No abstract

The migraineurs had lower rCBF at the frontal and temporal lobes, and the lower rCBF was correlated to the degree of headache.

Purpose To compare the diagnostic accuracy of dual-phase 99mTc-MIBI single photon emission computed tomography/computed tomography (SPECT/CT) and 4D CT for the localization of hyperfunctioning parathyroid glands, a systematic review and meta-analysis was performed. Whether 4D CT combined to SPECT/CT [contrast-enhanced (CE)-SPECT/CT] had a better diagnostic performance than SPECT/CT alone in this scenario was also evaluated. Material and methods PubMed and Embase databases were searched for eligible studies. To reduce interstudy heterogeneity, only studies with clear head-to-head comparison were included. Publication bias was assessed by the Deeks funnel plot. The pooled sensitivity, specificity and the area under the curve (AUC) for 4D CT, SPECT/CT and CE-SPECT/CT were determined by random-effect analysis, respectively. Results Nine studies met the inclusion criteria, with a total of 911 participants. The sensitivity and specificity of 4D CT were 0.85 [95% confidence interval (CI), 0.69–0.94] and 0.93 (95% CI, 0.88–0.96), whereas the sensitivity and specificity for SPECT/CT were 0.68 (95% CI, 0.51–0.82; P = 0.048 compared with 4D CT) and 0.98 (95% CI, 0.95–0.99; P = 0.014 compared with 4D CT), respectively. CE-SPECT/CT is comparable to SPECT/CT in specificity and AUC, but it may improve the sensitivity (although there was a lack of statistical difference, 0.87 vs. 0.78; P = 0.125). Conclusion Although 4D CT shows comparable AUC and borderline better sensitivity than SPECT/CT, its clinical application is confined by relatively low specificity and high radiation exposure. CE-SPECT/CT may improve the sensitivity without compromising the specificity and AUC of SPECT/CT.

Support vector regression has been proposed in a number of image processing tasks including blind image deconvolution, image denoising and single frame super-resolution. As for other machine learning methods, the training is slow. In this paper, we attempt to address this issue by reducing the feature dimensionality through Principal Component Analysis (PCA). Our single frame supper-resolution experiments show that PCA successfully reduces the feature dimensionality without degrading the performance of SVR when the training images and testing images share similarities (i.e. belong to the same category). In fact, in some cases the performance in terms of Peak Signal-to-Noise Ratio (PSNR), is even better.

No abstract