50 Hits in 3.7 sec

PadChest: A large chest x-ray image dataset with multi-label annotated reports [article]

Aurelia Bustos, Antonio Pertusa, Jose-Maria Salinas, Maria de la Iglesia-Vayá
2019 arXiv   pre-print
We present a labeled large-scale, high resolution chest x-ray dataset for the automated exploration of medical images along with their associated reports.  ...  Of these reports, 27% were manually annotated by trained physicians and the remaining set was labeled using a supervised method based on a recurrent neural network with attention mechanisms.  ...  The Medical Image Bank of the Valencian Community as well as de-identification and anonymization services, were partially funded by the Regional Ministry of Health (FEDER program) and the Horizon 2020  ... 
arXiv:1901.07441v2 fatcat:uuhka6akyrhr7orlppbgymxjsy

Semantic-guided Image Virtual Attribute Learning for Noisy Multi-label Chest X-ray Classification [article]

Yuanhong Chen, Fengbei Liu, Yu Tian, Yuyuan Liu, Gustavo Carneiro
2022 arXiv   pre-print
Many Chest X-ray (CXR) classifiers are modelled from datasets with machine-generated labels, but their training procedure is in general not robust to the presence of noisy-label samples and can overfit  ...  Deep learning methods have shown outstanding classification accuracy in medical image analysis problems, which is largely attributed to the availability of large datasets manually annotated with clean  ...  The OpenI [4] dataset contains 3,999 radiology reports and 7,470 frontal/lateral-view chest X-ray images from the Indiana Network for Patient Care.  ... 
arXiv:2203.01937v1 fatcat:wqxbrfcz3zafxhdapomwbwwvoi

Can we trust deep learning models diagnosis? The impact of domain shift in chest radiograph classification [article]

Eduardo H. P. Pooch, Pedro L. Ballester, Rodrigo C. Barros
2020 arXiv   pre-print
A high domain shift tends to implicate in a poor generalization performance from the models. In this work, we evaluate the extent of domain shift on four of the largest datasets of chest radiographs.  ...  We show how training and testing with different datasets (e.g., training in ChestX-ray14 and testing in CheXpert) drastically affects model performance, posing a big question over the reliability of deep  ...  Our experiments show that a model with reported radiologist-level performance had a huge drop in performance outside its source dataset, pointing the existence of domain shift in chest X-rays datasets.  ... 
arXiv:1909.01940v2 fatcat:e4lnzqvpizet5b2yvnpmxxby2e

UMLS-ChestNet: A deep convolutional neural network for radiological findings, differential diagnoses and localizations of COVID-19 in chest x-rays [article]

Germán González, Aurelia Bustos, José María Salinas, María de la Iglesia-Vaya, Joaquín Galant, Carlos Cano-Espinosa, Xavier Barber, Domingo Orozco-Beltrán, Miguel Cazorla, Antonio Pertusa
2020 arXiv   pre-print
We train the system on one large database of 92,594 frontal chest x-rays (AP or PA, standing, supine or decubitus) and a second database of 2,065 frontal images of COVID-19 patients identified by at least  ...  To our knowledge, this work uses the largest chest x-ray dataset of COVID-19 positive cases to date and is the first one to use a hierarchical labeling schema and to provide interpretability of the results  ...  We thank also NVIDIA for the generous donation of a Titan Xp and a Quadro P6000 used in this research. References  ... 
arXiv:2006.05274v1 fatcat:t4lue72ygnaj5kks2vrgc4vyza

Quantifying the Value of Lateral Views in Deep Learning for Chest X-rays [article]

Mohammad Hashir, Hadrien Bertrand, Joseph Paul Cohen
2020 arXiv   pre-print
PadChest is a large-scale chest X-ray dataset that has almost 200 labels and multiple views available.  ...  In this work, we use PadChest to explore multiple approaches to merging the PA and lateral views for predicting the radiological labels associated with the X-ray image.  ...  We also thank NVIDIA for donating a DGX-1 computer used in this work.  ... 
arXiv:2002.02582v1 fatcat:6l3sewwrzzcvjitstbqvnbfajy

