Aumento de la confianza en la interpretación del PET con 18F-Florbetaben: “machine learning” basado en la aproximación cuantitativa / Increasing the confidence of 18F-florbetaben PET interpretations: Machine learning quantitative approximation

Objetivo: Determinar el valor a-adido 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 de los SUVRs para predecir el resultado de la interpretación visual, la posibilidad de depósito preferencial del radiotrazador en algunas regiones “diana” así como las diferencias interhemisféricas. Resultados: 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. Conclusiones: La información obtenida de las regiones “diana” parece ser de ayuda en la clasificación visual, basado en un depósito preferencial de amiloide, lo que permitiría el “machine learning”. El depósito de amiloide, aunque difuso en todas las regiones corticales, parece no ser uniforme ni simétrico (AU)

Aim: 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 differenceswere analyzed. Results: 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. Conclusions: The derived information from target regions seems to help the visual classification, based on a preferential amyloid deposit, allowing machine learning. The amyloid deposit, although diffuse in all cortical regions, seems not to be uniform and symmetric (AU)

Global heterogeneity assessed with 18F-FDG PET/CT. Relation with biological variables and prognosis in locally advanced breast cancer. / Medidas de heterogeneidad global y esfericidad con 18F-FDG PET/TC en el cáncer de mama: relación con la biología tumoral, valor predictivo y pronóstico.

AIM: To analyze the relationship between measurements of global heterogeneity, obtained from 18F-FDG PET/CT, with biological variables, and their predictive and prognostic role in patients with locally advanced breast cancer (LABC). MATERIAL AND METHODS: 68 patients from a multicenter and prospective study, with LABC and a baseline 18F-FDG PET/CT were included. Immunohistochemical profile [estrogen receptors (ER) and progesterone receptors (PR), expression of the HER-2 oncogene, Ki-67 proliferation index and tumor histological grade], response to neoadjuvant chemotherapy (NC), overall survival (OS) and disease-free survival (DFS) were obtained as clinical variables. Three-dimensional segmentation of the lesions, providing SUV, volumetric [metabolic tumor volume (MTV) and total lesion glycolysis (TLG)] and global heterogeneity variables [coefficient of variation (COV) and SUVmean/SUVmax ratio], as well as sphericity was performed. The correlation between the results obtained with the immunohistochemical profile, the response to NC and survival was also analyzed. RESULTS: Of the patients included, 62 received NC. Only 18 responded. 13 patients relapsed and 11 died during follow-up. ER negative tumors had a lower COV (p=0.018) as well as those with high Ki-67 (p=0.001) and high risk phenotype (p=0.033) compared to the rest. No PET variable showed association with the response to NC nor OS. There was an inverse relationship between sphericity with DFS (p=0.041), so, for every tenth that sphericity increases, the risk of recurrence decreases by 37%. CONCLUSIONS: Breast tumors in our LABC dataset behaved as homogeneous and spherical lesions. Larger volumes were associated with a lower sphericity. Global heterogeneity variables and sphericity do not seem to have a predictive role in response to NC nor in OS. More spherical tumors with less variation in gray intensity between voxels showed a lower risk of recurrence.

18F-FDG PET/contrast enhanced CT in the standard follow-up of patients with lymphoma. / 18F-FDG PET/TC con contraste intravenoso en el seguimiento estandarizado de pacientes con linfoma.

AIM: To assess the diagnostic accuracy of 18F-FDG PET/contrast enhanced computed tomography (ceCT) in the detection of asymptomatic recurrences in patients with lymphoma. MATERIAL AND METHODS: Patients with lymphoma and clinical complete remission underwent 18F-FDG PET/ceCT for standard follow-up.18F-FDG PET and ceCT were evaluated blindly by two independent observers, and classified as positive or negative for recurrence. Additionally a combined evaluation of both techniques was performed. The final diagnosis was established by histopathological analysis or a clinical follow-up longer than 6 months. Statistical diagnostic parameters and concordance levels between both diagnostic techniques were calculated. RESULTS: A total of 114 explorations on 90 patients were analyzed. Only 4 patients were diagnosed as asymptomatic recurrence during the follow-up. 18F-FDG PET/ceCT, 18F-FDG PET and ceCT showed an association with the final diagnosis (p=0.002 and χ2=11.96; p<0.001 and χ2=15.60; p=0.001 and χ2=11.96, respectively). The concordance between 18F-FDG PET and ceCT was moderate/high and significant (kappa=0.672; p<0.001). A sensitivity and specificity of 50% and 88% was obtained for the 18F-FDG PET/ceCT civ, 50% and 93% for the 18F-FDG PET, and 50% and 91% for the ceCT. CONCLUSION: The combined use of 18F-FDG PET/ceCT did not offer any advantage compared to any isolated diagnostic technique in the detection of asymptomatic lymphoma recurrence.