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

Pranav Rajpurkar, Jeremy Irvin, Andrew Y. Ng, et al. · arXiv preprint · 2017 · medicine · record rajpurkar2017-chexnet
tag layer · index · concepts · authors · עברית

Where this record's text came from. faceted 2026-08 by reading the locally held text (pdftext); every evidence string verified as an exact substring of that text before merging. The third limitation quote is truncated exactly where the PDF extraction interrupts the sentence with the running header and Figure 2 captions; it is copied verbatim up to that break, including the source's double negative 'were not permitted'. The 'three limitations / two listed' gap is recorded as a limitation facet because it is what the paper says about itself. Outperforming Yao et al. (2017) and Wang et al. (2017) on AUROC is a benchmark comparison, not one of the four relation types, so it is left out of claim_relations. The ground truth for pneumonia labels comes from automatic extraction on radiology reports, which the paper states but does not flag as a limitation, so it is not recorded as one. 2026-08-14 and 2026-08-16 schema-0.3 passes: every quote verified as an exact substring of the staged text and anchored at merge time; concept terms verified present; every edge endpoint an existing node.

Some quotes on this page contain (cid:NN). The PDF this text was extracted from encodes 4 characters in a way that names no letter, so the extractor could not say what they were. The quotes keep them because a quote is reproduced exactly or it proves nothing — the marks are the source’s, not the tagging’s.

How to read this page. The article itself is not reproduced here — this paper is not cleared for redistribution, so what follows is the tag layer alone. The evidence sentences are withheld with the article. The table at the foot lists every tag the record carries; each row names the facet it belongs to, and the whose words column says whether the tag records the paper's own wording or the tagger's sentence about the paper. Every tag links to each other paper in the corpus carrying it. The machine-readable edition of the same thing is the TEI file beside this one, where the tags live in standOff, and the article is at its publisher via the link below. When we have changed our mind. Some entries in the table begin with a word in capitals and the reason for it. EVIDENCE CORRECTED — the finding still stands, but we had quoted the wrong sentence from the paper, and the quotation has been replaced with the right one. RETRACTED — the entry itself was wrong; it stays on the page, marked, with the reason, rather than being deleted. WITHDRAWN AND REPLACED — the entry was wrong, and a corrected version of it appears in the entries below. Each mark carries its own reason, in brackets, because the reasons differ from one entry to the next. An entry we have WITHDRAWN is removed from this page and kept in the record, with its reason. A line reading Audit and a date is a later re-reading of the entry against its whole sentence: DOUBTFUL means it was kept, and the reason says what is loose about it. Quotation marks inside the tagger's sentence. Where a tag is the tagger's own sentence, a phrase in quotation marks inside it is borrowed from the paper — the tagger's wording around it is not. The paper's own sentence is the evidence quote for that row; on this page it is withheld with the article, and the article is at its publisher. Nothing inside quotation marks anywhere on this page is ours: if it is quoted, it is the paper's. Whose words a concept carries. A concept entry records a term the paper itself uses, so the term, the sense given for it, and its evidence are the paper's own words, quoted where the paper fixes them. This is the opposite of a sense entry in the tag table, which is the tagger's sentence about how the paper uses a term. Where a concept entry could not be grounded in the paper's words, the entry says so on its own row.

Other fields define these differently the same word, defined another way in another discipline
deep learning 11 fields · disease 6 fields · ground truth 5 fields · F1 score 3 fields · standard-deviation 3 fields · bootstrap 2 fields · and 4 more →

Tags on this paper

Every tag the record carries, each linking to every other paper in the corpus that carries it. A tag appears here whether or not its words occur in the article — the spans below are only the ones a sentence in this paper licenses. Of the 9 concept tags on this paper, 5 are grounded in a quoted sentence.

