Amino-acids positron emission tomography (PET) is increasingly used in the diagnostic workup of patients with gliomas, including differential diagnosis, evaluation of tumor extension, treatment planning and follow-up. Recently, progresses of computer vision and machine learning have been translated for medical imaging. Aim was to demonstrate the feasibility of an automated 18F-fluoro-ethyl-tyrosine (18F-FET) PET lesion detection and segmentation relying on a full 3D U-Net Convolutional Neural Network (CNN). All dynamic 18F-FET PET brain image volumes were temporally realigned to the first dynamic acquisition, coregistered and spatially normalized onto the Montreal Neurological Institute template. Ground truth segmentations were obtained using manual delineation and thresholding (1.3 x background). The volumetric CNN was implemented based on a modified Keras implementation of a U-Net library with 3 layers for the encoding and decoding paths. Dice similarity coefficient (DSC) was used as an accuracy measure of segmentation. Thirty-seven patients were included (26 [70%] in the training set and 11 [30%] in the validation set). All 11 lesions were accurately detected with no false positive, resulting in a sensitivity and a specificity for the detection at the tumor level of 100%. After 150 epochs, DSC reached 0.7924 in the training set and 0.7911 in the validation set. After morphological dilatation and fixed thresholding of the predicted U-Net mask a substantial improvement of the DSC to 0.8231 (+ 4.1%) was noted. At the voxel level, this segmentation led to a 0.88 sensitivity [95% CI, 87.1 to, 88.2%] a 0.99 specificity [99.9 to 99.9%], a 0.78 positive predictive value: [76.9 to 78.3%], and a 0.99 negative predictive value [99.9 to 99.9%]. With relatively high performance, it was proposed the first full 3D automated procedure for segmentation of 18F-FET PET brain images of patients with different gliomas using a U-Net CNN architecture.
Background: Amyloidosis is characterized by extracellular deposits of insoluble proteins that cause tissue damage. The three main types are monoclonal light chain (AL), wild-type transthyretin (wt-TTR) and mutated transthyretin (m-TTR) amyloidosis. Cardiac amyloidosis (CA) raises diagnostic challenges. Objective: To assess the diagnostic accuracy of 99mTc-HMDP-scintigraphy for typing CA, differentiating CA from non-amyloid left ventricle hypertrophy (LVH), and predicting outcomes. Methods: 121 patients with suspected CA underwent 99mTc-HMDP-scintigraphy in addition to standard investigations. Results: CA was diagnosed in all AL (n = 14) and wt-TTR (n = 21). Among m-TTR (n = 34), 26 had CA, 4 neuropathy without CA and 4 were asymptomatic carriers. Of the 52 patients with non-amyloid heart disease, 37 had LVH and served as controls. 99mTc-HMDP cardiac uptake occurred in all wt-TTR, in m-TTR with CA except two and in one AL. A visual score ≥ 2 was 100% specific for diagnosing TTR-CA. Among TTR-CA, heart-to-skull retention (HR/SR) correlated with CA severity (LVEF and NT-proBNP). Median follow-up was 111 days (50;343). In a multivariate Cox model including clinical, echocardiographic and scintigraphic variables, NYHA III-IV and HR/SR > 1.94 predicted acute heart failure and/or death. Conclusions: This preliminary study suggests that 99mTc-HMDP-scintigraphy may aid differentiation between transthyretin and AL-CA as well as CA from other LVHs. 99mTc-HMDP-scintigraphy appears to provide prognostic information in CA.
28 September 2017 in European Journal of Neurology
Signature of survival: a 18 F-FDG PET based whole-liver radiomic analysis predicts survival after 90 Y-TARE for hepatocellular carcinoma Signature of survival: a 18F-FDG PET based whole-liver radiomic analysis predicts survival after 90Y-TARE for hepatocellular carcinoma