# LMBF-Net: A Lightweight Multipath Bidirectional Focal Attention Network for Multifeatures Segmentation

arXiv: https://arxiv.org/abs/2407.02871 · HTML: https://mlsanity.com/paper/2407.02871/

## Key facts

- Cited by 7 papers in the map (data through 14 Oct 2026).
- Builds on 16 of its 42 references that are in the map.
- First posted on arXiv 3 Jul 2024.

## Builds on (most cited first, 16 of 16)

- [Swin Transformer: Hierarchical Vision Transformer using Shifted Windows](https://mlsanity.com/paper/2103.14030/) (2021)
- [Fully Convolutional Networks for Semantic Segmentation](https://mlsanity.com/paper/1411.4038/) (2014)
- [TransUNet: Transformers Make Strong Encoders for Medical Image Segmentation](https://mlsanity.com/paper/2102.04306/) (2021)
- [UNet++: A Nested U-Net Architecture for Medical Image Segmentation](https://mlsanity.com/paper/1807.10165/) (2018)
- [Attention U-Net: Learning Where to Look for the Pancreas](https://mlsanity.com/paper/1804.03999/) (2018)
- [CE-Net: Context Encoder Network for 2D Medical Image Segmentation](https://mlsanity.com/paper/1903.02740/) (2019)
- [Focal Modulation Networks](https://mlsanity.com/paper/2203.11926/) (2022)
- [DUNet: A deformable network for retinal vessel segmentation](https://mlsanity.com/paper/1811.01206/) (2018)
- [BiO-Net: Learning Recurrent Bi-directional Connections for Encoder-Decoder Architecture](https://mlsanity.com/paper/2007.00243/) (2020)
- [Retinal Vessel Segmentation via a Multi-resolution Contextual Network and Adversarial Learning](https://mlsanity.com/paper/2304.12856/) (2023)
- [MKIS-Net: A Light-Weight Multi-Kernel Network for Medical Image Segmentation](https://mlsanity.com/paper/2210.08168/) (2022)
- [Feature Enhancer Segmentation Network (FES-Net) for Vessel Segmentation](https://mlsanity.com/paper/2309.03535/) (2023)
- [ESDMR-Net: A Lightweight Network With Expand-Squeeze and Dual Multiscale Residual Connections for Medical Image Segmentation](https://mlsanity.com/paper/2312.10585/) (2023)
- [BTS-DSN: Deeply Supervised Neural Network with Short Connections for Retinal Vessel Segmentation](https://mlsanity.com/paper/1803.03963/) (2018)
- [M2U-Net: Effective and Efficient Retinal Vessel Segmentation for Resource-Constrained Environments](https://mlsanity.com/paper/1811.07738/) (2018)
- [LMBiS-Net: A Lightweight Multipath Bidirectional Skip Connection based CNN for Retinal Blood Vessel Segmentation](https://mlsanity.com/paper/2309.04968/) (2023)

## Built on by (most cited first, 7 of 7)

- [TBConvL-Net: A Hybrid Deep Learning Architecture for Robust Medical Image Segmentation](https://mlsanity.com/paper/2409.03367/) (2024)
- [Region Guided Attention Network for Retinal Vessel Segmentation](https://mlsanity.com/paper/2407.18970/) (2024)
- [EUIS-Net: A Convolutional Neural Network for Efficient Ultrasound Image Segmentation](https://mlsanity.com/paper/2408.12323/) (2024)
- [LSSF-Net: Lightweight Segmentation with Self-Awareness, Spatial Attention, and Focal Modulation](https://mlsanity.com/paper/2409.01572/) (2024)
- [LFRA-Net: A Lightweight Focal and Region-Aware Attention Network for Retinal Vessel Segmentatio](https://mlsanity.com/paper/2509.11811/) (2025)
- [AD-Net: Attention-based dilated convolutional residual network with guided decoder for robust skin lesion segmentation](https://mlsanity.com/paper/2409.05420/) (2024)
- [Focal Modulation and Bidirectional Feature Fusion Network for Medical Image Segmentation](https://mlsanity.com/paper/2510.20933/) (2025)

## Abstract (arXiv)

Retinal diseases can cause irreversible vision loss in both eyes if not diagnosed and treated early. Since retinal diseases are so complicated, retinal imaging is likely to show two or more abnormalities. Current deep learning techniques for segmenting retinal images with many labels and attributes have poor detection accuracy and generalisability. This paper presents a multipath convolutional neural network for multifeature segmentation. The proposed network is lightweight and spatially sensitive to information. A patch-based implementation is used to extract local image features, and focal modulation attention blocks are incorporated between the encoder and the decoder for improved segmentation. Filter optimisation is used to prevent filter overlaps and speed up model convergence. A combination of convolution operations and group convolution operations is used to reduce computational costs. This is the first robust and generalisable network capable of segmenting multiple features of fundus images (including retinal vessels, microaneurysms, optic discs, haemorrhages, hard exudates, and soft exudates). The results of our experimental evaluation on more than ten publicly available datasets with multiple features show that the proposed network outperforms recent networks despite having a small number of learnable parameters.