A Synthesized Image Reconstruction Based Harmonization (Sirch)
Bibliographic record
Abstract
We describe a Synthesized Image ReConstruction based Harmonization (SIRCH) which achieves harmonization between images acquired from different scanners while minimizing the degradation in PET quantification within small structures. Our SIRCH transform is based on the recently proposed synthesized image reconstruction frame work as well as a unified PSF reconstruction engine with an advanced deep learning (DL) assisted de-noising (i.e. a modified DL HYPR4D kernel method). For proof-of-concept, our immediate aim is to transform the lower sensitivity HRRT PET images reconstructed with standard OSEM to match with the target SIGNA PET/MRI images from a current state-of-the-art TOF reconstruction with PSF modeling (i.e. DL init PSF-HYPR4D-K). The SIRCH method was first tested using experimental contrast phantom data and then using the same human subject18F-FDG and11C-DTBZ data acquired on both HRRT and SIGNA PET/MRI. Without any pre-/post-processing optimization, the sphere contrast recovery coefficients (%CRC) agreed within$\sim 5 \%$between the SIRCH transformed HRRT and the target SIGNA PET/MRI images. Human data showed similar trends; e.g. SUVR within the$\sim 4 ~\text{mm}$inferior colliculus structure from18F-FDG images agreed within 3 %, and11C-DTBZ BPNDwithin the striatal region also agreed within 3 % between the SIRCH transformed HRRT and the target SIGNA PET/MRI images while preserving the quantification within the structures. For comparison, postfiltering based harmonization with a target resolution of 5 mm FWHM produced a 10-20% underestimation bias within the small structures. Further optimization of the proposed SIRCH method is currently under investigation.
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 | 0.001 |
| Bibliometrics | 0.001 | 0.001 |
| Science and technology studies | 0.000 | 0.001 |
| Scholarly communication | 0.001 | 0.001 |
| Open science | 0.001 | 0.002 |
| Research integrity | 0.001 | 0.001 |
| Insufficient payload (model declined to judge) | 0.005 | 0.002 |
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".