RESUMEN
BACKGROUND: The prediction of Alzheimer's disease (AD) progression from its early stages is a research priority. In this context, the use of Artificial Intelligence (AI) in AD has experienced a notable surge in recent years. However, existing investigations predominantly concentrate on distinguishing clinical phenotypes through cross-sectional approaches. This study aims to investigate the potential of modeling additional dimensions of the disease, such as variations in brain metabolism assessed via [18F]-fluorodeoxyglucose positron emission tomography (FDG-PET), and utilize this information to identify patients with mild cognitive impairment (MCI) who will progress to dementia (pMCI). METHODS: We analyzed data from 1,617 participants from the Alzheimer's Disease Neuroimaging Initiative (ADNI) who had undergone at least one FDG-PET scan. We identified the brain regions with the most significant hypometabolism in AD and used Deep Learning (DL) models to predict future changes in brain metabolism. The best-performing model was then adapted under a multi-task learning framework to identify pMCI individuals. Finally, this model underwent further analysis using eXplainable AI (XAI) techniques. RESULTS: Our results confirm a strong association between hypometabolism, disease progression, and cognitive decline. Furthermore, we demonstrated that integrating data on changes in brain metabolism during training enhanced the models' ability to detect pMCI individuals (sensitivity=88.4%, specificity=86.9%). Lastly, the application of XAI techniques enabled us to delve into the brain regions with the most significant impact on model predictions, highlighting the importance of the hippocampus, cingulate cortex, and some subcortical structures. CONCLUSION: This study introduces a novel dimension to predictive modeling in AD, emphasizing the importance of projecting variations in brain metabolism under a multi-task learning paradigm.
Asunto(s)
Encéfalo , Disfunción Cognitiva , Aprendizaje Profundo , Progresión de la Enfermedad , Fluorodesoxiglucosa F18 , Tomografía de Emisión de Positrones , Humanos , Disfunción Cognitiva/diagnóstico por imagen , Disfunción Cognitiva/metabolismo , Femenino , Masculino , Tomografía de Emisión de Positrones/métodos , Anciano , Encéfalo/metabolismo , Encéfalo/diagnóstico por imagen , Fluorodesoxiglucosa F18/farmacocinética , Enfermedad de Alzheimer/diagnóstico por imagen , Enfermedad de Alzheimer/metabolismo , Anciano de 80 o más Años , Demencia/diagnóstico por imagen , Demencia/metabolismo , Inteligencia Artificial , Neuroimagen/métodosRESUMEN
Adult medulloblastoma (MB) is a rare disease affecting 0.6 persons per million adults over 19 years of age. The SHH-activated/TP53-wild type is the most common subtype, accounting for 60% of adult MBs, being characterized by mutations in PTCH1, SMO, or the TERT promoter. Several small studies demonstrate objective but short-lived responses to SMO inhibitors such as vismodegib or sonidegib. Like other oncogene-addicted solid tumors, detection of the corresponding drivers through liquid biopsy could aid in the molecular diagnosis and monitoring of the disease through less invasive procedures. However, most studies have only evaluated cerebrospinal fluid as the ctDNA reservoir, and very limited evidence exists on the role of liquid biopsy in plasma in patients with primary central nervous system tumors, including MB. We present the case of a 26-year-old patient with a recurrent MB, in which next-generation sequencing (FoundationOne CDx) revealed a mutation in PTCH1, allowing the patient to be treated with vismodegib in second line, resulting in a durable benefit lasting for 1 year. Using an in-house digital PCR probe, the PTCH1 mutation could be tracked in ctDNA during treatment with first-line chemotherapy and while on treatment with vismodegib, demonstrating a precise correlation with the radiological and clinical behavior of the disease.
