Uncertainty quantification in the radiogenomics modeling of EGFR amplification in glioblastoma.
Uncertainty quantification in the radiogenomics modeling of EGFR amplification in glioblastoma.
复制标题
胶质母细胞瘤EGFR扩增放射基因组学建模的不确定性量化。
DOI：
10.1038/s41598-021-83141-z
复制
发表时间：
2021-02-16
影响因子：
4.6
通讯作者：
Li J
中科院分区：
文献类型：
--
作者：
Hu LS;Wang L;Hawkins-Daarud A;Eschbacher JM;Singleton KW;Jackson PR;Clark-Swanson K;Sereduk CP;Peng S;Wang P;Wang J;Baxter LC;Smith KA;Mazza GL;Stokes AM;Bendok BR;Zimmerman RS;Krishna C;Porter AB;Mrugala MM;Hoxworth JM;Wu T;Tran NL;Swanson KR;Li J
放射基因组学使用机器学习（ML）将临床成像上肿瘤的形态和生理外观与潜在的基因组特征直接联系起来。尽管放射基因组学在许多癌症领域的广泛发展及其在推进临床决策方面的潜在作用，但没有发表的研究直接解决了这些模型预测的不确定性。我们开发了一个放射基因组学ML模型，使用转导高斯过程（GP）和来自25名未经治疗的胶质母细胞瘤（GBM）患者的空间匹配MRI的95个图像定位活检的独特数据集来量化不确定性。该模型生成了区域EGFR扩增状态（GBM中常见且重要的靶点）的预测，以解决每个个体肿瘤的肿瘤内遗传异质性-未来个性化治疗模式的关键因素。该模型使用每个样本预测的概率分布来量化不确定性，并使用转导学习来降低整体不确定性。我们比较了预测的准确性和不确定性的转导学习GP模型对标准GP模型使用留一病人交叉验证。此外，我们使用了一个单独的数据集，其中包含来自7名高级别胶质瘤患者的24个图像定位活检，以验证该模型。预测不确定性告知实现准确样品预测的可能性。当基于不确定性对预测进行分层时，我们观察到与具有较高不确定性的预测（48%准确度，n = 23）相比，组队列（75%准确度，n = 95）和具有最低不确定性的样本预测（83%准确度，n = 72）的性能显著更高，这主要是由于数据插值（而不是外推）。在单独的验证集上，我们的模型在不确定性最低的样本预测中达到了78%的准确率。我们提出了一种新的方法来量化放射基因组学的不确定性，以提高模型的性能和临床解释。这将有助于整合更可靠的放射基因组学模型，以改善医疗决策。
Radiogenomics uses machine-learning (ML) to directly connect the morphologic and physiological appearance of tumors on clinical imaging with underlying genomic features. Despite extensive growth in the area of radiogenomics across many cancers, and its potential role in advancing clinical decision making, no published studies have directly addressed uncertainty in these model predictions. We developed a radiogenomics ML model to quantify uncertainty using transductive Gaussian Processes (GP) and a unique dataset of 95 image-localized biopsies with spatially matched MRI from 25 untreated Glioblastoma (GBM) patients. The model generated predictions for regional EGFR amplification status (a common and important target in GBM) to resolve the intratumoral genetic heterogeneity across each individual tumor—a key factor for future personalized therapeutic paradigms. The model used probability distributions for each sample prediction to quantify uncertainty, and used transductive learning to reduce the overall uncertainty. We compared predictive accuracy and uncertainty of the transductive learning GP model against a standard GP model using leave-one-patient-out cross validation. Additionally, we used a separate dataset containing 24 image-localized biopsies from 7 high-grade glioma patients to validate the model. Predictive uncertainty informed the likelihood of achieving an accurate sample prediction. When stratifying predictions based on uncertainty, we observed substantially higher performance in the group cohort (75% accuracy, n = 95) and amongst sample predictions with the lowest uncertainty (83% accuracy, n = 72) compared to predictions with higher uncertainty (48% accuracy, n = 23), due largely to data interpolation (rather than extrapolation). On the separate validation set, our model achieved 78% accuracy amongst the sample predictions with lowest uncertainty. We present a novel approach to quantify radiogenomics uncertainty to enhance model performance and clinical interpretability. This should help integrate more reliable radiogenomics models for improved medical decision-making.
登录
查看更多内容
影响因子：
3.6
作者：
Briggs, Andrew H.;Weinstein, Milton C.;Paltiel, A. David
通讯作者：
Paltiel, A. David
影响因子：
15.9
作者：
Hu LS;Eschbacher JM;Heiserman JE;Dueck AC;Shapiro WR;Liu S;Karis JP;Smith KA;Coons SW;Nakaji P;Spetzler RF;Feuerstein BG;Debbins J;Baxter LC
通讯作者：
Baxter LC
影响因子：
17.1
作者：
Itakura H;Achrol AS;Mitchell LA;Loya JJ;Liu T;Westbroek EM;Feroze AH;Rodriguez S;Echegaray S;Azad TD;Yeom KW;Napel S;Rubin DL;Chang SD;Harsh GR 4th;Gevaert O
通讯作者：
Gevaert O
影响因子：
19.7
作者：
Jain, Rajan;Poisson, Laila M.;Flanders, Adam
通讯作者：
Flanders, Adam
DOI：
10.3174/ajnr.a4451
发表时间：
2015-12
期刊：
AJNR. American journal of neuroradiology
影响因子：
--
作者：
Hu LS;Kelm Z;Korfiatis P;Dueck AC;Elrod C;Ellingson BM;Kaufmann TJ;Eschbacher JM;Karis JP;Smith K;Nakaji P;Brinkman D;Pafundi D;Baxter LC;Erickson BJ
通讯作者：
Erickson BJ