Papers › CheXbert: Combining Automatic Labelers and Expert Annotations for Accurate Radiology...

CheXbert: Combining Automatic Labelers and Expert Annotations for Accurate Radiology Report Labeling Using BERT

20 Apr 2020arXiv:2004.09167archive 2025-07-28

Akshay Smit, Saahil Jain, Pranav Rajpurkar, Anuj Pareek, Andrew Y. Ng, Matthew P. Lungren

The extraction of labels from radiology text reports enables large-scale training of medical imaging models. Existing approaches to report labeling typically rely either on sophisticated feature engineering based on medical domain knowledge or manual annotations by experts. In this work, we introduce a BERT-based approach to medical image report labeling that exploits both the scale of available rule-based systems and the quality of expert annotations. We demonstrate superior performance of a biomedically pretrained BERT model first trained on annotations of a rule-based labeler and then finetuned on a small set of expert annotations augmented with automated backtranslation. We find that our final model, CheXbert, is able to outperform the previous best rules-based labeler with statistical significance, setting a new SOTA for report labeling on one of the largest datasets of chest x-rays.

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

The archive's official repository (stanfordmlgroup/CheXbert) was not harvested; the 17 samples below come from 3 community repositories.

Syntology 17 code samples harvested from 3 repositories linked to this paper: 15 ran (of which 0 constructed an object rather than computing a result; 10 with no instrument failure: 0 honoured, 0 violated, 10 with no contract checked; 5 where Syntology's instrument failed) · 2 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): 17 samples from 3 repositories, 15 ran (10 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.

No sample is linked to this paper from 1 of its repositories that Syntology harvested for other papers:

Levels written between 2026-09-22 and 2026-09-25 (UTC): the dates Syntology's graph wrote each sample's verification level, not when the code executed.

stanfordmlgroup/CheXbert officialmentioned in papermentioned on GitHubpytorchSyntology: not harvested report
abachaa/mediqa2021 mentioned on GitHubSyntology: not harvested report
mmcdermott/chexpertplusplus mentioned on GitHubpytorchSyntology: not harvested report
rajpurkarlab/cxr-report-metric mentioned on GitHubpytorchMITSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to RadGraph: Extracting Clinical Entities and Relations from Radiology Reports (arXiv:2106.14463; that paper's own run record: 7 ran (of which 0 constructed an object rather than computing a result; 7 with no instrument failure: 0 honoured, 0 violated, 7 with no contract checked; 0 where Syntology's instrument failed) · 2 unverified); nothing checks that they implement this paper's method. report
wjhou/icon mentioned on GitHubpytorchApache-2.0Syntology: 7 samples, 5 ran (0 instrument-failed) · 2 unverified report
wjhou/organ mentioned on GitHubpytorchApache-2.0Syntology: 3 samples, 3 ran (0 instrument-failed) · 0 unverified report
wjhou/recap mentioned on GitHubpytorchApache-2.0Syntology: 7 samples, 7 ran (5 instrument-failed) · 0 unverified 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.

A paper named beside a repository with no sample linked to this paper is shown with that paper's own run record, not this paper's: “ran” means executed on a synthesized input, not that the code is correct, and “where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. Papers are listed in arXiv-id order, at most three per repository.

Code Syntology ran Syntology

17 samples harvested: 15 ran (of which 0 constructed an object rather than computing a result; 10 with no instrument failure: 0 honoured, 0 violated, 10 with no contract checked; 5 where Syntology's instrument failed) · 2 unverified. “Where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. Syntology's record for this page last changed ; when this build read Syntology's graph is in the build record. That date is not when the samples ran.

5ran · our draft was wrong
10ran
2unverified

Licence: 3 of the 17 samples are pointer only, meaning Syntology does not serve that copy's text. For 3 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 3 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”. “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.

