Jung Ha Kyung, Choi Changyong, Park Ji Eun, Park Seo Young, Lee Jae Ho, Kim Namkug, Kim Ho Sung
Department of Radiology, Keimyung University Dongsan Hospital, Keimyung University School of Medicine, Daegu, Korea.
Department of Convergence Medicine, Asan Medical Center, University of Ulsan College of Medicine, Seoul, Korea.
Sci Rep. 2025 Aug 7;15(1):28913. doi: 10.1038/s41598-025-14477-z.
This study investigated the effects of feature augmentation, which uses generated images with specific imaging features, on the performance of isocitrate dehydrogenase (IDH) mutation prediction models in gliomas. A total of 598 patients were included from our institution (310 training, 152 internal test) and the Cancer Genome Atlas (136 external test). Score-based diffusion models were used to generate T2-weighted, FLAIR, and contrast-enhanced T1-weighted image triplets. Three neuroradiologists independently assessed visual Turing tests and various morphological features. Multivariable logistic regression models were developed using real images, random augmented data, and feature-augmented datasets. While random augmentation yielded models with AUCs comparable to real image-based models, it led to reduced specificity, particularly in the external test set (specificity: 83.2% vs. 73.0%, P = .013). In contrast, feature-augmented models maintained stable diagnostic performance; however, when more than 70% of training images included synthetic T2-FLAIR mismatch signs, AUC decreased in the external test set (AUC: 0.905-0.906 for ≤ 70%; 0.902-0.876 for ≥ 80%). These findings highlight the value of phenotype-specific augmentation for IDH prediction, while emphasizing the need to optimize augmentation proportion to avoid performance degradation.
本研究调查了特征增强(使用具有特定成像特征的生成图像)对神经胶质瘤中异柠檬酸脱氢酶(IDH)突变预测模型性能的影响。我们机构共纳入598例患者(310例用于训练,152例用于内部测试)以及癌症基因组图谱(136例用于外部测试)。基于分数的扩散模型用于生成T2加权、液体衰减反转恢复序列(FLAIR)和对比增强T1加权图像三联体。三名神经放射科医生独立评估视觉图灵测试和各种形态学特征。使用真实图像、随机增强数据和特征增强数据集开发多变量逻辑回归模型。虽然随机增强产生的模型的曲线下面积(AUC)与基于真实图像的模型相当,但它导致特异性降低,尤其是在外部测试集中(特异性:83.2%对73.0%,P = 0.013)。相比之下,特征增强模型保持了稳定的诊断性能;然而,当超过70%的训练图像包含合成的T2-FLAIR不匹配征象时,外部测试集中的AUC下降(AUC:≤70%时为0.905至0.906;≥80%时为0.902至0.876)。这些发现突出了表型特异性增强对IDH预测的价值,同时强调需要优化增强比例以避免性能下降。