HyperDense-Net: A Hyper-Densely Connected CNN for Multi-Modal Image Segmentation

By Jose Dolz, Karthik Gopinath, Jing Yuan, Herve Lombaert, Christian Desrosiers, Ismail Ben Ayed. IEEE Transactions on Medical Imaging, 2018

515 citations recorded by the source corpus.

Recently, dense connections have attracted substantial attention in computer vision because they facilitate gradient flow and implicit deep supervision during training. Particularly, DenseNet that connects each layer to every other layer in a feed-forward fashion and has shown impressive performances in natural image classification tasks. We propose HyperDenseNet, a 3-D fully convolutional neural network that extends the definition of dense connectivity to multi-modal segmentation problems. Each imaging modality has a path, and dense connections occur not only between the pairs of layers within the same path but also between those across different paths. This contrasts with the existing multi-modal CNN approaches, in which modeling several modalities relies entirely on a single joint layer (or level of abstraction) for fusion, typically either at the input or at the output of the network. Therefore, the proposed network has total freedom to learn more complex combinations between the modalities, within and in-between all the levels of abstraction, which increases significantly the learning representation. We report extensive evaluations over two different and highly competitive multi-modal brain tissue segmentation challenges, iSEG 2017 and MRBrainS 2013, with the former focusing on six month infant data and the latter on adult images. HyperDenseNet yielded significant improvements over many state-of-the-art segmentation networks, ranking at the top on both benchmarks. We further provide a comprehensive experimental analysis of features re-use, which confirms the importance of hyper-dense connections in multi-modal representation learning. Our code is publicly available.

Subfields: Artificial Intelligence, Computer Vision and Pattern Recognition, Pediatrics, Perinatology and Child Health

View Paper: https://www.semanticscholar.org/paper/3069b8a2e7ff22020e0cf9a6f8a2c6cf33a736f2

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

1. Qi-Yan Dou
2. P. Heng
3. Quande Liu
4. Jose Dolz
5. Su Ruan
6. Yin Dai
7. Ben Glocker
8. Stéphane Canu

In Computer Vision and Pattern Recognition

1. P. Heng
2. Qi-Yan Dou
3. Yin Dai
4. Yifan Gao
5. Quande Liu
6. Jose Dolz
7. Su Ruan
8. Ben Glocker

Citations in the corpus

• Multi-Scale Self-Guided Attention for Medical Image Segmentation (2019, background): “dominate the literature in medical image segmentation [1] and have achieved outstanding performance in a broad span of applications, including brain [2] or cardiac [3] imaging, for”
• A review: Deep learning for medical image segmentation using multi-modality fusion (2019, methodology): “Inspired by [16], Dolz, et al.”
• Unpaired Multi-Modal Segmentation via Knowledge Distillation (2020, background): “Recently, more complex multi-modal CNNs have been designed, by leveraging dense connections [12], inception modules [13] or multi-scale feature fusion [14].”
• TransMed: Transformers Advance Multi-Modal Medical Image Classification (2021, methodology): “Hyper DenseNet built dual deep networks for different modalities of Magnetic resonance imaging (MRI) and linked features across these streams [15].”