Swin UNet: a memory-efficient and accurate deep learning model for medical image segmentation
Bibliographic record
Abstract
Medical image segmentation is a challenging and important task that aims to identify and separate different anatomical structures or pathological regions from complex and noisy image data. However, most existing deep learning models for medical image segmentation are based on convolutional neural networks (CNNs), which have high memory consumption and limited spatial reasoning capabilities. In this paper, we propose a novel deep learning model for medical image segmentation based on Swin UNET, which combines the self-attention mechanism of Swin Transformer and the encoder-decoder architecture of U-Net. We also propose a memory management strategy that optimizes the number of heads of the multi-head self-attention mechanism using probabilistic mirror flipping and grid search. We conduct extensive experiments on a challenging medical image segmentation dataset and demonstrate that our model and strategy achieve comparable or better accuracy than the state-of-the-art models while significantly reducing the memory usage. Our model and strategy are robust and generalizable, as they can handle arbitrary input resolutions, scales, and modalities, and achieve state-of-the-art performance on a challenging medical image segmentation dataset. Our study contributes to the advancement of the research field of medical image segmentation, and provides a practical and scalable solution for real-world application scenarios with limited resources.
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 | 0.001 |
| 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 | 0.001 |
| Research integrity | 0.001 | 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".