CPFNet: Context Pyramid Fusion Network for Medical Image Segmentation

TLDR

Accurate automatic segmentation of medical images is essential for clinical diagnosis, yet single‑stage U‑shaped CNNs struggle with limited context extraction, class imbalance, and blurred boundaries. In this paper, we propose a novel Context Pyramid Fusion Network (CPFNet) that fuses global and multi‑scale context information. CPFNet builds on the U‑shaped backbone by inserting multiple global pyramid guidance modules between encoder and decoder to supply multi‑level global context, and a scale‑aware pyramid fusion module that dynamically merges multi‑scale high‑level features, progressively enriching context. Experiments on four challenging segmentation tasks—skin lesion, retinal linear lesion, thoracic organs at risk, and retinal edema—show that CPFNet is highly competitive with state‑of‑the‑art methods.

Abstract

Accurate and automatic segmentation of medical images is a crucial step for clinical diagnosis and analysis. The convolutional neural network (CNN) approaches based on the U-shape structure have achieved remarkable performances in many different medical image segmentation tasks. However, the context information extraction capability of single stage is insufficient in this structure, due to the problems such as imbalanced class and blurred boundary. In this paper, we propose a novel Context Pyramid Fusion Network (named CPFNet) by combining two pyramidal modules to fuse global/multi-scale context information. Based on the U-shape structure, we first design multiple global pyramid guidance (GPG) modules between the encoder and the decoder, aiming at providing different levels of global context information for the decoder by reconstructing skip-connection. We further design a scale-aware pyramid fusion (SAPF) module to dynamically fuse multi-scale context information in high-level features. These two pyramidal modules can exploit and fuse rich context information progressively. Experimental results show that our proposed method is very competitive with other state-of-the-art methods on four different challenging tasks, including skin lesion segmentation, retinal linear lesion segmentation, multi-class segmentation of thoracic organs at risk and multi-class segmentation of retinal edema lesions.