Jia Wei, Li Hailong, Ali Redha, Shanbhogue Krishna P, Masch William R, Aslam Anum, Harris David T, Reeder Scott B, Dillman Jonathan R, He Lili
Imaging Research Center, Department of Radiology, Cincinnati Children's Hospital Medical Center, 3333 Burnet Avenue, MLC 7009, Cincinnati, OH, 45229, USA.
Department of Environmental and Public Health, Division of Biostatistics and Bioinformatics, University of Cincinnati, Cincinnati College of Medicine, Cincinnati, OH, USA.
J Imaging Inform Med. 2025 Apr;38(2):1016-1027. doi: 10.1007/s10278-024-01253-0. Epub 2024 Sep 16.
ComBat harmonization has been developed to remove non-biological variations for data in multi-center research applying artificial intelligence (AI). We investigated the effectiveness of ComBat harmonization on radiomic and deep features extracted from large, multi-center abdominal MRI data. A retrospective study was conducted on T2-weighted (T2W) abdominal MRI data retrieved from individual patients with suspected or known chronic liver disease at three study sites. MRI data were acquired using systems from three manufacturers and two field strengths. Radiomic features and deep features were extracted using the PyRadiomics pipeline and a Swin Transformer. ComBat was used to harmonize radiomic and deep features across different manufacturers and field strengths. Student's t-test, ANOVA test, and Cohen's F score were applied to assess the difference in individual features before and after ComBat harmonization. Between two field strengths, 76.7%, 52.9%, and 26.7% of radiomic features, and 89.0%, 56.5%, and 0.1% of deep features from three manufacturers were significantly different. Among the three manufacturers, 90.1% and 75.0% of radiomic features and 89.3% and 84.1% of deep features from two field strengths were significantly different. After ComBat harmonization, there were no significant differences in radiomic and deep features among manufacturers or field strengths based on t-tests or ANOVA tests. Reduced Cohen's F scores were consistently observed after ComBat harmonization. ComBat harmonization effectively harmonizes radiomic and deep features by removing the non-biological variations due to system manufacturers and/or field strengths in large multi-center clinical abdominal MRI datasets.
ComBat归一化方法已被开发出来，用于消除多中心研究中应用人工智能（AI）的数据的非生物学变异。我们研究了ComBat归一化方法对从大型多中心腹部MRI数据中提取的放射组学特征和深度特征的有效性。对从三个研究地点的疑似或已知慢性肝病个体患者中检索到的T2加权（T2W）腹部MRI数据进行了回顾性研究。MRI数据使用来自三个制造商的系统和两种场强采集。使用PyRadiomics管道和Swin Transformer提取放射组学特征和深度特征。ComBat用于在不同制造商和场强之间对放射组学特征和深度特征进行归一化。应用学生t检验、方差分析和科恩F分数来评估ComBat归一化前后个体特征的差异。在两种场强之间，来自三个制造商的放射组学特征的76.7%、52.9%和26.7%，以及深度特征的89.0%、56.5%和0.1%有显著差异。在三个制造商中，来自两种场强的放射组学特征的90.1%和75.0%，以及深度特征的89.3%和84.1%有显著差异。经过ComBat归一化后，基于t检验或方差分析，制造商或场强之间的放射组学特征和深度特征没有显著差异。在ComBat归一化后，始终观察到科恩F分数降低。ComBat归一化通过消除大型多中心临床腹部MRI数据集中由于系统制造商和/或场强导致的非生物学变异，有效地对放射组学特征和深度特征进行了归一化。
