What is CheXpert?

CheXpert is a large dataset of chest X-rays and competition for automated chest x-ray interpretation, which features uncertainty labels and radiologist-labeled reference standard evaluation sets.

Read the Paper (Irvin & Rajpurkar et al.)

Why CheXpert?

Chest radiography is the most common imaging examination globally, critical for screening, diagnosis, and management of many life threatening diseases. Automated chest radiograph interpretation at the level of practicing radiologists could provide substantial benefit in many medical settings, from improved workflow prioritization and clinical decision support to large-scale screening and global population health initiatives. For progress in both development and validation of automated algorithms, we realized there was a need for a labeled dataset that (1) was large, (2) had strong reference standards, and (3) provided expert human performance metrics for comparison.

Leaderboard

Will your model perform as well as radiologists in detecting different pathologies in chest X-rays?

RankDateModelAUCNum Rads Below Curve
1
Aug 31, 2020DeepAUC-v1 ensemble https://arxiv.org/abs/2012.031730.9302.8
2
Sep 01, 2019Hierarchical-Learning-V1 (ensemble) Vingroup Big Data Institute https://arxiv.org/abs/1911.064750.9302.6
3
Oct 15, 2019Conditional-Training-LSR ensemble 0.9292.6
4
Dec 04, 2019Hierarchical-Learning-V4 (ensemble) Vingroup Big Data Institute https://arxiv.org/abs/1911.064750.9292.6
5
Oct 10, 2019YWW(ensemble) JF&NNU https://github.com/jfhealthcare/Chexpert0.9292.8
6
Oct 17, 2019Conditional-Training-LSR-V1 ensemble 0.9292.6
7
Nov 17, 2019Hierarchical-Learning-V0 (ensemble) Vingroup Big Data Institute 0.9292.6
8
Sep 09, 2019Multi-Stage-Learning-CNN-V3 (ensemble) VINBDI Medical Imaging Team 0.9282.6
9
Dec 30, 2019DeepCNNsGM(ensemble) HUST 0.9282.6
10
Dec 30, 2019DeepCNNs(ensemble) HUST 0.9272.6
11
Dec 16, 2019desmond https://github.com/inisis/chexpert https://github.com/inisis/chexpert)0.9273.0
11
Dec 23, 2019inisis https://github.com/inisis/chexpert https://github.com/inisis/chexpert)0.9273.0
12
Sep 19, 2019SenseXDR ensemble 0.9272.6
13
Sep 18, 2019ihil (ensemble) UESTC 0.9272.6
14
Jul 01, 2022Anatomy-XNet-V1 ensemble https://arxiv.org/abs/2106.059150.9262.6
15
Jul 31, 2019JF aboy ensemble_V2 JF HEALTHCAREhttps://github.com/deadpoppy/CheXpert-Challenge0.9263.0
16
Sep 01, 2019yww0.9262.6
17
Sep 16, 2019DRNet (ensemble) UESTC and SenseTime 0.9262.6
18
Feb 11, 2020alimebkovkz0.9252.4
18
Dec 26, 2019hoanganh_VB_ensemble370.9252.4
19
Dec 26, 2019hoanganh_VB_ensemble350.9252.4
20
Dec 12, 2019Hoang_VB_ensemble31_v10.9242.4
21
Dec 17, 2019tedtta0.9242.4
22
Sep 04, 2019uestc0.9242.6
23
Dec 09, 2019Hoang_VB_ensemble31_v20.9242.4
24
Dec 04, 2019as-hust-v3 ensemble 0.9242.4
25
Jan 10, 2020hoanganh_VB_VN30.9242.4
26
Sep 14, 2019Hierarchical-CNN-Ensemble-V1 (ensemble) Vingroup Big Data Institute 0.9242.4
27
Apr 25, 2020DE_APR ensemble ltts0.9232.6
28
Apr 25, 2020DE_APR_N ensemble ltts0.9232.6
29
Dec 10, 2019hoanganhcnu_ensemble27_v20.9232.4
30
Aug 22, 2019Multi-Stage-Learning-CNN-V2 (ensemble) VINBDI Medical Imaging Team 0.9232.6
31
Dec 16, 2019Weighted-CNN(ensemble) HUST 0.9232.6
32
Dec 10, 2019hoanganhcnu_ensemble27_v10.9232.4
33
Aug 17, 2019YJ&&YWW :https://github.com/inisis/chexpert0.9232.4
34
