PMID- 32046685
OWN - NLM
STAT- MEDLINE
DCOM- 20200925
LR  - 20200925
IS  - 1471-2342 (Electronic)
IS  - 1471-2342 (Linking)
VI  - 20
IP  - 1
DP  - 2020 Feb 11
TI  - Brain SegNet: 3D local refinement network for brain lesion segmentation.
PG  - 17
LID - 10.1186/s12880-020-0409-2 [doi]
LID - 17
AB  - MR images (MRIs) accurate segmentation of brain lesions is important for 
      improving cancer diagnosis, surgical planning, and prediction of outcome. 
      However, manual and accurate segmentation of brain lesions from 3D MRIs is highly 
      expensive, time-consuming, and prone to user biases. We present an efficient yet 
      conceptually simple brain segmentation network (referred as Brain SegNet), which 
      is a 3D residual framework for automatic voxel-wise segmentation of brain lesion. 
      Our model is able to directly predict dense voxel segmentation of brain tumor or 
      ischemic stroke regions in 3D brain MRIs. The proposed 3D segmentation network 
      can run at about 0.5s per MRIs - about 50 times faster than previous approaches 
      Med Image Anal 43: 98-111, 2018, Med Image Anal 36:61-78, 2017. Our model is 
      evaluated on the BRATS 2015 benchmark for brain tumor segmentation, where it 
      obtains state-of-the-art results, by surpassing recently published results 
      reported in Med Image Anal 43: 98-111, 2018, Med Image Anal 36:61-78, 2017. We 
      further applied the proposed Brain SegNet for ischemic stroke lesion outcome 
      prediction, with impressive results achieved on the Ischemic Stroke Lesion 
      Segmentation (ISLES) 2017 database.
FAU - Hu, Xiaojun
AU  - Hu X
AD  - Malong Technologies, Shenzhen, China.
AD  - Shenzhen Malong Artificial Intelligence Research Center, Shenzhen, China.
FAU - Luo, Weijian
AU  - Luo W
AD  - Department of Neurosurgery, Second Clinical Medical College of Jinan University 
      (Shenzhen People's Hospital), Shenzhen, China.
FAU - Hu, Jiliang
AU  - Hu J
AD  - Department of Neurosurgery, Second Clinical Medical College of Jinan University 
      (Shenzhen People's Hospital), Shenzhen, China. hforestwolf@163.com.
FAU - Guo, Sheng
AU  - Guo S
AD  - Malong Technologies, Shenzhen, China.
AD  - Shenzhen Malong Artificial Intelligence Research Center, Shenzhen, China.
FAU - Huang, Weilin
AU  - Huang W
AD  - Malong Technologies, Shenzhen, China. whuang@malong.com.
AD  - Shenzhen Malong Artificial Intelligence Research Center, Shenzhen, China. 
      whuang@malong.com.
FAU - Scott, Matthew R
AU  - Scott MR
AD  - Malong Technologies, Shenzhen, China.
AD  - Shenzhen Malong Artificial Intelligence Research Center, Shenzhen, China.
FAU - Wiest, Roland
AU  - Wiest R
AD  - Imaging A.I. Lab, Insel Data Science Center, Bern University Hospital, Bern, 
      Switzerland.
FAU - Dahlweid, Michael
AU  - Dahlweid M
AD  - Imaging A.I. Lab, Insel Data Science Center, Bern University Hospital, Bern, 
      Switzerland.
FAU - Reyes, Mauricio
AU  - Reyes M
AD  - Imaging A.I. Lab, Insel Data Science Center, Bern University Hospital, Bern, 
      Switzerland.
LA  - eng
PT  - Journal Article
DEP - 20200211
PL  - England
TA  - BMC Med Imaging
JT  - BMC medical imaging
JID - 100968553
SB  - IM
MH  - Brain Neoplasms/*diagnostic imaging
MH  - Humans
MH  - Image Processing, Computer-Assisted/*methods
MH  - Imaging, Three-Dimensional
MH  - Magnetic Resonance Imaging
MH  - Neural Networks, Computer
MH  - Radiographic Image Interpretation, Computer-Assisted
PMC - PMC7014943
OTO - NOTNLM
OT  - 3D brain MRIs
OT  - Brain tumor segmentation
OT  - Curriculum learning
OT  - Stroke outcome prediction
COIS- The authors declare that they have no competing interests.
EDAT- 2020/02/13 06:00
MHDA- 2020/09/26 06:00
PMCR- 2020/02/11
CRDT- 2020/02/13 06:00
PHST- 2019/09/12 00:00 [received]
PHST- 2020/01/03 00:00 [accepted]
PHST- 2020/02/13 06:00 [entrez]
PHST- 2020/02/13 06:00 [pubmed]
PHST- 2020/09/26 06:00 [medline]
PHST- 2020/02/11 00:00 [pmc-release]
AID - 10.1186/s12880-020-0409-2 [pii]
AID - 409 [pii]
AID - 10.1186/s12880-020-0409-2 [doi]
PST - epublish
SO  - BMC Med Imaging. 2020 Feb 11;20(1):17. doi: 10.1186/s12880-020-0409-2.