CheXstray: Real-time Multi-Modal Data Concordance for Drift Detection in Medical Imaging AI [article]

Arjun Soin, Jameson Merkow, Jin Long, Joseph Paul Cohen, Smitha Saligrama, Stephen Kaiser, Steven Borg, Ivan Tarapov, Matthew P Lungren
2022 arXiv   pre-print
We use the CheXpert and PadChest public datasets to build and test a medical imaging AI drift monitoring workflow to track data and model drift without contemporaneous ground truth.  ...  We simulate drift in multiple experiments to compare model performance with our novel multi-modal drift metric, which uses DICOM metadata, image appearance representation from a variational autoencoder  ...  Acknowledgments This work was was supported in part by the Stanford Center for Artificial Intelligence in Medicine and Imaging (AIMI) and Microsoft Health and Life Sciences.  ... 
arXiv:2202.02833v2 fatcat:kuhtj373mzev3nbmlhagm3jke4

Automated Chest Radiographs Triage Reading by a Deep Learning Referee Network [article]

Rafael Lopez-Gonzalez, Jose Sanchez-Garcia, Belen Fos-Guarinos, Fabio Garcia-Castro, Angel Alberich-Bayarri, Emilio Soria-Olivas, Carlos Munoz-Nunez, Luis Marti-Bonmati
2021 medRxiv   pre-print
in chest X-ray triage and worklist prioritization.  ...  The CNN models were trained with a combination of three large scale databases: ChestX-ray14, CheXpert and PadChest.  ...  To help researchers, the NIH released ChestX-ray14, a chest X-ray multi-label dataset which encloses 112,120 posterior-anterior chest exams labeled with 14 different radiological findings (Wang et al.  ... 
doi:10.1101/2021.06.01.21257399 fatcat:g3ycwaba5bb5xfwrknayeogdvm

BIMCV COVID-19+: a large annotated dataset of RX and CT images from COVID-19 patients [article]

Maria de la Iglesia Vayá, Jose Manuel Saborit, Joaquim Angel Montell, Antonio Pertusa, Aurelia Bustos, Miguel Cazorla, Joaquin Galant, Xavier Barber, Domingo Orozco-Beltrán, Francisco García-García, Marisa Caparrós, Germán González (+1 others)
2020 arXiv   pre-print
This paper describes BIMCV COVID-19+, a large dataset from the Valencian Region Medical ImageBank (BIMCV) containing chest X-ray images CXR (CR, DX) and computed tomography (CT) imaging of COVID-19+ patients  ...  Images are stored in high resolution and entities are localized with anatomical labels and stored in a Medical Imaging Data Structure (MIDS) format.  ...  Acknowledgements This work is first and foremost an open and free contribution from the authors in the working group with support from the Regional Ministry of Innovation, Universities, Science and Digital  ... 
arXiv:2006.01174v3 fatcat:i3dimqnjwfefhbbg55sxkv667u

Improving anatomical plausibility in medical image segmentation via hybrid graph neural networks: applications to chest x-ray analysis [article]

Nicolás Gaggion, Lucas Mansilla, Candelaria Mosquera, Diego H. Milone, Enzo Ferrante
2022 arXiv   pre-print
Our comprehensive experimental setup compares HybridGNet with other landmark and pixel-based models for anatomical segmentation in chest x-ray images, and shows that it produces anatomically plausible  ...  Anatomical segmentation is a fundamental task in medical image computing, generally tackled with fully convolutional neural networks which produce dense segmentation masks.  ...  We also thank Facundo Diaz and Martina Aineseder -specialists from the Radiology Department at Hospital Italiano de Buenos Aires-for their collaboration in the annotation of the Padchest images.  ... 
arXiv:2203.10977v2 fatcat:h5umvl3zljdyparkbi2ht5ussi

Breaking with Fixed Set Pathology Recognition through Report-Guided Contrastive Training [article]

