Papers › Robust and Efficient Medical Imaging with Self-Supervision

Robust and Efficient Medical Imaging with Self-Supervision

19 May 2022arXiv:2205.09723archive 2025-07-28

Shekoofeh Azizi, Laura Culp, Jan Freyberg, Basil Mustafa, Sebastien Baur, Simon Kornblith, Ting Chen, Patricia MacWilliams, S. Sara Mahdavi, Ellery Wulczyn, Boris Babenko, Megan Wilson, Aaron Loh, Po-Hsuan Cameron Chen, YuAn Liu, Pinal Bavishi, Scott Mayer McKinney, Jim Winkens, Abhijit Guha Roy, Zach Beaver, Fiona Ryan, Justin Krogue, Mozziyar Etemadi, Umesh Telang, Yun Liu, Lily Peng, Greg S. Corrado, Dale R. Webster, David Fleet, Geoffrey Hinton, Neil Houlsby, Alan Karthikesalingam, Mohammad Norouzi, Vivek Natarajan

Recent progress in Medical Artificial Intelligence (AI) has delivered systems that can reach clinical expert level performance. However, such systems tend to demonstrate sub-optimal "out-of-distribution" performance when evaluated in clinical settings different from the training environment. A common mitigation strategy is to develop separate systems for each clinical setting using site-specific data [1]. However, this quickly becomes impractical as medical data is time-consuming to acquire and expensive to annotate [2]. Thus, the problem of "data-efficient generalization" presents an ongoing difficulty for Medical AI development. Although progress in representation learning shows promise, their benefits have not been rigorously studied, specifically for out-of-distribution settings. To meet these challenges, we present REMEDIS, a unified representation learning strategy to improve robustness and data-efficiency of medical imaging AI. REMEDIS uses a generic combination of large-scale supervised transfer learning with self-supervised learning and requires little task-specific customization. We study a diverse range of medical imaging tasks and simulate three realistic application scenarios using retrospective data. REMEDIS exhibits significantly improved in-distribution performance with up to 11.5% relative improvement in diagnostic accuracy over a strong supervised baseline. More importantly, our strategy leads to strong data-efficient generalization of medical imaging AI, matching strong supervised baselines using between 1% to 33% of retraining data across tasks. These results suggest that REMEDIS can significantly accelerate the life-cycle of medical imaging AI development thereby presenting an important step forward for medical imaging AI to deliver broad impact.

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 28 code samples harvested from 2 repositories linked to this paper: 20 ran (of which 0 constructed an object rather than computing a result; 16 with no instrument failure: 0 honoured, 1 violated, 15 with no contract checked; 4 where Syntology's instrument failed) · 8 unverified. Where Syntology's instrument failed: 4 where our contract draft was wrong; failures of Syntology's instrument, not of the code.

By repository: official repository: 16 samples from 1 repository, 11 ran (9 with no instrument failure; 2 where Syntology's instrument failed); community (archive-listed): 12 samples from 1 repository, 9 ran (7 with no instrument failure; 2 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 2026-09-26 (UTC): the dates Syntology's graph wrote each sample's verification level, not when the code executed.

google-research/big_transfer officialmentioned in paperjaxApache-2.0Syntology: 16 samples, 11 ran (2 instrument-failed) · 5 unverified report
google-research/medical-ai-research-foundations mentioned on GitHubtfApache-2.0Syntology: 12 samples, 9 ran (2 instrument-failed) · 3 unverified report
mahmoodlab/hest mentioned on GitHubpytorchSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to HEST-1k: A Dataset for Spatial Transcriptomics and Histology Image Analysis (arXiv:2406.16192; that paper's own run record: 1 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified) and Deep Learning for BioImaging: What Are We Really Learning? (arXiv:2603.13377; that paper's own run record: 5 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 2 honoured, 0 violated, 0 with no contract checked; 3 where Syntology's instrument failed) · 1 unverified); nothing checks that they implement this paper's method. 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

28 samples harvested: 20 ran (of which 0 constructed an object rather than computing a result; 16 with no instrument failure: 0 honoured, 1 violated, 15 with no contract checked; 4 where Syntology's instrument failed) · 8 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 · violated contract
4ran · our draft was wrong
15ran
8unverified

Licence: 0 of the 28 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 2 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.

