Contralaterally Enhanced Networks for Thoracic Disease Detection
- URL: http://arxiv.org/abs/2010.04483v1
- Date: Fri, 9 Oct 2020 10:15:26 GMT
- Title: Contralaterally Enhanced Networks for Thoracic Disease Detection
- Authors: Gangming Zhao and Chaowei Fang and Guanbin Li and Licheng Jiao and
Yizhou Yu
- Abstract summary: There exist many similar structures in the left and right parts of the chest, such as ribs, lung fields and bronchial tubes.
This kind of similarities can be used to identify diseases in chest X-rays, according to the experience of broad-certificated radiologists.
We propose a deep end-to-end module to exploit the contralateral context information for enhancing feature representations of disease proposals.
- Score: 120.60868136876599
- License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
- Abstract: Identifying and locating diseases in chest X-rays are very challenging, due
to the low visual contrast between normal and abnormal regions, and distortions
caused by other overlapping tissues. An interesting phenomenon is that there
exist many similar structures in the left and right parts of the chest, such as
ribs, lung fields and bronchial tubes. This kind of similarities can be used to
identify diseases in chest X-rays, according to the experience of
broad-certificated radiologists. Aimed at improving the performance of existing
detection methods, we propose a deep end-to-end module to exploit the
contralateral context information for enhancing feature representations of
disease proposals. First of all, under the guidance of the spine line, the
spatial transformer network is employed to extract local contralateral patches,
which can provide valuable context information for disease proposals. Then, we
build up a specific module, based on both additive and subtractive operations,
to fuse the features of the disease proposal and the contralateral patch. Our
method can be integrated into both fully and weakly supervised disease
detection frameworks. It achieves 33.17 AP50 on a carefully annotated private
chest X-ray dataset which contains 31,000 images. Experiments on the NIH chest
X-ray dataset indicate that our method achieves state-of-the-art performance in
weakly-supervised disease localization.
Related papers
- Leveraging Anatomical Constraints with Uncertainty for Pneumothorax
Segmentation [8.198854439726853]
Pneumothorax is a medical emergency caused by abnormal accumulation of air in the pleural space.
Deep learning (DL) has increasingly been utilized to segment pneumothorax lesions in chest radiographs.
We propose a novel approach that incorporates the lung+ space as a constraint during DL model training for pneumothorax segmentation on 2D chest radiographs.
arXiv Detail & Related papers (2023-11-26T07:03:17Z) - Employing similarity to highlight differences: On the impact of
anatomical assumptions in chest X-ray registration methods [2.080328156648695]
We develop an anatomically penalized convolutional multi-stage solution on the National Institutes of Health (NIH) data set.
Our method proves to be a natural way to limit the folding percentage of the warp field to 1/6 of the state of the art.
We statistically evaluate the benefits of our method and highlight the limits of currently used metrics for registration of chest X-rays.
arXiv Detail & Related papers (2023-01-23T09:42:49Z) - Radiomics-Guided Global-Local Transformer for Weakly Supervised
Pathology Localization in Chest X-Rays [65.88435151891369]
Radiomics-Guided Transformer (RGT) fuses textitglobal image information with textitlocal knowledge-guided radiomics information.
RGT consists of an image Transformer branch, a radiomics Transformer branch, and fusion layers that aggregate image and radiomic information.
arXiv Detail & Related papers (2022-07-10T06:32:56Z) - SQUID: Deep Feature In-Painting for Unsupervised Anomaly Detection [76.01333073259677]
We propose the use of Space-aware Memory Queues for In-painting and Detecting anomalies from radiography images (abbreviated as SQUID)
We show that SQUID can taxonomize the ingrained anatomical structures into recurrent patterns; and in the inference, it can identify anomalies (unseen/modified patterns) in the image.
arXiv Detail & Related papers (2021-11-26T13:47:34Z) - Generative Residual Attention Network for Disease Detection [51.60842580044539]
We present a novel approach for disease generation in X-rays using a conditional generative adversarial learning.
We generate a corresponding radiology image in a target domain while preserving the identity of the patient.
We then use the generated X-ray image in the target domain to augment our training to improve the detection performance.
arXiv Detail & Related papers (2021-10-25T14:15:57Z) - Weighing Features of Lung and Heart Regions for Thoracic Disease
Classification [15.128119121297507]
We propose a novel deep learning framework to explore discriminative information from lung and heart regions.
By zeroing features of non-lung and heart regions in attention maps, we can effectively exploit their disease-specific cues in lung and heart regions.
arXiv Detail & Related papers (2021-05-26T09:37:39Z) - A Structure-Aware Relation Network for Thoracic Diseases Detection and
Segmentation [63.76299770460766]
Instance level detection and segmentation of thoracic diseases or abnormalities are crucial for automatic diagnosis in chest X-ray images.
We propose a structure-aware relation network (SAR-Net) extending Mask R-CNN.
We release ChestX-Det, a chest X-Ray dataset with instance-level annotations (boxes and masks)
arXiv Detail & Related papers (2021-04-21T02:57:02Z) - Cross-Modal Contrastive Learning for Abnormality Classification and
Localization in Chest X-rays with Radiomics using a Feedback Loop [63.81818077092879]
We propose an end-to-end semi-supervised cross-modal contrastive learning framework for medical images.
We first apply an image encoder to classify the chest X-rays and to generate the image features.
The radiomic features are then passed through another dedicated encoder to act as the positive sample for the image features generated from the same chest X-ray.
arXiv Detail & Related papers (2021-04-11T09:16:29Z) - Weakly Supervised Thoracic Disease Localization via Disease Masks [29.065791290544983]
weakly supervised localization methods have been proposed that use only image-level annotation.
We propose a spatial attention method using disease masks that describe the areas where diseases mainly occur.
We show that the proposed method results in superior localization performances compared to state-of-the-art methods.
arXiv Detail & Related papers (2021-01-25T06:52:57Z) - DeScarGAN: Disease-Specific Anomaly Detection with Weak Supervision [0.98314893665023]
We present a weakly supervised and detail-preserving method for anomaly detection in medical images.
Our method extracts information about the disease characteristics from two groups: a group of patients affected by the same disease and a healthy control group.
Our method called DeScarGAN outperforms other anomaly detection methods on a synthetic data set and by visual inspection on the chest X-ray image data set.
arXiv Detail & Related papers (2020-07-28T10:50:38Z)
This list is automatically generated from the titles and abstracts of the papers in this site.
This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.