deep learning convolutional neural network medical imaging computer-aided diagnosis F1 score ground truth pneumonia detection task pathology labels automatic extraction methods the binary cross entropy is weighted by the prevalence of the OPPOSITE class - w+ is the negative share and w- the positive share - so the rarer label carries the larger weight dense connections improve the flow of information and gradients through the network, which is what the paper credits for making the optimization of a very deep network tractable the network is not trained from scratch: the final layer is replaced and the rest starts from ImageNet weights the learning rate is cut only when the validation loss stops improving, and the returned model is the best validation checkpoint rather than the last each radiologist and the model are scored against the OTHER FOUR radiologists' labels, taken as ground truth, and the reported figure is the mean of those four scores significance is taken from the DIFFERENCE between the two averages computed on the same bootstrap samples, and read off whether the 95% CI on that difference contains zero the heatmap is the weighted sum of the final convolutional feature maps, weighted by the final classification layer's own weights for that pathology, then upscaled and overlaid CheXNet radiologist pneumonia X-ray DenseNet chest disease network images ChestX-ray14 dataset chest X-ray image F1 metric bootstrap confidence-interval confidence intervals mean mean of standard-deviation standard deviation statistical-significance statistically significantly system-or-tool-building

Legend

relation to other work	`claim_relations`	how this paper stands to another: agrees, contradicts, extends, qualifies
claim type	`claim_type`	the shape of the claim: existence, mechanism, method, critique, prediction, null
concept edge	`concept_edges`	an asserted relation between two concepts, with the sentence asserting it
concept	`concepts`	an idea the paper works with, quoted where the paper uses it
content tag	`content_tags`	a finding, definition, quantity, statistic or variable named in the paper
control	`controls`	an experiment run to eliminate a rival explanation
limitation	`limitations`	what the paper says its evidence cannot support
mechanism	`mechanisms`	how the reported effect is said to come about
method	`method`	how the paper produced its evidence
phenomenon	`phenomenon`	the effect or regularity under study
sense	`senses`	a distinct use of a term, quoted where the paper fixes it
transfer	`transfers`	a method or concept carried in from another field

The paper

The full text is not reproduced here. This article is not cleared for redistribution, so the page carries the tag layer only. Its evidence sentences are withheld; the grounding status remains with each tag, and the article itself is at https://arxiv.org/abs/1711.05225. The reading view exists for the papers whose licence permits it.

Every tag on this page

claim_relations 4 · claim_type 1 · concept_edges 1 · concepts 5 · content_tags 16 · controls 1 · limitations 8 · mechanisms 7 · method 1 · phenomenon 1 · senses 3 · transfers 1

Relations on this page carry a quotation for the claim. Where a relation was separately evidenced — and so tested against the vocabulary for its type — the row says so; none of 1 relation here carry that mark. The rest are the tagger’s reading of the sentence quoted beside them.