Sep 15, 2022Maxium (ensemble) Macao Polytechnic University 0.9232.4
35
Dec 04, 2019as-hust-v1 ensemble 0.9232.4
36
Dec 16, 2019Average-CNN(ensemble) HUST 0.9222.4
37
Dec 04, 2019as-hust-v2 ensemble 0.9222.8
38
Aug 04, 2020MaxAUC ensemble 0.9222.4
39
Nov 21, 2019hoangnguyenkcv170.9212.4
40
Sep 04, 2019null0.9222.2
41
Sep 02, 2020SuperCNNv3 ensemble 0.9212.4
42
Aug 13, 2019null0.9212.2
43
Aug 15, 2019zjr(ensembel) CSU 0.9212.6
44
Aug 15, 2019hyc ensemble 0.9212.4
45
Jan 10, 2020HOANG_VB_VN_2 ensemble 0.9202.4
46
Nov 23, 2019null0.9202.6
47
Aug 18, 2019BDNB ensemble 0.9192.6
48
Dec 20, 2019thang ensemble coloa0.9192.4
49
Nov 30, 2019null0.9192.2
50
Jul 16, 2019JF Coolver ensemble ensemble model 0.9192.6
51
Nov 21, 2019hoangnn9 ensemble VBVN0.9192.4
52
Jul 27, 2019JF aboy ensemble_V1 JF HEALTHCAREhttps://github.com/deadpoppy/CheXpert-Challenge0.9192.4
53
Sep 08, 2022A Good Model (single model) Macao Polytechnic University 0.9182.6
54
Nov 07, 2019brian-baseline-v2 ensemble 0.9192.2
55
Jun 22, 2020DE_JUN4_RS_EN ensemble LTTS0.9182.6
56
Jun 22, 2019Mehdi_You (ensemble) IPM_HPC 0.9182.6
57
Apr 17, 2022Anatomy-XNet (ensemble) mHealth-BUET https://arxiv.org/abs/2106.059150.9172.6
58
Oct 01, 2021Overfit ensemble OTH-AW0.9172.2
59
Aug 15, 2019Deep-CNNs-V1 ensemble 0.9172.2
60
Nov 22, 2019thangbk(ensemble) SNU 0.9172.0
61
Jul 18, 2019Ensemble_v2 Ian, Wingspan https://github.com/Ien001/CheXpert_challenge_20190.9172.4
62
Jan 21, 2020vdn6 ensemble ltts0.9172.2
63
Jun 22, 2020DE_JUN3_RS_EN ensemble LTTS0.9162.4
64
Nov 25, 2019null0.9162.4
65
Nov 25, 2019ATT-AW-v1 ensemble 0.9162.4
66
Nov 14, 2019null0.9162.2
67
Dec 14, 2019desmond https://github.com/inisis/chexpert https://github.com/inisis/chexpert)0.9162.6
67
Jun 22, 2020DE_JUN1_RS_EN ensemble LTTS0.9162.6
68
Oct 10, 2019desmond https://github.com/inisis/chexpert https://github.com/inisis/chexpert)0.9162.6
69
Aug 25, 2019Multi-Stage-Learning-CNN-V0 ensemble 0.9162.2
70
Aug 19, 2019TGNB ensemble 0.9152.6
71
Jul 15, 2019Deadpoppy Ensemble ensemble model 0.9152.2
72
Nov 18, 2019hoangnguyenkcv-ensemble28 ensemble 0.9152.2
73
Aug 05, 2019zhangjingyang0.9152.4
74
Dec 10, 2019ensemble SNU0.9152.4
75
Jun 22, 2020DE_JUN2_RS_EN ensemble LTTS0.9142.6
76
Aug 16, 2019GRNB ensemble 0.9142.4
77
Jul 31, 2019Deep-CNNs (ensemble) Vingroup Big Data Institute 0.9142.0
78
Dec 02, 2019Sky-Model ensemble 0.9132.2
79
Jul 23, 2019JF Deadpoppy ensemble 0.9132.2
80
Aug 14, 2019YWW-YJ:https://github.com/inisis/chexpert0.9132.0
81
Aug 17, 2019zjy ensemble 0.9122.2
82
Jun 29, 2020WL_Baseline (ensemble) WL 0.9122.0
83
Oct 30, 2021anatomy_xnet_v1 (single model) BUET 0.9112.2
84
Aug 01, 2019songtao0.9112.2
85
Oct 25, 2019bhtrung0.9112.2
85
Oct 27, 2019KCV-CNN-ensemble-CNU0.9112.2
86
Apr 25, 2020DS_APR_N single model ltts0.9112.0
87
Apr 25, 2020DS_APR single model LTTS0.9112.0
88
Oct 24, 2019brian-baseline ensemble 0.9112.0
89
Dec 10, 2019ensemble SNU30.9102.2
90
Dec 09, 2019HinaNetV2 (ensemble) VietAI http://vietai.org0.9092.2
91
Oct 21, 2022KD-Prune10 (Single model) MPU 0.9092.0
92
Jun 05, 2022G_Mans_ensemble0.9091.8
93
Jan 12, 2020vdnnn (ensemble) LTTS 0.9081.8
94
May 25, 2022BAAZT Ensemble 0.9081.8
95
Jul 31, 2019guran_rib0.9082.0
96
Jan 12, 2020vbn (single model) LTTS 0.9071.6
97
Apr 06, 2019muti_base (ensemble) SCU_MILAB 0.9071.6
98
