Papers › CheXNet: Radiologist-Level Pneumonia Detection on Chest X-Rays with Deep Learning

CheXNet: Radiologist-Level Pneumonia Detection on Chest X-Rays with Deep Learning

14 Nov 2017arXiv:1711.05225archive 2025-07-28

Pranav Rajpurkar, Jeremy Irvin, Kaylie Zhu, Brandon Yang, Hershel Mehta, Tony Duan, Daisy Ding, Aarti Bagul, Curtis Langlotz, Katie Shpanskaya, Matthew P. Lungren, Andrew Y. Ng

We develop an algorithm that can detect pneumonia from chest X-rays at a level exceeding practicing radiologists. Our algorithm, CheXNet, is a 121-layer convolutional neural network trained on ChestX-ray14, currently the largest publicly available chest X-ray dataset, containing over 100,000 frontal-view X-ray images with 14 diseases. Four practicing academic radiologists annotate a test set, on which we compare the performance of CheXNet to that of radiologists. We find that CheXNet exceeds average radiologist performance on the F1 metric. We extend CheXNet to detect all 14 diseases in ChestX-ray14 and achieve state of the art results on all 14 diseases.

PaperPDFCodeCode Syntology ran

In Syntology View this paper on Syntology, its page in Syntology's graph. That page adds which of its functions are also present in other papers' code Syntology holds, with dates, and its dated run record as JSON and a README badge. It also lists the repositories linked to the paper, the abstract and the calls for agents.

Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.

For agents, on Syntology's MCP service (how to connect):

Code

Syntology 37 code samples harvested from 12 repositories linked to this paper: 29 ran (of which 0 constructed an object rather than computing a result; 24 with no instrument failure: 1 honoured, 1 violated, 22 with no contract checked; 5 where Syntology's instrument failed) · 8 unverified. Where Syntology's instrument failed: 5 where our contract draft was wrong; failures of Syntology's instrument, not of the code.

By repository: community (archive-listed): 37 samples from 12 repositories, 29 ran (24 with no instrument failure; 5 where Syntology's instrument failed). The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

Levels written between 2026-09-22 and 2026-09-26 (UTC): the dates Syntology's graph wrote each sample's verification level, not when the code executed.

47 repositories listed; official and paper-mentioned ones first.

