A Novel Continual Learning Approach for Robust Medical Image Segmentation
Bibliographic record
Abstract
Medical image segmentation is crucial for computeraided diagnosis, yet traditional deep learning models often fail to generalize across different domains due to variations in acquisition settings. We propose a source-free, integrated novel continual learning scheme for domain-incremental medical image segmentation. Our scheme consists of three different steps that use U-Net to train on a source domain in the first step, evaluate zeroshot performance on a target domain in the second step, and reevaluate on the source to assess forgetting in the third step. Without accessing prior data during adaptation, our method remains privacy-preserving and scalable. Experiments show high performance on the source domain, competitive results on the target domain, and minimal forgetting. The performances are measured in terms of dice score, Hausdorff distance (HD), and average symmetric surface distance (ASSD). Compared to the state-of-the-art, our approach balances generalization and retention, showing robustness under domain shifts. Our proposed work establishes a reproducible and clinically practical benchmark using continual learning in segmentation.
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 distilled prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. Learned from the 10,348 direct Codex labels and 10,348 direct Gemma labels. Candidate is the union of thresholded teacher heads; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels or direct frontier model labels.
Codex and Gemma teacher scores by category
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.002 | 0.001 |
| Meta-epidemiology (narrow) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.000 |
| Bibliometrics | 0.000 | 0.001 |
| Science and technology studies | 0.001 | 0.000 |
| Scholarly communication | 0.001 | 0.001 |
| Open science | 0.001 | 0.000 |
| Research integrity | 0.000 | 0.001 |
| Insufficient payload (model declined to judge) | 0.001 | 0.000 |
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 teacher head, 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".