Jan 23, 2019Stanford Baseline (ensemble) Stanford University https://arxiv.org/abs/1901.070310.9071.8
99
Mar 02, 2022Z_Ensemble_V10.9071.4
100
Sep 11, 2019{ForwardModelEnsembleCorrected} (ensemble) Stanford 0.9061.6
101
Jun 14, 2019Multi-CNN ensemble 0.9052.4
102
Oct 13, 2021LBC-v2 (ensemble) Macao Polytechnic University https://arxiv.org/abs/2210.059540.9061.6
103
Jul 25, 2019hyc0.9051.8
104
Oct 02, 2019ForwardMECorrectedFull (ensemble) Institution 0.9051.6
105
Jul 21, 2019Multi-CNN ensemble 0.9052.0
106
Jun 22, 2019JustAnotherDensenet single model 0.9041.2
107
May 06, 2022Orlando (single model) Macao Polytechnic University 0.9031.6
108
May 30, 2022Max (single model) Macao Polytechnic University 0.9022.0
109
Mar 03, 2020DeepLungsEnsemble Alimbekov R. & Vassilenko I. 0.9021.8
110
Sep 29, 2019Nakajima_ayase0.9011.4
111
Jul 04, 2019Ensemble_v1 Ian, Wingspan https://github.com/Ien001/CheXpert_challenge_20190.9011.6
112
May 24, 2019MLC11 NotDense (single-model) Leibniz University Hannover 0.9001.6
113
Jan 23, 2020vn_2 single_model ltts0.9001.2
114
Apr 19, 2022Z_Ensemble_20.8991.8
115
Jul 22, 2019adoudou0.8991.6
116
Jul 22, 2019{AVG_MAX}(ensemble) NNU 0.8992.0
117
Aug 01, 2019null0.8991.6
118
Jul 24, 2019llllldz single model 0.8991.6
118
Aug 17, 2020DiseaseNet Samg2003 single model, DPS RKP,http://sambhavgupta.com0.8991.6
119
Sep 18, 2021LBC-v0 (ensemble) Macao Polytechnic University https://arxiv.org/abs/2210.059540.8991.4
120
Nov 09, 2019BUAA0.8981.8
121
Jan 29, 2022G_Mans_v2 (single model): LibAUC + coat_mini timm lib 0.8981.4
122
May 07, 2021ljc22660.8981.2
123
Jun 03, 2019ForwardModelEnsemble (ensemble) Stanford 0.8971.6
124
Aug 11, 2020NewTrickTest (ensemble) XBSJ 0.8971.6
125
May 28, 2021AccidentNet v1 (single model) Macao Polytechnic Institute 0.8971.2
126
Feb 05, 2020ylz-v01 single model 0.8961.6
127
Aug 26, 2021Stellarium-CheXpert-Local single model https://arxiv.org/abs/2210.059540.8961.4
128
Jun 25, 2019ldz single model 0.8961.4
129
Feb 17, 2020Densenet single 0.8961.4
130
Jul 13, 2019Deadpoppy Single single model 0.8951.8
131
Aug 02, 2019adoudou0.8951.6
132
Sep 11, 2020{koala-large} (single model) SJTU 0.8951.4
133
Dec 26, 2019MM1 ensemble 0.8941.6
134
May 07, 2021MVD121 single model 0.8951.2
135
Jul 21, 2019hust(single model) HUST 0.8951.0
136
Jul 29, 2019zhujieru0.8941.6
136
Jul 28, 2019hycNB0.8941.6
137
Jul 04, 2019U-Random-Ind (single) BHSB 0.8941.0
138
Jun 03, 2019HybridModelEnsemble (ensemble) Stanford 0.8921.6
139
May 11, 2021MVD121-320 single model 0.8911.2
140
Feb 05, 2020ylz-v02 single model 0.8911.0
141
Jul 31, 2019pause single model 0.8901.0
142
Jul 22, 2019Haruka_Hamasaki0.8900.80
142
Aug 27, 2019Haruka_Hamasaki0.8900.80
143
Aug 05, 2019DenseNet169 at 320x320 (single model) Lafayette 0.8891.4
144
Apr 12, 2020LR-baseline (ensemble) IITB 0.8891.4
145
Jul 05, 2019DataAugFTW (single model) University Hannover 0.8881.0
146
Aug 25, 2020{koala} (single model) SJTU 0.8881.0
147
Nov 02, 2022pm_rn50_0.15ppl0.8871.2
148
May 25, 2021Stellarium single model 0.8871.2
149
Nov 01, 2022PrateekMunjal0.8861.0
150
Oct 22, 2019baseline3 single model 0.8861.2
151
May 07, 2021MVR50 single model 0.8860.80
152
Aug 25, 2022MNet-Fix (Single Model) MPU 0.8841.6
153
Jun 04, 2019Coolver XH single model 0.8840.80
154
Mar 24, 2019Naive Densenet single model https://github.com/simongrest/chexpert-entries0.8831.2
