Implementación de un algoritmo para la registración elástica de imágenes médicas
Bibliographic record
Abstract
La registracion de imagenes es el proceso de establecer correspondencia entre dos imagenes adquiridas en diferentes momentos y/o a traves de distintas modalidades. Existe en la actualidad un interes generalizado de relacionar informacion proveniente de diferentes imagenes de forma precisa, ya sea para diagnostico, tratamiento o ciencia basica. El objetivo central del trabajo consiste en evaluar un algoritmo de registracion 3D, con minima intervencion del usuario, robusto, versatil, con tiempos de computo acordes a la clinica rutinaria corriendo en una computadora de escritorio estandar. Se espera que el mismo sea potencialmente extensible a registraciones intermodalidad. Se presenta aqui la implementacion a nivel de software de una metodologia de registracion 3D con deformaciones de forma libre, por medio de calculo variacional. Para el desarrollo se utiliza el lenguaje de programacion C++ con herramientas de software libre. Se prueba exhaustivamente el desempeno del algoritmo implementado en registraciones intramodalidad y se realizan pruebas de registracion intermodalidad, preprocesando las imagenes por medio de filtrado y normalizacion de los rangos dinamicos de intensidad. A nivel intramodalidad se evalua el desempeno sobre imagenes de TAC de pacientes, sobre imagenes de TAC y SPECT de fantomas fisicos deformables elasticamente desarrollados ad hoc, y sobre imagenes de TAC de pacientes deformadas artificialmente. Se prueban algunas registraciones intermodalidad con imagenes TAC-PET sobre pacientes y TAC-SPECT sobre un fantoma.
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 | 0.001 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.001 | 0.001 |
| Bibliometrics | 0.001 | 0.000 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.001 | 0.001 |
| Open science | 0.001 | 0.001 |
| Research integrity | 0.001 | 0.001 |
| Insufficient payload (model declined to judge) | 0.007 | 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".