Deep learning for lung cancer prognostication: A retrospective multi-cohort radiomics study.
Deep learning for lung cancer prognostication: A retrospective multi-cohort radiomics study.
复制标题
肺癌预后的深度学习：一项回顾性多核心放射线学研究。
DOI：
10.1371/journal.pmed.1002711
复制
发表时间：
2018-11
期刊：
影响因子：
15.8
通讯作者：
Aerts HJWL
中科院分区：
文献类型：
--
作者：
Hosny A;Parmar C;Coroller TP;Grossmann P;Zeleznik R;Kumar A;Bussink J;Gillies RJ;Mak RH;Aerts HJWL
非小细胞肺癌（NSCLC）患者通常表现出不同的临床病程和结局，即使在相同的肿瘤阶段。这项研究探讨了深度学习在医学成像中的应用，允许自动量化放射学特征，并可能改善患者分层。我们对5家机构的7个独立数据集进行了综合分析，共计1，194例NSCLC患者（中位年龄= 68.3岁[范围32.5-93.3]，中位生存期= 1.7年[范围0.0-11.7]）。使用计算机断层扫描（CT）数据的外部验证，我们使用3D卷积神经网络（CNN）识别了接受放疗患者的预后特征（n = 771，年龄中位数= 68.0岁[范围32.5-93.3]，生存中位数= 1.3年[范围0.0-11.7]）。然后，我们采用迁移学习方法来实现手术患者的相同目标（n = 391，年龄中位数= 69.1岁[范围37.2-88.0]，生存中位数= 3.1年[范围0.0-8.8]）。我们发现，CNN预测与放疗（受试者工作特征曲线下面积[AUC] = 0.70 [95%CI 0.63-0.78]，p < 0.001）和手术（AUC = 0.71 [95%CI 0.60-0.82]，p < 0.001）患者各自治疗开始后的2年总生存率显著相关。CNN还能够在放疗（p < 0.001）和手术（p = 0.03）数据集中将患者显著分层为低死亡率和高死亡率风险组。此外，CNN被发现显着优于随机森林模型建立在临床参数，包括年龄，性别和肿瘤淋巴结转移阶段，以及表现出较高的鲁棒性对重测（组内相关系数= 0.91）和读者间（斯皮尔曼的秩相关性= 0.88）的变化。为了更好地理解CNN捕获的特征，我们确定了对预测贡献最大的区域，并强调了肿瘤周围组织在患者分层中的重要性。我们还提出了捕获的表型与细胞周期和转录过程相关的生物学基础上的初步研究结果。局限性包括这项研究的回顾性以及深度学习网络的不透明黑盒性质。我们的研究结果提供了证据，表明深度学习网络可用于基于NSCLC患者标准护理CT图像的死亡风险分层。这一证据激励未来的研究更好地破译深度学习网络的临床和生物学基础，以及在前瞻性数据中进行验证。Hugo April及其同事评估了深度学习网络从计算机断层扫描肺癌图像中提取相关特征的能力，并将患者分为低死亡率和高死亡率风险组。癌症是世界范围内的主要死亡原因之一，肺癌是美国男性和女性中第二大最常见的诊断癌症。肺癌患者的预后主要通过肿瘤分期来确定，而肿瘤分期又基于相对粗糙和离散的分层。放射学医学图像提供了患者和肿瘤特异性信息，可用于补充临床预后评估工作。通过人工智能、计算机视觉和深度学习的应用，放射组学的最新进展允许从放射图像中提取和挖掘许多定量特征。我们设计了一个分析设置，包括5个机构的7个独立数据集，共计1，194例非小细胞肺癌患者，采用计算机断层扫描成像并接受放疗或手术治疗。我们评估了通过深度学习网络提取的定量成像特征的预后特征，并评估了其根据2年总生存截止值将患者分为低死亡率和高死亡率风险组的能力。在接受手术治疗的患者中，深度学习网络的表现明显优于基于预定义肿瘤特征以及肿瘤体积和最大直径的模型。除了突出显示具有预后影响的图像区域外，我们还评估了深度学习功能对生理成像伪影和输入可变性的鲁棒性，并通过基因表达数据将其与分子信息相关联。我们发现，深度学习功能在手术患者中的表现明显优于现有的统计方法，这暗示了它们在患者分层中的效用，并可能使低死亡率风险组免于辅助化疗。我们证明了肿瘤内外的区域，尤其是肿瘤-间质界面，对预后特征的贡献最大，突出了肿瘤周围组织在患者分层中的重要性。这项研究中的初步基因组关联表明，深度学习特征表示与细胞周期和转录过程之间存在相关性。尽管它们的内部工作原理模糊不清，缺乏强有力的理论支持，但深度学习网络展示了预测信号和对特定噪声伪影的鲁棒性。这一发现激发了进一步的前瞻性研究，验证其在患者分层和个性化癌症治疗计划开发中的效用。
Non-small-cell lung cancer (NSCLC) patients often demonstrate varying clinical courses and outcomes, even within the same tumor stage. This study explores deep learning applications in medical imaging allowing for the automated quantification of radiographic characteristics and potentially improving patient stratification. We performed an integrative analysis on 7 independent datasets across 5 institutions totaling 1,194 NSCLC patients (age median = 68.3 years [range 32.5–93.3], survival median = 1.7 years [range 0.0–11.7]). Using external validation in computed tomography (CT) data, we identified prognostic signatures using a 3D convolutional neural network (CNN) for patients treated with radiotherapy (n = 771, age median = 68.0 years [range 32.5–93.3], survival median = 1.3 years [range 0.0–11.7]). We then employed a transfer learning approach to achieve the same for surgery patients (n = 391, age median = 69.1 years [range 37.2–88.0], survival median = 3.1 years [range 0.0–8.8]). We found that the CNN predictions were significantly associated with 2-year overall survival from the start of respective treatment for radiotherapy (area under the receiver operating characteristic curve [AUC] = 0.70 [95% CI 0.63–0.78], p < 0.001) and surgery (AUC = 0.71 [95% CI 0.60–0.82], p < 0.001) patients. The CNN was also able to significantly stratify patients into low and high mortality risk groups in both the radiotherapy (p < 0.001) and surgery (p = 0.03) datasets. Additionally, the CNN was found to significantly outperform random forest models built on clinical parameters—including age, sex, and tumor node metastasis stage—as well as demonstrate high robustness against test–retest (intraclass correlation coefficient = 0.91) and inter-reader (Spearman’s rank-order correlation = 0.88) variations. To gain a better understanding of the characteristics captured by the CNN, we identified regions with the most contribution towards predictions and highlighted the importance of tumor-surrounding tissue in patient stratification. We also present preliminary findings on the biological basis of the