Quantitative evaluation method of image segmentation techniques for Magnetic Resonance guided High Intensity Focused Ultrasound therapy
Bibliographic record
Abstract
This paper describes a quantitative evaluation method for the accuracy of two different segmentation techniques for the treatment planning of Magnetic Resonance guided High Intensity Focused Ultrasound (MRgHIFU). The first technique is a combination of image segmentation methods consisting of Otsu's method, global, edge detection with Laplacian of Gaussian method, region growing algorithm and variable thresholding method. The second technique is a combination of image segmentation methods consisting of Otsu's method and the selection of regions using variable thresholding. These methods were used to classify the pixels of real Magnetic Resonance (MR) images obtained for the study of the distribution of heat in abscess treatment in a murine model with High-Intensity Focused Ultrasound (HIFU). In the evaluation, a total of nine surveys of 48 images each were used, and a methodology including three main steps was followed: establishment of ground truth images and calculation of areas from the segmented images, discrepancy measure calculation, and data normalization. For the evaluation an area-based metric was used and it was based on a discrepancy measure proposed for two regions and on the generalized version for c regions. After the evaluation of both segmentation techniques it was found that they presented a better performance in axial MR images than in sagittal MR images. In sagittal MR images, the average error and standard deviation error measures indicated a high variability in the segmentation for both techniques. Due to the performance of the segmentation for sagittal images, improvements will be implemented taking into account the combination of the evaluated methods in order to exploit the benefits of each one.
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 | 0.011 | 0.020 |
| Meta-epidemiology (narrow) | 0.001 | 0.001 |
| Meta-epidemiology (broad) | 0.001 | 0.001 |
| Bibliometrics | 0.005 | 0.003 |
| Science and technology studies | 0.001 | 0.001 |
| Scholarly communication | 0.002 | 0.001 |
| Open science | 0.001 | 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".