155
Mar 03, 2021mhealth_buet (single model) BUET 0.8830.60
156
Apr 17, 2021Aoitori (single model) Macao Polytechnic Institute 0.8820.80
157
Feb 01, 2022{chexpert-classifier}(single model) G42 0.8820.60
158
Mar 01, 2021DearBrave (single model) Macao Polytechnic Institute 0.8820.40
159
Jun 11, 2021AccidentNet V2 (single model) Macao Polytechnic Institute 0.8811.0
160
May 04, 2019{densenet} (single model) Microsoft 0.8801.2
161
Mar 28, 2021Yoake (single model) Macao Polytechnic Institute 0.8790.60
162
May 14, 2019MLC11 Baseline (single-model) Leibniz University Hannover 0.8780.60
163
May 27, 2019null0.8780.80
164
Jul 07, 2019DenseNet single 0.8761.2
165
Nov 22, 2019HCL1 (single model) LTTS 0.8761.0
166
Oct 28, 2019GCN_densenet121-single model0.8751.0
167
Jul 11, 2019MLGCN (single model) sensetime 0.8751.2
168
Feb 22, 2021GreenTeaCalpis (single model) Macao Polytechnic Institute 0.8730.80
169
Jun 03, 2019Multi-CNN (ensemble) VinGroup Big Data Institute 0.8730.40
170
Oct 25, 2021BASELINE ResNet50 ensemble 0.8710.60
171
Aug 16, 2021Baseline DenseNet161 single model http://www.cadcovid19.dcc.ufmg.br/classification0.8680.60
172
Oct 14, 2019baseline1 (single model) Endimension 0.8680.80
173
May 03, 2020DSENet single model 0.8650.60
174
Apr 26, 2019Densenet-Basic Single NUST0.8630.80
175
Aug 12, 2022KD_Mobilenet (single model) IPM 0.8620.80
176
May 27, 2019null0.8620.40
177
Apr 25, 2019{GoDense} (single model) UPenn 0.8611.0
178
May 16, 2019inceptionv3_single_NNU0.8610.40
179
Aug 22, 2022MLKD (Single model) IPM 0.8600.80
180
Jun 29, 2020BASELINE Acorn single model 0.8600.60
181
Mar 05, 2022ErrorNet (single model) IPM 0.8590.60
181
Mar 18, 2022SleepNet (single model) MPI 0.8590.60
182
Oct 22, 2019baseline2 single model 0.8581.0
183
Oct 04, 2022UMLS_CLIP (single model) SJTU 0.8580.0
184
Feb 27, 2022haw02 (single model) IPM 0.8540.80
185
Jul 14, 2020CombinedTrainDenseNet121 (single model) University of Westminster, Silva R. 0.8530.0
186
Apr 28, 2019rayOfLightSingle (Single Model) GeorgiaTech CSE6250 Team58 0.8510.40
187
Apr 24, 2019Model_Team_34 (single model) Gatech 0.8500.60
188
Apr 27, 2019Test model habbes0.8500.40
189
Feb 02, 2021model2_DenseNet121 single 0.8480.60
190
Apr 27, 2019Baseline Ensemble 0.8480.20
191
Nov 01, 2019HinaNet (single model) VietAI http://vietai.org0.8440.40
192
Apr 24, 2019singlehead_models (single model combined) Gatech CSE6250 Team30 0.8420.20
193
Jan 12, 2021mwowra-conditional (single) AGH UST 0.8400.40
194
Apr 24, 2019multihead_model (one model for all pathologies) Gatech CSE6250 Team30 0.8380.40
195
Aug 12, 2022mobilenet (single model) ipm 0.8370.20
196
Jun 13, 2019MLC9_Densenet (single model) Leibniz University Hannover 0.8340.40
197
Sep 24, 2020Grp12BigCNN ensemble 0.8350.0
198
Feb 16, 2020Grp12v2USup2OSamp (ensemble) AITD 0.8300.20
199
Mar 03, 2020null0.8290.20
200
May 16, 2019DNET121-single Ian,Wingspan http://www.wingspan.cn/0.8220.0
201
Feb 03, 2020null0.8210.40
202
Jul 02, 202012ASLv2(single) AITD 0.7690.0
203
May 11, 2019DenseNet121 (single model) hemil10 0.7600.0
204
Jul 02, 202012ASLv1(single) AITD 0.7360.0
205
Jun 23, 2020null0.7320.0
206
Apr 26, 2019rayOfLight (ensemble) GeorgiaTech CSE6250 Team58 0.7270.0
207
Nov 25, 2019BASELINE DenseNet121 single model 0.7240.0
208
Jun 23, 2020null0.7010.0

