EFCNet: Every Feature Counts for Small Medical Object Segmentation

TL;DR

EFCNet is a novel segmentation model specifically designed for small medical objects, addressing information loss issues in CNNs and Transformers through innovative modules, and demonstrating superior performance on benchmark datasets.

Contribution

The paper introduces EFCNet, featuring the CSAA and MPS modules, which effectively reduce information loss during encoding and decoding in small object segmentation tasks.

Findings

EFCNet outperforms previous methods on benchmark datasets.

The CSAA module improves feature integration across encoder stages.

The MPS mechanism enhances global perception by focusing on low-resolution features.

Abstract

This paper explores the segmentation of very small medical objects with significant clinical value. While Convolutional Neural Networks (CNNs), particularly UNet-like models, and recent Transformers have shown substantial progress in image segmentation, our empirical findings reveal their poor performance in segmenting the small medical objects and lesions concerned in this paper. This limitation may be attributed to information loss during their encoding and decoding process. In response to this challenge, we propose a novel model named EFCNet for small object segmentation in medical images. Our model incorporates two modules: the Cross-Stage Axial Attention Module (CSAA) and the Multi-Precision Supervision Module (MPS). These modules address information loss during encoding and decoding procedures, respectively. Specifically, CSAA integrates features from all stages of the encoder to adaptively learn suitable information needed in different decoding stages, thereby reducing information loss in the encoder. On the other hand, MPS introduces a novel multi-precision supervision mechanism to the decoder. This mechanism prioritizes attention to low-resolution features in the initial stages of the decoder, mitigating information loss caused by subsequent convolution and sampling processes and enhancing the model's global perception. We evaluate our model on two benchmark medical image datasets. The results demonstrate that EFCNet significantly outperforms previous segmentation methods designed for both medical and normal images.