Active Learning for Lesion Segmentation Using Contrastive Learning with Strong Augmentation
Bibliographic record
Abstract
Active learning effectively reduces annotation costs while enhancing model performance in medical image segmentation tasks. One-shot active learning presents a highly practical scenario where valuable samples for annotation are selected in a single round. However, current one-shot active learning methods predominantly rely on sampling selection methods based on global information. In contrast, focusing on the selection of features specific to local lesion regions would be more targeted and effective. In this work, we introduce a novel deep active learning framework specifically designed for pathological lesion segmentation tasks. To enable the model to effectively capture lesion-related regions of interest, we propose a strong augmentation strategy for image samples in self-supervised contrastive training. These strong augmentation samples are generated through cluster-based background subtraction using cluster projector, thereby emphasizing the features of the target lesion and improving the model's sensitivity to these areas. We utilize the Segment Anything Model as the base model to facilitate training and sample selection in a one-shot manner. Experimental results on two lesion segmentation datasets demonstrate that the proposed framework outperforms several existing active learning methods.
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 | 0.002 | 0.004 |
| Meta-epidemiology (narrow) | 0.001 | 0.001 |
| Meta-epidemiology (broad) | 0.001 | 0.001 |
| Bibliometrics | 0.001 | 0.001 |
| Science and technology studies | 0.000 | 0.001 |
| Scholarly communication | 0.001 | 0.002 |
| Open science | 0.003 | 0.002 |
| Research integrity | 0.002 | 0.002 |
| 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 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".