Poster - Wed Eve-50: Correcting for Fat-Shift Artifacts in Magnetic Resonance Images
Bibliographic record
Abstract
The inclusion of magnetic resonance (MR) images in radiation therapy treatment planning has been hampered by inherent image distortions. As such, distortion correction algorithms have been under investigation for many years. Although distortion maps can be derived through a number of methods, a common problem arises when the resultant distortion transformation is not unique. This situation is present at the interfaces between tissues experiencing different chemical shift environments (i.e. at fat / water boundaries), and leads to hypo- and hyper-intense artifacts in the distorted image. Correcting image distortion by interpolating between true and distorted coordinates cannot fully correct for the erroneous high intensity region because the distortion transformation at such locations is not unique. Thus, residual distortion artifacts remain and may hinder the accurate delineation of areas associated with fat signal, i.e. external body contours. Here we propose a series of image processing steps which are carried out prior to the standard distortion correction procedure. The method involves establishing regions of signal overlap in the distorted image (i.e. where the distortion transformation is not unique) and separating the resultant high signal into the water-based signal component and the shifted fat-based signal component. The fat signal is unshifted prior to the standard distortion correction technique. When the described methods are applied, the residual high-intensity regions associated with the chemical shift artifact can be eliminated.
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 | 0.002 | 0.003 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.001 |
| Bibliometrics | 0.001 | 0.001 |
| Science and technology studies | 0.001 | 0.001 |
| Scholarly communication | 0.001 | 0.001 |
| Open science | 0.001 | 0.001 |
| Research integrity | 0.001 | 0.001 |
| Insufficient payload (model declined to judge) | 0.017 | 0.010 |
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".