captured phenotypes as being linked to cell cycle and transcriptional processes. Limitations include the retrospective nature of this study as well as the opaque black box nature of deep learning networks. Our results provide evidence that deep learning networks may be used for mortality risk stratification based on standard-of-care CT images from NSCLC patients. This evidence motivates future research into better deciphering the clinical and biological basis of deep learning networks as well as validation in prospective data. Hugo Aerts and colleagues evaluate the ability of deep learning networks to extract relevant features from computed tomography lung cancer images and stratify patients into low and high mortality risk groups. Cancer is one of the leading causes of death worldwide, with lung cancer being the second most commonly diagnosed cancer in both men and women in the US. Prognosis in lung cancer patients is primarily determined through tumor staging, which in turn is based on a relatively coarse and discrete stratification. Radiographic medical images offer patient- and tumor-specific information that could be used to complement clinical prognostic evaluation efforts. Recent advances in radiomics through applications of artificial intelligence, computer vision, and deep learning allow for the extraction and mining of numerous quantitative features from radiographic images. We designed an analysis setup comprising 7 independent datasets across 5 institutions totaling 1,194 patients with non-small-cell lung cancer imaged with computed tomography and treated with either radiotherapy or surgery. We evaluated the prognostic signatures of quantitative imaging features extracted through deep learning networks, and assessed their ability to stratify patients into low and high mortality risk groups as per a 2-year overall survival cutoff. In patients treated with surgery, deep learning networks significantly outperformed models based on predefined tumor features as well as tumor volume and maximum diameter. In addition to highlighting image regions with prognostic influence, we evaluated the deep learning features for robustness against physiological imaging artifacts and input variability, as well as correlated them with molecular information through gene expression data. We found that deep learning features significantly outperform existing prognostication methods in surgery patients, hinting at their utility in patient stratification and potentially sparing low mortality risk groups from adjuvant chemotherapy. We demonstrated that areas within and beyond the tumor—especially the tumor–stroma interfaces—had the largest contributions to the prognostic signature, highlighting the importance of tumor-surrounding tissue in patient stratification. Preliminary genomic associations in this study suggest correlations between the deep learning feature representations and cell cycle and transcriptional processes. Despite their obscure inner workings and lack of a strong theoretical backing, deep learning networks demonstrate a prognostic signal and robustness against specific noise artifacts. This finding motivates further prospective studies validating their utility in patient stratification and the development of personalized cancer treatment plans.
登录
查看更多内容
DOI：
10.1016/j.radonc.2016.04.004
发表时间：
2016-06
期刊：
Radiotherapy and oncology : journal of the European Society for Therapeutic Radiology and Oncology
影响因子：
--
作者：
Coroller TP;Agrawal V;Narayan V;Hou Y;Grossmann P;Lee SW;Mak RH;Aerts HJ
通讯作者：
Aerts HJ
DOI：
10.1111/j.2517-6161.1995.tb02031.x
发表时间：
1995-01-01
影响因子：
5.8
作者：
BENJAMINI, Y;HOCHBERG, Y
通讯作者：
HOCHBERG, Y
影响因子：
2.4
作者：
Cistaro A;Quartuccio N;Mojtahedi A;Fania P;Filosso PL;Campenni A;Ficola U;Baldari S
通讯作者：
Baldari S
影响因子：
254.7
作者：
Amin, Mahul B.;Greene, Frederick L.;Winchester, David P.
通讯作者：
Winchester, David P.
DOI：
10.1097/jto.0000000000000302
发表时间：
2014-11
期刊：
Journal of thoracic oncology : official publication of the International Association for the Study of Lung Cancer
影响因子：
--
作者：
Burotto M;Thomas A;Subramaniam D;Giaccone G;Rajan A
通讯作者：
Rajan A