PMID- 36129645
OWN - NLM
STAT- MEDLINE
DCOM- 20221010
LR  - 20221011
IS  - 1741-0444 (Electronic)
IS  - 0140-0118 (Print)
IS  - 0140-0118 (Linking)
VI  - 60
IP  - 11
DP  - 2022 Nov
TI  - DMs-MAFM+EfficientNet: a hybrid model for predicting dysthyroid optic neuropathy.
PG  - 3217-3230
LID - 10.1007/s11517-022-02663-4 [doi]
AB  - Thyroid-associated ophthalmopathy (TAO) is a very common autoimmune orbital 
      disease. Approximately 4%-8% of TAO patients will deteriorate and develop the 
      most severe dysthyroid optic neuropathy (DON). According to the current data 
      provided by clinical experts, there is still a certain proportion of suspected 
      DON patients who cannot be diagnosed, and the clinical evaluation has low 
      sensitivity and specificity. There is an urgent need for an efficient and 
      accurate method to assist physicians in identifying DON. This study proposes a 
      hybrid deep learning model to accurately identify suspected DON patients using 
      computed tomography (CT). The hybrid model is mainly composed of the double 
      multiscale and multi attention fusion module (DMs-MAFM) and a deep convolutional 
      neural network. The DMs-MAFM is the feature extraction module proposed in this 
      study, and it contains a multiscale feature fusion algorithm and improved channel 
      attention and spatial attention, which can capture the features of tiny objects 
      in the images. Multiscale feature fusion is combined with an attention mechanism 
      to form a multilevel feature extraction module. The multiscale fusion algorithm 
      can aggregate different receptive field features, and then fully obtain the 
      channel and spatial correlation of the feature map through the multiscale channel 
      attention aggregation module and spatial attention module, respectively. 
      According to the experimental results, the hybrid model proposed in this study 
      can accurately identify suspected DON patients, with Accuracy reaching 96%, 
      Specificity reaching 99.5%, Sensitivity reaching 94%, Precision reaching 98.9% 
      and F1-score reaching 96.4%. According to the evaluation by experts, the hybrid 
      model proposed in this study has some enlightening significance for the diagnosis 
      and prediction of clinically suspect DON.
CI  - (c) 2022. International Federation for Medical and Biological Engineering.
FAU - Wu, Cong
AU  - Wu C
AUID- ORCID: 0000-0003-1360-1617
AD  - School of Computer Science, Hubei University of Technology, Nanli Street 28, 
      Wuhan, 430068, China. oidipous@hbut.edu.cn.
FAU - Li, Shijun
AU  - Li S
AD  - School of Computer Science, Hubei University of Technology, Nanli Street 28, 
      Wuhan, 430068, China.
FAU - Liu, Xiao
AU  - Liu X
AD  - School of Computer Science, Hubei University of Technology, Nanli Street 28, 
      Wuhan, 430068, China.
FAU - Jiang, Fagang
AU  - Jiang F
AD  - Union Hosptial Tongji Medical College Huazhong University of Science and 
      Technology, Zhongshan Park, Wuhan, 430022, China.
FAU - Shi, Bingjie
AU  - Shi B
AD  - Union Hosptial Tongji Medical College Huazhong University of Science and 
      Technology, Zhongshan Park, Wuhan, 430022, China.
LA  - eng
PT  - Journal Article
DEP - 20220921
PL  - United States
TA  - Med Biol Eng Comput
JT  - Medical & biological engineering & computing
JID - 7704869
SB  - IM
MH  - *Graves Ophthalmopathy/diagnostic imaging
MH  - Humans
MH  - *Optic Nerve Diseases/diagnostic imaging
PMC - PMC9490694
OTO - NOTNLM
OT  - Convolutional neural network
OT  - Deep learning
OT  - Dysthyroid optic neuropathy
OT  - Medical imaging prediction
OT  - Thyroid-associated ophthalmopathy
COIS- The authors declare no competing interests.
EDAT- 2022/09/22 06:00
MHDA- 2022/10/12 06:00
PMCR- 2022/09/21
CRDT- 2022/09/21 11:21
PHST- 2022/03/17 00:00 [received]
PHST- 2022/08/19 00:00 [accepted]
PHST- 2022/09/22 06:00 [pubmed]
PHST- 2022/10/12 06:00 [medline]
PHST- 2022/09/21 11:21 [entrez]
PHST- 2022/09/21 00:00 [pmc-release]
AID - 10.1007/s11517-022-02663-4 [pii]
AID - 2663 [pii]
AID - 10.1007/s11517-022-02663-4 [doi]
PST - ppublish
SO  - Med Biol Eng Comput. 2022 Nov;60(11):3217-3230. doi: 10.1007/s11517-022-02663-4. 
      Epub 2022 Sep 21.