facet	tag	field	conf.	whose words
claim_type	method Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above.	`claim_type`		the paper's words
phenomenon	pneumonia detection on chest radiographs Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above.	`phenomenon`		the paper's words
method	system-or-tool-building Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above. also in: system-or-tool-building	`method`		the paper's words
mechanisms	mechanisms Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above. also in: the binary cross entropy is weighted by the prevalence of the OPPOSITE class - w+ is the negative share and w- the positive share - so the rarer label carries the larger weight	`mechanisms[0]`	0.9	the tagger's words
mechanisms	mechanisms Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above. also in: dense connections improve the flow of information and gradients through the network, which is what the paper credits for making the optimization of a very deep network tractable	`mechanisms[1]`	0.9	the tagger's words
mechanisms	mechanisms Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above. also in: the network is not trained from scratch: the final layer is replaced and the rest starts from ImageNet weights	`mechanisms[2]`	0.9	the tagger's words
mechanisms	mechanisms Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above. also in: the learning rate is cut only when the validation loss stops improving, and the returned model is the best validation checkpoint rather than the last	`mechanisms[3]`	0.9	the tagger's words
mechanisms	that this makes reader agreement the standard rather than the presence of disease is already recorded on this record as a limitation, not claimed here Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above. also in: each radiologist and the model are scored against the OTHER FOUR radiologists' labels, taken as ground truth, and the reported figure is the mean of those four scores	`mechanisms[4]`	0.9	the tagger's words
mechanisms	mechanisms Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above. also in: significance is taken from the DIFFERENCE between the two averages computed on the same bootstrap samples, and read off whether the 95% CI on that difference contains zero	`mechanisms[5]`	0.9	the tagger's words
mechanisms	mechanisms Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above. about this quote: 2026-08-16: FAILED GLYPH INSIDE THIS QUOTE. The staged text reads "Formally, Mc = (cid:88) k wc,kfk" - (cid:88) is the SUMMATION SIGN, so the formula is Mc = sum over k of w_c,k * f_k, the weighted sum of feature maps the sentence has just described in words. The prose on either side is intact and states the mechanism; only the symbol is lost. The quote is an exact substring of the staged file; the file is incomplete here, not the tag. also in: the heatmap is the weighted sum of the final convolutional feature maps, weighted by the final classification layer's own weights for that pathology, then upscaled and overlaid	`mechanisms[6]`	0.9	the tagger's words
limitations	the paper identifies three limitations of its radiologist comparison Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above. what this limits: the radiologist comparison, which the authors themselves qualify: WE IDENTIFY THREE LIMITATIONS OF THIS COMPARISON	`limitations[0]`		the tagger's words
limitations	The paper announces three limitations of the radiologist comparison but enumerates only two (a 'First' and a 'Third'); the second is missing from the text. Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above. duplicate of: limitations[0] · what this limits: the completeness of that qualification: the paper announces three limitations and prints a FIRST and a THIRD with no SECOND. Verified in the version of record, arXiv 1711.05225v3 (25 Dec 2017), not only in our staged copy - so this is the paper's own text and not a lost sentence in extraction	`limitations[1]`		the tagger's words
limitations	Only frontal radiographs were shown to both model and radiologists, although a share of accurate diagnoses requires the lateral view. Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above. what this limits: the diagnostic setup for both model and radiologists: ONLY FRONTAL RADIOGRAPHS WERE PRESENTED ... BUT IT HAS BEEN SHOWN THAT UP TO 15% OF ACCURATE DIAGNOSES REQUIRE THE LATERAL VIEW	`limitations[2]`		the tagger's words
limitations	Neither model nor radiologists could use patient history, which is known to change radiologist diagnostic performance. Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above. what this limits: the comparison against clinical practice: NEITHER THE MODEL NOR THE RADIOLOGISTS WERE ... PERMITTED TO USE PATIENT HISTORY, WHICH HAS BEEN SHOWN TO DECREASE RADIOLOGIST DIAGNOSTIC PERFORMANCE	`limitations[3]`		the tagger's words
limitations	The standard the model is measured against is the other radiologists' labels, not the presence of disease. Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above. what this limits: the claim that this model exceeds practicing radiologists: the F1 score for each radiologist and for the model is computed against each of the other four radiologists' labels as ground truth, so the comparison is agreement with those four rather than detection of disease	`limitations[4]`	1.0	the tagger's words
limitations	The training labels were produced by text extraction from reports rather than by anyone looking at the images. Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above. what this limits: the labels this model was trained on: they were assigned by automatic extraction methods applied to radiology reports, so a label records what a report said rather than what an image shows	`limitations[5]`	1.0	the tagger's words
