TUNA-Net: Task-oriented UNsupervised Adversarial Network for Disease Recognition in Cross-Domain Chest X-rays

by   Yuxing Tang, et al.

In this work, we exploit the unsupervised domain adaptation problem for radiology image interpretation across domains. Specifically, we study how to adapt the disease recognition model from a labeled source domain to an unlabeled target domain, so as to reduce the effort of labeling each new dataset. To address the shortcoming of cross-domain, unpaired image-to-image translation methods which typically ignore class-specific semantics, we propose a task-driven, discriminatively trained, cycle-consistent generative adversarial network, termed TUNA-Net. It is able to preserve 1) low-level details, 2) high-level semantic information and 3) mid-level feature representation during the image-to-image translation process, to favor the target disease recognition task. The TUNA-Net framework is general and can be readily adapted to other learning tasks. We evaluate the proposed framework on two public chest X-ray datasets for pneumonia recognition. The TUNA-Net model can adapt labeled adult chest X-rays in the source domain such that they appear as if they were drawn from pediatric X-rays in the unlabeled target domain, while preserving the disease semantics. Extensive experiments show the superiority of the proposed method as compared to state-of-the-art unsupervised domain adaptation approaches. Notably, TUNA-Net achieves an AUC of 96.3 pediatric pneumonia classification, which is very close to that of the supervised approach (98.1 domain.


Learning Domain Adaptive Features with Unlabeled Domain Bridges

Conventional cross-domain image-to-image translation or unsupervised dom...

Semantics-Aware Image to Image Translation and Domain Transfer

Image to image translation is the problem of transferring an image from ...

Generative Residual Attention Network for Disease Detection

Accurate identification and localization of abnormalities from radiology...

NAM: Non-Adversarial Unsupervised Domain Mapping

Several methods were recently proposed for the task of translating image...

Pixel and Feature Level Based Domain Adaption for Object Detection in Autonomous Driving

Annotating large scale datasets to train modern convolutional neural net...

Cross Domain Knowledge Transfer for Unsupervised Vehicle Re-identification

Vehicle re-identification (reID) is to identify a target vehicle in diff...

Cross Domain Knowledge Learning with Dual-branch Adversarial Network for Vehicle Re-identification

The widespread popularization of vehicles has facilitated all people's l...

Please sign up or login with your details

Forgot password? Click here to reset