Federated Learning for Multi-Center Medical Image Classification Using Deep Learning Models
Bibliographic record
Abstract
Artificial intelligence is being applied in numerous industries, including healthcare among others.Due in great part to needs like dependable findings, data security, exact prediction, and a volume of data, among other things, research is being undertaken in the AI-enabled healthcare market.Regarding conventional deep learning models, datasets saved on a single device are used throughout the training process.Training the data calls for both highly efficient equipment and a lot of storage capacity.The work shown here suggests a federated learning approach suitable for five different customers.9702 ultrasonic images of the gallbladder (GB) correspond with eight distinct disease types.Every client owns a part of the dataset with some unique classes from those of other clients.This is so since clients have divided the dataset.Two deep learning models applied and assessed in this work were CNN and VGG16.Clients used both models as well as the global ones.This paper proposes a possible global model solution based on the FedAvg aggregation method.The results show that VGG16 shows better outcomes in classification for both the client and the global model with a 99% accuracy rate in FL and a 94% accuracy rate for local training alone operations.CNN shows accuracy with a 99% in Florida and an 81% for local training initiatives.
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 | 0.001 | 0.002 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.001 | 0.001 |
| Bibliometrics | 0.001 | 0.001 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.001 | 0.001 |
| Open science | 0.001 | 0.001 |
| Research integrity | 0.002 | 0.001 |
| Insufficient payload (model declined to judge) | 0.002 | 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".