MétaCan
Menu
← Back to cohort
Record W1967789417 · doi:10.1118/1.3244150

Poster — Wed Eve—46: Quantitative Evaluation on the Accuracy of Image Registration Methods in SPECT Guided Radiation Therapy for Lung Cancer Patients

2009· article· en· W1967789417 on OpenAlexaff
Lingshu Yin, Lisa Tang, Ghassan Hamarneh, Vitali Moiseenko, A. Ćeller, Sergey Shcherbinin, T‐F Fua, Anna Thompson, M Liu, Cheryl Duzenli, B.S. Gill, Finbar Sheehan, John Powe, Daniel F. Worsley

Bibliographic record

VenueMedical Physics · 2009
Typearticle
Languageen
FieldMedicine
TopicRadiomics and Machine Learning in Medical Imaging
Canadian institutionsVancouver General HospitalSimon Fraser UniversityUniversity of British ColumbiaBC Cancer Agency
Fundersnot available
KeywordsImage registrationNuclear medicineSingle-photon emission computed tomographyArtificial intelligenceMedical imagingRadiation treatment planningComputer scienceMedicineComputer visionRadiation therapyRadiologyImage (mathematics)

Abstract

fetched live from OpenAlex

Purpose: To quantitatively evaluate the accuracy of several SPECT/CT image registration methods in recent studies and its impact on the functional lung volume segmentation in SPECT guided radiation therapy (RT) treatment planning. Methods and Materials: Five lung cancer patients were consented to have a perfusion SPECT scan with 99mTc‐macroaggregated albumin. During the scan, a low resolution CT image was acquired using the SPECT/CT scanner. This CT scan was co‐registered to the patient's planning CT scan through four rigid and deformable image registration programs (rigid registration, skin/lung control points based registration and B‐spline deformable registration). After the CT to CT co‐registration, original SPECT reconstructions were warped and co‐registered to the planning CT scan. The functional lung volumes were segmented from each deformed SPECT using 10, 20, …, 90% of maximum pixel value as a threshold. The differences in the size and contours of each functional volume were calculated. Results: Based on the evaluation of registered CT images, the result from B‐spline registration demonstrated the smallest intensity difference. Using the warped SPECT images obtained from this registration method as a reference, the smallest difference in the size and contour of functional volumes was found using rigid registration. In the point‐based registrations, a better result was found when the control points were placed on lung volume instead of body contour. Conclusion: Apply B‐spline based image registration method in SPECT‐guided RT studies was shown to be accurate. Point‐based image registration using skin markers with a standalone SPECT scanner was found least accurate.

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 imitation

Not 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.

metaresearch head score (Codex)0.004
metaresearch head score (Gemma)0.009
Version: metacan-v3-hybrid-931329e0061cValidation status: machine_predicted_unvalidated
Candidate categoriesnone
Consensus categoriesnone
DomainCandidate signal: none · Consensus signal: none
Study designCandidate signal: Observational · Consensus signal: none
GenreCandidate signal: Empirical · Consensus signal: Empirical
Teacher disagreement score0.004
Threshold uncertainty score0.021

Distilled classifier scores by category (both heads)

CategoryCodexGemma
Metaresearch0.0040.009
Meta-epidemiology (narrow)0.0000.000
Meta-epidemiology (broad)0.0000.001
Bibliometrics0.0010.000
Science and technology studies0.0000.000
Scholarly communication0.0010.000
Open science0.0000.000
Research integrity0.0010.000
Insufficient payload (model declined to judge)0.0030.001

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.

Opus teacher head0.057
GPT teacher head0.479
Teacher spread0.422 · 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 source (direct Gemma or distilled Codex), not a consensus.

The models applied no category: nothing in the taxonomy fit this work.
Study designObservational
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

Citations0
Published2009
Admission routes1
Has abstractyes

Explore more

Same venueMedical Physics→Same topicRadiomics and Machine Learning in Medical Imaging→French-language works237,207→