AbdulrahmanCE/-pneumonia-detection- mentioned on GitHubMITSyntology: not harvested report
Azure/AzureChestXRay mentioned on GitHubpytorchMITSyntology: 7 samples, 6 ran (0 instrument-failed) · 1 unverified report
DineshAnalyticsandAI/Pneumonia-Detection-Chest-X-Rays mentioned on GitHubSyntology: not harvested report
ElliotY-ML/Pneumonia_Detection_ChestX mentioned on GitHubNOASSERTIONSyntology: not harvested report
MRD-Git/Medical-Applications mentioned on GitHubMITSyntology: not harvested report
MicroprocessorX069/Pneumonia-detection-Dense-Conv-Net mentioned on GitHubpytorchSyntology: not harvested report
Mnpr/OC-DeepLearning mentioned on GitHubMITSyntology: 7 samples, 5 ran (0 instrument-failed) · 2 unverified report
Mnpr/Thoractic-Diseases-Detection mentioned on GitHubMITSyntology: not harvested report
Mnpr/Thoractic_Disease_Detection mentioned on GitHubMITSyntology: not harvested report
Raghuvar/pneumonia_detection_using_X-rays mentioned on GitHubSyntology: not harvested report
Raisony/machine-learning-project mentioned on GitHubSyntology: not harvested report
SGNovice/Disease-detection-using-chest-xrays mentioned on GitHubpytorchMITSyntology: 2 samples, 2 ran (0 instrument-failed) · 0 unverified report
SenWu/emmental-tutorials mentioned on GitHubpytorchMITSyntology: 7 samples, 6 ran (1 instrument-failed) · 1 unverified report
Songloading/Image-Classfication-Tasks mentioned on GitHubpytorchSyntology: not harvested report
TheInfamousWayne/CheXNet mentioned on GitHubpytorchGPL-3.0Syntology: not harvested report
VinGPan/paper_implementations mentioned on GitHubtfMITSyntology: not harvested report
anantvir/Detecting_Localizing_Pneumonia_from_Chest_X-Ray_Scans mentioned on GitHubSyntology: not harvested report
anshuak100/NIH-Chest-X-ray-Dataset mentioned on GitHubSyntology: not harvested report
arnoweng/CheXNet mentioned on GitHubpytorchSyntology: 1 sample, 1 ran (1 instrument-failed) · 0 unverified report
b5510546671/Chest-Xrays-Leaning mentioned on GitHubtfMITSyntology: not harvested report
brucechou1983/CheXNet-Keras mentioned on GitHubtfSyntology: 1 sample, 1 ran (1 instrument-failed) · 0 unverified report
dreamenwalker/Multi-focusNet mentioned on GitHubtfSyntology: not harvested report
dstrick17/Deep-Learning-Project mentioned on GitHubpytorchMITSyntology: 4 samples, 3 ran (0 instrument-failed) · 1 unverified report
fatLime/Predict-Lung-Disease mentioned on GitHubtfSyntology: not harvested report
ferhatkkochan/deeplearning-notes mentioned on GitHubSyntology: not harvested report
fkochan/deeplearning-notes mentioned on GitHubSyntology: not harvested report
gaetandi/cheXpert mentioned on GitHubpytorchSyntology: not harvested report
gshashank84/CheXNet mentioned on GitHubpytorchSyntology: not harvested report
iamrehman/chestXrayDiseaseDetection mentioned on GitHubSyntology: not harvested report
jm12138/Paddle-CheXNet mentioned on GitHubpaddleSyntology: not harvested report
jrzech/reproduce-chexnet mentioned on GitHubpytorchBSD-3-ClauseSyntology: 3 samples, 1 ran (0 instrument-failed) · 2 unverified report
karandesaiii/CheXNet mentioned on GitHubpytorchGPL-3.0Syntology: not harvested report
liyu10000/pneumoconiosis mentioned on GitHubpytorchSyntology: not harvested report
nhatanh81096/Pneumonia-Detector mentioned on GitHubSyntology: not harvested report
nsourlos/pneumonia_detection mentioned on GitHubSyntology: not harvested report
odokumaci/pneumonia-rsna mentioned on GitHubSyntology: 2 samples, 2 ran (1 instrument-failed) · 0 unverified report
omrifried/NIH_XRay_Faster_RCNN mentioned on GitHubpytorchnot reachable when probed 2026-09-18 — repositories for recent papers often appear after camera-readySyntology: not harvested report
omrifried/RSNA_Chest_X-Ray_Faster_RCNN mentioned on GitHubpytorchnot reachable when probed 2026-09-18 — repositories for recent papers often appear after camera-readySyntology: not harvested report
rahulcoding/CheXNet mentioned on GitHubpytorchSyntology: 1 sample, 1 ran (0 instrument-failed) · 0 unverified report
skaravind/Whatsapp-Radiologist mentioned on GitHubMITSyntology: 1 sample, 0 ran · 1 unverified report
thibaultwillmann/CheXNet-Pytorch mentioned on GitHubpytorchSyntology: 1 sample, 1 ran (1 instrument-failed) · 0 unverified report
thtang/CheXNet-with-localization mentioned on GitHubpytorchGPL-3.0Syntology: not harvested report
trangiabach/Lung-Iris mentioned on GitHubtfSyntology: not harvested report
vkduy19/paper_implementations-master mentioned on GitHubtfMITSyntology: not harvested report
zoogzog/chexnet mentioned on GitHubpytorchSyntology: not harvested report
dagshub.com/nirbarazida/CheXNet Syntology: not harvested report
ekagra-ranjan/AE-CNN pytorchSyntology: not harvested report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

Code Syntology ran Syntology

37 samples harvested: 29 ran (of which 0 constructed an object rather than computing a result; 24 with no instrument failure: 1 honoured, 1 violated, 22 with no contract checked; 5 where Syntology's instrument failed) · 8 unverified. “Where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. Syntology's record for this page has not changed since , the first build that kept a record date for it; when this build read Syntology's graph is in the build record. That date is not when the samples ran.

