Papers › G-CASCADE: Efficient Cascaded Graph Convolutional Decoding for 2D Medical Image Segmentation

G-CASCADE: Efficient Cascaded Graph Convolutional Decoding for 2D Medical Image Segmentation

24 Oct 2023arXiv:2310.16175archive 2025-07-28

Md Mostafijur Rahman, Radu Marculescu

In recent years, medical image segmentation has become an important application in the field of computer-aided diagnosis. In this paper, we are the first to propose a new graph convolution-based decoder namely, Cascaded Graph Convolutional Attention Decoder (G-CASCADE), for 2D medical image segmentation. G-CASCADE progressively refines multi-stage feature maps generated by hierarchical transformer encoders with an efficient graph convolution block. The encoder utilizes the self-attention mechanism to capture long-range dependencies, while the decoder refines the feature maps preserving long-range information due to the global receptive fields of the graph convolution block. Rigorous evaluations of our decoder with multiple transformer encoders on five medical image segmentation tasks (i.e., Abdomen organs, Cardiac organs, Polyp lesions, Skin lesions, and Retinal vessels) show that our model outperforms other state-of-the-art (SOTA) methods. We also demonstrate that our decoder achieves better DICE scores than the SOTA CASCADE decoder with 80.8% fewer parameters and 82.3% fewer FLOPs. Our decoder can easily be used with other hierarchical encoders for general-purpose semantic and medical image segmentation tasks.

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 9 code samples harvested from 1 repository linked to this paper: 6 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 1 honoured, 0 violated, 0 with no contract checked; 5 where Syntology's instrument failed) · 3 unverified. Where Syntology's instrument failed: 1 where our contract draft was wrong; 4 where the contract check could not run; failures of Syntology's instrument, not of the code.

By repository: official repository: 9 samples from 1 repository, 6 ran (1 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 on 2026-09-22 (UTC): the dates Syntology's graph wrote each sample's verification level, not when the code executed. 2 of the 6 samples that ran have no recorded date.

SLDGroup/G-CASCADE officialmentioned on GitHubpytorchNOASSERTIONSyntology: 9 samples, 6 ran (5 instrument-failed) · 3 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.

Code Syntology ran Syntology

9 samples harvested: 6 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 1 honoured, 0 violated, 0 with no contract checked; 5 where Syntology's instrument failed) · 3 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 · our draft was wrong
4ran; the contract check could not run
3unverified

Licence: 9 of the 9 samples are pointer only, meaning Syntology does not serve that copy's text. This page shows no code text for any sample; each one links to its file in the repository.

Harvested from SLDGroup/G-CASCADE. “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. 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.

SLDGroup/G-CASCADE official repository 9 samples, 6 ran (5 instrument-failed) · 3 unverified
np2th in 31 papers
census: 2 implementations from 9 papers, 1 distinct output on one shared input this sample: bucket 1 of 1, arg 1: rank 4, kind float, dtype float32
lib/networks.py ran; the contract check could not run (RAISES) · metamorphic tier: invariant no licence file found · pointer only · 7d8eaf5537f699e4 · report fixture: signature weights:ndarray/4/float, conv:bool/0/bool · returned Tensor · level recorded, date not recorded
num_groups in 5 papers lib/maxxvit_4out.py ran · honoured contract fingerprinted no licence file found · pointer only · c6946ef9a1244755 · report fixture: signature group_size:int/0/int, channels:int/0/int · returned int · level recorded, date not recorded
pairwise_distance in 55 papers
census: 6 implementations from 7 papers, 5 distinct outputs across 3 buckets, one shared input per bucket this sample: bucket 3 of 3, arg 1: rank 3, kind float, dtype float32
lib/gcn_lib/torch_edge.py ran; the contract check could not run (RAISES) · metamorphic tier: invariant fingerprinted no licence file found · pointer only · 82aeae314890e7ed · report fixture: signature x:Tensor/3/float · returned Tensor · level recorded 2026-09-22
part_pairwise_distance lib/gcn_lib/torch_edge.py ran · our draft was wrong fingerprinted no licence file found · pointer only · 102d0e5b09e9b385 · report fixture: signature x:Tensor/3/float, start_idx:int/0/int, end_idx:int/0/int · returned Tensor · level recorded 2026-09-22
structure_loss in 8 papers train_ISIC2018.py ran; the contract check could not run (RAISES) · metamorphic tier: invariant fingerprinted no licence file found · pointer only · 797eafbb72dabcfd · report fixture: signature pred:Tensor/4/float, mask:Tensor/4/float · returned Tensor · level recorded 2026-09-22
xy_pairwise_distance lib/gcn_lib/torch_edge.py ran; the contract check could not run (RAISES) · metamorphic tier: invariant fingerprinted no licence file found · pointer only · 160401504e7d0dbb · report fixture: signature x:Tensor/3/float, y:Tensor/3/float · returned Tensor · level recorded 2026-09-22
get_2d_relative_pos_embed in 5 papers lib/gcn_lib/pos_embed.py unverified no licence file found · pointer only · 571021715428528c · report
get_2d_sincos_pos_embed in 170 papers lib/gcn_lib/pos_embed.py unverified no licence file found · pointer only · 3185afc3e87293ed · report
get_2d_sincos_pos_embed_from_grid in 140 papers lib/gcn_lib/pos_embed.py unverified no licence file found · pointer only · f10004e059714d42 · report

Tasks

DecoderImage SegmentationMedical Image SegmentationRetinal Vessel SegmentationSegmentationSemantic Segmentation

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Medical Image Segmentation Automatic Cardiac Diagnosis Challenge (ACDC) MERIT-GCASCADE Avg DSC 92.23 #7 of 20 Archive leaderboard report
Medical Image Segmentation Automatic Cardiac Diagnosis Challenge (ACDC) PVT-GCASCADE Avg DSC 91.95 #11 of 20 Archive leaderboard report
Medical Image Segmentation CHASE_DB1 MERIT-GCASCADE DSC 0.8267 #1 of 3 Archive leaderboard report
Medical Image Segmentation CHASE_DB1 PVT-GCASCADE DSC 0.8251 #2 of 3 Archive leaderboard report
Medical Image Segmentation CVC-ClinicDB PVT-GCASCADE mIoU 0.9018 #14 of 48 Archive leaderboard report
Medical Image Segmentation CVC-ClinicDB PVT-GCASCADE mean Dice 0.9468 #14 of 48 Archive leaderboard report
Medical Image Segmentation CVC-ColonDB PVT-GCASCADE mIoU 0.7460 #9 of 25 Archive leaderboard report
Medical Image Segmentation CVC-ColonDB PVT-GCASCADE mean Dice 0.8261 #9 of 25 Archive leaderboard report
Medical Image Segmentation DRIVE MERIT-GCASCADE F1 score 0.8290 #1 of 5 Archive leaderboard report
Medical Image Segmentation DRIVE MERIT-GCASCADE Recall 0.8281 #1 of 5 Archive leaderboard report
Medical Image Segmentation DRIVE MERIT-GCASCADE Specificity 0.9844 #1 of 5 Archive leaderboard report
Medical Image Segmentation DRIVE MERIT-GCASCADE mIoU 0.7081 #1 of 5 Archive leaderboard report
Medical Image Segmentation DRIVE PVT-GCASCADE F1 score 0.8210 #2 of 5 Archive leaderboard report
Medical Image Segmentation DRIVE PVT-GCASCADE Recall 0.83 #2 of 5 Archive leaderboard report
Medical Image Segmentation DRIVE PVT-GCASCADE Specificity 0.9822 #2 of 5 Archive leaderboard report
Medical Image Segmentation DRIVE PVT-GCASCADE mIoU 0.697 #2 of 5 Archive leaderboard report
Medical Image Segmentation ISIC 2018 PVT-GCASCADE DSC 91.51 #2 of 5 Archive leaderboard report
Medical Image Segmentation ISIC 2018 PVT-GCASCADE mIoU 86.53 #2 of 5 Archive leaderboard report
Medical Image Segmentation Kvasir-SEG PVT-GCASCADE mIoU 0.8790 #17 of 58 Archive leaderboard report
Medical Image Segmentation Kvasir-SEG PVT-GCASCADE mean Dice 0.9274 #17 of 58 Archive leaderboard report
Medical Image Segmentation MICCAI 2015 Multi-Atlas Abdomen Labeling Challenge MERIT-GCASCADE Avg DSC 84.54 #2 of 8 Archive leaderboard report
Medical Image Segmentation MICCAI 2015 Multi-Atlas Abdomen Labeling Challenge MERIT-GCASCADE Avg HD 10.38 #2 of 8 Archive leaderboard report
Medical Image Segmentation MICCAI 2015 Multi-Atlas Abdomen Labeling Challenge PVT-GCASCADE Avg DSC 83.28 #5 of 8 Archive leaderboard report
Medical Image Segmentation MICCAI 2015 Multi-Atlas Abdomen Labeling Challenge PVT-GCASCADE Avg HD 15.83 #5 of 8 Archive leaderboard report
Retinal Vessel Segmentation CHASE_DB1 MERIT-GCASCADE F1 score 0.8267 #14 of 16 Archive leaderboard report
Retinal Vessel Segmentation CHASE_DB1 MERIT-GCASCADE Sensitivity 0.8493 #14 of 16 Archive leaderboard report
Retinal Vessel Segmentation CHASE_DB1 MERIT-GCASCADE mIOU 0.7050 #14 of 16 Archive leaderboard report
Retinal Vessel Segmentation CHASE_DB1 PVT-GCASCADE F1 score 0.8251 #15 of 16 Archive leaderboard report
Retinal Vessel Segmentation CHASE_DB1 PVT-GCASCADE Sensitivity 0.8584 #15 of 16 Archive leaderboard report
Retinal Vessel Segmentation CHASE_DB1 PVT-GCASCADE mIOU 0.7024 #15 of 16 Archive leaderboard report
Retinal Vessel Segmentation DRIVE MERIT-GCASCADE Accuracy 0.9707 #17 of 22 Archive leaderboard report
Retinal Vessel Segmentation DRIVE MERIT-GCASCADE F1 score 0.8290 #17 of 22 Archive leaderboard report
Retinal Vessel Segmentation DRIVE MERIT-GCASCADE Specificity 0.9844 #17 of 22 Archive leaderboard report
Retinal Vessel Segmentation DRIVE MERIT-GCASCADE mIoU 0.7081 #17 of 22 Archive leaderboard report
Retinal Vessel Segmentation DRIVE MERIT-GCASCADE sensitivity 0.8281 #17 of 22 Archive leaderboard report
Retinal Vessel Segmentation DRIVE PVT-GCASCADE Accuracy 0.9689 #20 of 22 Archive leaderboard report
Retinal Vessel Segmentation DRIVE PVT-GCASCADE F1 score 0.8210 #20 of 22 Archive leaderboard report
Retinal Vessel Segmentation DRIVE PVT-GCASCADE Specificity 0.9822 #20 of 22 Archive leaderboard report
Retinal Vessel Segmentation DRIVE PVT-GCASCADE mIoU 0.6970 #20 of 22 Archive leaderboard report
Retinal Vessel Segmentation DRIVE PVT-GCASCADE sensitivity 0.83 #20 of 22 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

Convolution

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