Improving clinical disease subtyping and future events prediction through a chest CT-based deep learning approach.
Improving clinical disease subtyping and future events prediction through a chest CT-based deep learning approach.
复制标题
通过基于胸部CT的深度学习方法来改善临床疾病的亚型和未来事件的预测。
DOI：
10.1002/mp.14673
复制
发表时间：
2021-03
期刊：
影响因子：
3.8
通讯作者：
Batmanghelich K
中科院分区：
文献类型：
--
作者：
Singla S;Gong M;Riley C;Sciurba F;Batmanghelich K
开发和评估深度学习（DL）方法，以从慢性阻塞性肺疾病（COPD）患者的高分辨率计算机断层扫描（HRCT）中提取丰富的信息。我们开发了一个基于DL的模型来学习受试者的紧凑表示，这可以预测COPD的生理严重程度和其他结果。我们的DL模型学习到：（a）从HRCT中提取信息丰富的区域图像特征;（B）自适应地对这些特征进行加权并形成聚集的患者表示;以及最后，（c）预测若干COPD结果。自适应权重对应于区域肺对疾病的贡献。我们对来自COPDGene队列的10300名参与者进行了模型评估。我们的模型对肺功能测定阻塞有很强的预测性（= 0.67），并且正确地将65.4%的受试者分组，89.1%的受试者在其GOLD严重程度阶段的一个阶段内分组。我们的模型在基于小叶中心（5级）和隔旁（3级）肺气肿严重程度评分对人群进行分层时，准确率分别为41.7%和52.8%。为了预测未来的急性加重，将来自我们的模型的受试者的陈述与他们过去的急性加重历史相结合，实现了80.8%的准确性（ROC曲线下面积为0.73）。对于全因死亡率，在考克斯回归分析中，我们优于BODE指数，提高了一致性指标（我们的：0.61 vs BODE：0.56）。我们的模型独立预测肺功能障碍，肺气肿的严重程度，恶化的风险，和死亡率单独从CT成像。该方法在研究和临床实践中具有潜在的适用性。
To develop and evaluate a deep learning (DL) approach to extract rich information from high‐resolution computed tomography (HRCT) of patients with chronic obstructive pulmonary disease (COPD). We develop a DL‐based model to learn a compact representation of a subject, which is predictive of COPD physiologic severity and other outcomes. Our DL model learned: (a) to extract informative regional image features from HRCT; (b) to adaptively weight these features and form an aggregate patient representation; and finally, (c) to predict several COPD outcomes. The adaptive weights correspond to the regional lung contribution to the disease. We evaluate the model on 10 300 participants from the COPDGene cohort. Our model was strongly predictive of spirometric obstruction ( = 0.67) and grouped 65.4% of subjects correctly and 89.1% within one stage of their GOLD severity stage. Our model achieved an accuracy of 41.7% and 52.8% in stratifying the population‐based on centrilobular (5‐grade) and paraseptal (3‐grade) emphysema severity score, respectively. For predicting future exacerbation, combining subjects’ representations from our model with their past exacerbation histories achieved an accuracy of 80.8% (area under the ROC curve of 0.73). For all‐cause mortality, in Cox regression analysis, we outperformed the BODE index improving the concordance metric (ours: 0.61 vs BODE: 0.56). Our model independently predicted spirometric obstruction, emphysema severity, exacerbation risk, and mortality from CT imaging alone. This method has potential applicability in both research and clinical practice.
登录
查看更多内容
影响因子：
--
作者：
Cielen N;Maes K;Gayan-Ramirez G
通讯作者：
Gayan-Ramirez G
影响因子：
0.6
作者：
Bhalla, Ashu Seith;Das, Abanti;Goyal, Ankur
通讯作者：
Goyal, Ankur
DOI：
10.1164/rccm.201402-0256pp
发表时间：
2014-07-15
影响因子：
24.7
作者：
Coxson, Harvey O.;Leipsic, Jonathon;Sin, Don D.
通讯作者：
Sin, Don D.
影响因子：
5.8
作者：
Ash, Samuel Y.;Harmouche, Rola;Washko, George R.
通讯作者：
Washko, George R.
DOI：
10.1164/rccm.201705-0860oc
发表时间：
2018-01-15
影响因子：
24.7
作者：
Gonzalez, German;Ash, Samuel Y.;Washko, George R.
通讯作者：
Washko, George R.