limitations	Every image the extractor did not mark becomes a negative example. Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above. what this limits: the negative class in this task: images are negative when pneumonia is not among the annotated pathologies, so absence of a label is used in place of absence of the condition	`limitations[6]`	1.0	the tagger's words
limitations	The model reports fourteen findings while the headline number describes one of them. Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above. what this limits: the performance figure quoted for this model: the network outputs a vector of binary labels over fourteen pathology classes, while the radiologist comparison concerns the pneumonia task alone	`limitations[7]`	1.0	the tagger's words
transfers	a deep convolutional network (DenseNet) applied to detect disease from chest X-rays at radiologist level Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above.	`transfers[0]`		the tagger's words
controls	four practising academic radiologists annotating the same test set, used as the comparison for the model Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above. eliminates: a number that looks good against no reference - the baseline here is people doing the task on the same images · outcome (stated by the tagger, no quotation): held	`controls[0]`	0.85	the tagger's words
concepts	F1 score Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above. also in: F1 score	`concepts[4]`		the paper's words
concepts	ground truth Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above. also in: ground truth	`concepts[5]`		the paper's words
concepts	pneumonia detection task Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above. also in: pneumonia detection task	`concepts[6]`		the paper's words
concepts	pathology labels Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above. also in: pathology labels	`concepts[7]`		the paper's words
concepts	automatic extraction methods Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above. also in: automatic extraction methods	`concepts[8]`		the paper's words
senses	'exceeding practicing radiologists' - AS AGREEMENT WITH FOUR OF THEM: the F1 for the model and for each radiologist is computed against the other four radiologists' labels, so the claim is about concordance with a particular panel and not about detecting pneumonia in a patient Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above.	`senses[0]`	1.0	the tagger's words
senses	a pathology label - AS A FACT ABOUT A REPORT, NOT AN IMAGE: the fourteen labels are assigned by automatic extraction from radiology reports, so the target the network learns is what a radiologist wrote down, filtered through a text-mining tool Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above.	`senses[1]`	1.0	the tagger's words
senses	'negative' - AS NOT-LABELLED: every image without pneumonia among its annotated pathologies becomes a negative example, so the class means the extractor found nothing rather than that nothing was there Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above.	`senses[2]`	1.0	the tagger's words
claim_relations	builds-on → convolutional neural networks (deep learning) Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above.	`claim_relations[0]`		the tagger's words
claim_relations	builds-on → DenseNet (Huang et al., 2016) Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above.	`claim_relations[1]`		the tagger's words
claim_relations	builds-on → the ChestX-ray14 dataset of Wang et al. (2017) Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above.	`claim_relations[2]`		the tagger's words
claim_relations	builds-on → the evaluation protocol of Wang et al. (2017) and Yao et al. (2017) Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above.	`claim_relations[3]`		the tagger's words
concept_edges	pathology labels —operationalised-as→ automatic extraction methods Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above. strength of the relation: 1 Audit 2026-09-28: DOUBTFUL - read against its full span and kept, but the span says labels were annotated USING automatic extraction methods; operationalised-as is loose. also in: pathology labels · automatic extraction methods	`concept_edges[1]`		the tagger's words
content_tags	121 — depth of the DenseNet CNN (CheXNet) Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above.	`content_tags.quantities[0]`		the tagger's words
content_tags	112,120 — chest X-ray images in the ChestX-ray14 dataset Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above. about this quote: QUOTE REPAIRED: the extractor split a hyphen-space and the quote was recorded faithfully with the damage in it, which made it unanchorable. The repaired string is an EXACT SUBSTRING of the staged text - that is why it was accepted, not because a rule produced it. The text as originally recorded is kept in evidence as extracted.	`content_tags.quantities[1]`		the tagger's words
content_tags	14 — thoracic disease labels detected Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above. about this quote: QUOTE REPAIRED: the extractor split a hyphen-space and the quote was recorded faithfully with the damage in it, which made it unanchorable. The repaired string is an EXACT SUBSTRING of the staged text - that is why it was accepted, not because a rule produced it. The text as originally recorded is kept in evidence as extracted.	`content_tags.quantities[2]`		the tagger's words
content_tags	420 — size of the radiologist-annotated test set Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above.	`content_tags.quantities[3]`		the tagger's words
content_tags	> 0.05 — margin over previous state of the art (emphysema) Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above.	`content_tags.quantities[4]`		the tagger's words