1ran · honoured contract
1ran · violated contract
5ran · our draft was wrong
22ran
8unverified

Licence: 13 of the 37 samples are pointer only, meaning Syntology does not serve that copy's text. For 1 of them, this paper's copy is under a permissive licence and cleared, but the stored copy of the same code that Syntology serves is not; the licence label's tooltip gives Syntology's recorded reason. This page shows no code text for any sample; each one links to its file in the repository.

Harvested from 12 repositories linked to this paper, official or community; the list below is grouped by repository, each group headed by its name and what it is to the paper. “Ran” means the sample executed on a synthesized input. It does not mean the output is correct, and nothing here reproduces the paper's results. A line beginning “fixture:” under a sample that ran gives the arguments Syntology's fixture called the sample with, each as name:type/rank/element kind (? where none was recorded), and the type of what the fixture's run returned, exactly as the harness recorded them; the arguments and the returned type were recorded by two separate runs of the same fixture. No output value is shown, and a returned type says nothing about whether the output was right. “Level recorded” gives the UTC date when Syntology's graph wrote the sample's verification level, not when the code executed; where the level was written before Syntology's graph kept that date, the row says “level recorded, date not recorded”. For 1 sample that ran, the graph records a signature this page does not show: an argument's recorded type or element kind is a printout of an object in Syntology's harness (such as a mock object, a class or a pandas printout), not the type of an input, so it does not describe the call's shape. “Honoured” and “violated” refer to a contract Syntology drafted from the code itself. “Our draft was wrong” and “the contract check could not run” are failures of Syntology's instrument, not of the code: the sample ran on Syntology's synthesized input, and then the drafted contract did not describe it, or the check itself raised an error (RAISES), lacked a dependency (DEP_MISSING) or ran out of time (TIMEOUT); hover the label for which. A metamorphic tier, where shown, is evidence of the output's shape, not that the sample implements the method.

Each sample ends with its code_sha256. A sample's code_sha256 is Syntology's identity for that exact code. It is printed in full (16 hexadecimal characters for every sample in this build), and get_code(code_sha256="…") takes it exactly as printed. An agent calls it on Syntology's MCP service (how to connect); click an identity to copy that call.

Repository labels, per sample. official repository: The archive marks this repository official for the paper. named in the paper: The archive records that the paper mentions this repository; it is not marked official. community (archive-listed): In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper. found in paper text by Syntology: Syntology found this repository in the paper's own text; whether it is the authors' implementation is not asserted. community: Not in the archive's code links for this paper; a community repository Syntology harvested. Samples are grouped by repository: a repository marked official first, then by how directly the repository is tied to the paper, then in the archive's order; never by how many ran. Licence labels name the repository's licence as recorded at harvest. “Pointer only” means Syntology does not serve that copy's text, for one of six reasons: no licence file was found; the licence was not identified; the licence is recorded as permissive but that copy's record is not marked cleared; the licence is outside the permissive list Syntology serves text under (MIT, Apache-2.0, BSD and similar); this paper's copy was not located, so its licence is not recorded; or this paper's copy is cleared, but the stored copy of the same code that Syntology serves is not. Some licences outside that list permit redistribution, such as WTFPL, and GPL-3.0 under its conditions; they are simply not on the list. Hover a licence label for the reason. File links open the file on GitHub at the default branch, which may have changed since the harvest.