wjhou/icon community (archive-listed) 7 samples, 5 ran (0 instrument-failed) · 2 unverified
extract_temporal_info src_stage1/dataset_ende.py ran Apache-2.0 (permissive) · a58f9ee70337dd6e · report fixture: signature samples:list/1/dict, ref_samples:list/1/dict, temporal_ids:dict/0/? · returned list · level recorded 2026-09-24
f1 in 57 papers src_retrieval/retrieval.py ran Apache-2.0 (permissive) · 6d01795fce054855 · report fixture: signature x:set/0/?, y:set/0/? · returned float · level recorded 2026-09-24
label_func eval/eval_consistency.py ran Apache-2.0 (permissive) · 1cecec4bb2430637 · report fixture: signature texts:list/1/str, model:callable/0/?, tokenizer:callable/0/?, max_batch_size:int/0/int · returned list · level recorded 2026-09-24
load_images in 48 papers src_stage1/dataset_ende.py ran Apache-2.0 (permissive) · b878a058d12646b0 · report fixture: signature root_path:str/0/str, image_paths:list/1/list · returned dict · level recorded 2026-09-24
process_examples src_stage1/dataset_ende.py ran Apache-2.0 (permissive) · 47141bbf9a391e9d · report fixture: signature examples:dict/0/? · returned tuple · level recorded 2026-09-24
compute_ce_metric src_stage1/chexbert_eval.py unverified Apache-2.0 (permissive) · a5d48d0faff8e506 · report
load_chexbert src_stage1/chexbert_eval.py unverified Apache-2.0 (permissive) · 6b14457458f396df · report
wjhou/organ community (archive-listed) 3 samples, 3 ran (0 instrument-failed) · 0 unverified
load_mentions src/plan_extraction.py ran Apache-2.0 (permissive) · 673d3788abc824eb · report fixture: signature folder:str/0/str · returned dict · level recorded 2026-09-24
load_pmi_mentions src/plan_extraction.py ran Apache-2.0 (permissive) · 4cb2e174305de20f · report fixture: signature path:str/0/str, topk:int/0/int · returned defaultdict · level recorded 2026-09-24
stemming src/plan_extraction.py ran Apache-2.0 (permissive) · 41fd9b56fd1a9569 · report fixture: signature stemmer:PorterStemmer/0/?, tokens:list/1/str · returned list · level recorded 2026-09-24
wjhou/recap community (archive-listed) 7 samples, 7 ran (5 instrument-failed) · 0 unverified
cook_refs in 36 papers pycocoevalcap/cider/cider_scorer.py ran · our draft was wrong Apache-2.0 (permissive) here; the stored copy is pointer only · 4c1b107103b7c856 · report fixture: signature refs:list/1/str, n:int/0/int · returned list · level recorded 2026-09-22
cook_refs in 36 papers pycocoevalcap/bleu/bleu_scorer.py ran · our draft was wrong Apache-2.0 (permissive) · 7586e1d32f7325f7 · report fixture: signature refs:list/1/str, eff:str/0/str, n:int/0/int · returned tuple · level recorded 2026-09-25
cook_test in 35 papers pycocoevalcap/cider/cider_scorer.py ran · our draft was wrong fingerprinted Apache-2.0 (permissive) here; the stored copy is pointer only · 3573c4bc85f65dfd · report fixture: signature test:str/0/str, n:int/0/int · returned defaultdict · level recorded 2026-09-22
cook_test in 35 papers pycocoevalcap/bleu/bleu_scorer.py ran Apache-2.0 (permissive) · bc5342cb883ef9da · report fixture: signature test:str/0/str, refs:tuple/1/list, eff:NoneType/0/?, n:int/0/int · returned dict · level recorded 2026-09-25
precook in 38 papers pycocoevalcap/bleu/bleu_scorer.py ran · our draft was wrong fingerprinted Apache-2.0 (permissive) · ec4448373d72d636 · report fixture: signature s:str/0/str, n:int/0/int, out:bool/0/bool · returned tuple · level recorded 2026-09-22
precook in 38 papers pycocoevalcap/cider/cider_scorer.py ran · our draft was wrong fingerprinted Apache-2.0 (permissive) here; the stored copy is pointer only · 9560e3e3e41bc1b2 · report fixture: signature s:str/0/str, n:int/0/int, out:bool/0/bool · returned defaultdict · level recorded 2026-09-22
process_examples src_stage1/data_process_ende.py ran Apache-2.0 (permissive) · a56bdab712ac729b · report fixture: signature examples:dict/0/? · returned tuple · level recorded 2026-09-24

Tasks

Feature Engineering

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

Methods

AdamAttentionAttention DropoutBERTDense ConnectionsDropoutLayer NormalizationLinear LayerLinear Warmup With Linear DecayMulti-Head AttentionResidual ConnectionSoftmaxWeight DecayWordPiece

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