PENet-a scalable deep-learning model for automated diagnosis of pulmonary embolism using volumetric CT imaging
PENet-a scalable deep-learning model for automated diagnosis of pulmonary embolism using volumetric CT imaging
复制标题
DOI：
10.1038/s41746-020-0266-y
复制
发表时间：
2020-04-24
影响因子：
15.2
通讯作者：
Lungren, Matthew P.
中科院分区：
文献类型：
--
作者：
Huang, Shih-Cheng;Kothari, Tanay;Lungren, Matthew P.
肺栓塞（PE）是一种危及生命的临床问题，计算机断层扫描肺血管造影（CTPA）是诊断的金标准。及时诊断和立即治疗对于避免高发病率和死亡率至关重要，但 PE 仍然是最常被漏诊或延误的诊断之一。在本研究中，我们开发了一种深度学习模型 - PENet，用于在体积 CTPA 扫描上自动检测 PE，作为此目的的端到端解决方案。 PENet 是一个 77 层 3D 卷积神经网络 (CNN)，在 Kinetics-600 数据集上进行预训练，并在从单个学术机构收集的回顾性 CTPA 数据集上进行微调。 PENet 模型的性能在检测来自两个不同机构的数据的 PE 时进行了评估：一个作为来自同一机构的训练数据的保留数据集，另一个从外部机构收集，用于评估模型对不相关人口数据集的泛化能力。 PENet 在内部测试集上检测 PE 时取得了 0.84 [0.82-0.87] 的 AUROC，在外部数据集上取得了 0.85 [0.81-0.88] 的 AUROC。 PENet 的性能也优于当前最先进的 3D CNN 模型。结果代表了端到端 3D CNN 模型在 PE 诊断复杂任务中的成功应用，无需计算密集且耗时的预处理，并展示了来自外部机构的数据的持续性能。我们的模型可以用作分类工具，自动识别临床上重要的 PE，从而确定诊断放射学解释的优先级，并通过更有效的诊断来改进护理途径。
Pulmonary embolism (PE) is a life-threatening clinical problem and computed tomography pulmonary angiography (CTPA) is the gold standard for diagnosis. Prompt diagnosis and immediate treatment are critical to avoid high morbidity and mortality rates, yet PE remains among the diagnoses most frequently missed or delayed. In this study, we developed a deep learning model-PENet, to automatically detect PE on volumetric CTPA scans as an end-to-end solution for this purpose. The PENet is a 77-layer 3D convolutional neural network (CNN) pretrained on the Kinetics-600 dataset and fine-tuned on a retrospective CTPA dataset collected from a single academic institution. The PENet model performance was evaluated in detecting PE on data from two different institutions: one as a hold-out dataset from the same institution as the training data and a second collected from an external institution to evaluate model generalizability to an unrelated population dataset. PENet achieved an AUROC of 0.84 [0.82-0.87] on detecting PE on the hold out internal test set and 0.85 [0.81-0.88] on external dataset. PENet also outperformed current state-of-the-art 3D CNN models. The results represent successful application of an end-to-end 3D CNN model for the complex task of PE diagnosis without requiring computationally intensive and time consuming preprocessing and demonstrates sustained performance on data from an external institution. Our model could be applied as a triage tool to automatically identify clinically important PEs allowing for prioritization for diagnostic radiology interpretation and improved care pathways via more efficient diagnosis.