Optical coherence tomography (OCT) offers significant advantages of noncontact operation, high resolution, and real-time imaging, making it particularly suitable for acquiring human retinal images and playing a crucial role in diagnosing and monitoring retinal diseases such as diabetic macular edema (DME). OCT is a key noninvasive imaging modality for retinal diseases such as DME, offering high-resolution visualization of retinal layers and fluid accumulations. However, retinal fluid segmentation faces several challenges including variations in fluid size, location, and shape, as well as complex irregular boundaries. To address these issues, we propose TL-TransUNet, a novel lightweight segmentation model based on TransUNet. The model incorporates a hybrid self-attention mechanism that effectively combines linear self-attention with residual filtered multilayer perceptron modules, reducing both parameter size and computational complexity while capturing global relationships and local details to improve segmentation performance for small lesions. Furthermore, the decoder employs wavelet convolution that utilizes wavelet transform to extract multi-scale features from low- to high-frequency components, enhancing the model’s multi-scale learning capability. Experimental results on a public DME dataset demonstrate that our proposed method outperforms several mainstream segmentation approaches, demonstrating superior performance.
WuM, ChenQ, HeX, et al.Automatic subretinal fluid segmentation of retinal SD-OCT images with neurosensory retinal detachment guided by enface fundus imaging. IEEE Trans Biomed Eng, 2018; 65(1):87–95; doi: 10.1109/TBME.2017.2695461
3.
XieH, XuW, WangYX, et al.Deep learning network with differentiable dynamic programming for retina OCT surface segmentation. Biomed Opt Express, 2023; 14(7):3190–3202; doi: 10.1364/BOE.492670
4.
DufourPA, CeklicL, AbdillahiH, et al.Graph-based multi-surface segmentation of OCT data using trained hard and soft constraints. IEEE Trans Med Imaging, 2013; 32(3):531–543; doi: 10.1109/TMI.2012.2225152
5.
MontuoroA, WaldsteinSM, GerendasBS, et al.Joint retinal layer and fluid segmentation in OCT scans of eyes with severe macular edema using unsupervised representation and auto-context. Biomed Opt Express, 2017; 8(3):1874–1888; doi: 10.1364/BOE.8.001874
6.
DodoBI, LiY, EltayefK, et al.Automatic annotation of retinal layers in optical coherence tomography images. J Med Syst, 2019; 43(12):336; doi: 10.1007/s10916-019-1452-9
7.
LongJ, ShelhamerE, DarrellT. Fully convolutional networks for semantic segmentation. In: 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR). IEEE: Boston, MA; 2015; pp. 3431–3440; doi: 10.1109/CVPR.2015.7298965
8.
RonnebergerO, FischerP, BroxT, et al.U-Net: Convolutional networks for biomedical image segmentation. In: Medical Image Computing and Computer-Assisted Intervention – MICCAI 2015. Lecture Notes in Computer Science. (NavabN, HorneggerJ, WellsWM eds.) Springer International Publishing: Cham; 2015; pp. 234–241; doi: 10.1007/978-3-319-24574-4_28
9.
LuD, HeislerM, LeeS, et al.Deep-learning based multiclass retinal fluid segmentation and detection in optical coherence tomography images using a fully convolutional neural network. Med Image Anal, 2019; 54:100–110; doi: 10.1016/j.media.2019.02.011
10.
SinghP, KumarS, DeitchI, et al.A deep learning based automatic drusen segmentation model for age related macular degeneration in ultra wide-field imaging. Invest Ophthalmol Vis Sci, 2024; 65(7):2416–2416.
11.
HuJ, ChenY, YiZ. Automated segmentation of macular edema in OCT using deep neural networks. Med Image Anal, 2019; 55:216–227; doi: 10.1016/j.media.2019.05.002
12.
FengS, ZhaoH, ShiF, et al.CPFNet: Context pyramid fusion network for medical image segmentation. IEEE Trans Med Imaging, 2020; 39(10):3008–3018; doi: 10.1109/TMI.2020.2983721
13.
LiuX, WangS, ZhangY, et al.Automatic fluid segmentation in retinal optical coherence tomography images using attention based deep learning. Neurocomputing (Amst), 2021; 452:576–591; doi: 10.1016/j.neucom.2020.07.143
14.
ChenT, ZhangD, ChenD, et al.Neovascularization segmentation via a multilateral interaction-enhanced graph convolutional network. IEEE Trans Pattern Anal Mach Intell, 2025; 47(12):11107–11123; doi: 10.1109/TPAMI.2025.3600335
15.
