RESUMO
Objective.to develop an optimization and training pipeline for a classification model based on principal component analysis and logistic regression using neuroimages from PET with 2-[18F]fluoro-2-deoxy-D-glucose (FDG PET) for the diagnosis of Alzheimer's disease (AD).Approach.as training data, 200 FDG PET neuroimages were used, 100 from the group of patients with AD and 100 from the group of cognitively normal subjects (CN), downloaded from the repository of the Alzheimer's Disease Neuroimaging Initiative (ADNI). Regularization methods L1 and L2 were tested and their respective strength varied by the hyperparameter C. Once the best combination of hyperparameters was determined, it was used to train the final classification model, which was then applied to test data, consisting of 192 FDG PET neuroimages, 100 from subjects with no evidence of AD (nAD) and 92 from the AD group, obtained at the Centro de Diagnóstico por Imagem (CDI).Main results.the best combination of hyperparameters was L1 regularization andC≈ 0.316. The final results on test data were accuracy = 88.54%, recall = 90.22%, precision = 86.46% and AUC = 94.75%, indicating that there was a good generalization to neuroimages outside the training set. Adjusting each principal component by its respective weight, an interpretable image was obtained that represents the regions of greater or lesser probability for AD given high voxel intensities. The resulting image matches what is expected by the pathophysiology of AD.Significance.our classification model was trained on publicly available and robust data and tested, with good results, on clinical routine data. Our study shows that it serves as a powerful and interpretable tool capable of assisting in the diagnosis of AD in the possession of FDG PET neuroimages. The relationship between classification model output scores and AD progression can and should be explored in future studies.
Assuntos
Doença de Alzheimer , Fluordesoxiglucose F18 , Humanos , Doença de Alzheimer/diagnóstico por imagem , Compostos Radiofarmacêuticos , Modelos Logísticos , Encéfalo/diagnóstico por imagem , Neuroimagem , Tomografia por Emissão de Pósitrons/métodosRESUMO
Hypercalcemia is a frequent condition in clinical practice and when the most frequent causes are excluded, etiological diagnosis can be challenging. A rare cause of PTH-independent hypercalcemia is described in the present case report. A male adult with a history of androgenic-anabolic steroids abuse, and injection of mineral oil and oily veterinary compound containing vitamins A, D and E into muscles for local hypertrophy presented with hypercalcemia, nephrocalcinosis, and end-stage renal disease. On physical examination, the presence of calcified subcutaneous nodules and calcification of musculature previously infused with oily substances drew attention. Laboratory tests confirmed hypercalcemia of 12.62 mg/L, low levels of PTH (10 pg/mL), hyperphosphatemia (6.0 mg/dL), 25(OH)D of 23.3 ng/mL, and elevated 1,25(OH)2D (138 pg/mL). Imaging exams showed diffuse calcification of muscle tissue, subcutaneous tissue, and organs such as the heart, lung, and kidneys. The patient was diagnosed with PTH-independent hypercalcemia secondary to foreign body reaction in areas of oil injection. The patient underwent treatment with hydrocortisone for 10 days, single dose zoledronic acid and hemodialysis. He evolved with serum calcium levels of 10.4 mg/dL and phosphorus of 7.1 mg/dL. In addition, sertraline and quetiapine were prescribed to control body dysmorphic disorder. The medical community should become aware of new causes of hypercalcemia as secondary to oil injection since this should become increasingly frequent due to the regularity with which such procedures have been performed.