PMID- 37711807
OWN - NLM
STAT- PubMed-not-MEDLINE
LR  - 20230917
IS  - 2223-4292 (Print)
IS  - 2223-4306 (Electronic)
IS  - 2223-4306 (Linking)
VI  - 13
IP  - 9
DP  - 2023 Sep 1
TI  - Optimization and validation of voxel size-related radiomics variability by 
      combatting batch effect harmonization in pulmonary nodules: a phantom and 
      clinical study.
PG  - 6139-6151
LID - 10.21037/qims-22-992 [doi]
AB  - BACKGROUND: Broad generalization of radiomics-assisted models may be impeded by 
      concerns about variability. This study aimed to evaluate the merit of combatting 
      batch effect (ComBat) harmonization in reducing the variability of voxel 
      size-related radiomics in both phantom and clinical study in comparison with 
      image resampling correction method. METHODS: A pulmonary phantom with 22 
      different types of nodules was scanned by computed tomography (CT) with different 
      voxel sizes. The variability of voxel size-related radiomics features was 
      evaluated using concordance correlation coefficient (CCC), dynamic range (DR), 
      and intraclass correlation coefficient (ICC). ComBat and image resampling 
      compensation methods were used to reduce variability of voxel size-related 
      radiomics. The percentage of robust radiomics features was compared before and 
      after optimization. Pathologically differential diagnosis of invasive 
      adenocarcinoma (IAC) from adenocarcinoma in situ (AIS) and minimally invasive 
      adenocarcinoma (MIA) (AIS-MIA group) was used for clinical validation in 134 
      patients. RESULTS: Before optimization, the number of excellent features in the 
      phantom and clinical data was 26.12% and 32.31%, respectively. The excellent 
      features were increased after image resampling and ComBat correction. For 
      clinical optimization, the effect of the ComBat compensation method was 
      significantly better than that of image resampling, with excellent features 
      reaching 90.96% and poor features only amounting to 4.96%. In addition, the 
      hierarchical clustering analysis showed that the first-order and shape features 
      had better robustness than did texture features. In clinical validation, the area 
      under the curve (AUC) of the testing set was 0.865 after ComBat correction. 
      CONCLUSIONS: The ComBat harmonization can optimize voxel size-related CT 
      radiomics variability in pulmonary nodules more efficiently than image resampling 
      harmonization.
CI  - 2023 Quantitative Imaging in Medicine and Surgery. All rights reserved.
FAU - Zhuo, Yaoyao
AU  - Zhuo Y
AD  - Department of Radiology, Zhongshan Hospital, Fudan University, Shanghai, China.
AD  - Department of Radiology, Shanghai Public Health Clinical Center, Fudan 
      University, Shanghai, China.
FAU - Shen, Jie
AU  - Shen J
AD  - Department of Radiology, Shanghai Public Health Clinical Center, Fudan 
      University, Shanghai, China.
FAU - Zhan, Yi
AU  - Zhan Y
AD  - Department of Radiology, Shanghai Public Health Clinical Center, Fudan 
      University, Shanghai, China.
FAU - Tian, Ye
AU  - Tian Y
AD  - Department of Radiology, Beilun Second People's Hospital, Ningbo, China.
FAU - Yu, Mingfeng
AU  - Yu M
AD  - Department of Thoracic Surgery, Beilun Second People's Hospital, Ningbo, China.
FAU - Yang, Shuyi
AU  - Yang S
AD  - Department of Radiology, Zhongshan Hospital, Fudan University, Shanghai, China.
FAU - Ye, Peiyan
AU  - Ye P
AD  - Department of Traditional Chinese Medicine, Shanghai Public Health Clinical 
      Center, Fudan University, Shanghai, China.
FAU - Fan, Li
AU  - Fan L
AD  - Department of Radiology, Changzheng Hospital, Naval Medical University, Shanghai, 
      China.
FAU - Zhang, Zhiyong
AU  - Zhang Z
AD  - Department of Radiology, Zhongshan Hospital, Fudan University, Shanghai, China.
AD  - Department of Radiology, Shanghai Public Health Clinical Center, Fudan 
      University, Shanghai, China.
AD  - Research Institute of Big Data, Fudan University, Shanghai, China.
FAU - Shan, Fei
AU  - Shan F
AD  - Department of Radiology, Shanghai Public Health Clinical Center, Fudan 
      University, Shanghai, China.
AD  - Research Institute of Big Data, Fudan University, Shanghai, China.
LA  - eng
PT  - Journal Article
DEP - 20230713
PL  - China
TA  - Quant Imaging Med Surg
JT  - Quantitative imaging in medicine and surgery
JID - 101577942
PMC - PMC10498235
OTO - NOTNLM
OT  - Combatting batch effect (ComBat)
OT  - computed tomography radiomics (CT radiomics)
OT  - image resampling
OT  - pulmonary nodule
OT  - radiomics variability
COIS- Conflicts of Interest: All authors have completed the ICMJE uniform disclosure 
      form (available at 
      https://qims.amegroups.com/article/view/10.21037/qims-22-992/coif). The authors 
      have no conflicts of interest to declare.
EDAT- 2023/09/15 06:42
MHDA- 2023/09/15 06:43
PMCR- 2023/09/01
CRDT- 2023/09/15 03:58
PHST- 2022/09/19 00:00 [received]
PHST- 2023/06/15 00:00 [accepted]
PHST- 2023/09/15 06:43 [medline]
PHST- 2023/09/15 06:42 [pubmed]
PHST- 2023/09/15 03:58 [entrez]
PHST- 2023/09/01 00:00 [pmc-release]
AID - qims-13-09-6139 [pii]
AID - 10.21037/qims-22-992 [doi]
PST - ppublish
SO  - Quant Imaging Med Surg. 2023 Sep 1;13(9):6139-6151. doi: 10.21037/qims-22-992. 
      Epub 2023 Jul 13.