基于 3D 卷积神经网络的高分辨率 CT 图像分析可以提高放射科医生对肺非实性结节分类的分类性能。

High-resolution CT image analysis based on 3D convolutional neural network can enhance the classification performance of radiologists in classifying pulmonary non-solid nodules.

机构信息

Department of Radiology, The First Affiliated Hospital of Nanjing Medical University, Nanjing, 210029, China.

Shanghai Key Laboratory of Magnetic Resonance, East China Normal University, Shanghai, 200062, China.

出版信息

Eur J Radiol. 2021 Aug;141:109810. doi: 10.1016/j.ejrad.2021.109810. Epub 2021 Jun 3.

DOI:10.1016/j.ejrad.2021.109810

PMID:34102564

Abstract

OBJECTIVE

To investigate whether 3D convolutional neural network (CNN) is able to enhance the classification performance of radiologists in classifying pulmonary non-solid nodules (NSNs).

MATERIALS AND METHODS

Data of patients with solitary NSNs and diagnosed as adenocarcinoma in situ (AIS), minimally invasive adenocarcinoma (MIA), or invasive adenocarcinoma (IAC) in pathological after surgical resection were analyzed retrospectively. Ultimately, 532 patients in our institution were included in the study: 427 cases (144 AIS, 167 MIA, 116 IAC) were assigned to training dataset and 105 cases (36 AIS, 41 MIA and 28 IAC) were assigned to validation dataset. For external validation, 177 patients (60 AIS, 69 MIA and 48 IAC) from another hospital were assigned to testing dataset. The clinical and morphological characteristics of NSNs were established as radiologists' model. The trained classification model based on 3D CNN was used to identify NSNs types automatically. The evaluation and comparison on classification performance of the two models and CNN + radiologists' model were performed via receiver operating curve (ROC) analysis and integrated discrimination improvement (IDI) index. The Akaike information criterion (AIC) was calculated to find the best-fit model.

RESULTS

In external testing dataset, radiologists' model showed inferior classification performance than CNN model both in discriminating AIS from MIA-IAC and AIS-MIA from IAC (the area under the ROC curve (Az value), 0.693 vs 0.820, P = 0.011; 0.746 vs 0.833, P = 0.026, respectively). However, combining CNN significantly enhanced the classification performance of radiologists and exhibited higher Az values than CNN model alone (Az values, 0.893 vs 0.820, P < 0.001; 0.906 vs 0.833, P < 0.001, respectively). The IDI index further confirmed CNN's contribution to radiologists in classifying NSNs (IDI = 25.8 % (18.3-46.1 %), P < 0.001; IDI = 30.1 % (26.1-45.2 %), P < 0.001, respectively). The CNN + radiologists' model also provided the best fit over radiologists' model and CNN model alone (AIC value 63.3 % vs. 29.5 %, 49.5 %, P < 0.001; 69.2 % vs. 34.9 %, 53.6 %, P < 0.001, respectively).

CONCLUSION

CNN successfully classified NSNs based on CT images and its classification performance were superior to radiologists' model. But the classification performance of radiologists can be significantly enhanced when combined with CNN in classifying NSNs.

摘要

目的

研究三维卷积神经网络（CNN）是否能提高放射科医生对肺非实性结节（NSN）分类的准确性。

材料与方法

回顾性分析我院经手术切除、病理诊断为原位腺癌（AIS）、微浸润腺癌（MIA）和浸润性腺癌（IAC）的单发 NSN 患者的临床资料。最终，我院共纳入 532 例患者（AIS 患者 144 例，MIA 患者 167 例，IAC 患者 116 例），将其作为训练集，105 例患者（AIS 患者 36 例，MIA 患者 41 例，IAC 患者 28 例）作为验证集。为了进行外部验证，我们从另一所医院选取了 177 例患者（AIS 患者 60 例，MIA 患者 69 例，IAC 患者 48 例）作为测试集。通过构建放射科医生的模型来确定 NSN 的临床和形态学特征，使用基于 3D CNN 的分类模型自动识别 NSN 类型。通过绘制受试者工作特征曲线（ROC）和计算综合判别改善（IDI）指数，对两种模型和 CNN+放射科医生模型的分类性能进行评估和比较。通过计算赤池信息量准则（AIC）来确定最佳模型。

结果

在外部测试集中，与放射科医生的模型相比，CNN 模型在区分 AIS 与 MIA-IAC 以及 AIS 与 IAC 方面的分类性能均较差（ROC 曲线下面积（Az 值），0.693 比 0.820，P=0.011；0.746 比 0.833，P=0.026）。然而，与放射科医生的模型相比，CNN 与放射科医生的组合模型能够显著提高分类性能，且具有更高的 Az 值（Az 值，0.893 比 0.820，P<0.001；0.906 比 0.833，P<0.001）。IDI 指数进一步证实了 CNN 对放射科医生在 NSN 分类中的贡献（IDI=25.8%（18.3-46.1%），P<0.001；IDI=30.1%（26.1-45.2%），P<0.001）。CNN+放射科医生的模型也优于放射科医生的模型和 CNN 模型（AIC 值，63.3%比 29.5%、49.5%，P<0.001；69.2%比 34.9%、53.6%，P<0.001）。