optic disc by a novel loss function. Then, we propose a self-supervised contrastive learning method for optic disc and cup segmentation. The unsupervised feature representation is learned by matching an encoded query to a dictionary of encoded keys using a contrastive technique. Finetuning the pre-trained model using the proposed loss function can help achieve good performance for the task. To validate the effectiveness of the proposed method, extensive systemic evaluations on different public challenging optic disc and cup benchmarks, including DRISHTI-GS and REFUGE datasets demonstrate the superiority of the proposed method, which can achieve new state-of-the-art performance approaching 0.9801 and 0.9087 F1 score respectively while gaining 0.9657 $$DC_{disc}$$ D C disc and 0.8976 $$DC_{cup}$$ D C cup . The code will be made publicly available.

show abstract

Section: Related Workmentioning

confidence: 99%

Self-supervised pre-training for joint optic disc and cup segmentation via attention-aware network

Zhou,

Zheng,

Zhou

et al. 2024

BMC Ophthalmol

View full text Add to dashboard Cite

show abstract

“…He et al [8] proposed an evolvable adversarial framework that has fewer missegmented regions and more accurate boundaries. Liu et al [9] proposed the OCTA retinal vessel segmentation method (ARP-Net) based on the adaptive gated axial transformer (AGAT), Residual and point repair modules guide the network to focus on low vessel edge visibility.…”

Section: Retinal Vessel Segmentationmentioning

confidence: 99%

Self-Paced Dual-Axis Attention Fusion Network for Retinal Vessel Segmentation

et al. 2023

View full text Add to dashboard Cite

The segmentation of retinal vessels plays an essential role in the early recognition of ophthalmic diseases in clinics. Increasingly, approaches based on deep learning have been pushing vessel segmentation performance, yet it is still a challenging problem due to the complex structure of retinal vessels and the lack of precisely labeled samples. In this paper, we propose a self-paced dual-axis attention fusion network (SPDAA-Net). Firstly, a self-paced learning mechanism using a query-by-committee algorithm is designed to guide the model to learn from easy to hard, which makes model training more intelligent. Secondly, during fusing of multi-scale features, a dual-axis attention mechanism composed of height and width attention is developed to perceive the object, which brings in long-range dependencies while reducing computation complexity. Furthermore, CutMix data augmentation is applied to increase the generalization of the model, enhance the recognition ability of global and local features, and ultimately boost accuracy. We implement comprehensive experiments validating that our SPDAA-Net obtains remarkable performance on both the public DRIVE and CHASE-DB1 datasets.

show abstract

“…Simultaneously, deep learning approaches have evolved in both the clinical and pre-clinical non-lung tissue segmentation space. This includes use of 3D convolutional models for segmentation of skeletal muscle in murine hind-limbs [29] , blood vessels in human liver [30] , and structures of human eyes, where custom deep learning models have been developed to identify extraocular muscles and optic nerves [31] , retinal vessels [32] , and even arteries related to intracranial aneurysms [33] . Such work demonstrates the widespread success of deep learning in accelerating the work of the medical imaging community.…”

Section: Introductionmentioning

confidence: 99%

Applying deep learning to segmentation of murine lung tumors in pre-clinical micro-computed tomography

Montgomery,

Duan,

Manzuk

et al. 2024

Translational Oncology

View full text Add to dashboard Cite

Transformer and convolutional based dual branch network for retinal vessel segmentation in OCTA images

Cited by 37 publications

References 25 publications

Self-supervised pre-training for joint optic disc and cup segmentation via attention-aware network

Self-supervised pre-training for joint optic disc and cup segmentation via attention-aware network

Self-Paced Dual-Axis Attention Fusion Network for Retinal Vessel Segmentation

Applying deep learning to segmentation of murine lung tumors in pre-clinical micro-computed tomography

Contact Info

Product

Resources

About