Measuring distance from the incisors to the esophageal cancer by FDG PET/CT: endoscopy as the reference.

BACKGROUND: Using endoscopy as the reference, this study evaluated the accuracy of 18F-fluorodeoxyglucose positron emission tomography/computed tomography (FDG PET/CT) in measuring distance from the incisors to the PET detectable esophageal cancer. If there is high concordance between endoscopic and PET measurements, our results may provide a basis to use FDG PET/CT in cooperation with endoscopic measurement to localize those PET/CT and CT undetectable esophageal tumors for radiotherapy planning. MATERIALS: Esophageal cancer patients with pretreatment endoscopy and FDG PET/CT detectable esophageal tumors were recruited retrospectively. The distances from the incisors to the proximal esophageal tumor margins were determined by endoscopy and by the sagittal images of FDG PET/CT. The endoscopic measurement was used as the comparative reference. A nuclear medicine doctor and a radiation oncologist each performed the FDG PET/CT measurement twice for every patient. We analyzed the differences in these measurements, and assessed agreement and reproducibility of the results by the intraclass correlation coefficient (ICC). RESULTS: Thirty-four patients, with 35 esophageal tumors, were included. By endoscopy and FDG PET/CT, the mean distances from the incisors to the proximal esophageal tumor margin were 27.3 ± 6.4 cm (range 17.1-40.0 cm) and 26.8 ± 6.3 cm (range 15.7-41.3 cm), respectively. The mean absolute differences between the endoscopic and four FDG PET/CT measurements ranged from 1.129 to 1.289 cm (SD: 0.98-1.19). The measurement agreement between FDG PET/CT and endoscopy by ICC was between 0.962 and 0.971. The intra- and interobserver reproducibilities of the two readers were excellent (intraobserver ICC: 0.985, 0.996; interobserver ICC: 0.976-0.984). CONCLUSIONS: FDG PET/CT was in high agreement with endoscopy in measuring the distance from the incisors to the proximal esophageal tumor margin. For FDG PET/CT and CT undetectable esophageal cancer, incorporation of the endoscopic measurement with PET/CT might be a way for making radiotherapy plan.

Using Artificial Neural Network to Discriminate Parkinson's Disease from Other Parkinsonisms by Focusing on Putamen of Dopamine Transporter SPECT Images.

BACKGROUND: The challenge of differentiating, at an early stage, Parkinson's disease from parkinsonism caused by other disorders remains unsolved. We proposed using an artificial neural network (ANN) to process images of dopamine transporter single-photon emission computed tomography (DAT-SPECT). METHODS: Abnormal DAT-SPECT images of subjects with Parkinson's disease and parkinsonism caused by other disorders were divided into training and test sets. Striatal regions of the images were segmented by using an active contour model and were used as the data to perform transfer learning on a pre-trained ANN to discriminate Parkinson's disease from parkinsonism caused by other disorders. A support vector machine trained using parameters of semi-quantitative measurements including specific binding ratio and asymmetry index was used for comparison. RESULTS: The predictive accuracy of the ANN classifier (86%) was higher than that of the support vector machine classifier (68%). The sensitivity and specificity of the ANN classifier in predicting Parkinson's disease were 81.8% and 88.6%, respectively. CONCLUSIONS: The ANN classifier outperformed classical biomarkers in differentiating Parkinson's disease from parkinsonism caused by other disorders. This classifier can be readily included into standalone computer software for clinical application.