google-research/big_transfer official repository 16 samples, 11 ran (2 instrument-failed) · 5 unverified
add_name_prefix bit_tf2/models.py ran fingerprinted Apache-2.0 (permissive) · 113df01dadeca915 · report fixture: signature name:str/0/str, prefix:str/0/str · returned str · level recorded 2026-09-24
conv1x1 in 691 papers bit_pytorch/models.py ran · our draft was wrong Apache-2.0 (permissive) · ee80cf467065076b · report fixture: signature cin:int/0/int, cout:int/0/int, stride:int/0/int, bias:bool/0/bool · returned StdConv2d · level recorded 2026-09-22
conv3x3 in 1,376 papers bit_pytorch/models.py ran · our draft was wrong Apache-2.0 (permissive) · f01b8d3901f0b289 · report fixture: signature cin:int/0/int, cout:int/0/int, stride:int/0/int, groups:int/0/int, bias:bool/0/bool · returned StdConv2d · level recorded 2026-09-22
fixed_padding in 28 papers bit_jax/models.py ran Apache-2.0 (permissive) · d65ebdb640d62fc2 · report fixture: signature x:ArrayImpl/4/float, kernel_size:int/0/int · returned ArrayImpl · level recorded 2026-09-24
get_mixup in 5 papers bit_hyperrule.py ran fingerprinted Apache-2.0 (permissive) · 7d63034d0bfadd78 · report fixture: signature dataset_size:int/0/int · returned float · level recorded 2026-09-25
get_resolution in 5 papers bit_hyperrule.py ran fingerprinted Apache-2.0 (permissive) · a933bb17fdb8ebb4 · report fixture: signature original_resolution:tuple/1/int · returned tuple · level recorded 2026-09-26
get_resolution_from_dataset bit_hyperrule.py ran Apache-2.0 (permissive) · 53256b67d70b0daf · report fixture: signature dataset:str/0/str · returned tuple · level recorded 2026-09-26
group_normalize bit_tf2/normalization.py ran Apache-2.0 (permissive) · 65a7c9919024b795 · report fixture: signature x:EagerTensor/4/float, gamma:EagerTensor/1/float, beta:EagerTensor/1/float, num_groups:int/0/int, group_size:NoneType/0/?, eps:float/0/float · returned EagerTensor · level recorded 2026-09-24
setup_logger in 122 papers bit_common.py ran Apache-2.0 (permissive) · 12323f0640436acc · report fixture: signature args:Args/0/? · returned Logger · level recorded 2026-09-25
standardize in 47 papers bit_jax/models.py ran Apache-2.0 (permissive) · c272f024d815d59d · report fixture: signature x:ArrayImpl/2/float, axis:int/0/int, eps:float/0/float · returned ArrayImpl · level recorded 2026-09-24
tf2th in 19 papers bit_pytorch/models.py ran · violated contract fingerprinted Apache-2.0 (permissive) · 7023eb86801bb3a3 · report fixture: signature conv_weights:ndarray/4/float · returned Tensor · level recorded 2026-09-22
create_dat in 6 papers bit_pytorch/lbtoolbox.py unverified Apache-2.0 (permissive) · d38eeb648f68f197 · report
find_fewshot_indices bit_pytorch/fewshot.py unverified Apache-2.0 (permissive) · eec365515fbb2119 · report
find_indices_loader bit_pytorch/fewshot.py unverified Apache-2.0 (permissive) · 55be7cb60b3a523c · report
load_dat in 7 papers bit_pytorch/lbtoolbox.py unverified Apache-2.0 (permissive) · 12109eac56e48b6b · report
sample_subset input_pipeline_tf2_or_jax.py unverified Apache-2.0 (permissive) · 1614afcca20ebedf · report
google-research/medical-ai-research-foundations community (archive-listed) 12 samples, 9 ran (2 instrument-failed) · 3 unverified
add_contrastive_loss objective.py ran · our draft was wrong Apache-2.0 (permissive) · 8924ee1d1cde05c4 · report fixture: signature hidden:SymbolicTensor/2/float, hidden_norm:bool/0/bool, temperature:float/0/float, tpu_context:NoneType/0/?, weights:float/0/float · returned tuple · level recorded 2026-09-22
add_supervised_loss objective.py ran Apache-2.0 (permissive) · 8af989f02c354e14 · report fixture: signature labels:SymbolicTensor/2/float, logits:SymbolicTensor/2/float, weights:SymbolicTensor/1/float · returned SymbolicTensor · level recorded 2026-09-25
dropblock resnet.py ran Apache-2.0 (permissive) · a068248c1b6c4117 · report fixture: signature net:SymbolicTensor/4/float, is_training:bool/0/bool, keep_prob:float/0/float, dropblock_size:int/0/int, data_format:str/0/str · returned SymbolicTensor · level recorded 2026-09-24
equalize_histogram_fn data_util.py ran Apache-2.0 (permissive) · 6cc1fe250eeb4811 · report fixture: signature image:SymbolicTensor/3/float · returned SymbolicTensor · level recorded 2026-09-24
fixed_padding in 28 papers resnet.py ran Apache-2.0 (permissive) · b1b73febd494c9b7 · report fixture: signature inputs:SymbolicTensor/4/float, kernel_size:int/0/int, data_format:str/0/str · returned SymbolicTensor · level recorded 2026-09-24
pad_to_batch data.py ran Apache-2.0 (permissive) · 0c26c80b6286f5ec · report fixture: signature dataset:DatasetV1Adapter/0/?, batch_size:int/0/int · returned DatasetV1Adapter · level recorded 2026-09-25
random_apply in 8 papers data_util.py ran Apache-2.0 (permissive) · d04f187058cb2a9c · report fixture: signature func:callable/0/?, p:float/0/float, x:SymbolicTensor/1/float · returned SymbolicTensor · level recorded 2026-09-25
random_brightness in 6 papers data_util.py ran Apache-2.0 (permissive) · 6c4f36fab52ddbe9 · report fixture: signature image:SymbolicTensor/4/float, max_delta:float/0/float · returned SymbolicTensor · level recorded 2026-09-24
tpu_cross_replica_concat objective.py ran · our draft was wrong Apache-2.0 (permissive) · 7aac0de5d1568953 · report fixture: signature tensor:SymbolicTensor/2/float, tpu_context:TPUContext/0/? · returned SymbolicTensor · level recorded 2026-09-22
get_train_steps in 5 papers model_util.py unverified Apache-2.0 (permissive) · 14ec8ff095316493 · report
learning_rate_schedule in 15 papers model_util.py unverified Apache-2.0 (permissive) · fb45bd9f63767265 · report
linear_layer in 18 papers model_util.py unverified Apache-2.0 (permissive) · c2be9d262aacedc9 · report

Tasks

DiagnosticRepresentation LearningSelf-Supervised LearningTransfer Learning

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

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