MM-UNet: A Mixed MLP Architecture for Improved Ophthalmic Image Segmentation

TL;DR

This paper introduces MM-UNet, a novel mixed MLP architecture designed for ophthalmic image segmentation, combining multi-scale feature interaction to outperform existing models while reducing computational costs.

Contribution

The paper proposes a new mixed MLP-based model, MM-UNet, with a multi-scale MLP module for improved feature interaction in ophthalmic image segmentation.

Findings

MM-UNet outperforms state-of-the-art segmentation networks on ophthalmic datasets.

The multi-scale MLP module effectively captures global and local features.

The model demonstrates efficiency with reduced computational overhead.

Abstract

Ophthalmic image segmentation serves as a critical foundation for ocular disease diagnosis. Although fully convolutional neural networks (CNNs) are commonly employed for segmentation, they are constrained by inductive biases and face challenges in establishing long-range dependencies. Transformer-based models address these limitations but introduce substantial computational overhead. Recently, a simple yet efficient Multilayer Perceptron (MLP) architecture was proposed for image classification, achieving competitive performance relative to advanced transformers. However, its effectiveness for ophthalmic image segmentation remains unexplored. In this paper, we introduce MM-UNet, an efficient Mixed MLP model tailored for ophthalmic image segmentation. Within MM-UNet, we propose a multi-scale MLP (MMLP) module that facilitates the interaction of features at various depths through a grouping strategy, enabling simultaneous capture of global and local information. We conducted extensive experiments on both a private anterior segment optical coherence tomography (AS-OCT) image dataset and a public fundus image dataset. The results demonstrated the superiority of our MM-UNet model in comparison to state-of-the-art deep segmentation networks.