Comparing knowledge-based 3D Reconstruction to Conventional MRI Algorithms Measuring Left Cardiac Chamber Volumes in Pediatrics
Bibliographic record
Abstract
Abstract Objectives: Compare accuracy of 3D knowledge-based reconstruction (3D KBR) algorithm to standard measurement of left atrial (LA) and left ventricle (LV) volumes.Background: Accurate measurement of LV and LA volume is essential in assessing cardiac function. Cardiac magnetic resonance imaging (CMR) is the gold standard, but analysis is relatively time consuming. Our study compared analysis time and agreement of 3D KBR algorithm to conventional CMR. Methods: CMR studies of children aged 3-17 years with iron-overload were analyzed. DiCOM data was uploaded into the 3D KBR software calculated the LA and LV volumes in end systole and diastole, and ejection fraction. LA volumes were calculated using biplane method. LV measurements were calculated using Simpson's method (using a short axis stack) (SAX) technique. These methods were compared using intraclass coefficients (ICC) and Bland-Altman plots.Results: 71 CMR studies of 31 patients were analyzed. No mean bias between SAX and VMS (Ventripoint software) measurement of LV end diastolic volume (EDV), biplane and VMS measurements of LA end systolic volume (ESV) or LA EDV were found. A small positive bias in VMS LV ESV; with moderate agreement in LV EDV, LA ESV and LV ejection fraction (EF)/ LA EF and wider limits of agreement in LV ESV and LA EDV. Excellent correlation between SAX and VMS in measuring LV volumes, biplane and VMS LA volumes. Interobserver agreement for VMS LV and LA volumes were excellent. VMS LV analysis time was 2.43 min and VMS LA analysis time was 1.46 min.Conclusion: 3DKBR offers a time efficient alternative with comparable accuracy to the current LV and LA measurements used in clinical practice.
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 | 0.004 | 0.019 |
| Meta-epidemiology (narrow) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.000 |
| Bibliometrics | 0.002 | 0.001 |
| Science and technology studies | 0.000 | 0.000 |
| 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".