• Proceedings of the KSMRM Conference
• /
• 2001.11a
• /
• pp.140-140
• /
• 2001

We present two cases of surgically proven focal nodular hyperplasia whou underwent tri contrast-enhance MR imaging using gadolinium chelates, mangafodipir trisodium, and ferumoxides After the unehanced MR images were obtained, dynamic gadolinium-enhanced T1-weighted imagi were performed, then mangafodipir enhanced and ferumoxides-enhanced images were obtained. In one case, the mass was isointense on both T1- and T2-weighted images on the unehanced M images, iso and slightly hyperintense on ferumoxides-enhanced FSE and GRE images, strong hyperintense on the mangafodipir enhanced and gadolinium enhanced arterial phase images. In th other case, the mass was isointense on T2-weighted and hypointense on T1-weighted image isointense on ferumoxides-enhanced images, and hyperintense on mangafodipir enhanced an gadolinium enhanced arterial phase images. Triple contrast enhanced MR images were useful correctly diagnose these two cases preoperatively.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.14 no.3
• /
• pp.962-975
• /
• 2020

The accurate segmentation of infant brain MR image into white matter (WM), gray matter (GM), and cerebrospinal fluid (CSF) is very important for early studying of brain growing patterns and morphological changes in neurodevelopmental disorders. Because of inherent myelination and maturation process, the WM and GM of babies (between 6 and 9 months of age) exhibit similar intensity levels in both T1-weighted (T1w) and T2-weighted (T2w) MR images in the isointense phase, which makes brain tissue segmentation very difficult. We propose a deep network architecture based on U-Net, called Triple Residual Multiscale Fully Convolutional Network (TRMFCN), whose structure exists three gates of input and inserts two blocks: residual multiscale block and concatenate block. We solved some difficulties and completed the segmentation task with the model. Our model outperforms the U-Net and some cutting-edge deep networks based on U-Net in evaluation of WM, GM and CSF. The data set we used for training and testing comes from iSeg-2017 challenge (http://iseg2017.web.unc.edu).