A function or class name links to its page when the name occurs in the harvested code of at least 5 papers; the name is a string, not an identity. A census tag appears when Syntology's census ran implementations with that name on one shared input per bucket: it gives how many were compared, from how many papers, and how many distinct outputs they produced, and names this sample's bucket when this sample was one of them.

Azure/AzureChestXRay community (archive-listed) 7 samples, 6 ran (0 instrument-failed) · 1 unverified
as_string_b64encoded_pickled AzureChestXRay_AMLWB/Code/src/score_image_and_cam.py ran MIT recorded; this copy not marked cleared · pointer only · 7c43090ecf7d0f02 · report fixture: signature input_object:dict/0/? · returned str · level recorded 2026-09-26
build_model in 469 papers AzureChestXRay_AMLWB/Code/src/azure_chestxray_keras_utils.py ran MIT recorded; this copy not marked cleared · pointer only · a46ebda77ad3d0aa · report fixture: signature crt_densenet_function:callable/0/? · returned Functional · level recorded 2026-09-26
get_files_in_dir AzureChestXRay_AMLWB/Code/src/azure_chestxray_utils.py ran MIT recorded; this copy not marked cleared · pointer only · 72f20cc06cb7434e · report fixture: signature crt_dir:str/0/str · returned list · level recorded 2026-09-26
normalize_nd_array AzureChestXRay_AMLWB/Code/src/azure_chestxray_utils.py ran fingerprinted MIT recorded; this copy not marked cleared · pointer only · 387c1efccf13f7e6 · report fixture: signature crt_array:ndarray/2/float · returned ndarray · level recorded 2026-09-26
plot_cam_results AzureChestXRay_AMLWB/Code/src/azure_chestxray_cam.py ran MIT recorded; this copy not marked cleared · pointer only · e4aacbed9ef38d69 · report fixture: signature crt_blended_image:ndarray/3/float, crt_cam_image:ndarray/2/float, crt_xray_image:ndarray/2/float, map_caption:str/0/str · returned BytesIO · level recorded 2026-09-26
unpickled_b64decoded_as_bytes AzureChestXRay_AMLWB/Code/src/score_image_and_cam.py ran MIT recorded; this copy not marked cleared · pointer only · 494670e9ddb36e8d · report fixture: signature input_object:str/0/str · returned dict · level recorded 2026-09-26
get_score_and_cam_picture AzureChestXRay_AMLWB/Code/src/azure_chestxray_cam.py unverified MIT recorded; this copy not marked cleared · pointer only · 0f1e64d7ffdfee1e · report
Mnpr/OC-DeepLearning community (archive-listed) 7 samples, 5 ran (0 instrument-failed) · 2 unverified
false_positives Utils/eval_utils.py ran MIT (permissive) · 99e667e09872acea · report fixture: signature y:ndarray/1/int, y_pred:ndarray/1/float, threshold:float/0/float · returned int64 · level recorded 2026-09-26
get_roc_curve Utils/img_utils.py ran MIT (permissive) · d811f5c1c652d270 · report fixture: returned list · level recorded 2026-09-26
get_weighted_loss Utils/loss_utils.py ran MIT (permissive) · b782f8a4ff94df4d · report fixture: signature pos_weights:ndarray/1/float, neg_weights:ndarray/1/float, epsilon:float/0/float · returned function · level recorded 2026-09-26
true_negatives Utils/eval_utils.py ran MIT (permissive) · 3fb4e876ce3e9212 · report fixture: signature y:ndarray/1/int, y_pred:ndarray/1/float, threshold:float/0/float · returned int64 · level recorded 2026-09-26
true_positives Utils/eval_utils.py ran MIT (permissive) · 3d0485840aa0f58c · report fixture: signature y:ndarray/1/int, y_pred:ndarray/1/float, threshold:float/0/float · returned int64 · level recorded 2026-09-26