Constantin Seibold, Simon Reiß, M. Saquib Sarfraz, Rainer Stiefelhagen, Jens Kleesiek
2022 arXiv   pre-print
We evaluate our approach on the large-scale chest X-Ray datasets MIMIC-CXR, CheXpert, and ChestX-Ray14 for disease classification.  ...  We show that despite using unstructured medical report supervision, we perform on par with direct label supervision through a sophisticated inference setting.  ...  -PadChest: It consists 160k chest X-rays of 67k patients with 174 findings.  ... 
arXiv:2205.07139v1 fatcat:dqwcpv5ozbezvfkteumpdhvjza

NVUM: Non-Volatile Unbiased Memory for Robust Medical Image Classification [article]

Fengbei Liu, Yuanhong Chen, Yu Tian, Yuyuan Liu, Chong Wang, Vasileios Belagiannis, Gustavo Carneiro
2022 arXiv   pre-print
We run extensive experiments to evaluate NVUM on new benchmarks proposed by this paper, where training is performed on noisy multi-label imbalanced chest X-ray (CXR) training sets, formed by Chest-Xray14  ...  and CheXpert, and the testing is performed on the clean multi-label CXR datasets OpenI and PadChest.  ...  PadChest (PDC) is a large-scale dataset containing 158,626 images with 37.5% of images manually labelled. In our experiment, we only use the manually labelled samples as the clean test set.  ... 
arXiv:2103.04053v5 fatcat:mbnlpf34hncp7ghges6ckahu54

Deep Hiearchical Multi-Label Classification Applied to Chest X-Ray Abnormality Taxonomies [article]

Haomin Chen, Shun Miao, Daguang Xu, Gregory D. Hager, Adam P. Harrison
2020 arXiv   pre-print
When using complete labels, we report a mean AUC of 0.887, the highest yet reported for this dataset.  ...  We extensively evaluate our approach on detecting abnormality labels from the CXR arm of the PLCO dataset, which comprises over 198,000 manually annotated CXRs.  ...  We also thank Chaochao Yan for help on pre-processing the PLCO images and labels. Finally, we thank anonymous reviewers for their constructive comments and criticisms.  ... 
arXiv:2009.05609v3 fatcat:3t64c3bxsfbffhlbt2xqbfwta4

A dataset of chest X-ray reports annotated with Spatial Role Labeling annotations

Surabhi Datta, Kirk Roberts
2020 Data in Brief  
In this paper, we present a dataset consisting of 2000 chest X-ray reports (available as part of the Open-i image search platform) annotated with spatial information.  ...  The annotation is based on Spatial Role Labeling.  ...  Acknowledgments This work was supported in part by the National Institute of Biomedical Imaging and Bioengineering (NIBIB: R21EB029575), the U.S.  ... 
doi:10.1016/j.dib.2020.106056 pmid:32904141 pmcid:PMC7451761 fatcat:bicdg2yyhnay5mokz2hvq2ntbi

Deep learning in generating radiology reports: A survey

Maram Mahmoud A. Monshi, Josiah Poon, Vera Chung
2020 Artificial Intelligence in Medicine  
Substantial progress has been made towards implementing automated radiology reporting models based on deep learning (DL). This is due to the introduction of large medical text/image datasets.  ...  Generating radiology coherent paragraphs that do more than traditional medical image annotation, or single sentence-based description, has been the subject of recent academic attention.  ...  Figure 1 shows an example in the form of an IU X-ray [21] dataset. Here, each report is associated with two chest X-ray images.  ... 
doi:10.1016/j.artmed.2020.101878 pmid:32425358 pmcid:PMC7227610 fatcat:ccy2g2rh2zavdjjvvjlv7poxau

Review on Deep Learning Methods for Chest X-Ray based Abnormality Detection and Thoracic Pathology Classification

Joana Rocha, Ana Maria Mendonça, Aurélio Campilho
2021 U Porto Journal of Engineering  
In addition, the paper discloses the current annotated public chest X-ray databases, covering the common thorax diseases.  ...  detection and multi-label thoracic pathology classification.  ...  Introduction Among the popular medical imaging exams, the Chest X-Ray (CXR) is frequently requested by healthcare professionals to assess the presence of thoracic diseases, due to its low-cost noninvasive  ... 
doi:10.24840/2183-6493_007.004_0002 fatcat:iwtaykty7jcydjk67sdg5gad7a
« Previous Showing results 1 — 15 out of 50 results