Asunto(s)
Anilidas , ADN Tumoral Circulante , Meduloblastoma , Mutación , Receptor Patched-1 , Piridinas , Humanos , Meduloblastoma/tratamiento farmacológico , Meduloblastoma/genética , Meduloblastoma/sangre , Meduloblastoma/patología , Piridinas/uso terapéutico , Receptor Patched-1/genética , Adulto , Anilidas/uso terapéutico , ADN Tumoral Circulante/genética , ADN Tumoral Circulante/sangre , Neoplasias Cerebelosas/tratamiento farmacológico , Neoplasias Cerebelosas/genética , Neoplasias Cerebelosas/patología , Neoplasias Cerebelosas/sangre , Masculino , FemeninoRESUMEN
Patients with recurrent/metastatic (R/M) platinum-refractory squamous cell carcinoma of the head and neck (SCCHN) have fewer treatment options and harbor an especially poor prognosis. Maintaining treatment with anti-PD1 agents beyond response evaluation criteria in solid tumors-defined disease progression (TBP) has been shown to be efficacious in several solid tumors, including head and neck cancer. We present the case of a platinum-refractory locally recurrent, PD-L1-negative hypopharyngeal carcinoma, that received second-line nivolumab which was then maintained beyond progression under the following criteria: no Eastern Cooperative Oncology Group performance status deterioration, no rapidly progressive disease, no severe toxicity, and evidence of overall treatment benefit. The patient achieved a partial response 8â months after starting second-line nivolumab, with progressive disease at 26â months, then followed by the first TBP with nivolumab lasting for 15â months due to a new tumor progression. A second TBP with nivolumab lasting for 7â months, was followed by a third TBP with nivolumab for 12â months and achieving a major tumor response. Treatment is still ongoing 60â months after starting nivolumab, with excellent tolerance to therapy. Maintaining anti-PD1 agents beyond progression is an efficacious treatment option for patients with R/M SCCHN, that may achieve very durable disease control and even late major responses.
RESUMEN
Pharmacokinetic positron emission tomography (PET) studies rely on the measurement of the arterial input function (AIF), which represents the time-activity curve of the radiotracer concentration in the blood plasma. Traditionally, obtaining the AIF requires invasive procedures, such as arterial catheterization, which can be challenging, time-consuming, and associated with potential risks. Therefore, the development of non-invasive techniques for AIF measurement is highly desirable. This study presents a detector for the non-invasive measurement of the AIF in PET studies. The detector is based on the combination of scintillation fibers and silicon photomultipliers (SiPMs) which leads to a very compact and rugged device. The feasibility of the detector was assessed through Monte Carlo simulations conducted on mouse tail and human wrist anatomies studying relevant parameters such as energy spectrum, detector efficiency and minimum detectable activity (MDA). The simulations involved the use of 18F and 68Ga isotopes, which exhibit significantly different positron ranges. In addition, several prototypes were built in order to study the different components of the detector including the scintillation fiber, the coating of the fiber, the SiPMs, and the operating configuration. Finally, the simulations were compared with experimental measurements conducted using a tube filled with both 18F and 68Ga to validate the obtained results. The MDA achieved for both anatomies (approximately 1000 kBq/mL for mice and 1 kBq/mL for humans) falls below the peak radiotracer concentrations typically found in PET studies, affirming the feasibility of conducting non-invasive AIF measurements with the fiber detector. The sensitivity for measurements with a tube filled with 18F (68Ga) was 1.2 (2.07) cps/(kBq/mL), while for simulations, it was 2.81 (6.23) cps/(kBq/mL). Further studies are needed to validate these results in pharmacokinetic PET studies.