get_mean_std_per_batch Utils/img_utils.py unverified MIT (permissive) · 9a63d14257252b9a · report
load_image in 273 papers Utils/img_utils.py unverified MIT (permissive) · bc1bdcf24dd0d85e · report
SGNovice/Disease-detection-using-chest-xrays community (archive-listed) 2 samples, 2 ran (0 instrument-failed) · 0 unverified
get_tensor in 8 papers commons.py ran MIT (permissive) · d4a498230f440c39 · report fixture: signature image_bytes:bytes/0/? · returned Tensor · level recorded 2026-09-26
mila commons.py ran fingerprinted MIT (permissive) · 0c0269d8f261c2e5 · report fixture: signature input:Tensor/2/float, beta:float/0/float · returned Tensor · level recorded 2026-09-26
SenWu/emmental-tutorials community (archive-listed) 7 samples, 6 ran (1 instrument-failed) · 1 unverified
ce_loss in 34 papers chexnet/task.py ran MIT (permissive) · 463d3f2f4d6be38d · report fixture: signature module_name:str/0/str, immediate_ouput_dict:dict/0/?, Y:Tensor/1/int, active:Tensor/1/bool · returned Tensor · level recorded 2026-09-26
get_data_transforms chexnet/transforms.py ran fingerprinted MIT (permissive) · 39ba58dee4170072 · report fixture: signature dataset_name:str/0/str · returned dict · level recorded 2026-09-26
get_tasks in 21 papers glue/download_glue_data.py ran · our draft was wrong MIT (permissive) here; the stored copy is pointer only · 18962b43885bc12f · report fixture: signature task_names:str/0/str · returned list · level recorded 2026-09-22
mse_loss in 73 papers
census: 8 implementations from 12 papers, 6 distinct outputs across 4 buckets, one shared input per bucket
glue/glue_tasks.py ran MIT (permissive) · 7807bb921c12897c · report fixture: signature task_name:str/0/str, immediate_ouput_dict:dict/0/?, Y:Tensor/2/float, active:Tensor/1/bool · returned Tensor · level recorded 2026-09-26
output chexnet/task.py ran MIT (permissive) · f5559f1c12f663be · report fixture: signature module_name:str/0/str, immediate_ouput_dict:dict/0/? · returned Tensor · level recorded 2026-09-26
output glue/glue_tasks.py ran MIT (permissive) · 1ce4ca882a4b2472 · report fixture: signature task_name:str/0/str, immediate_ouput_dict:dict/0/? · returned Tensor · level recorded 2026-09-26
ce_loss in 34 papers glue/glue_tasks.py unverified MIT (permissive) · 188aff3170045ab9 · report
arnoweng/CheXNet community (archive-listed) 1 sample, 1 ran (1 instrument-failed) · 0 unverified
compute_AUCs model.py ran · our draft was wrong fingerprinted no licence file found · pointer only · fc2e02e8ee2be889 · report fixture: signature gt:Tensor/2/float, pred:Tensor/2/float · returned list · level recorded 2026-09-22
brucechou1983/CheXNet-Keras community (archive-listed) 1 sample, 1 ran (1 instrument-failed) · 0 unverified
get_output_layer cam.py ran · our draft was wrong MIT (permissive) · 548c0fe9e1ac8315 · report fixture: signature model:Model/0/?, layer_name:str/0/str · returned Layer · level recorded 2026-09-22
dstrick17/Deep-Learning-Project community (archive-listed) 4 samples, 3 ran (0 instrument-failed) · 1 unverified
generate_gradcam XRay_app/utils/model_utils.py ran MIT (permissive) · 2bd1a227991d09e4 · report fixture: signature model:callable/0/?, input_tensor:Tensor/3/float, target_class:int/0/int, device:str/0/str · returned ndarray · level recorded 2026-09-26
predict in 126 papers XRay_app/utils/model_utils.py ran MIT (permissive) · 1de89e0659407359 · report fixture: signature model:callable/0/?, img_tensor:Tensor/4/float, device:str/0/str · returned dict · level recorded 2026-09-26
