A Lightweight Attention-Enhanced SegResNet for Medical Image Segmentation: Design, Evaluation, and CPU-Based Deployment
Bibliographic record
Abstract
We present a lightweight segmentation framework tailored for medical image analysis and optimized for deployment on low-cost edge devices. The proposed model is built upon SegResNet and integrates channel-wise attention (SE module) to enhance feature representation without significantly increasing computational burden. Using the VerSe spinal CT dataset, we benchmarked four lightweight architectures and found that the attention-enhanced SegResNet achieved the best trade-off between segmentation accuracy, model complexity, and CPU inference speed. The trained model was exported in ONNX format and successfully deployed on an entry-level E5 industrial computer without a dedicated GPU, with total system cost (including display) under $120. The complete system runs smoothly in offline environments without internet dependency, further enhancing its suitability for primary healthcare scenarios. The full deployment pipeline includes preprocessing, segmentation, and visualization, making it feasible for real-world application in rural or resource-constrained healthcare institutions. This work offers a practical and reproducible solution for accessible AI-powered medical assistance.
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 | 0.000 |
| Bibliometrics | 0.001 | 0.001 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.001 | 0.001 |
| Open science | 0.002 | 0.001 |
| Research integrity | 0.001 | 0.001 |
| Insufficient payload (model declined to judge) | 0.007 | 0.003 |
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".