ObjectiveTo discuss the application value of the two kinds of three dimensional reformatting techniques of spiral CT: volume rendering (VR) and maximum intensity projection (MIP) in the evaluation of children's skeletal abnormality. MethodsEighteen children with skeletal abnormality in our hospital treated between March and June 2014 were recruited in this study, diagnosed by CT transversal images and images of multiplanar reformatting (MPR). VR and MIP were made with the raw data. All three dimensional images were independently evaluated by two doctors of the Radiology Department (a score of 1-4). Images with a score of 4 were excellent. Wilcoxon signed ranks test was done for all scores and Kappa values were calculated. ResultsImages score of VR was 3.28±0.96 and of MIP was 2.89±0.90, without statistically significant difference (Z=-1.732, P=0.125). Kappa value of VR was 0.730 and of MIP was 0.593, with good and moderate consistency. ConclusionWith the special superiority of displaying spatial configuration, VR and MIP can be used to help two dimensional CT images to evaluate children's skeletal abnormality more comprehensively.
Conventional maximum intensity projection (MIP) images tend to ignore some morphological features in the detection of intracranial aneurysms, resulting in missed detection and misdetection. To solve this problem, a new method for intracranial aneurysm detection based on omni-directional MIP image is proposed in this paper. Firstly, the three-dimensional magnetic resonance angiography (MRA) images were projected with the maximum density in all directions to obtain the MIP images. Then, the region of intracranial aneurysm was prepositioned by matching filter. Finally, the Squeeze and Excitation (SE) module was used to improve the CaraNet model. Excitation and the improved model were used to detect the predetermined location in the omni-directional MIP image to determine whether there was intracranial aneurysm. In this paper, 245 cases of images were collected to test the proposed method. The results showed that the accuracy and specificity of the proposed method could reach 93.75% and 93.86%, respectively, significantly improved the detection performance of intracranial aneurysms in MIP images.