生成式人工智能在胶质瘤中的应用:确保训练图像表型多样性以提高IDH突变预测的诊断性能
本研究评估基于生成式人工智能的增强(GAA)能否提供多样且真实的影像表型,并提升深度学习对胶质瘤IDH分型的分类性能。研究纳入565例患者开发模型,并在内部(119例)和外部(108例)测试集上验证。结果显示,使用11万张生成切片增强的最优GAA模型AUC达0.938,在内部和外部测试集上均显著优于两位神经放射科医生。
要点
- 生成图像在真实性(图灵测试47.5-50.5%)和表型多样性上表现良好。
- 最优GAA使用11万张生成切片增强,AUC为0.938。
- 最优GAA分类器在内部和外部测试集的AUC均显著高于神经放射科医生。
核心结论
- 应用具有真实且多样图像的生成式人工智能,在预测胶质瘤IDH分型方面提供了优于神经放射科医生的诊断性能。
研究设计与样本
- 模型开发纳入来自三级医院和癌症影像档案库的565例患者(346例IDH野生型,219例IDH突变型),均具有配对增强T1和FLAIR MRI扫描。
- 性能在内部测试集(119例,78例IDH野生型,41例IDH突变型[IDH1和2])和外部测试集(108例,72例IDH野生型,36例IDH突变型)上测试。
- GAA使用基于分数的扩散模型和ResNet50分类器开发,并与零模型比较选择最优GAA。
- 两位神经放射科医生(R1、R2)评估真实性、影像表型多样性和预测IDH突变。
主要发现
- 生成图像展示了真实性(图灵测试:47.5-50.5%)和表明IDH类型的多样性。
- 最优GAA通过11万张生成切片增强实现,AUC为0.938。
- 使用最优GAA训练的分类器在内部测试集(R1,P=0.003;R2,P<0.001)和外部测试集(R1,P<0.01;R2,P<0.001)的AUC值均显著高于神经放射科医生。
- 大肿瘤或主要增强的GAA性能与最优GAA相当(内部测试:AUC 0.956和0.922;外部测试:0.810和0.749)。
临床怎么用
- 原文未据此给出推荐。
局限性
- 原文未报告局限性。
以上解读依据论文摘要(全文未开放获取或许可不允许翻译转载)。
原文
BACKGROUND: This study evaluated whether generative artificial intelligence (AI)-based augmentation (GAA) can provide diverse and realistic imaging phenotypes and improve deep learning-based classification of isocitrate dehydrogenase (IDH) type in glioma compared with neuroradiologists. METHODS: For model development, 565 patients (346 IDH-wildtype, 219 IDH-mutant) with paired contrast-enhanced T1 and FLAIR MRI scans were collected from tertiary hospitals and The Cancer Imaging Archive. Performance was tested on internal (119, 78 IDH-wildtype, 41 IDH-mutant [IDH1 and 2]) and external test sets (108, 72 IDH-wildtype, 36 IDH-mutant). GAA was developed using a score-based diffusion model and ResNet50 classifier. The optimal GAA was selected in comparison with the null model. Two neuroradiologists (R1, R2) assessed realism, diversity of imaging phenotypes, and predicted IDH mutation. The performance of a classifier trained with optimal GAA was compared with that of neuroradiologists using the area under the receiver operating characteristics curve (AUC). The effect of tumor size and contrast enhancement on GAA performance was tested. RESULTS: Generated images demonstrated realism (Turing's test: 47.5-50.5%) and diversity indicating IDH type. Optimal GAA was achieved with augmentation with 110 000 generated slices (AUC: 0.938). The classifier trained with optimal GAA demonstrated significantly higher AUC values than neuroradiologists in both the internal (R1, P = .003; R2, P < .001) and external test sets (R1, P < .01; R2, P < .001). GAA with large-sized tumors or predominant enhancement showed comparable performance to optimal GAA (internal test: AUC 0.956 and 0.922; external test: 0.810 and 0.749). CONCLUSIONS: The application of generative AI with realistic and diverse images provided better diagnostic performance than neuroradiologists for predicting IDH type in glioma.
引用
- Moon HH, Jeong J, Park JE, et al. Generative AI in glioma: Ensuring diversity in training image phenotypes to improve diagnostic performance for IDH mutation prediction. Neuro Oncol. 2024. PMID: 38253989. doi:10.1093/neuonc/noae012
供执业医师工作参考,不替代临床判断;数值与分级以指南原文为准。