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

arXiv: https://arxiv.org/abs/2203.03640 · HTML: https://mlsanity.com/paper/2203.03640/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 21 of its 42 references that are in the map.
- First posted on arXiv 7 Mar 2022.

## Builds on (most cited first, 21 of 21)

- [Deep Residual Learning for Image Recognition](https://mlsanity.com/paper/1512.03385/) (2015)
- [U-Net: Convolutional Networks for Biomedical Image Segmentation](https://mlsanity.com/paper/1505.04597/) (2015)
- [Fully Convolutional Networks for Semantic Segmentation](https://mlsanity.com/paper/1411.4038/) (2014)
- [Encoder-Decoder with Atrous Separable Convolution for Semantic Image Segmentation](https://mlsanity.com/paper/1802.02611/) (2018)
- [Xception: Deep Learning with Depthwise Separable Convolutions](https://mlsanity.com/paper/1610.02357/) (2016)
- [V-Net: Fully Convolutional Neural Networks for Volumetric Medical Image Segmentation](https://mlsanity.com/paper/1606.04797/) (2016)
- [Rethinking Atrous Convolution for Semantic Image Segmentation](https://mlsanity.com/paper/1706.05587/) (2017)
- [3D U-Net: Learning Dense Volumetric Segmentation from Sparse Annotation](https://mlsanity.com/paper/1606.06650/) (2016)
- [Attention U-Net: Learning Where to Look for the Pancreas](https://mlsanity.com/paper/1804.03999/) (2018)
- [nnU-Net: Self-adapting Framework for U-Net-Based Medical Image Segmentation](https://mlsanity.com/paper/1809.10486/) (2018)
- [Med3D: Transfer Learning for 3D Medical Image Analysis](https://mlsanity.com/paper/1904.00625/) (2019)
- [MS-Net: Multi-Site Network for Improving Prostate Segmentation with Heterogeneous MRI Data](https://mlsanity.com/paper/2002.03366/) (2020)
- [3D Anisotropic Hybrid Network: Transferring Convolutional Features from 2D Images to 3D Anisotropic Volumes](https://mlsanity.com/paper/1711.08580/) (2017)
- [Automatic Liver Lesion Segmentation Using A Deep Convolutional Neural Network Method](https://mlsanity.com/paper/1704.07239/) (2017)
- [Liver lesion segmentation informed by joint liver segmentation](https://mlsanity.com/paper/1707.07734/) (2017)
- [Hierarchical Convolutional-Deconvolutional Neural Networks for Automatic Liver and Tumor Segmentation](https://mlsanity.com/paper/1710.04540/) (2017)
- [Thickened 2D Networks for Efficient 3D Medical Image Segmentation](https://mlsanity.com/paper/1904.01150/) (2019)
- [Attentive CT Lesion Detection Using Deep Pyramid Inference with Multi-Scale Booster](https://mlsanity.com/paper/1907.03958/) (2019)
- [A 2D dilated residual U-Net for multi-organ segmentation in thoracic CT](https://mlsanity.com/paper/1905.07710/) (2019)
- [Neural Network-Based Automatic Liver Tumor Segmentation With Random Forest-Based Candidate Filtering](https://mlsanity.com/paper/1706.00842/) (2017)
- [Reinventing 2D Convolutions for 3D Images](https://mlsanity.com/paper/1911.10477/) (2019)

## Built on by (most cited first, 2 of 2)

- [Simultaneous Alignment and Surface Regression Using Hybrid 2D-3D Networks for 3D Coherent Layer Segmentation of Retinal OCT Images with Full and Sparse Annotations](https://mlsanity.com/paper/2312.01726/) (2023)
- [RECIST Weakly Supervised Lesion Segmentation via Label-Space Co-Training](https://mlsanity.com/paper/2303.00205/) (2023)

## Abstract (arXiv)

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.