# Multi-Slice Dense-Sparse Learning for Efficient Liver and Tumor Segmentation

arXiv: https://arxiv.org/abs/2108.06761 · HTML: https://mlsanity.com/paper/2108.06761/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 13 of its 24 references that are in the map.
- First posted on arXiv 15 Aug 2021.

## Builds on (most cited first, 13 of 13)

- [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)
- [A Survey on Deep Learning in Medical Image Analysis](https://mlsanity.com/paper/1702.05747/) (2017)
- [The Liver Tumor Segmentation Benchmark (LiTS)](https://mlsanity.com/paper/1901.04056/) (2019)
- [CE-Net: Context Encoder Network for 2D Medical Image Segmentation](https://mlsanity.com/paper/1903.02740/) (2019)
- [3D Deeply Supervised Network for Automatic Liver Segmentation from CT Volumes](https://mlsanity.com/paper/1607.00582/) (2016)
- [Automatic Liver and Lesion Segmentation in CT Using Cascaded Fully Convolutional Neural Networks and 3D Conditional Random Fields](https://mlsanity.com/paper/1610.02177/) (2016)
- [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)
- [Automatic 3D liver location and segmentation via convolutional neural networks and graph cut](https://mlsanity.com/paper/1605.03012/) (2016)
- [H-DenseUNet: Hybrid Densely Connected UNet for Liver and Tumor Segmentation from CT Volumes](https://mlsanity.com/paper/1709.07330/) (2017)
- [Multi-Phase Cross-modal Learning for Noninvasive Gene Mutation Prediction in Hepatocellular Carcinoma](https://mlsanity.com/paper/2005.04069/) (2020)
- [Multi-Instance Multi-Label Learning for Gene Mutation Prediction in Hepatocellular Carcinoma](https://mlsanity.com/paper/2005.04073/) (2020)

## Built on by (most cited first, 1 of 1)

- [Self-supervised Assisted Active Learning for Skin Lesion Segmentation](https://mlsanity.com/paper/2205.07021/) (2022)

## Abstract (arXiv)

Accurate automatic liver and tumor segmentation plays a vital role in treatment planning and disease monitoring. Recently, deep convolutional neural network (DCNNs) has obtained tremendous success in 2D and 3D medical image segmentation. However, 2D DCNNs cannot fully leverage the inter-slice information, while 3D DCNNs are computationally expensive and memory intensive. To address these issues, we first propose a novel dense-sparse training flow from a data perspective, in which, densely adjacent slices and sparsely adjacent slices are extracted as inputs for regularizing DCNNs, thereby improving the model performance. Moreover, we design a 2.5D light-weight nnU-Net from a network perspective, in which, depthwise separable convolutions are adopted to improve the efficiency. Extensive experiments on the LiTS dataset have demonstrated the superiority of the proposed method.