H2Former: An Efficient Hierarchical Hybrid Transformer for Medical Image Segmentation
Top Cited Papers
- 5 April 2023
- journal article
- research article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Medical Imaging
- Vol. 42 (9) , 2763-2775
Abstract
Accurate medical image segmentation is of great significance for computer aided diagnosis. Although methods based on convolutional neural networks (CNNs) have achieved good results, it is weak to model the long-range dependencies, which is very important for segmentation task to build global context dependencies. The Transformers can establish long-range dependencies among pixels by self-attention, providing a supplement to the local convolution. In addition, multi-scale feature fusion and feature selection are crucial for medical image segmentation tasks, which is ignored by Transformers. However, it is challenging to directly apply self-attention to CNNs due to the quadratic computational complexity for high-resolution feature maps. Therefore, to integrate the merits of CNNs, multi-scale channel attention and Transformers, we propose an efficient hierarchical hybrid vision Transformer (H2Former) for medical image segmentation. With these merits, the model can be data-efficient for limited medical data regime. The experimental results show that our approach exceeds previous Transformer, CNNs and hybrid methods on three 2D and two 3D medical image segmentation tasks. Moreover, it keeps computational efficiency in model parameters, FLOPs and inference time. For example, H2Former outperforms TransUNet by 2.29% in IoU score on KVASIR-SEG dataset with 30.77% parameters and 59.23% FLOPs.Keywords
Funding Information
- National Natural Science Foundation (62272248)
- CAAI-Huawei MindSpore Open Fund (CAAIXSJLJJ-2021-025A)
- AISG Tech Challenge Fundin (AISG2-TC-2021-003)
- A*STAR CDF (C222812010)
This publication has 25 references indexed in Scilit:
- UNet++: Redesigning Skip Connections to Exploit Multiscale Features in Image SegmentationIEEE Transactions on Medical Imaging, 2019
- CE-Net: Context Encoder Network for 2D Medical Image SegmentationIEEE Transactions on Medical Imaging, 2019
- Indian Diabetic Retinopathy Image Dataset (IDRiD): A Database for Diabetic Retinopathy Screening ResearchData, 2018
- H-DenseUNet: Hybrid Densely Connected UNet for Liver and Tumor Segmentation From CT VolumesIEEE Transactions on Medical Imaging, 2018
- Deep Learning Techniques for Automatic MRI Cardiac Multi-Structures Segmentation and Diagnosis: Is the Problem Solved?IEEE Transactions on Medical Imaging, 2018
- Joint Optic Disc and Cup Segmentation Based on Multi-Label Deep Network and Polar TransformationIEEE Transactions on Medical Imaging, 2018
- Densely Connected Convolutional Networks2017
- Pyramid Scene Parsing Network2017
- Deep Residual Learning for Image Recognition2016
- ImageNet: A large-scale hierarchical image database2009