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 WITHDRAWN AND REPLACED — the entry was wrong, and a corrected version of it appears in the entries below.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 An entry we have WITHDRAWN is removed from this page and kept in the record, with its reason.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.| 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 |
| contribution | contribution | what the paper claims to add |
| 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 |
| object of study | object_of_study | what the paper is about — the thing it investigates |
| phenomenon | phenomenon | the effect or regularity under study |
| research question | research_question | the question the paper sets itself |
| 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 |
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; 3 of 3 relations here carry that mark. The rest are the tagger’s reading of the sentence quoted beside them.
| facet | tag | field | conf. | whose words |
|---|---|---|---|---|
| object_of_study | whether a network can be made to find the organ it is supposed to measure, instead of being handed a cropped region by a second network trained to find it Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above. | object_of_study | the paper's words | |
| research_question | whether a soft attention gate inside a single CNN can replace the cascade - a localisation model followed by a segmentation model - without losing accuracy or adding many parameters Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above. | research_question | the paper's words | |
| contribution | a grid-based additive attention gate that drops into VGG or U-Net, learns where to look with no bounding boxes and no extra supervision, improves recall and precision on CT pancreas segmentation and fetal ultrasound plane detection, and is shown to beat simply making the baseline bigger Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above. | contribution | the paper's 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 | small, variable-shaped structures that a single-stage network misses, and the cascades built to hand it a cropped view of them - which repeat the same low-level features in every model of the chain 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 | a cascade spends a whole network learning where the organ is and then throws that network's features away; a gate computes the same decision from features the predictor already has, so the localisation costs 8% more parameters instead of a second model, and the low-level features are extracted once Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above. | mechanisms[0] | 0.95 | the tagger's words |
| mechanisms | the gating parameters start so that every feature vector passes at every location - the network begins as its own baseline and has to learn to suppress, which is why no multi-stage training schedule is needed and why any difference is attributable to what the gate learned rather than to where it started Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above. also in: a gate initialised to do nothing | mechanisms[1] | 0.95 | the tagger's words |
| mechanisms | the gating signal is taken from a coarser grid, where the receptive field is large enough to know where the organ is, and applied to a finer map, where the resolution is enough to draw its boundary - which is the same division of labour a cascade makes between its two networks, done inside one Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above. | mechanisms[2] | 0.95 | the tagger's words |
| mechanisms | softmax over the attention map produces sparse, intensity-sensitive attention, which is bad in ultrasound; sigmoid only rescales and lets more information through, and pays for it with gradient saturation. Neither is free and the paper reports both costs Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above. | mechanisms[3] | 0.95 | the tagger's words |
| limitations | the attention map outlines the discriminant region and does not necessarily coincide with the entire object, so it localises without delineating Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above. | limitations[0] | 0.95 | the tagger's words |
| limitations | the comparison against 2D cascaded state-of-the-art models is called insufficient to draw a final conclusion, because the 3D model has context and the 2D models have resolution Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above. | limitations[1] | 0.95 | the tagger's words |
| limitations | softmax normalisation gives sparse, intensity-sensitive maps and sigmoid gives gradient saturation - the normalisation choice has no free option Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above. | limitations[2] | 0.95 | the tagger's words |
| limitations | training the attention mechanism is more complex than the baseline, and the most stable route was per-scale training followed by fine-tuning Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above. | limitations[3] | 0.95 | the tagger's words |
| limitations | residual connections around the gate gave no significant improvement in the segmentation experiments Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above. | limitations[4] | 0.95 | the tagger's words |
| transfers | additive soft attention, carried from sentence-to-sentence machine translation into a convolutional network over medical images, and re-based on an image grid so the coefficients can be local Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above. | transfers[0] | 0.95 | the tagger's words |
| controls | higher-capacity U-Net models trained and compared against the smaller gated model, rather than only against the same-size baseline Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above. eliminates: the extra parameters as the explanation of the gain - a module that adds 8% capacity and improves DSC by 2-3% has to be shown to beat 8% more capacity spread uniformly, and it does at p = .007 · outcome: held | controls[0] | 0.95 | the tagger's words |
| controls | the same two models retrained at a smaller training size (30 images instead of 120) Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above. eliminates: the improvement being an artefact of one data budget - if attention only helps when data is plentiful it is not solving the localisation problem it claims to · outcome: held | controls[1] | 0.95 | the tagger's words |
