Machine learning models for the differential diagnosis of vascular parkinsonism and Parkinson's disease using [(123)I]FP-CIT SPECT.

PURPOSE: The study's objective was to develop diagnostic predictive models using data from two commonly used [(123)I]FP-CIT SPECT assessment methods: region-of-interest (ROI) analysis and whole-brain voxel-based analysis. METHODS: We included retrospectively 80 patients with vascular parkinsonism (VP) and 164 patients with Parkinson's disease (PD) who underwent [(123)I]FP-CIT SPECT. Nuclear-medicine specialists evaluated the scans and calculated bilateral caudate and putamen [(123)I]FP-CIT uptake and asymmetry indices using BRASS software. Statistical parametric mapping (SPM) was used to compare the radioligand uptake between the two diseases at the voxel level. Quantitative data from these two methods, together with potential confounding factors for dopamine transporter availability (sex, age, disease duration and severity), were used to build predictive models following a tenfold cross-validation scheme. The performance of logistic regression (LR), linear discriminant analysis and support vector machine (SVM) algorithms for ROI data, and their penalized versions for SPM data (penalized LR, penalized discriminant analysis and SVM), were assessed. RESULTS: Significant differences were found in the ROI analysis after covariate correction between VP and PD patients in [(123)I]FP-CIT uptake in the more affected side of the putamen and the ipsilateral caudate. Age, disease duration and severity were also found to be informative in feeding the statistical model. SPM localized significant reductions in [(123)I]FP-CIT uptake in PD with respect to VP in two specular clusters comprising areas corresponding to the left and right striatum. The diagnostic predictive accuracy of the LR model using ROI data was 90.3 % and of the SVM model using SPM data was 90.4 %. CONCLUSION: The predictive models built with ROI data and SPM data from [(123)I]FP-CIT SPECT provide great discrimination accuracy between VP and PD. External validation of these methods is necessary to confirm their applicability across centres.

123I-MIBG, 18F-DOPA y 18F-FDG en una paciente con síndrome de neoplasia endocrina múltiple tipo 2 y recidiva de feocromocitoma / 123I-MIBG, 18F-DOPA and 18F-FDG in a patient with MEN2 syndrome and recurrent pheochromocytoma

El feocromocitoma es un tumor poco frecuente localizado en la médula de la glándula adrenal y caracterizado por una elevada síntesis de catecolaminas. La cirugía es el tratamiento de elección y es potencialmente curativa si se diagnostica y reseca adecuadamente. Los métodos de diagnóstico por imagen, tanto morfológica como funcional, son de gran importancia en la evaluación prequirúrgica. Se presenta el caso de una paciente con síndrome de neoplasia endocrina múltiple tipo 2 con suprarrenalectomía bilateral por sendos feocromocitomas y elevación progresiva de la metanefrina urinaria. En la resonancia magnética realizada se observó una imagen nodular en la fosa suprarrenal derecha, por lo que se remitió a nuestra unidad con el objetivo de confirmar la sospecha de recidiva. Dada la ausencia de hallazgos patológicos en la gammagrafía con 123I-MIBG y ante la alta sospecha de recidiva se realizaron estudios PET/TAC con 18F-DOPA y 18F-FDG que confirmaron el diagnóstico(AU)

Pheochromocytoma is a rare tumor located in the medulla of the adrenal gland that is characterized by high catecholamine synthesis. Surgery is the treatment of choice and is usually curative if appropriately diagnosed and excised. Imaging methods, both morphological and functional, are of great importance in presurgical evaluation. We report the case of a female patient with multiple endocrine neoplasia syndrome type 2, with bilateral adrenalectomy due to two pheochromocytomas and progressive elevation of urinary metanephrine. Magnetic resonance imaging showed a nodular image in the right adrenal fossa. The patient was referred to our unit in order to confirm suspicion of recurrence. Due to the absence of pathological findings in the 123I-MIBG scintigraphy and high suspicion of recurrence, PET/CT imaging with 18F-DOPA and 18F-FDG were performed, and the diagnosis was confirmed(AU)

[Elaboration of the SPM template for the standardization of SPECT images with 123I-Ioflupane]. / Elaboración de una plantilla de SPM para la normalización de imágenes de SPECT con 123I-Ioflupano.

PURPOSE: Statistical parametric mapping (SPM) is a widely used produced for normalization of functional images. This study has aimed to develop a normalization template of (123)I-Ioflupane SPECT-imaging DaTSCAN(®), GE Healthcare), not available in SPM5, and to validate it compared to other quantification methods. MATERIAL AND METHODS: In order to write the template we retrospectively selected 26 subjects who had no evidence of nigrostriatal degeneration and whose age distribution was similar to that of the patients in the usual practice of our Department: 2 subjects (7.6%) were < 35 years, 9 between 35-65 years (34.6%) and 15 > 65 years (57.7%). All the studies were normalized with the T1-template available in SPM5 and an average image of the value was obtained for each voxel. For validation we analyzed 60 patients: 30 with idiopathic Parkinson's disease patients (iPD) with right involvement (66.83±12.20 years) and 30 with essential tremor patients (ET) (67.27±8.33 years). Specific uptake rates (SUR) of different striatal regions were compared after image normalization with our template and the application of a semiautomated VOIs-map created with Analyze v9.0 ((©)BIR, Mayo Clinic), against two quantification methods: a) manual adjustment of a ROIs-map drawn in Analyze, and b) semi-automated method (HERMES-BRASS) with normalization and implementation of VOIs-map. RESULTS: No statistically significant differences in the iPD/ET discriminatory capacity between the three methods analyzed were observed (p<0,001). The correlation of SUR after normalization with our «template¼ was higher than that obtained by method b) (R>0,871, p<0,001). This difference was greater in patients with PD. CONCLUSIONS: Our study demonstrates the efficacy of our SPM «template¼ for (123)I-Ioflupane SPECT-imaging, obtained from normalization with «T1-template¼.

123I-MIBG, 18F-DOPA and 18F-FDG in a patient with MEN2 syndrome and recurrent pheochromocytoma.

Pheochromocytoma is a rare tumor located in the medulla of the adrenal gland that is characterized by high catecholamine synthesis. Surgery is the treatment of choice and is usually curative if appropriately diagnosed and excised. Imaging methods, both morphological and functional, are of great importance in presurgical evaluation. We report the case of a female patient with multiple endocrine neoplasia syndrome type 2, with bilateral adrenalectomy due to two pheochromocytomas and progressive elevation of urinary metanephrine. Magnetic resonance imaging showed a nodular image in the right adrenal fossa. The patient was referred to our unit in order to confirm suspicion of recurrence. Due to the absence of pathological findings in the (123)I-MIBG scintigraphy and high suspicion of recurrence, PET/CT imaging with (18)F-DOPA and (18)F-FDG were performed, and the diagnosis was confirmed.