Page 52 - Handbook of Deep Learning in Biomedical Engineering Techniques and Applications

Article type Journal Journal Conference

References [76] [52] [77]

taken IBSR_V2.0 ISOASIS the data age acquired T1- acquired a

was Segmentation Probabilistic entitled the at multimodal from different infants T2- infants T1- and that diffusion-weighted using
which as such Brain was of acquired 53 of suffering multiforme five preterm postmenstrual axial axial adults years, adults years used were infants scanner
used, sets LONI which discs was to of PMA, preterm PMA, aging 70 young 23 healthy MR
set Internet the two one consisted patients applied weeks weeks of weeks of of of of sets and head-only
data were data the (IBSR), project first last and glioblastoma was images 30 40 images 40 images age images age data T2-, 10 of
on scans different from Atlas the the from method coronal T2-weighted at and at average average public T1-, images 3T
Remark 188 Total from came Repository Brain LPBA40, project, institution images recurrent The sets: acquired (PMA) weighted acquired weighted an at weighted an at Multiple acquired MR Siemens

imaging.dcontinued Modality CNN MRI MRI CNN MRI

medical of Type CNN 3D Multiscale CNN Fully (FCNN)

to i.e., MR of
application stripping, skull extraction automatic segmentation segmentation images brain

CNN for brain for for infant

of designed MRI designed images developed
Literature Applications System deep System brain Model isointense

2.2 Year
Table Body part