Thirdly, location information of the input image, consisting of the occurrence frequencies of different diseases in the CT scans on certain locations, is used to calculate a location weight vector. Secondly, a modified CNN model is used to produce a vector of classification probability for each tissue. Firstly, ILD images are added with their medical information by re-scaling the original image in Hounsfield Units. In order to improve the classification precision, our study proposes a convolutional neural networks-based framework with additional information. Although previous work has produced impressive results in classifying interstitial lung diseases, there is still room for improving the accuracy of these techniques, mainly to enhance automated decision-making. Accurately diagnosing these diseases has significant guiding value for formulating treatment plans. Interstitial lung diseases are a large group of heterogeneous diseases characterized by different degrees of alveolitis and pulmonary fibrosis. Considering the fact that gray scale in CBCT is the criteria in measurement of bone density before implant treatments, it is recommended because of the lower dose and cost compared to CT scan. A strong correlation between gray scales of CBCT and HUs of CT scan was determined.Ĭonclusion. Reconstructed data were analyzed to investigate relationship between CBCT gray scales and HUs. Gray scales and HUs were detected on images. In this descriptive study, the head of a sheep was scanned with 3 CBCT and one medical CT scanner. The aim of the present study was to investigate the relationship between gray scale in CBCT) and Hounsfield Unit (HU) in CT scan. In CBCT, the degree of x-ray attenuation is shown by gray scale (voxel value). In CT scan, Hounsfield Unit (HU) is proportional to the degree of x-ray attenuation by the tissue. Cone-beam computed tomography (CBCT) is an imaging system which has many advantages over computed tomography (CT).
0 kommentar(er)
