Conquering Data Variations in Resolution: A Slice-Aware Multi-Branch Decoder Network

TL;DR

This paper introduces a slice-aware multi-branch decoder network that effectively handles variations in intra- and inter-slice resolutions, improving liver and tumor segmentation accuracy by emphasizing slice-specific features and coherence.

Contribution

The paper proposes a novel 2.5D slice-aware network with a multi-branch decoder and attention mechanism to address data resolution variations in medical image segmentation.

Findings

Achieved state-of-the-art results on the MICCAI 2017 LiTS dataset.

Demonstrated robustness and generalizability on the ISBI 2019 SegTHOR dataset.

Effectively models intra- and inter-slice information for improved segmentation.

Abstract

Fully convolutional neural networks have made promising progress in joint liver and liver tumor segmentation. Instead of following the debates over 2D versus 3D networks (for example, pursuing the balance between large-scale 2D pretraining and 3D context), in this paper, we novelly identify the wide variation in the ratio between intra- and inter-slice resolutions as a crucial obstacle to the performance. To tackle the mismatch between the intra- and inter-slice information, we propose a slice-aware 2.5D network that emphasizes extracting discriminative features utilizing not only in-plane semantics but also out-of-plane coherence for each separate slice. Specifically, we present a slice-wise multi-input multi-output architecture to instantiate such a design paradigm, which contains a Multi-Branch Decoder (MD) with a Slice-centric Attention Block (SAB) for learning slice-specific features and a Densely Connected Dice (DCD) loss to regularize the inter-slice predictions to be coherent and continuous. Based on the aforementioned innovations, we achieve state-of-the-art results on the MICCAI 2017 Liver Tumor Segmentation (LiTS) dataset. Besides, we also test our model on the ISBI 2019 Segmentation of THoracic Organs at Risk (SegTHOR) dataset, and the result proves the robustness and generalizability of the proposed method in other segmentation tasks.