VaswaniA, ShazeerN, ParmarN, et al.Attention is all you need. In: Proceedings of the 31st International Conference on Neural Information Processing Systems. NIPS’17 Curran Associates Inc.: Red Hook, NY; 2017; pp. 6000–6010.
16.
DosovitskiyA, BeyerL, KolesnikovA, et al.An image is worth 16x16 words: Transformers for image recognition at scale. ArXiv, 2020; doi: 10.48550/ARXIV.2010.11929
17.
ChenJ, MeiJ, LiX, et al.TransUNet: Rethinking the U-Net architecture design for medical image segmentation through the lens of transformers. Med Image Anal, 2024; 97:103280; doi: 10.1016/j.media.2024.103280
18.
CaoH, WangY, ChenJ, et al.Swin-Unet: Unet-like pure transformer for medical image segmentation. In: Computer Vision – ECCV 2022 Workshops. Lecture Notes in Computer Science. (KarlinskyL, MichaeliNishino T,Keds.) Springer Nature Switzerland: Cham; 2023; pp. 205–218; doi: 10.1007/978-3-031-25066-8_9
19.
LiuZ, LinY, CaoY, et al.Swin transformer: Hierarchical vision transformer using shifted windows. In: 2021 IEEE/CVF International Conference on Computer Vision (ICCV). IEEE: Montreal, QC; 2021; pp. 9992–10002; doi: 10.1109/ICCV48922.2021.00986
20.
HuangX, DengZ, LiD, et al.MISSFormer: An effective transformer for 2D medical image segmentation. IEEE Trans Med Imaging, 2023; 42(5):1484–1494; doi: 10.1109/TMI.2022.3230943
21.
KhanR, AlzabenN, DaradkehYI, et al.Pyramidal attention with progressive multi-stage iterative feature refinement for salient object segmentation. Image Vis Comput, 2025; 162:105670; doi: 10.1016/j.imavis.2025.105670
22.
WangJ, ZhuW, WangP, et al.Selective structured state-spaces for long-form video understanding. In: 2023 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR). IEEE: Vancouver, BC; 2023; pp. 6387–6397; doi: 10.1109/CVPR52729.2023.00618
GuA, DaoT. Mamba: Linear-time sequence modeling with selective state spaces. ArXiv, 2023; doi: 10.48550/ARXIV.2312.00752
25.
XingZ, YeT, YangY, et al.SegMamba: Long-range sequential modeling mamba for 3D medical image segmentation. In: Medical Image Computing and Computer Assisted Intervention – MICCAI 2024. Lecture Notes in Computer Science. (LinguraruMG, DouQ, FeragenA eds.) Springer Nature Switzerland: Cham; 2024; pp. 578–588; doi: 10.1007/978-3-031-72111-3_54
26.
WuR, LiuY, LiangP, et al.H-vmunet: High-order vision mamba UNet for medical image segmentation. Neurocomputing (Amst), 2025; 624:129447; doi: 10.1016/j.neucom.2025.129447
27.
TolstikhinIO, HoulsbyN, KolesnikovA, et al.MLP-mixer: An all-MLP architecture for vision. In: Advances in Neural Information Processing Systems. (RanzatoM, BeygelzimerA, DauphinY eds.) Curran Associates, Inc.; 2021; pp. 24261–24272.
28.
MehtaS, RastegariM. Separable self-attention for mobile vision transformers. Trans Mach Learn Res, 2023; 2023.
29.
ZhouK, YuH, ZhaoWX, et al.Filter-enhanced MLP is all you need for sequential recommendation. In: Proceedings of the ACM Web Conference 2022. ACM: Lyon, France; 2022; pp. 2388–2399; doi: 10.1145/3485447.3512111
30.
HeK, ZhangX, RenS, et al.Deep residual learning for image recognition. In: 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR). IEEE; 2016; pp. 770–778; doi: 10.1109/CVPR.2016.90
31.
FinderSE, AmoyalR, TreisterE, et al.Wavelet convolutions for large receptive fields. In: Computer Vision – ECCV 2024: 18th European Conference, Milan, Italy, September 29–October 4, 2024, Proceedings, Part LIV. Springer-Verlag: Berlin, Heidelberg; 2024; pp. 363–380; doi: 10.1007/978-3-031-72949-2_21
32.
SrinivasanPP, KimLA, MettuPS, et al.Fully automated detection of diabetic macular edema and dry age-related macular degeneration from optical coherence tomography images. Biomed Opt Express, 2014; 5(10):3568–3577; doi: 10.1364/BOE.5.003568
