PMID- 31323604
OWN - NLM
STAT- MEDLINE
DCOM- 20200908
LR  - 20200908
IS  - 1879-0534 (Electronic)
IS  - 0010-4825 (Linking)
VI  - 111
DP  - 2019 Aug
TI  - Cine MRI analysis by deep learning of optical flow: Adding the temporal 
      dimension.
PG  - 103356
LID - S0010-4825(19)30233-1 [pii]
LID - 10.1016/j.compbiomed.2019.103356 [doi]
AB  - Accurate segmentation of the left ventricle (LV) from cine magnetic resonance 
      imaging (MRI) is an important step in the reliable assessment of cardiac function 
      in cardiovascular disease patients. Several deep learning convolutional neural 
      network (CNN) models have achieved state-of-the-art performances for LV 
      segmentation from cine MRI. However, most published deep learning methods use 
      individual cine frames as input and process each frame separately. This approach 
      entirely ignores an important visual clue-the dynamic cardiac motion along the 
      temporal axis, which radiologists observe closely when viewing cine MRI. To 
      imitate the approach of experts, we propose a novel U-net-based method (OF-net) 
      that integrates temporal information from cine MRI into LV segmentation. Our 
      proposed network adds the temporal dimension by incorporating an optical flow 
      (OF) field to capture the cardiac motion. In addition, we introduce two 
      additional modules, a LV localization module and an attention module, that 
      provide improved LV detection and segmentation accuracy, respectively. We 
      evaluated OF-net on the public Cardiac Atlas database with multicenter cine MRI 
      data. The results showed that OF-net achieves an average perpendicular distance 
      (APD) of 0.90+/-0.08 pixels and a Dice index of 0.95+/-0.03 for LV segmentation in 
      the middle slices, outperforming the classical U-net model (APD 0.92+/-0.04 pixels, 
      Dice 0.94+/-0.16, p < 0.05). Specifically, the proposed method enhances the 
      temporal continuity of segmentation at the apical and basal slices, which are 
      typically more difficult to segment than middle slices. Our work exemplifies the 
      ability of CNN to "learn" from expert experience when applied to specific 
      analysis tasks.
CI  - Copyright (c) 2019 Elsevier Ltd. All rights reserved.
FAU - Yan, Wenjun
AU  - Yan W
AD  - Department of Electronic Engineering, Fudan University, Shanghai, China.
FAU - Wang, Yuanyuan
AU  - Wang Y
AD  - Department of Electronic Engineering, Fudan University, Shanghai, China; Key 
      Laboratory of Medical Imaging Computing and Computer Assisted Intervention 
      (MICCAI) of Shanghai, Shanghai, China. Electronic address: yywang@fudan.edu.cn.
FAU - van der Geest, Rob J
AU  - van der Geest RJ
AD  - Department of Radiology, Leiden University Medical Center, Leiden, the 
      Netherlands.
FAU - Tao, Qian
AU  - Tao Q
AD  - Department of Radiology, Leiden University Medical Center, Leiden, the 
      Netherlands. Electronic address: q.tao@lumc.nl.
LA  - eng
PT  - Journal Article
PT  - Research Support, Non-U.S. Gov't
DEP - 20190712
PL  - United States
TA  - Comput Biol Med
JT  - Computers in biology and medicine
JID - 1250250
SB  - IM
MH  - Algorithms
MH  - *Deep Learning
MH  - Heart/diagnostic imaging
MH  - Heart Ventricles/diagnostic imaging
MH  - Humans
MH  - Image Processing, Computer-Assisted/*methods
MH  - Magnetic Resonance Imaging, Cine/*methods
OTO - NOTNLM
OT  - Cine MRI
OT  - LV segmentation
OT  - Optical flow
OT  - U-net
EDAT- 2019/07/20 06:00
MHDA- 2020/09/09 06:00
CRDT- 2019/07/20 06:00
PHST- 2019/04/11 00:00 [received]
PHST- 2019/07/11 00:00 [revised]
PHST- 2019/07/11 00:00 [accepted]
PHST- 2019/07/20 06:00 [pubmed]
PHST- 2020/09/09 06:00 [medline]
PHST- 2019/07/20 06:00 [entrez]
AID - S0010-4825(19)30233-1 [pii]
AID - 10.1016/j.compbiomed.2019.103356 [doi]
PST - ppublish
SO  - Comput Biol Med. 2019 Aug;111:103356. doi: 10.1016/j.compbiomed.2019.103356. Epub 
      2019 Jul 12.