MétaCan
Menu
Back to cohort
Record W4400102386 · doi:10.1093/ehjci/jeae142.016

Fully automated aortic diameter measurements on SPECT/CT attenuation maps in patients undergoing myocardial perfusion imaging

2024· article· en· W4400102386 on OpenAlexaff
Anusha Shanbhag, A N N A Michalowska, Wei Zhang, R J H Miller, M A R K Lemley, A N D R E W Einstein, Jiaming Liang, V A L E R I Builoff, Berman Ds, D A M I N I Dey, PJ Slomka

Bibliographic record

VenueEuropean Heart Journal - Cardiovascular Imaging · 2024
Typearticle
Languageen
FieldEngineering
TopicAdvanced X-ray and CT Imaging
Canadian institutionsUniversity of Calgary
Fundersnot available
KeywordsPerfusionCorrection for attenuationMedicineNuclear medicinePerfusion scanningMyocardial perfusion imagingRadiologyAttenuationCardiologyInternal medicinePositron emission tomographyPhysics

Abstract

fetched live from OpenAlex

Abstract Background SPECT/CT integrates functional nuclear medicine imaging with anatomic CT characteristics. Aortic diameter provides important information when increased, indicating patients at higher risk of aortic dissection or rupture, and is routinely evaluated on CT scans but rarely on CT attenuation correction (CTAC) maps from SPECT/CT. Purpose We aimed to develop a deep learning (DL) method for fully automatic aortic diameter measurements on CTAC in patients undergoing SPECT/CT myocardial perfusion imaging (MPI). Methods Figure 1 shows the study design. We included CTAC from patients undergoing SPECT/CT MPI from 2 sites participating in the REFINE SPECT registry. An open-source multi-structure CT segmentation was used to segment the aorta, pulmonary artery (PA), and 3 thoracic vertebrae (Th4-Th6). The diameter of the ascending (Asc) and descending (Desc) aorta was measured automatically at each slice (on average 7 slices) at the level of the PA bifurcation (Th4-Th6). The median value of all obtained measurements of the diameter of the Asc and Desc aorta was used in further analysis. The abnormal diameter of the Asc aorta was defined as an aortic diameter >40 mm whereas the abnormal diameter of the Desc aorta >30 mm. Abnormal myocardial perfusion was defined as total perfusion deficit (TPD) >5%. Results In total 4,589 patients were included, of whom 2,596 (56.6%) were male, and the median age was 66.0 (interquartile range [IQR] 57.0-74.0). During the median 3.6 years (2.0-5.0) follow-up, 352 (7.7%) patients died. The median Asc aorta diameter was 36.4 mm (33.6-39.4), whereas the median Desc aorta diameter was 30.8 mm (28.6-33.3). Patients with abnormal Asc and Desc aortic diameter were at higher risk of death compared to subjects with normal aortic diameter (Asc aorta - unadjusted hazard ratio [HR] 1.37, 95% CI 1.08-1.74, p=0.01; Desc aorta – unadjusted HR 1.9, 95% CI 1.51-2.40, p<0.001) (Figure 2). Abnormal TPD was present in 2,302 (50.2%) patients. Patients with normal TPD and abnormal Asc aortic diameter were at higher risk of death compared to patients with normal TPD and normal Asc aorta diameter (unadjusted HR 1.26, 95% CI 0.83-1.90, p=0.27). Subjects with normal TPD and abnormal Desc aorta diameter had an elevated risk of death compared to patients with abnormal TPD and normal Desc aorta diameter (unadjusted HR 2.10, 95% CI 1.43-3.08, p<0.001). Patients with abnormal TPD and abnormal Asc aortic diameter were at higher risk of death compared to patients with abnormal TPD and normal Asc aorta diameter (unadjusted HR 1.35, 95% CI 1.00-1.81, p=0.04). Moreover, subjects with abnormal TPD and abnormal Desc aorta diameter had an elevated risk of death compared to patients with abnormal TPD and normal Desc aorta diameter (unadjusted HR 1.57, 95% CI 1.18-2.10, p<0.001). Conclusion DL-based aortic diameter measurements on CTAC in patients undergoing SPECT/CT MPI can help identify patients at higher risk of death due to abnormal aortic diameter.

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 distilled prediction

Teacher imitation

Not calibrated prevalence, not ground truth. Human validation pending. Learned from the 10,348 direct Codex labels and 10,348 direct Gemma labels. Candidate is the union of thresholded teacher heads; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels or direct frontier model labels.

metaresearch head score (Codex)0.002
metaresearch head score (Gemma)0.000
Version: codex-gemma-dda1882f352aValidation status: machine_predicted_unvalidated
Candidate categoriesMeta-epidemiology (narrow)
Consensus categoriesnone
DomainCandidate signal: none · Consensus signal: none
Study designCandidate signal: Simulation or modeling · Consensus signal: none
GenreCandidate signal: Empirical · Consensus signal: Empirical
Teacher disagreement score0.388
Threshold uncertainty score1.000

Codex and Gemma teacher scores by category

CategoryCodexGemma
Metaresearch0.0020.000
Meta-epidemiology (narrow)0.0000.000
Meta-epidemiology (broad)0.0000.001
Bibliometrics0.0010.001
Science and technology studies0.0000.000
Scholarly communication0.0010.001
Open science0.0000.000
Research integrity0.0000.001
Insufficient payload (model declined to judge)0.0000.000

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.

Opus teacher head0.016
GPT teacher head0.235
Teacher spread0.219 · how far apart the two teachers sit on this one work
Validation statusscore_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from it

Classification

machine, unvalidated

Machine predicted; a candidate call from one teacher head, not a consensus.

Study designSimulation or modeling
Domainnot available
GenreEmpirical

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".

Quick stats

Citations1
Published2024
Admission routes1
Has abstractyes

Explore more

Same venueEuropean Heart Journal - Cardiovascular ImagingSame topicAdvanced X-ray and CT ImagingFrench-language works237,207