CheXpert: A Large Chest Radiograph Dataset with Uncertainty Labels and Expert Comparison

Irvin, Jeremy; Rajpurkar, Pranav; Ko, Michael L.; Yu, Yifan; Ciurea-Ilcus, Silviana; Chute, Chris; Marklund, Henrik; Haghgoo, Behzad; Ball, Robyn L.; Shpanskaya, Katie; Seekins, Jayne; Mong, David A.; Halabi, Safwan; Sandberg, Jesse K.; Jones, Ricky; Larson, David B.; Langlotz, Curtis P.; Patel, Bhavik N.; Lungren, Matthew P.; Ng, Andrew Y.

doi:10.48550/arxiv.1901.07031

Cited by 49 publications

(114 citation statements)

References 0 publications

Supporting

Mentioning

113

Contrasting

Unclassified

Order By: Relevance

“…A. Datasets and Settings 1) Experimental settings: We conduct experiments on the NIH Chest-Xray14 dataset [8] and CheXpert dataset [9], two large-scale CXR datasets. In our experiments, we use dilated ResNet50 [33] as the backbone.…”

Section: Methodsmentioning

confidence: 99%

“…1) Abnormality classification: The authors of CheXpert [9] propose an evaluation protocol over 5 categories: "Atelectasis", "Cardiomegaly", "Consolidation", "Edema", and "Pleural Effusion", which were selected based on the clinical importance and prevalence from the validation set. In this experiment, we use the official set to train all the models, and show the AUC scores of these 5 abnormalities on official validation set.…”

Section: Chexpert Datasetmentioning

confidence: 99%

“…There are a few significant differences between the performance of the uncertainty approaches. U-Ignore [9] ignores the uncertainty labels during training, while U-Zeros [9] and U-Ones [9] treat them as 0 or 1. Since the U-Ones model achieves the best AUC performance in this dataset, we treat all uncertainty labels as 1 in our experiments.…”

Section: Chexpert Datasetmentioning

confidence: 99%

“…The public release of the large-scale NIH Chest X-ray14 [8] and CheXpert [9] datasets, both including more than 100,000 images, has further fostered research in this field, with many prominent techniques [3], [4], [5], [10], [11] formulating CXR image diagnosis as a multi-label classification problem. Despite their high classification accuracies, physicians find it difficult to interpret these "black-box" models.…”

Section: Introductionmentioning

confidence: 99%

“…• We demonstrate improved abnormality localization performance, establishing state-of-the-art results on the NIH ChestX-ray14 dataset. • We invite an experienced radiologist to provide box annotations in the CheXpert [9] dataset to help evaluate our method's localization performance. In total, 2345 images in the CheXpert dataset have been annotated with 6099 bounding boxes for 9 abnormality types.…”

Section: Introductionmentioning

confidence: 99%

See 4 more Smart Citations

Learning Hierarchical Attention for Weakly-Supervised Chest X-Ray Abnormality Localization and Diagnosis

Ouyang

Karanam²,

Wu³

et al. 2021

IEEE Trans. Med. Imaging

View full text Add to dashboard Cite

We consider the problem of abnormality localization for clinical applications. While deep learning has driven much recent progress in medical imaging, many clinical challenges are not fully addressed, limiting its broader usage. While recent methods report high diagnostic accuracies, physicians have concerns trusting these algorithm results for diagnostic decision-making purposes because of a general lack of algorithm decision reasoning and interpretability. One potential way to address this problem is to further train these models to localize abnormalities in addition to just classifying them. However, doing this accurately will require a large amount of disease localization annotations by clinical experts, a task that is prohibitively expensive to accomplish for most applications. In this work, we take a step towards addressing these issues by means of a new attention-driven weakly supervised algorithm comprising a hierarchical attention mining framework that unifies activation-and gradient-based visual attention in a holistic manner. Our key algorithmic innovations include the design of explicit ordinal attention constraints, enabling principled model training in a weakly-supervised fashion, while also facilitating the generation of visual-attention-driven model explanations by means of localization cues. On two largescale chest X-ray datasets (NIH ChestX-ray14 and CheXpert), we demonstrate significant localization performance improvements over the current state of the art while also achieving competitive classification performance. Our code is available on https://github.com/oyxhust/HAM.

show abstract

Section: Methodsmentioning

confidence: 99%

Section: Chexpert Datasetmentioning

confidence: 99%

Section: Chexpert Datasetmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 3 more Smart Citations

Learning Hierarchical Attention for Weakly-Supervised Chest X-Ray Abnormality Localization and Diagnosis

Ouyang

Karanam²,

Wu³

et al. 2021

IEEE Trans. Med. Imaging

View full text Add to dashboard Cite

show abstract

Automatic Radiology Report Generation Based on Multi-view Image Fusion and Medical Concept Enrichment

Yuan

Liao

Luo

et al. 2019

Lecture Notes in Computer Science

110

View full text Add to dashboard Cite

Generating radiology reports is time-consuming and requires extensive expertise in practice. Therefore, reliable automatic radiology report generation is highly desired to alleviate the workload. Although deep learning techniques have been successfully applied to image classification and image captioning tasks, radiology report generation remains challenging in regards to understanding and linking complicated medical visual contents with accurate natural language descriptions. In addition, the data scales of open-access datasets that contain paired medical images and reports remain very limited. To cope with these practical challenges, we propose a generative encoder-decoder model and focus on chest x-ray images and reports with the following improvements. First, we pretrain the encoder with a large number of chest x-ray images to accurately recognize 14 common radiographic observations, while taking advantage of the multi-view images by enforcing the cross-view consistency. Second, we synthesize multi-view visual features based on a sentence-level attention mechanism in a late fusion fashion. In addition, in order to enrich the decoder with descriptive semantics and enforce the correctness of the deterministic medical-related contents such as mentions of organs or diagnoses, we extract medical concepts based on the radiology reports in the training data and fine-tune the encoder to extract the most frequent medical concepts from the x-ray images. Such concepts are fused with each decoding step by a word-level attention model. The experimental results conducted on the Indiana University Chest X-Ray dataset demonstrate that the proposed model achieves the state-of-the-art performance compared with other baseline approaches.

show abstract

Influence of Cross Histology Transfer Learning on the Accuracy of Medical Diagnostics Systems

Mongolin

Khomeriki

Karnaukhov

et al. 2023

Innovations in Bio-Inspired Computing and Applications

View full text Add to dashboard Cite

CheXpert: A Large Chest Radiograph Dataset with Uncertainty Labels and Expert Comparison

Cited by 49 publications

References 0 publications

Learning Hierarchical Attention for Weakly-Supervised Chest X-Ray Abnormality Localization and Diagnosis

Learning Hierarchical Attention for Weakly-Supervised Chest X-Ray Abnormality Localization and Diagnosis

Automatic Radiology Report Generation Based on Multi-view Image Fusion and Medical Concept Enrichment

Influence of Cross Histology Transfer Learning on the Accuracy of Medical Diagnostics Systems

Contact Info

Product

Resources

About