PMID- 34865622
OWN - NLM
STAT- MEDLINE
DCOM- 20211210
LR  - 20231108
IS  - 1475-925X (Electronic)
IS  - 1475-925X (Linking)
VI  - 20
IP  - 1
DP  - 2021 Dec 5
TI  - Pulmonary lesion subtypes recognition of COVID-19 from radiomics data with 
      three-dimensional texture characterization in computed tomography images.
PG  - 123
LID - 10.1186/s12938-021-00961-w [doi]
LID - 123
AB  - BACKGROUND: The COVID-19 disease is putting unprecedented pressure on the global 
      healthcare system. The CT (computed tomography) examination as a auxiliary 
      confirmed diagnostic method can help clinicians quickly detect lesions locations 
      of COVID-19 once screening by PCR test. Furthermore, the lesion subtypes 
      classification plays a critical role in the consequent treatment decision. 
      Identifying the subtypes of lesions accurately can help doctors discover changes 
      in lesions in time and better assess the severity of COVID-19. METHOD: The most 
      four typical lesion subtypes of COVID-19 are discussed in this paper, which are 
      GGO (ground-glass opacity), cord, solid and subsolid. A computer-aided diagnosis 
      approach of lesion subtype is proposed in this paper. The radiomics data of 
      lesions are segmented from COVID-19 patients CT images with diagnosis and lesions 
      annotations by radiologists. Then the three-dimensional texture descriptors are 
      applied on the volume data of lesions as well as shape and first-order features. 
      The massive feature data are selected by HAFS (hybrid adaptive feature selection) 
      algorithm and a classification model is trained at the same time. The classifier 
      is used to predict lesion subtypes as side decision information for radiologists. 
      RESULTS: There are 3734 lesions extracted from the dataset with 319 patients 
      collection and then 189 radiomics features are obtained finally. The random 
      forest classifier is trained with data augmentation that the number of different 
      subtypes of lesions is imbalanced in initial dataset. The experimental results 
      show that the accuracy of the four subtypes of lesions is (93.06%, 96.84%, 
      99.58%, and 94.30%), the recall is (95.52%, 91.58%, 95.80% and 80.75%) and the 
      f-score is (93.84%, 92.37%, 95.47%, and 84.42%). CONCLUSION: The 
      three-dimensional radiomics features used in this paper can better express the 
      high-level information of COVID-19 lesions in CT slices. HAFS method aggregates 
      the results of multiple feature selection algorithms intersects with traditional 
      methods to filter out redundant features more accurately. After selection, the 
      subtype of COVID-19 lesion can be judged by inputting the features into the RF 
      (random forest) model, which can help clinicians more accurately identify the 
      subtypes of COVID-19 lesions and provide help for further research.
CI  - (c) 2021. The Author(s).
FAU - Li, Wei
AU  - Li W
AD  - Key Laboratory of Intelligent Computing in Medical Image (MIIC), Northeastern 
      University, Ministry of Education, Shenyang, China.
FAU - Cao, Yangyong
AU  - Cao Y
AD  - School of Computer Science and Engineering, Northeastern University, Shenyang, 
      China. 1971582@stu.neu.edu.cn.
FAU - Yu, Kun
AU  - Yu K
AD  - Biomedical and Information Engineering School, Northeastern University, Shenyang, 
      China.
FAU - Cai, Yibo
AU  - Cai Y
AD  - School of Computer Science and Engineering, Northeastern University, Shenyang, 
      China.
FAU - Huang, Feng
AU  - Huang F
AD  - Neusoft Medical System Co., Ltd., Shenyang, Liaoning, China.
FAU - Yang, Minglei
AU  - Yang M
AD  - Neusoft Medical System Co., Ltd., Shenyang, Liaoning, China.
FAU - Xie, Weidong
AU  - Xie W
AUID- ORCID: 0000-0003-1930-4509
AD  - School of Computer Science and Engineering, Northeastern University, Shenyang, 
      China. 1910638@stu.neu.edu.cn.
LA  - eng
GR  - N2016006/Fundamental Research Funds for Central Universities of the Central South 
      University/
GR  - 17-134-8-00/Shenyang Medical Imaging Processing Engineering Technology Research 
      Center/
GR  - No.U1708261/National Natural Science Foundation of China/
PT  - Journal Article
DEP - 20211205
PL  - England
TA  - Biomed Eng Online
JT  - Biomedical engineering online
JID - 101147518
SB  - IM
MH  - Algorithms
MH  - *COVID-19
MH  - Humans
MH  - Lung
MH  - SARS-CoV-2
MH  - Tomography, X-Ray Computed
PMC - PMC8645296
OTO - NOTNLM
OT  - 3D texture feature
OT  - COVID-19
OT  - Hybrid adaptive feature selection
OT  - Lesion subtypes
OT  - Radiomics
OT  - Random forest
COIS- There are no conflicts of interest declared.
EDAT- 2021/12/07 06:00
MHDA- 2021/12/15 06:00
PMCR- 2021/12/05
CRDT- 2021/12/06 05:30
PHST- 2021/05/17 00:00 [received]
PHST- 2021/11/19 00:00 [accepted]
PHST- 2021/12/06 05:30 [entrez]
PHST- 2021/12/07 06:00 [pubmed]
PHST- 2021/12/15 06:00 [medline]
PHST- 2021/12/05 00:00 [pmc-release]
AID - 10.1186/s12938-021-00961-w [pii]
AID - 961 [pii]
AID - 10.1186/s12938-021-00961-w [doi]
PST - epublish
SO  - Biomed Eng Online. 2021 Dec 5;20(1):123. doi: 10.1186/s12938-021-00961-w.