How can I participate?

Update: the competition is now closed.

How did we collect and label CheXpert?

CheXpert is a large public dataset for chest radiograph interpretation, consisting of 224,316 chest radiographs of 65,240 patients. We retrospectively collected the chest radiographic examinations from Stanford Hospital, performed between October 2002 and July 2017 in both inpatient and outpatient centers, along with their associated radiology reports.

Label Extraction from Radiology Reports

Each report was labeled for the presence of 14 observations as positive, negative, or uncertain. We decided on the 14 observations based on the prevalence in the reports and clinical relevance, conforming to the Fleischner Society’s recommended glossary whenever applicable. We then developed an automated rule-based labeler to extract observations from the free text radiology reports to be used as structured labels for the images.

Our labeler is set up in three distinct stages: mention extraction, mention classification, and mention aggregation. In the mention extraction stage, the labeler extracts mentions from a list of observations from the Impression section of radiology reports, which summarizes the key findings in the radiographic study. In the mention classification stage, mentions of observations are classified as negative, uncertain, or positive. In the mention aggregation stage, we use the classification for each mention of observations to arrive at a final label for the 14 observations (blank for unmentioned, 0 for negative, -1 for uncertain, and 1 for positive).

Use the labeling tool

What is our baseline model?

We train models that take as input a single-view chest radiograph and output the probability of each of the 14 observations. When more than one view is available, the models output the maximum probability of the observations across the views.

Leveraging Uncertainty Labels

The training labels in the dataset for each observation are either 0 (negative), 1 (positive), or u (uncertain). We explore different approaches to using the uncertainty labels during the model training.

  • U-Ignore: We ignore the uncertain labels during training.
  • U-Zeroes: We map all instances of the uncertain label to 0.
  • U-Ones: We map all instances of the uncertain label to 1.
  • U-SelfTrained: We first train a model using the U-Ignore approach to convergence, and then use the model to make predictions that re-label each of the uncertainty labels with the probability prediction outputted by the model.
  • U-MultiClass: We treat the uncertainty label as its own class.

