Buscar en
Revista Española de Medicina Nuclear e Imagen Molecular (English Edition)
Toda la web
Inicio Revista Española de Medicina Nuclear e Imagen Molecular (English Edition) Increasing the confidence of 18F-Florbetaben PET interpretations: Machine learni...
Journal Information
Vol. 41. Issue 3.
Pages 153-163 (May - June 2022)
Download PDF
More article options
Vol. 41. Issue 3.
Pages 153-163 (May - June 2022)
Original Article
Increasing the confidence of 18F-Florbetaben PET interpretations: Machine learning quantitative approximation
Aumento de la confianza en la interpretación del PET con 18F-Florbetaben: “machine learning” basado en la aproximación cuantitativa
Ana María García Vicentea,
Corresponding author

Corresponding author.
, María Jesús Tello Galána, Francisco José Pena Pardoa, Mariano Amo-Salasb, Beatriz Mondejar Marínc, Santiago Navarro Muñozd, Ignacio Rueda Medinad, Víctor Manuel Poblete Garcíaa, Carlos Marsal Alonsoc, Ángel Soriano Castrejóna
a Nuclear Medicine Department, University General Hospital, Ciudad Real, Spain
b Mathematics Department, Castilla-La Mancha University, Ciudad Real, Spain
c Neurology Department, Complejo Hospitalario de Toledo, Spain
d Neurology Department, La Mancha Centro Hospital, Alcázar de San Juan, Ciudad Real, Spain
This item has received
Article information
Full Text
Download PDF
Figures (3)
Show moreShow less
Tables (7)
Table 1. Values of indexes of cortical locations to grey cerebellum and their differences.
Table 2. Values of indexes of cortical locations to total cerebellum and their differences.
Table 3. Values of indexes of cortical locations to pons and their differences.
Table 4. Interhemisphere differences in positive 18F-Florbetaben PET.
Table 5. Interhemisphere differences in negative 18F-Florbetaben PET.
Table 6. Thresholds of SUVR obtained in ROC analysis effective for the classification of a positive 18F-Florbetaben PET.
Table 7. Reported SUVR using cortical semiquantification of 18F-Florbetaben PET in the patient classification.
Show moreShow less

To assess the added value of semiquantitative parameters on the visual assessment and to study the patterns of 18F-Florbetaben brain deposition.

Materials and methods

Retrospective analysis of multicenter study performed in patients with mild cognitive impairment or dementia of uncertain origin. 18F-Florbetaben PET scans were visually interpreted by two experienced observers, analyzing target regions in order to calculate the interobserver agreement. Semiquantification of all cortical regions with respect to three reference regions was performed to obtain standardized uptake value ratios (SUVRs). The ability of SUVRs to predict the visual evaluation, the possibility of preferential radiotracer deposition in some target regions and interhemisphere differences were analyzed.


135 patients were evaluated. In the visual assessment, 72 were classified as positive. Interobserver agreement was excellent. All SUVRs were significantly higher in positive PET scans than in negative ones. Prefrontal area and posterior cingulate were the cortical regions with the best correlations with the visual evaluation, followed by the composite region. Using ROC analysis, the SUVRs obtained in same target locations showed the best diagnostic performance.


The derived information from target regions seems to help the visual classification, based on a preferential amyloid β deposit, allowing machine learning. The amyloid β deposit, although diffuse in all cortical regions, seems not to be uniform and symmetric.

Amyloid beta
Interhemisphere differences
Target regions
Machine learning

Determinar el valor añadido de los parámetros semicuantitativos en el análisis visual y estudiar los patrones del depósito cerebral de 18F-Florbetaben.

Material y métodos

Análisis retrospectivo de pacientes con deterioro cognitivo leve o demencia de origen incierto procedentes de un estudio multicentrico. Los PET con 18F-Florbetaben fueron interpretados de forma visual por dos observadores independientes, analizando las regiones “diana” con la finalidad de calcular el acuerdo interobservador. Se realizó análisis semicuantitativo de todas las regiones corticales con respecto a tres regiones de referencia para obtener índices de captación (SUVRs). Se analizó la capacidad del los SUVRs para predecir el resultado de la interpretación visual, la posibilidad de deposito preferencial del radiotrazador en algunas regiones “diana” así como las diferencias interhemisféricas.


Se evaluaron 135 pacientes. En la valoración visual, 72 estudios se clasificaron como positivos. El acuerdo interobservador fue excelente. Todos los SUVRs fueron significativamente superiores en pacientes con PET positivos con respecto a los negativos. Las regiones corticales correspondientes al área prefrontal y al cingulado posterior mostraron la mejor correlación con la evaluación visual, seguidas por la valoración integrada cortical. Usando análisis de ROC, los SUVRs obtenidos en las mismas regiones “diana” mostraron la mejor capacidad diagnóstica.


La información obtenida de las regiones “diana” parece ser de ayuda en la clasificación visual, basado en un depósito preferencial de amiloide β, lo que permitiría el “machine learning”. El deposito de amiloide β, aunque difuso en todas las regiones corticales, parece no ser uniforme ni simétrico.

Palabras clave:
diferencias interhemisféricas
regiones “diana”
machine learning


These are the options to access the full texts of the publication Revista Española de Medicina Nuclear e Imagen Molecular (English Edition)

If you already have your login data, please click here .

If you have forgotten your password you can you can recover it by clicking here and selecting the option “I have forgotten my password”
Subscribe to

Revista Española de Medicina Nuclear e Imagen Molecular (English Edition)

Purchase article

Purchasing article the PDF version will be downloaded

Price 19.34 €

Purchase now
Phone for subscriptions and reporting of errors
From Monday to Friday from 9 a.m. to 6 p.m. (GMT + 1) except for the months of July and August which will be from 9 a.m. to 3 p.m.
Calls from Spain
932 415 960
Calls from outside Spain
+34 932 415 960
Article options
es en pt

¿Es usted profesional sanitario apto para prescribir o dispensar medicamentos?

Are you a health professional able to prescribe or dispense drugs?

Você é um profissional de saúde habilitado a prescrever ou dispensar medicamentos

Quizás le interese:
No mostrar más