疑似早期进展或假性进展患者的传统MRI影像组学

Conventional MRI radiomics in patients with suspected early- or pseudo-progression.

作者信息

Bani-Sadr Alexandre, Eker Omer Faruk, Berner Lise-Prune, Ameli Roxana, Hermier Marc, Barritault Marc, Meyronet David, Guyotat Jacques, Jouanneau Emmanuel, Honnorat Jerome, Ducray François, Berthezene Yves

机构信息

Department of Neuroradiology, East Group Hospital, Hospices Civils de Lyon, Lyon Cedex, France.

Department of Molecular Biology, East Group Hospital, Hospices Civils de Lyon, Lyon Cedex, France.

出版信息

Neurooncol Adv. 2019 Sep 1;1(1):vdz019. doi: 10.1093/noajnl/vdz019. eCollection 2019 May-Dec.

BACKGROUND

After radiochemotherapy, 30% of patients with early worsening MRI experience pseudoprogression (Psp) which is not distinguishable from early progression (EP). We aimed to assess the diagnostic value of radiomics in patients with suspected EP or Psp.

METHODS

Radiomics features (RF) of 76 patients (53 EP and 23 Psp) retrospectively identified were extracted from conventional MRI based on four volumes-of-interest. Subjects were randomly assigned into training and validation groups. Classification model (EP versus Psp) consisted of a random forest algorithm after univariate filtering. Overall (OS) and progression-free survivals (PFS) were predicted using a semi-supervised principal component analysis, and forecasts were evaluated using C-index and integrated Brier scores (IBS).

RESULTS

Using 11 RFs, radiomics classified patients with 75.0% and 76.0% accuracy, 81.6% and 94.1% sensitivity, 50.0% and 37.5% specificity, respectively, in training and validation phases. Addition of promoter status improved accuracy to 83% and 79.2%, and specificity to 63.6% and 75%. OS model included 14 RFs and stratified low- and high-risk patients both in the training (hazard ratio [HR], 3.63; = .002) and the validation (HR, 3.76; = .001) phases. Similarly, PFS model stratified patients during training (HR, 2.58; = .005) and validation (HR, 3.58; = .004) phases using 5 RF. OS and PFS forecasts had C-index of 0.65 and 0.69, and IBS of 0.122 and 0.147, respectively.

CONCLUSIONS

Conventional MRI radiomics has promising diagnostic value, especially when combined with promoter status, but with moderate specificity. In addition, our results suggest a potential for predicting OS and PFS.

背景

在放化疗后，30%早期MRI表现恶化的患者会出现假性进展（Psp），这与早期进展（EP）难以区分。我们旨在评估影像组学在疑似EP或Psp患者中的诊断价值。

方法

基于四个感兴趣体积，从76例患者（53例EP和23例Psp）的常规MRI中回顾性提取影像组学特征（RF）。将受试者随机分为训练组和验证组。分类模型（EP与Psp）由单变量筛选后的随机森林算法组成。使用半监督主成分分析预测总生存期（OS）和无进展生存期（PFS），并使用C指数和综合Brier评分（IBS）评估预测结果。

结果

在训练阶段和验证阶段，使用11个RF，影像组学对患者的分类准确率分别为（EP与Psp）75.0%和76.0%，灵敏度分别为81.6%和94.1%，特异性分别为50.0%和37.5%。加入启动子状态后，准确率提高到83%和79.2%，特异性提高到63.6%和75%。OS模型包括14个RF，在训练阶段（风险比[HR]，3.63；P = 0.002）和验证阶段（HR，3.76；P = 0.001）均对低风险和高风险患者进行了分层。同样，PFS模型在训练阶段（HR，2.58；P = 0.005）和验证阶段（HR，3.58；P = 0.004）使用5个RF对患者进行了分层。OS和PFS预测的C指数分别为0.65和0.69，IBS分别为0.122和0.147。