We focus on the evaluation of 5 observations which we call the competition tasks, selected based of clinical importance and prevalence: (a) Atelectasis, (b) Cardiomegaly, (c) Consolidation, (d) Edema, and (e) Pleural Effusion. We compare the performance of the different uncertainty approaches on a validation set of 200 studies on which the consensus of three radiologist annotations serves as ground truth. Our baseline model is selected based on the best performing approach on each competition tasks on the validation set: U-Ones for Atelectasis and Edema, U-MultiClass for Cardiomegaly and Pleural Effusion, and U-SelfTrained for Consolidation.

How is the test designed?

The test set consists of 500 studies from 500 unseen patients. Eight board-certified radiologists individually annotated each of the studies in the test set, classifying each observation into one of present, uncertain likely, uncertain unlikely, and absent. Their annotations were binarized such that all present and uncertain likely cases are treated as positive and all absent and uncertain unlikely cases are treated as negative. The majority vote of 5 radiologist annotations serves as a strong ground truth; the remaining 3 radiologist annotations were used to benchmark radiologist performance.

For each of the 3 individual radiologists and for their majority vote, we compute sensitivity (recall), specificity, and precision against the test set ground truth. To compare the model to radiologists, we plot the radiologist operating points with the model on both the ROC and Precision-Recall (PR) space. We examine whether the radiologist operating points lie below the curves to determine if the model is superior to the radiologists.

How well does the baseline model do on the test set?

The model achieves the best AUC on Pleural Effusion (0.97), and the worst on Atelectasis (0.85). The AUC of all other observations are at least 0.9. On Cardiomegaly, Edema, and Pleural Effusion, the model achieves higher performance than all 3 radiologists but not their majority vote. On Consolidation, model performance exceeds 2 of the 3 radiologists, and on Atelectasis, all 3 radiologists perform better than the model.

Bonus: Extra Dataset From MIT

We're co-releasing our dataset with MIMIC-CXR, a large dataset of 371,920 chest x-rays associated with 227,943 imaging studies sourced from the Beth Israel Deaconess Medical Center between 2011 - 2016. Each imaging study can pertain to one or more images, but most often are associated with two images: a frontal view and a lateral view. Images are provided with 14 labels derived from a natural language processing tool applied to the corresponding free-text radiology reports.

Both our dataset and MIMIC-CXR share a common labeler, the CheXpert labeler, for deriving the same set of labels from free-text radiology reports.

Read MIMIC-CXR paper by Alistair E. W. Johnson, Tom J. Pollard, Seth Berkowitz, Nathaniel R. Greenbaum, Matthew P. Lungren, Chih-ying Deng, Roger G. Mark, Steven Horng

Author Notes

One of the main obstacles in the development of chest radiograph interpretation models has been the lack of datasets with strong radiologist-annotated groundtruth and expert scores against which researchers can compare their models. We hope that CheXpert will address that gap, making it easy to track the progress of models over time on a clinically important task.

Furthermore, we have developed and open-sourced the CheXpert labeler, an automated rule-based labeler to extract observations from the free text radiology reports to be used as structured labels for the images. We hope that this makes it easy to help other institutions extract structured labels from their reports and release other large repositories of data that will allow for cross-institutional testing of medical imaging models.

Finally, we hope that the dataset will help development and validation of chest radiograph interpretation models towards improving healthcare access and delivery worldwide.

In the U.S., about half of all radiology studies are x-rays, mostly of the chest. Chest x-ray studies are even more common around the world. Chest x-ray interpretation is a “bread and butter” problem for radiologists with vital public health implications. Chest x-rays can stop the spread of tuberculosis, detect lung cancer early, and support the responsible use of antibiotics.

Ground truth is critical in evaluating deep learning models in medical imaging and provide the foundation for clinical relevance when interpreting results in this field - this is why we focus a lot of our effort on considering the best available ground truth via a panel of medical sub specialist experts to best understand the clinical implication of our model results.

Downloading the Dataset (v1.0)

Find the dataset on the Stanford AIMI website. The test set labels (and image links) are available on this GitHub repository.

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

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

Read the Paper