content_tags	EVIDENCE CORRECTED (RE-GROUNDED - THE POINTER WAS WRONG, NOT THE CLAIM) · CheXNet is a 121-layer CNN, trained on the ChestX-ray14 dataset of over 100,000 frontal-view X-rays covering 14 diseases. Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above. EVIDENCE CORRECTED: RE-GROUNDED - THE POINTER WAS WRONG, NOT THE CLAIM. The old evidence was verbatim, anchored and correctly cut, and it contained NONE of this claim's numbers (121, 14). The paper states the claim in one sentence elsewhere and the tagger did not use it. the project, 2026-08-23: 'WE HAVE SPENT THE DAY VERIFYING THAT QUOTES ARE REAL AND NONE OF IT ASKS WHETHER THEY ARE RELEVANT.' Confirmed by reading the claim, the old span and the candidate together; the candidate carries every number AND the claim's own content words. — about this quote: QUOTE REPAIRED: the extractor split a hyphen-space and the quote was recorded faithfully with the damage in it, which made it unanchorable. The repaired string is an EXACT SUBSTRING of the staged text - that is why it was accepted, not because a rule produced it. The text as originally recorded is kept in evidence as extracted.	`content_tags.findings[0]`		the tagger's words
content_tags	Extended to all 14 thoracic diseases, CheXNet achieves state-of-the-art results on every one. Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above. about this quote: QUOTE REPAIRED: the extractor split a hyphen-space and the quote was recorded faithfully with the damage in it, which made it unanchorable. The repaired string is an EXACT SUBSTRING of the staged text - that is why it was accepted, not because a rule produced it. The text as originally recorded is kept in evidence as extracted.	`content_tags.findings[1]`		the tagger's words
content_tags	chest X-ray image Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above. also in: chest X-ray image	`content_tags.variables[0]`		the tagger's words
content_tags	F1 metric Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above. about this quote: QUOTE REPAIRED: the extractor split a hyphen-space and the quote was recorded faithfully with the damage in it, which made it unanchorable. The repaired string is an EXACT SUBSTRING of the staged text - that is why it was accepted, not because a rule produced it. The text as originally recorded is kept in evidence as extracted. also in: F1 metric	`content_tags.variables[1]`		the tagger's words
content_tags	CheXNet Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above. also in: CheXNet	`content_tags.definitions[0]`		the tagger's words
content_tags	ChestX-ray14 dataset Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above. about this quote: QUOTE RECOVERED FROM THE PAPER'S OWN CHARACTERS. The recorded quote was LETTERS-ONLY IDENTICAL to this stretch of the staged text but not an exact substring of it - spaces, hyphens, ligature glyphs or mathematical operators differed, so it could never anchor. This is the file's own text between the same two letters: not produced by a rule about the damage, copied out of the file. Round-trip checked (the recovered span is letters-only equal to the original) and length-checked. The text as originally recorded is kept in evidence as extracted. also in: ChestX-ray14 dataset	`content_tags.definitions[1]`		the tagger's words
content_tags	bootstrap Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above. about this quote: QUOTE REPAIRED: the extractor split a hyphen-space and the quote was recorded faithfully with the damage in it, which made it unanchorable. The repaired string is an EXACT SUBSTRING of the staged text - that is why it was accepted, not because a rule produced it. The text as originally recorded is kept in evidence as extracted. also in: bootstrap	`content_tags.statistics[0]`		the tagger's words
content_tags	confidence-interval Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above. about this quote: QUOTE REPAIRED: the extractor split a hyphen-space and the quote was recorded faithfully with the damage in it, which made it unanchorable. The repaired string is an EXACT SUBSTRING of the staged text - that is why it was accepted, not because a rule produced it. The text as originally recorded is kept in evidence as extracted. also in: confidence-interval	`content_tags.statistics[1]`		the tagger's words
content_tags	mean Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above. about this quote: QUOTE REPAIRED: the extractor split a hyphen-space and the quote was recorded faithfully with the damage in it, which made it unanchorable. The repaired string is an EXACT SUBSTRING of the staged text - that is why it was accepted, not because a rule produced it. The text as originally recorded is kept in evidence as extracted. also in: mean	`content_tags.statistics[2]`		the tagger's words
content_tags	standard-deviation Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above. also in: standard-deviation	`content_tags.statistics[3]`		the tagger's words
content_tags	statistical-significance Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above. about this quote: QUOTE REPAIRED: the extractor split a hyphen-space and the quote was recorded faithfully with the damage in it, which made it unanchorable. The repaired string is an EXACT SUBSTRING of the staged text - that is why it was accepted, not because a rule produced it. The text as originally recorded is kept in evidence as extracted. also in: statistical-significance	`content_tags.statistics[4]`		the tagger's words

Interpretive choices

Tags that could not be placed in the text:

none — every tag was located in the text

What was deliberately not tagged, and why, is recorded per paper by the tagger. Where a paper has no such record, this page says so rather than implying that nothing was declined.