| controls | models trained on CT-150 applied directly to the public CT-82 benchmark with no fine-tuning, before any adaptation is done Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above. eliminates: the result being tied to one institution's data - the transfer is measured before the models are allowed to see the new distribution · outcome: held | controls[2] | 0.95 | the tagger's words |
| controls | both models also trained from scratch on 61 CT-82 images, in addition to the fine-tuned and directly-applied conditions Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above. eliminates: pre-training on the private dataset as a hidden advantage in the public benchmark comparison · outcome: held | controls[3] | 0.95 | the tagger's words |
| controls | 5-fold cross-validation on CT-82 with the Attention U-Net, reported with its standard deviation Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above. eliminates: a single favourable train/test split - the spread of 6.23 DSC is the size of the effect being claimed, and reporting it makes that visible · outcome: held | controls[4] | 0.95 | the tagger's words |
| controls | conditional random field post-processing deliberately NOT applied, and said so, although the comparison methods use it Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above. eliminates: post-processing absorbing or masking the gate's contribution - the measured difference is the module's in an isolated setting, at the cost of a lower absolute number · outcome: held | controls[5] | 0.95 | the tagger's words |
| controls | ultrasound frames cropped to the central 208 x 272 so the network cannot read the annotations the scanner prints around the image Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above. eliminates: the network reading the annotations the scanner prints around the image instead of the anatomy - a leak that would look like accuracy · outcome (stated by the tagger, no quotation): held | controls[6] | 0.85 | the tagger's words |
| controls | gating parameters initialised so that the gates pass every feature vector at every location, making the network start as its own baseline Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above. eliminates: that the attention gates help only because they change the initialisation - starting open makes the network its own baseline at step zero · outcome (stated by the tagger, no quotation): held | controls[7] | 0.95 | the tagger's words |
| controls | class imbalance handled by weighted sampling for classification and a Dice loss for segmentation, in both the attention and the baseline networks Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above. eliminates: the dominant background class carrying the score, and any difference between the two networks being a difference in how each one met the imbalance · outcome (stated by the tagger, no quotation): held | controls[8] | 0.95 | the tagger's words |
| concepts | attention gates Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above. also in: attention gates | concepts[0] | 0.95 | the paper's words |
| concepts | cascaded Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above. also in: cascaded | concepts[1] | 0.95 | the paper's words |
| concepts | soft attention Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above. also in: soft attention | concepts[2] | 0.95 | the paper's words |
| concepts | Hard attention Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above. also in: Hard attention | concepts[3] | 0.95 | the paper's words |
| concepts | discriminant region Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above. also in: discriminant region | concepts[4] | 0.95 | the paper's words |
| concepts | recall Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above. also in: recall | concepts[5] | 0.95 | the paper's words |
| concepts | trainable parameters Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above. also in: trainable parameters | concepts[6] | 0.95 | the paper's words |
| concepts | DSC Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above. also in: DSC | concepts[7] | 0.95 | the paper's words |
| concepts | conditional random field Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above. also in: conditional random field | concepts[8] | 0.95 | the paper's words |
| senses | an attention map - AS THE PAPER USES IT: a soft region proposal that suppresses background and lets the network localise without a second model Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above. | senses[0] | 0.95 | the tagger's words |
| senses | an attention map - AS THE PAPER SAYS IT IS NOT: the object. It outlines the DISCRIMINANT REGION and does not necessarily coincide with the whole structure Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above. | senses[1] | 0.95 | the tagger's words |
| senses | the gain from attention - AGAINST THE SAME-SIZE BASELINE: 2-3 DSC points for 8% extra parameters Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above. | senses[2] | 0.95 | the tagger's words |
| senses | the gain from attention - AGAINST A BASELINE GROWN TO MATCH: still significant at p = .007, which is what makes it a claim about the gate rather than about size Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above. | senses[3] | 0.95 | the tagger's words |
| senses | the state-of-the-art comparison - AS THE TABLE READS: comparable to 2D cascaded models and better than single-model frameworks Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above. | senses[4] | 0.95 | the tagger's words |
| senses | the state-of-the-art comparison - AS THE AUTHORS QUALIFY IT: not sufficient to draw a final conclusion, because their 3D model trades resolution for context and the 2D models trade context for resolution Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above. | senses[5] | 0.95 | the tagger's words |
| claim_relations | critiques → cascaded multi-stage CNN frameworks, which reach 81-82% DSC on the TCIA pancreas benchmark but re-extract the same low-level features in every model of the chain Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above. | claim_relations[0] | 0.95 | the tagger's words |
| claim_relations | critiques → hard-attention approaches, which crop, are non-differentiable, and need reinforcement learning for parameter updates Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above. | claim_relations[1] | 0.95 | the tagger's words |
| claim_relations | extends → soft attention as used for adaptive feature pooling in natural image classification and captioning, generalised here to grid-based gating so coefficients can be specific to local regions Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above. | claim_relations[2] | 0.95 | the tagger's words |
