Truly Generalizable Radiograph Segmentation With Conditional Domain Adaptation

  title={Truly Generalizable Radiograph Segmentation With Conditional Domain Adaptation},
  author={Hugo Neves de Oliveira and Edemir Ferreira and Jefersson Alex dos Santos},
  journal={IEEE Access},
Digitization techniques for biomedical images yield disparate visual patterns in radiological exams. These pattern differences, which can be viewed as a domain-shift problem, may hamper the use of data-driven approaches for inference over these images, such as Deep Neural Networks. Another noticeable difficulty in this field is the lack of labeled data, even though in many cases there is an abundance of unlabeled data available. Therefore, an important step in improving the generalization… Expand
Progressive Adversarial Semantic Segmentation
This work proposes a novel end - to-end medical image segmentation model, namely Progressive Adversarial Semantic Segmentation (PASS), which can make improved and consistent pixel-wise segmentation predictions without requiring any domain-specific data during training. Expand
Unsupervised domain adaptation for the segmentation of breast tissue in mammography images.
The potential for adversarial-based domain adaptation with U-Net architectures for segmentation of breast tissue in mammograms coming from several devices is demonstrated and it has been found that combining adversarial and reconstruction-based methods can provide a simple and effective solution for training with multiple unlabelled target domains. Expand
Advancing Medical Imaging Informatics by Deep Learning-Based Domain Adaptation
DA has emerged as a promising solution to deal with the lack of annotated training data, especially for segmentation tasks and among various DA approaches, domain transformation (DT) and latent feature-space transformation (LFST) are discussed. Expand
From 3D to 2D: Transferring knowledge for rib segmentation in chest X-rays
Results show that the proposed pipeline outperforms shallow rib segmentation baselines in almost all quantitative metrics and produce higher fidelity pixel-map predictions than simply using the pretrained Neural Networks on the flattened 3D data, mainly in datasets where domain shift is more pronounced. Expand
Adversarial Domain Adaptation for Sensor Networks
With the recent surge of big data, manually annotating datasets has become an impossible task. As a result, domain adaptation has gained more importance than ever, since it allows the transfer ofExpand
Deep Learning for Chest X-ray Analysis: A Survey
All studies using deep learning on chest radiographs published before March 2021 are reviewed, categorizing works by task: image-level prediction, segmentation, localization, image generation and domain adaptation. Expand


Task Driven Generative Modeling for Unsupervised Domain Adaptation: Application to X-ray Image Segmentation
A novel model framework for learning automatic X-ray image parsing from labeled CT scans is proposed and an added module leveraging the pre-trained DI2I to enforce segmentation consistency is introduced. Expand
Deep Transfer Learning for Segmentation of Anatomical Structures in Chest Radiographs
  • H. Oliveira, J. D. Santos
  • Computer Science
  • 2018 31st SIBGRAPI Conference on Graphics, Patterns and Images (SIBGRAPI)
  • 2018
This work proposes a novel method for Cross-Dataset Transfer Learning in Chest X-Ray images based on Unsupervised Image Translation architectures and achieves state-of-the-art results in lung field, heart, and clavicle segmentation. Expand
TUNA-Net: Task-oriented UNsupervised Adversarial Network for Disease Recognition in Cross-Domain Chest X-rays
A task-driven, discriminatively trained, cycle-consistent generative adversarial network, termed TUNA-Net, which can adapt labeled adult chest X-rays in the source domain such that they appear as if they were drawn from pediatric X-ray in the unlabeled target domain, while preserving the disease semantics. Expand
Unsupervised Pixel-Level Domain Adaptation with Generative Adversarial Networks
This generative adversarial network (GAN)-based method adapts source-domain images to appear as if drawn from the target domain, and outperforms the state-of-the-art on a number of unsupervised domain adaptation scenarios by large margins. Expand
Transfer Learning for Domain Adaptation in MRI: Application in Brain Lesion Segmentation
This study trained a CNN on legacy MR images of brain and evaluated the performance of the domain-adapted network on the same task with images from a different domain, substantially outperforming a similar network trained on the the same set of examples from scratch. Expand
Unsupervised Domain Adaptation via Disentangled Representations: Application to Cross-Modality Liver Segmentation
This work achieves cross-modality domain adaptation, i.e. between CT and MRI images, via disentangled representations, using the state-of-art CycleGAN to recover a manyto-many mapping between domains to capture the complex cross-domain relations. Expand
FCNs in the Wild: Pixel-level Adversarial and Constraint-based Adaptation
This paper introduces the first domain adaptive semantic segmentation method, proposing an unsupervised adversarial approach to pixel prediction problems, and outperforms baselines across different settings on multiple large-scale datasets. Expand
PadChest: A large chest x-ray image dataset with multi-label annotated reports
This dataset includes more than 160,000 images obtained from 67,000 patients that were interpreted and reported by radiologists at San Juan Hospital (Spain) from 2009 to 2017, covering six different position views and additional information on image acquisition and patient demography. Expand
U-Net: Convolutional Networks for Biomedical Image Segmentation
It is shown that such a network can be trained end-to-end from very few images and outperforms the prior best method (a sliding-window convolutional network) on the ISBI challenge for segmentation of neuronal structures in electron microscopic stacks. Expand
Identifying Medical Diagnoses and Treatable Diseases by Image-Based Deep Learning
A diagnostic tool based on a deep-learning framework for the screening of patients with common treatable blinding retinal diseases, which demonstrates performance comparable to that of human experts in classifying age-related macular degeneration and diabetic macular edema. Expand