3D Anisotropic Hybrid Network: Transferring Convolutional Features from 2D Images to 3D Anisotropic Volumes

By Siqi Liu, Daguang Xu, Shaohua Kevin Zhou, Thomas Mertelmeier, Julia Wicklein, Anna K. Jerebko, Sasa Grbic, Olivier Pauly, Weidong (Tom) Cai, Dorin Comaniciu. 2017

158 citations recorded by the source corpus.

While deep convolutional neural networks (CNN) have been successfully applied to 2D image analysis, it is still challenging to apply them to 3D medical images, especially when the within-slice resolution is much higher than the between-slice resolution. We propose a 3D Anisotropic Hybrid Network (AH-Net) that transfers convolutional features learned from 2D images to 3D anisotropic volumes. Such a transfer inherits the desired strong generalization capability for within-slice information while naturally exploiting between-slice information for more effective modelling. We experiment with the proposed 3D AH-Net on two different medical image analysis tasks, namely lesion detection from a Digital Breast Tomosynthesis volume, and liver and liver tumor segmentation from a Computed Tomography volume and obtain state-of-the-art results.

Subfields: Artificial Intelligence, Computer Vision and Pattern Recognition

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 Computer Vision and Pattern Recognition

Citations in the corpus

A review of deep learning in medical imaging: Imaging traits, technology trends, case studies with progress highlights, and future promises (2020, background): “[55] propose a 3-D anisotropic hybrid network that effectively transfers convolutional features learned from 2-D images to 3-D anisotropic volumes.”
Med3D: Transfer Learning for 3D Medical Image Analysis (2019, background): “As shown in Table 4, the Med3D network achieves 94.6% Dice score without any post-processing, which is very close to state-of-the-art networks using ensemble techniques [43, 44].”
Embracing Imperfect Datasets: A Review of Deep Learning Solutions for Medical Image Segmentation (2019, methodology): “t al.(2018) transfer models based on natural scene video by treating the third dimension of medical scans as a temporal axis. This approach however may fail to capture the 3D context of medical scans.Liu et al. (2018) propose to turn a 2D model into a 3D network by extending 2D convolution ﬁlters in”
Generalizing Deep Learning for Medical Image Segmentation to Unseen Domains via Deep Stacked Transformation (2020, methodology): “The BigAug technique is integrated and demonstrated on a 3D Anisotropic Hybrid Network (AH-Net) [29] architecture.”
Uncertainty-aware multi-view co-training for semi-supervised medical image segmentation and domain adaptation (2020, methodology): “[38] proposed a 3D architecture which can be initialized by 2D pre-trained models.”