| claim_relations | qualifies → its own state-of-the-art comparison, which the authors say is not sufficient to draw a final conclusion because the 3D and 2D models are given different information Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above. | claim_relations[3] | 0.95 | the tagger's words |
| claim_relations | qualifies → the interpretability claim for attention maps - they outline what the model used, not the object, and the paper says so in the same paragraph that offers them for localisation Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above. | claim_relations[4] | 0.95 | the tagger's words |
| concept_edges | attention gates —distinct-from→ cascaded Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above. differs in: whether localisation is a separate model with its own parameters or a module inside the predictor · the relation itself is separately evidenced · strength of the relation: 0.95 · differs in (stated by the tagger, no quotation): whether localisation is a separate model with its own parameters or a module inside the predictor · the relation stated: the gates suppress background progressively inside one network instead of cropping a region of interest between two
Audit 2026-09-28: DOUBTFUL - read against its span and kept, but attention gates remove the need for an external localisation module; distinct-from 'cascaded' is terse. also in: attention gates · cascaded | concept_edges[0] | 0.95 | the tagger's words |
| concept_edges | soft attention —distinct-from→ Hard attention Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above. differs in: whether the attention step can be differentiated through · the relation itself is separately evidenced · strength of the relation: 0.95 · differs in (stated by the tagger, no quotation): whether the attention step can be differentiated through · the relation stated: hard attention crops and is non-differentiable, needing reinforcement learning; soft attention is probabilistic and trains by ordinary backpropagation also in: soft attention · Hard attention | concept_edges[1] | 0.95 | the tagger's words |
| concept_edges | attention gates —distinct-from→ trainable parameters Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above. differs in: whether the extra parameters are spread across all layers or spent on localisation · the relation itself is separately evidenced · strength of the relation: 0.95 · differs in (stated by the tagger, no quotation): whether the extra parameters are spread across all layers or spent on localisation · the relation stated: a U-Net grown uniformly to the same size does not reach the gated model, so the gain is not capacity
Audit 2026-09-28: DOUBTFUL - read against its full span and kept, but the span writes 'AGs' and says they contribute more than simply increasing capacity; distinct-from is loose. also in: attention gates · trainable parameters | concept_edges[3] | 0.95 | the tagger's words |
| content_tags | attention gates beat a U-Net grown uniformly to the same parameter count, at p = .007, so the gain is the module and not the capacity Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above. | content_tags.findings[0] | 0.95 | the tagger's words |
| content_tags | the improvement holds at 30 training images as well as 120, so it is not an artefact of one data budget Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above. | content_tags.findings[1] | 0.95 | the tagger's words |
| content_tags | Attention gates increase recall in pancreas segmentation (p = .005). Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above. | content_tags.findings[2] | 0.95 | the tagger's words |
| content_tags | the attention map outlines the discriminant region and does not necessarily coincide with the entire object Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above. | content_tags.findings[3] | 0.95 | the tagger's words |
| content_tags | No post-processing such as a conditional random field was used, so as to isolate the gates' contribution. Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above. | content_tags.findings[4] | 0.95 | the tagger's words |
| content_tags | AG-Sononet performs close to a Sononet with double the capacity. Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above. | content_tags.findings[5] | 0.95 | the tagger's words |
| content_tags | each attention gate learns to focus on a particular subset of organs, starting from a uniform distribution and localising over training Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above. | content_tags.findings[6] | 0.95 | the tagger's words |
| content_tags | probabilistic, end-to-end differentiable attention using standard backpropagation without posterior sampling - as against hard attention, which crops and needs reinforcement learning Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above. also in: soft attention | content_tags.definitions[0] | 0.95 | the tagger's words |
| content_tags | what an attention map outlines - the part of the object the classifier uses, which the authors state does not necessarily coincide with the entire object Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above. also in: discriminant region | content_tags.definitions[1] | 0.95 | the tagger's words |
| content_tags | extra capacity added to the standard U-Net by the attention gates, for a 2-3% DSC improvement Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above. | content_tags.quantities[0] | 0.95 | the tagger's words |
| content_tags | mean pancreas DSC over 5-fold cross-validation on CT-82, with a standard deviation of 6.23 Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above. | content_tags.quantities[1] | 0.95 | the tagger's words |
| content_tags | the bottom of the atlas-method DSC range on the TCIA pancreas benchmark Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above. | content_tags.quantities[2] | 0.95 | the tagger's words |
| content_tags | DSC Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above. also in: DSC | content_tags.statistics[0] | 0.95 | the tagger's words |
| content_tags | p Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above. also in: p | content_tags.statistics[1] | 0.95 | the tagger's words |
| content_tags | recall Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above. also in: recall | content_tags.variables[0] | 0.95 | the tagger's words |
| content_tags | trainable parameters Quotation withheld — this record is not cleared for redistribution. The sentence is in the paper at the link above. also in: trainable parameters | content_tags.variables[1] | 0.95 | the tagger's words |
Tags that could not be placed 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.