preprocess_image in 65 papers
census: 4 implementations from 6 papers, 2 distinct outputs on one shared input
XRay_app/utils/preprocessing.py ran MIT (permissive) · 0ce6f4b5e608f7a7 · report fixture: signature img:Image/0/? · returned Tensor · level recorded 2026-09-26
load_model in 479 papers XRay_app/utils/model_utils.py unverified MIT (permissive) · 7ae48b7e9a8d2e9b · report
jrzech/reproduce-chexnet community (archive-listed) 3 samples, 1 ran (0 instrument-failed) · 2 unverified
calc_cam visualize_prediction.py ran BSD-3-Clause (permissive) · 7f830b60d3c5b796 · report fixture: signature x:Tensor/4/float, label:str/0/str, model:callable/0/? · returned ndarray · level recorded 2026-09-26
show_next visualize_prediction.py unverified BSD-3-Clause (permissive) · 831d63f3b9377e8b · report
train_model in 103 papers model.py unverified BSD-3-Clause (permissive) · 41e9cbb003cda3c5 · report
odokumaci/pneumonia-rsna community (archive-listed) 2 samples, 2 ran (1 instrument-failed) · 0 unverified
get_dicom_fps pnclassify.py ran · our draft was wrong fingerprinted no licence file found · pointer only · c64618410ac55c1d · report fixture: signature dicom_dir:str/0/str · returned list · level recorded 2026-09-22
lrate_epoch pnclassify.py ran · honoured contract fingerprinted no licence file found · pointer only · a5d85630dbde2484 · report fixture: signature epoch:int/0/int · returned float · level recorded 2026-09-22
rahulcoding/CheXNet community (archive-listed) 1 sample, 1 ran (0 instrument-failed) · 0 unverified
func in 29 papers
census: 5 implementations from 5 papers, 5 distinct outputs across 4 buckets, one shared input per bucket
denseNet_localization.py ran · violated contract fingerprinted GPL-3.0 (copyleft) · pointer only · 7fc4e9d73fe8bdc0 · report fixture: signature keys_passed:str/0/str · returned str · level recorded 2026-09-22
skaravind/Whatsapp-Radiologist community (archive-listed) 1 sample, 0 ran · 1 unverified
caption loreal.py unverified MIT (permissive) · 8b83b4cf085aa1e2 · report
thibaultwillmann/CheXNet-Pytorch community (archive-listed) 1 sample, 1 ran (1 instrument-failed) · 0 unverified
tile in 109 papers
census: 5 implementations from 7 papers, 4 distinct outputs across 3 buckets, one shared input per bucket this sample: bucket 1 of 3, arg 1: rank 3, kind float, dtype float32
model.py ran · our draft was wrong fingerprinted no licence file found · pointer only · 732062e802565311 · report fixture: signature a:Tensor/3/float, dim:int/0/int, n_tile:int/0/int · returned Tensor · level recorded 2026-09-22

Tasks

Pneumonia Detection

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Pneumonia Detection ChestX-ray14 CheXNet AUROC 0.844 #3 of 5 Archive leaderboard report
Pneumonia Detection ChestX-ray14 CheXNet FLOPS 2800M #3 of 5 Archive leaderboard report
Pneumonia Detection ChestX-ray14 CheXNet Params 7.0M #3 of 5 Archive leaderboard report

Ranks are positions in the archive's leaderboards as they stood at the 2025-07-28 snapshot. Results published since then are not among these rows, so a rank here is not a current standing.

Methods

Introduced by this paper: CheXNet

1x1 ConvolutionAverage PoolingBatch NormalizationCheXNetConcatenated Skip ConnectionConvolutionDense BlockDense ConnectionsDropoutGlobal Average PoolingKaiming InitializationMax PoolingReLUSoftmax

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections