Papers › 3D Self-Supervised Methods for Medical Imaging

3D Self-Supervised Methods for Medical Imaging

6 Jun 2020NeurIPS 2020 12arXiv:2006.03829archive 2025-07-28

Aiham Taleb, Winfried Loetzsch, Noel Danz, Julius Severin, Thomas Gaertner, Benjamin Bergner, Christoph Lippert

Self-supervised learning methods have witnessed a recent surge of interest after proving successful in multiple application fields. In this work, we leverage these techniques, and we propose 3D versions for five different self-supervised methods, in the form of proxy tasks. Our methods facilitate neural network feature learning from unlabeled 3D images, aiming to reduce the required cost for expert annotation. The developed algorithms are 3D Contrastive Predictive Coding, 3D Rotation prediction, 3D Jigsaw puzzles, Relative 3D patch location, and 3D Exemplar networks. Our experiments show that pretraining models with our 3D tasks yields more powerful semantic representations, and enables solving downstream tasks more accurately and efficiently, compared to training the models from scratch and to pretraining them on 2D slices. We demonstrate the effectiveness of our methods on three downstream tasks from the medical imaging domain: i) Brain Tumor Segmentation from 3D MRI, ii) Pancreas Tumor Segmentation from 3D CT, and iii) Diabetic Retinopathy Detection from 2D Fundus images. In each task, we assess the gains in data-efficiency, performance, and speed of convergence. Interestingly, we also find gains when transferring the learned representations, by our methods, from a large unlabeled 3D corpus to a small downstream-specific dataset. We achieve results competitive to state-of-the-art solutions at a fraction of the computational expense. We publish our implementations for the developed algorithms (both 3D and 2D versions) as an open-source library, in an effort to allow other researchers to apply and extend our methods on their datasets.

PaperPDFConference PDFCodeCode 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 16 code samples harvested from 1 repository linked to this paper: 14 ran (of which 0 constructed an object rather than computing a result; 14 with no instrument failure: 0 honoured, 0 violated, 14 with no contract checked; 0 where Syntology's instrument failed) · 2 unverified. “Where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code; here there are none.

By repository: official repository: 16 samples from 1 repository, 14 ran (14 with no instrument failure; 0 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 2026-09-25 (UTC): the dates Syntology's graph wrote each sample's verification level, not when the code executed.

HealthML/self-supervised-3d-tasks officialmentioned in papermentioned on GitHubtfApache-2.0Syntology: 16 samples, 14 ran (0 instrument-failed) · 2 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

16 samples harvested: 14 ran (of which 0 constructed an object rather than computing a result; 14 with no instrument failure: 0 honoured, 0 violated, 14 with no contract checked; 0 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 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.

14ran
2unverified

Licence: 16 of the 16 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 HealthML/self-supervised-3d-tasks. “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.

HealthML/self-supervised-3d-tasks official repository 16 samples, 14 ran (0 instrument-failed) · 2 unverified
basic_block in 6 papers self_supervised_3d_tasks/models/resnet3d.py ran Apache-2.0 recorded; this copy not marked cleared · pointer only · e44e5354592522fd · report fixture: signature filters:int/0/int, strides:tuple/1/int, kernel_regularizer:callable/0/?, is_first_block_of_first_layer:bool/0/bool · returned function · level recorded 2026-09-25
bottleneck self_supervised_3d_tasks/models/resnet3d.py ran Apache-2.0 recorded; this copy not marked cleared · pointer only · 9ba8fad266d73744 · report fixture: signature filters:int/0/int, strides:tuple/1/int, kernel_regularizer:callable/0/?, is_first_block_of_first_layer:bool/0/bool · returned function · level recorded 2026-09-25
conv3d_block self_supervised_3d_tasks/models/unet3d.py ran Apache-2.0 recorded; this copy not marked cleared · pointer only · dff642f195244e6a · report fixture: signature inputs:KerasTensor/0/float, use_batch_norm:bool/0/bool, dropout:float/0/float, filters:int/0/int, kernel_size:tuple/1/int, activation:str/0/str, kernel_initializer:str/0/str, padding:str/0/str · returned KerasTensor · level recorded 2026-09-25
conv_block in 95 papers self_supervised_3d_tasks/models/unet.py ran Apache-2.0 recorded; this copy not marked cleared · pointer only · 40baa5aebd753951 · report fixture: signature inputs:KerasTensor/0/float, use_batch_norm:bool/0/bool, dropout:float/0/float, filters:int/0/int, kernel_size:tuple/1/int, activation:str/0/str, kernel_initializer:str/0/str, padding:str/0/str · returned KerasTensor · level recorded 2026-09-25
convolutional_block in 5 papers self_supervised_3d_tasks/models/resnet2d.py ran Apache-2.0 recorded; this copy not marked cleared · pointer only · 6244a4f28078ae41 · report fixture: signature X:EagerTensor/4/float, f:int/0/int, filters:list/1/int, stage:int/0/int, block:str/0/str, s:int/0/int · returned EagerTensor · level recorded 2026-09-25
fully_connected in 9 papers self_supervised_3d_tasks/models/fully_connected.py ran Apache-2.0 recorded; this copy not marked cleared · pointer only · 1c2811866c2a26d0 · report fixture: signature inputs:EagerTensor/2/float, num_classes:int/0/int, rate:float/0/float, include_top:bool/0/bool · returned EagerTensor · level recorded 2026-09-25
fully_connected_big self_supervised_3d_tasks/models/fully_connected.py ran Apache-2.0 recorded; this copy not marked cleared · pointer only · e1bbace6125c7aeb · report fixture: signature inputs:KerasTensor/0/float, dropout_rate:float/0/float, include_top:bool/0/bool · returned KerasTensor · level recorded 2026-09-25
network_autoregressive self_supervised_3d_tasks/algorithms/cpc.py ran Apache-2.0 recorded; this copy not marked cleared · pointer only · b22f0f43e5c590ec · report fixture: signature x:EagerTensor/3/float · returned EagerTensor · level recorded 2026-09-25
network_prediction self_supervised_3d_tasks/algorithms/cpc.py ran Apache-2.0 recorded; this copy not marked cleared · pointer only · 5d58accf52fd2af4 · report fixture: signature context:KerasTensor/0/float, code_size:int/0/int, predict_terms:int/0/int · returned KerasTensor · level recorded 2026-09-25
simple_multiclass self_supervised_3d_tasks/models/fully_connected.py ran Apache-2.0 recorded; this copy not marked cleared · pointer only · e966d75ef97edd7f · report fixture: signature inputs:KerasTensor/2/float, dropout_rate:float/0/float, include_top:bool/0/bool · returned KerasTensor · level recorded 2026-09-25
upsample_conv self_supervised_3d_tasks/models/unet.py ran Apache-2.0 recorded; this copy not marked cleared · pointer only · e2d86f5679b725c2 · report fixture: signature filters:int/0/int, kernel_size:int/0/int, strides:int/0/int, padding:str/0/str · returned Conv2DTranspose · level recorded 2026-09-25
upsample_conv_3d self_supervised_3d_tasks/models/unet3d.py ran Apache-2.0 recorded; this copy not marked cleared · pointer only · 52b48cda55024c56 · report fixture: signature filters:int/0/int, kernel_size:int/0/int, strides:int/0/int, padding:str/0/str · returned Conv3DTranspose · level recorded 2026-09-25
upsample_simple self_supervised_3d_tasks/models/unet.py ran Apache-2.0 recorded; this copy not marked cleared · pointer only · d86c12d7bc272c23 · report fixture: signature filters:int/0/int, kernel_size:int/0/int, strides:int/0/int, padding:str/0/str · returned UpSampling2D · level recorded 2026-09-25
upsample_simple_3d self_supervised_3d_tasks/models/unet3d.py ran Apache-2.0 recorded; this copy not marked cleared · pointer only · aef4a468650afe2b · report fixture: signature filters:int/0/int, kernel_size:int/0/int, strides:int/0/int, padding:str/0/str · returned UpSampling3D · level recorded 2026-09-25
ResNet50 in 83 papers self_supervised_3d_tasks/models/resnet2d.py unverified Apache-2.0 recorded; this copy not marked cleared · pointer only · 19d6b316ce0edb54 · report
identity_block in 32 papers self_supervised_3d_tasks/models/resnet2d.py unverified Apache-2.0 recorded; this copy not marked cleared · pointer only · fa73582eb102fe4d · report

Tasks

Brain Tumor SegmentationDiabetic Retinopathy DetectionSelf-Supervised LearningTumor Segmentation

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

Methods

Contrastive Predictive CodingInfoNCEJigsawSPEED

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