Evaluation of Segmentation Quality in Magnetic Resonance Images Using Singular Value Decomposition: A Feasibility Study
Bibliographic record
Abstract
In the present research work, the use of Singular Value Decomposition is investigated as part of an evaluation metric for the segmentation quality of regions of interest in magnetic resonance imaging used in an experiment of High-Intensity Focused Ultrasound therapy. Accurate segmentation is essential for clinical and research applications in computer vision. However, current evaluation methods have limitations in sensitivity to the shape of segmented objects, highlighting the need for a quantitative shape-sensitive metric. SVD is a promising tool for assessing segmentation similarity to ground truths in therapy planning images through component comparison. The proposed$S_{F}$metric shows strong positive correlations with Global Consistency Error scores across transverse and sagittal images. In the air region, correlations range from 0.66 (transverse) to 0.75 (sagittal), in the gel-pad from 0.72 to 0.91, in tissue from 0.87 to 0.91, in the transducer from 0.78 to 0.91, and in water from 0.93 to 0.94, indicating that SFcan capture structural similarities and segmentation consistency as GCE evaluates alignment with the ground truth, focusing on boundary accuracy and region continuity. The findings suggest that this tool could enhance sensitivity to object shapes in medical image analysis, improving segmentation quality assessments, clinical diagnostics, and treatment planning.
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 | 0.009 | 0.026 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.001 | 0.001 |
| Bibliometrics | 0.002 | 0.001 |
| Science and technology studies | 0.000 | 0.001 |
| Scholarly communication | 0.001 | 0.001 |
| Open science | 0.001 | 0.001 |
| Research integrity | 0.001 | 0.000 |
| 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".