• The Journal of the Korea Contents Association
• /
• v.14 no.6
• /
• pp.247-254
• /
• 2014

For the purpose of early diagnosis of the breast cancer, the attention on the screening mammography has been increasing-with supply of digital mammography day by day. Image quality is decided by target materials and filter combinations. Optimized selection by a glandular density and a thickness is needed, because these combinations change x-ray spectrum and effect to image quality. The purpose of this study is to find out optimized target and filter combinations through the evaluation of quantitative image quality and to suggest means which minimize patient dose through MCNPX. In results, spatial frequency resolution evaluation which is quantitative image quality evaluation method, MTF, NPS, DQE shows that we have to select Mo/Mo combinations or Mo/Rh combinations when compressed breast is thin. but in case of that when compressed breast is thick, we have to select Rh/Rh combinations or W /Rh combinations. In a comprehensive evaluation, W!Rh combinations which are not used in thin breasts in practice was superior to all image quality evaluation. This result is somewhat different-with clinical examination results. Secondary end point was organ dose evaluation, radiation dose of opposite breast was approximately 47 ~73% effectiveness when selecting standard breast. In conculsion, the most important point is that we have to select the optimal combinations-with considering dose evaluation and various thickness.

• Journal of Biomedical Engineering Research
• /
• v.38 no.6
• /
• pp.321-329
• /
• 2017

This paper presents a bone metastasis Detection algorithm on abdominal computed tomography images for early detection using fully convolutional neural networks. The images were taken from patients with various cancers (such as lung cancer, breast cancer, colorectal cancer, etc), and thus the locations of those lesions were varied. To overcome the lack of data, we augmented the data by adjusting the brightness of the images or flipping the images. Before the augmentation, when 70% of the whole data were used in the pre-test, we could obtain the pixel-wise sensitivity of 18.75%, the specificity of 99.97% on the average of test dataset. With the augmentation, we could obtain the sensitivity of 30.65%, the specificity of 99.96%. The increase in sensitivity shows that the augmentation was effective. In the result obtained by using the whole data, the sensitivity of 38.62%, the specificity of 99.94% and the accuracy of 99.81% in the pixel-wise. lesion-wise sensitivity is 88.89% while the false alarm per case is 0.5. The results of this study did not reach the level that could substitute for the clinician. However, it may be helpful for radiologists when it can be used as a screening tool.