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

By Xiaomeng Li, Hao Chen, Xiaojuan Qi, Qi-Yan Dou, Chi-Wing Fu, P. Heng. IEEE Transactions on Medical Imaging, 2018

2,217 citations recorded by the source corpus.

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 2-D and 3-D FCNs, serve as the backbone in many volumetric image segmentation. However, 2-D convolutions cannot fully leverage the spatial information along the third dimension while 3-D 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 2-D DenseUNet for efficiently extracting intra-slice features and a 3-D 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 the 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 layer. We extensively evaluated our method on the data set of the MICCAI 2017 Liver Tumor Segmentation Challenge and 3DIRCADb data set. 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.

Subfields: Artificial Intelligence, Biomedical Engineering, Computer Vision and Pattern Recognition

View Paper: https://www.semanticscholar.org/paper/a86d7289c76d832e83c99539859b7b186e4ea6c8

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

In Biomedical Engineering

In Computer Vision and Pattern Recognition

Citations in the corpus

Swin-Unet: Unet-like Pure Transformer for Medical Image Segmentation (2021, methodology): “Due to the simplicity and superior performance of the U-shaped structure, various Unet-like methods are constantly emerging, such as Res-UNet [7], Dense-UNet [22], U-Net++ [8] and UNet3+ [9].”
Modified U-Net (mU-Net) with Incorporation of Object-Dependent High Level Features for Improved Liver and Liver-Tumor Segmentation in CT Images (2019, background): “[36], (e) proposed network, and (f) ground truth from segmentation results in Fig.”
3D radiotherapy dose prediction on head and neck cancer patients with a hierarchically densely connected U-net deep learning architecture (2018, background): “Xiaomeng et al previously attempted to combat this with a hybrid densely connected U-net, where they combine a 2D Dense U-net, to extract intra-slice features, with a 3D counterpart for aggregating volumetric contexts (Li et al 2018).”
3D Deep Learning on Medical Images: A Review (2020, methodology): “In this sequence, another work, based on the 2D DenseUnet and hierarchical diagnosis approach (H-DensNet) for the segmentation of liver lesions, has been presented in Reference [70].”
Fully Dense UNet for 2-D Sparse Photoacoustic Tomography Artifact Removal (2018, background): “a more compact and superior CNN [23], [33], [34].”
Semi-supervised semantic segmentation needs strong, varied perturbations (2019, methodology): “Encoder-decoder networks [2, 20, 30] use skip connections to connect an image classiﬁer like encoder to a decoder.”
The state of the art in kidney and kidney tumor segmentation in contrast-enhanced CT imaging: Results of the KiTS19 challenge (2019, background): “, 2016), dense connections (Li et al., 2018), and attention mechanisms (Oktay et al.”
UNETR: Transformers for 3D Medical Image Segmentation (2021, methodology): “CNN-based Segmentation Networks : Since the introduction of the seminal U-Net [36], CNN-based networks have achieved state-of-the-art results on various 2D and 3D various medical image segmentation tasks [15, 54, 49, 17, 28].”
Recent advances and clinical applications of deep learning in medical image analysis (2021, background): “Dense convolutional blocks (Huang et al., 2017) also demonstrated its superiority in enhancing segmentation performance on liver and tumor CT volumes (Li et al., 2018).”
U-Net and Its Variants for Medical Image Segmentation: A Review of Theory and Applications (2020, background): “of brain tumors [20], [45], retinal blood vessel segmentation [45], cerebral blood vessel segmentation [68], [69], melanoma [70], lung cancer [70], liver cancer [71], andmultiorgan segmentation [72].”
AMOS: A Large-Scale Abdominal Multi-Organ Benchmark for Versatile Medical Image Segmentation (2022, background): “For example, to precisely segment the liver and tumor, H-DenseUNet [13] designs a hybrid 2D/3D network for better features extraction.”
Mamba-UNet: UNet-Like Pure Visual Mamba for Medical Image Segmentation (2024, methodology): “…U-Net with advanced network blocks techniques such as dense connections [12], residual blocks [10], attention mechanisms [30], depthwise convolutions [11], and atrous convolutions [33,35], resulting in various modified UNet in CT, MRI, Ultrasound medical image segmentation [23,13,15,29,34,36].”