Cascade Decoder: A Universal Decoding Method For Biomedical Image Segmentation

The Encoder-Decoder architecture is a main stream deep learning model for biomedical image segmentation. The encoder fully compresses the input and generates encoded features, and the decoder then produces dense predictions using encoded features. However, decoders are still under-explored in such architectures. In this paper, we comprehensively study the state-of-the-art Encoder-Decoder architectures, and propose a new universal decoder, called cascade decoder, to improve semantic segmentation accuracy. Our cascade decoder can be embedded into existing networks and trained altogether in an end-to-end fashion. The cascade decoder structure aims to conduct more effective decoding of hierarchically encoded features and is more compatible with common encoders than the known decoders. We replace the decoders of state-of-the-art models with our cascade decoder for several challenging biomedical image segmentation tasks, and the considerable improvements achieved demonstrate the efficacy of our new decoding method.

1. Introduction

Image segmentation is a fundamental problem in biomedical image analysis. Recently, deep learning has significantly improved image segmentation accuracy on many problems. Most state-of-the-art deep learning segmentation models are based on the Encoder-Decoder architecture. The “encoder” is a typical deep convolutional network to encode hierarchical information into feature maps, while the “decoder” aims to make effective dense predictions using encoded features. The essential spirit of the Encoder-Decoder architecture is to first interpret the images and then predict the segmentation of the images based on the interpretation.