HiFormer: Hierarchical Multi-scale Representations Using Transformers for Medical Image Segmentation
By Moein Heidari, Amirhossein Kazerouni, Milad Soltany Kadarvish, Reza Azad, Ehsan Khodapanah Aghdam, Julien Cohen-Adad, Dorit Merhof. IEEE Workshop/Winter Conference on Applications of Computer Vision, 2022
389 citations recorded by the source corpus.
Convolutional neural networks (CNNs) have been the consensus for medical image segmentation tasks. However, they suffer from the limitation in modeling long-range dependencies and spatial correlations due to the nature of convolution operation. Although transformers were first developed to address this issue, they fail to capture low-level features. In contrast, it is demonstrated that both local and global features are crucial for dense prediction, such as segmenting in challenging contexts. In this paper, we propose HiFormer, a novel method that efficiently bridges a CNN and a transformer for medical image segmentation. Specifically, we design two multi-scale feature representations using the seminal Swin Transformer module and a CNN-based encoder. To secure a fine fusion of global and local features obtained from the two aforementioned representations, we propose a Double-Level Fusion (DLF) module in the skip connection of the encoder-decoder structure. Extensive experiments on various medical image segmentation datasets demonstrate the effectiveness of HiFormer over other CNN-based, transformer-based, and hybrid methods in terms of computational complexity, quantitative and qualitative results. Our code is publicly available at GitHub.
Subfields: Computer Vision and Pattern Recognition, Radiology, Nuclear Medicine and Imaging
View Paper: https://www.semanticscholar.org/paper/3de7e0c4bb5648a8368135592e11e991305ac426
How researchers see this paper
The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.
In Computer Vision and Pattern Recognition
- Ehsan Khodapanah Aghdam
- Moein Heidari
- Dorit Merhof
- Reza Azad
- Ilker Hacihaliloglu
- Amirhossein Kazerouni
- Dong Liu
- Kaiwen Zhang
In Radiology, Nuclear Medicine and Imaging
- Ehsan Khodapanah Aghdam
- Moein Heidari
- Dorit Merhof
- Reza Azad
- Ilker Hacihaliloglu
- Amirhossein Kazerouni
- Dong Liu
- Kaiwen Zhang
Citations in the corpus
- Customized Segment Anything Model for Medical Image Segmentation (2023, methodology): “We compare SAMed with current SOTA methods on Synapse dataset, including U-Net [29], Att-UNet [25], TransUnet [4], SwinUnet [3], MissFormer [13], TransDeepLab [2], HiFormer [10] and DAE-Former [1].”
- Diffusion models in medical imaging: A comprehensive survey (2022, background): “Image segmentation is a vital task in computer vision, which investigates simplifying the complexity of the image by decomposing an image into multiple meaningful image segments [113, 114].”