Research on image segmentation techniques based on algebraic topology methods in computer vision
Bibliographic record
Abstract
Medical image segmentation is the basis for realizing intelligent medical treatment, and plays a very important clinical significance in the localization and identification of lesion areas and the formulation of surgical plans.In this paper, we investigate the image segmentation techniques based on algebraic topology methods in computer vision, and propose an image segmentation network model based on asymmetric topology preservation (ATSNet), with a view to applying it to clinical practice.The ATSNet model adopts the parallel branching structure of CNN and Transformer in the coding part, and proposes a hybrid feature aggregation strategy (HFAS) to achieve image segmentation with high efficiency.Comparison experiments on three benchmark datasets and one clinical dataset prove that the ATSNet model proposed in this paper achieves better results on different datasets, and the statistical analysis results obtained by the model are consistent with those of clinical experts (P>0.05).Meanwhile, ablation experiments demonstrate the effectiveness of the hybrid feature aggregation strategy used in this paper in improving the image segmentation performance of the model.In addition, the proposed method in the Transformer branch when the number of network layers is 3 when the overall accuracy of the largest, and the use of bilateral filtering can be better edge retention, improve the effect of image segmentation.This paper provides a technical path for the practical application of image segmentation technology.
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 | 0.003 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.001 | 0.001 |
| Bibliometrics | 0.002 | 0.002 |
| Science and technology studies | 0.000 | 0.001 |
| Scholarly communication | 0.001 | 0.004 |
| Open science | 0.001 | 0.001 |
| Research integrity | 0.001 | 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 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".