RESUMEN
Objetivos: En este trabajo se realizó un metaanálisis de la literatura para evaluar la exactitud diagnóstica de la PET 18F-FDG en la sospecha de recurrencia de cánceres de cabeza y cuello. Material y métodos: Inicialmente se realizó una búsqueda sistemática de la literatura en las fuentes MEDLINE y CANCERLITE hasta mayo de 2007, aplicando unos criterios de cribado a los estudios hallados. Se calcularon los valores de sensibilidad, especificidad, cocientes de probabilidad positivo y negativo y la odds ratio diagnóstica. El rendimiento diagnóstico se valoró mediante curvas ROC (receive-operating-characteristic). Resultados: Fueron incluidos 19 artículos en el metaanálisis. La sensibilidad de la PET 18F-FDG fue del 94 %, la especificidad del 80 % y la curva ROC mostró una buena relación entre sensibilidad y especificidad. Conclusiones: La PET 18F-FDG fue útil en pacientes con sospecha de recurrencia tumoral por cáncer de cabeza y cuello; mostró una sensibilidad alta y una especificidad intermedia-alta
Objectives: A meta-analysis of the literature was performed in this article in order to evaluate the diagnostic accuracy of 18F-FDG PET in suspected recurrent head and neck cancer. Material and methods: A systematic review of the literature was performed using 1987 to 2007 MEDLINE and CANCERLIT databases, applying selection criteria to the studies found. Sensitivity, specificity, positive and negative likelihood ratios, and odds ratio were calculated. The diagnostic accuracy was evaluated with ROC (receive-operating-characteristics) curves. Results: Nineteen articles were included in the meta-analysis. Sensitivity of 18F-FDG PET was 94 %, specificity 80 %, and the summary ROC curve showed a good trade-off between sensitivity and specificity. Conclusions: 18F-FDG PET was useful in patients with suspected recurrence of head and neck cancer, showing a high sensitivity and intermediate-high specificity
Asunto(s)
Humanos , Masculino , Femenino , Neoplasias de Cabeza y Cuello/metabolismo , Tomografía Computarizada de Emisión , Recurrencia Local de Neoplasia/complicaciones , Fluorodesoxiglucosa F18 , Radiofármacos , Sensibilidad y Especificidad , Diagnóstico DiferencialRESUMEN
Objetivo: Valorar las modificaciones en el tratamiento inducidas por la tomografía por emisión de positrones con 18F-desoxiglucosa (PET-FDG) en pacientes con sospecha de enfermedad residual o recurrente de cáncer diferenciado de tiroides (CDT) con tiroglobulina (Tg) elevada y rastreo corporal total (RCT) con 131I negativo. Pacientes y método: Se analizó de forma retrospectiva a un grupo de 50 pacientes (35 mujeres y 15 varones) tratados de CDT, a los que se hizo estudio PET-FDG (51 exploraciones) por elevación de Tg con RCT con 131I negativo. La comprobación de resultados se hizo según la anatomía patológica, respuesta al tratamiento o seguimiento clínico. Valoraron el impacto los médicos, que indicaron cómo influyó esta técnica en las decisiones terapéuticas, y se clasificó como alto, moderado, bajo o sin impacto, según los criterios de Hicks modificados. Resultados: La PET-FDG tuvo alto impacto en 18 (35,3%) pacientes, en los que se modificó la estrategia terapéutica; en 2 (3,9%) el impacto fue moderado, ya que no se aplicó tratamiento pero el resultado negativo de la PET-FDG evitó la realización de otros métodos diagnósticos; en 18 (35,3%), el impacto fue bajo, ya que no modificó el tratamiento; en 13 (25,5%) no tuvo impacto, pues no se tuvo en cuenta a la hora de decidir el tratamiento. Conclusiones: La PET-FDG resulta una técnica diagnóstica útil para la toma de decisiones terapéuticas en pacientes con sospecha de enfermedad residual o recurrente de CDT que presentan Tg elevada y RCT con 131I negativo (AU)
Objective: To assess FDG-PET-induced treatment modifications in patients with suspected recurrent or residual differentiated thyroid cancer (DTC) with elevated thyroglobulin (Tg) and negative 131I whole body scan (WBS). Patients and method: Fifty-one FDG-PET studies due to elevated Tg with negative WBS were retrospectively analyzed in 50 patients treated for DTC (35 women and 15 men). The results were verified by pathological analysis, treatment response or clinical follow-up. The impact of FDG-PET was assessed by asking the physicians to indicate how this technique had affected their therapeutic decisions and the influence was classified as high, moderate, low or nil according to Hicks' modified criteria. Results: The impact of FDG-PET was high in 18 patients (35.3%), in whom the therapeutic strategy was modified. A moderate impact was found in 2 patients (3.9%) since no treatment was applied; however, in these patients, negative FDG-PET results obviated the need for other diagnostic methods. Impact was low in 18 patients (35.3%) as treatment was not modified, and was null in 13 (25.5%) since this technique was not considered when therapeutic decisions were made. Conclusions: FDG-PET is a useful diagnostic technique for therapeutic decision-making in patients with suspected residual or recurrent DTC, elevated Tg and negative 131I-WBS (AU)