# H-DenseUNet: Hybrid Densely Connected UNet for Liver and Tumor Segmentation from CT Volumes

arXiv: https://arxiv.org/abs/1709.07330 · HTML: https://mlsanity.com/paper/1709.07330/

## Key facts

- Cited by 11 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 21 Sep 2017.

## Built on by (most cited first, 11 of 11)

- [Devil is in the Queries: Advancing Mask Transformers for Real-world Medical Image Segmentation and Out-of-Distribution Localization](https://mlsanity.com/paper/2304.00212/) (2023)
- [SAR-U-Net: squeeze-and-excitation block and atrous spatial pyramid pooling based residual U-Net for automatic liver segmentation in Computed Tomography](https://mlsanity.com/paper/2103.06419/) (2021)
- [Automated CT Lung Cancer Screening Workflow using 3D Camera](https://mlsanity.com/paper/2309.15750/) (2023)
- [Dense Dilated UNet: Deep Learning for 3D Photoacoustic Tomography Image Reconstruction](https://mlsanity.com/paper/2104.03130/) (2021)
- [Multi-Slice Dense-Sparse Learning for Efficient Liver and Tumor Segmentation](https://mlsanity.com/paper/2108.06761/) (2021)
- [MorphoSeg: An Uncertainty-Aware Deep Learning Method for Biomedical Segmentation of Complex Cellular Morphologies](https://mlsanity.com/paper/2409.17110/) (2024)
- [Adversarial Multi-Task Learning for Liver Tumor Segmentation, Dynamic Enhancement Regression, and Classification](https://mlsanity.com/paper/2511.20793/) (2025)
- [LightMedSeg: Lightweight 3D Medical Image Segmentation with Learned Spatial Anchors](https://mlsanity.com/paper/2603.07228/) (2026)
- [Sparse-shot Learning with Exclusive Cross-Entropy for Extremely Many Localisations](https://mlsanity.com/paper/2104.10425/) (2021)
- [Segment Anything in Defect Detection](https://mlsanity.com/paper/2311.10245/) (2023)
- [RefineFormer3D: Efficient 3D Medical Image Segmentation via Adaptive Multi-Scale Transformer with Cross Attention Fusion](https://mlsanity.com/paper/2602.16320/) (2026)

## Abstract (arXiv)

Liver cancer is one of the leading causes of cancer death. To assist doctors in hepatocellular carcinoma diagnosis and treatment planning, an accurate and automatic liver and tumor segmentation method is highly demanded in the clinical practice. Recently, fully convolutional neural networks (FCNs), including 2D and 3D FCNs, serve as the back-bone in many volumetric image segmentation. However, 2D convolutions can not fully leverage the spatial information along the third dimension while 3D convolutions suffer from high computational cost and GPU memory consumption. To address these issues, we propose a novel hybrid densely connected UNet (H-DenseUNet), which consists of a 2D DenseUNet for efficiently extracting intra-slice features and a 3D counterpart for hierarchically aggregating volumetric contexts under the spirit of the auto-context algorithm for liver and tumor segmentation. We formulate the learning process of H-DenseUNet in an end-to-end manner, where the intra-slice representations and inter-slice features can be jointly optimized through a hybrid feature fusion (HFF) layer. We extensively evaluated our method on the dataset of MICCAI 2017 Liver Tumor Segmentation (LiTS) Challenge and 3DIRCADb Dataset. Our method outperformed other state-of-the-arts on the segmentation results of tumors and achieved very competitive performance for liver segmentation even with a single model.