When Federated Learning Meets Medical Image Analysis: A Systematic Review with Challenges and Solutions
Bibliographic record
Abstract
Deep learning has been a powerful tool for medical image analysis, but large amount of high-quality labeled datasets are generally required to train deep learning models with satisfactory performance and generalization capability. In medical applications, collecting such large-scale datasets involves specific challenges: data annotation is time-consuming and expert-requisite, and privacy restrictions make it impractical for different institutions to share their own data to construct single large datasets. Federated learning (FL) is an effective method for addressing such concerns since it allows multiple institutions to collaboratively train deep learning models, without sharing individual data samples directly, in line with privacy protection requirements. However, there are numerous challenges when applying FL in medical image analysis, including data heterogeneity and low label quality, that may impede FL from being implemented effectively. This paper conducts a systematic literature review of the challenges and solutions when applying FL in medical image analysis. We present a novel taxonomy of FL-specific challenges in medical image analysis research and summarize representative solutions for these challenges. We anticipate this review will be proved helpful for researchers to have better knowledge of challenges and existing solutions in related fields, and provide inspiration for developing more advanced solutions in the future.
Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.
How this classification was reachedexpand
Full frame machine prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. The Gemma side is a direct model label for every work in the frame, read from the title-only record. The Codex side is a classifier learned from the 10,348 direct Codex labels and calibrated to design-weighted sample rates; fields without enough sample support carry no Codex call. Candidate is the union of the two sides; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels.
Distilled classifier scores by category (both heads)
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.007 | 0.024 |
| Meta-epidemiology (narrow) | 0.001 | 0.001 |
| Meta-epidemiology (broad) | 0.004 | 0.003 |
| Bibliometrics | 0.007 | 0.006 |
| Science and technology studies | 0.000 | 0.001 |
| Scholarly communication | 0.003 | 0.004 |
| Open science | 0.002 | 0.001 |
| Research integrity | 0.002 | 0.002 |
| Insufficient payload (model declined to judge) | 0.003 | 0.001 |
Machine scores (provisional)
The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.
Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.
score_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from itClassification
machine, unvalidatedMachine predicted; a candidate call from one source (direct Gemma or distilled Codex), not a consensus.
How this classification was reached, model by model and score by score, is at the end of the page under "How this classification was reached".