Automatic classification of solitary pulmonary nodules in PET/CT imaging employing transfer learning techniques,Medical & Biological Engineering & Computing

当前位置： X-MOL 学术 › Med. Biol. Eng. Comput. › 论文详情

Our official English website, www.x-mol.net, welcomes your feedback! (Note: you will need to create a separate account there.)

Automatic classification of solitary pulmonary nodules in PET/CT imaging employing transfer learning techniques
Medical & Biological Engineering & Computing ( IF 2.6 ) Pub Date : 2021-05-18 , DOI: 10.1007/s11517-021-02378-y
Ioannis D Apostolopoulos ₁ , Emmanuel G Pintelas ₂ , Ioannis E Livieris ₂ , Dimitris J Apostolopoulos ₃ , Nikolaos D Papathanasiou ₃ , Panagiotis E Pintelas ₂ , George S Panayiotakis ₁

Affiliation

Early and automatic diagnosis of Solitary Pulmonary Nodules (SPN) in Computed Tomography (CT) chest scans can provide early treatment for patients with lung cancer, as well as doctor liberation from time-consuming procedures. The purpose of this study is the automatic and reliable characterization of SPNs in CT scans extracted from Positron Emission Tomography and Computer Tomography (PET/CT) system. To achieve the aforementioned task, Deep Learning with Convolutional Neural Networks (CNN) is applied. The strategy of training specific CNN architectures from scratch and the strategy of transfer learning, by utilizing state-of-the-art pre-trained CNNs, are compared and evaluated. To enhance the training sets, data augmentation is performed. The publicly available database of CT scans, named as Lung Image Database Consortium and Image Database Resource Initiative (LIDC-IDRI), is also utilized to further expand the training set and is added to the PET/CT dataset. The results highlight the effectiveness of transfer learning and data augmentation for the classification task of small datasets. The best accuracy obtained on the PET/CT dataset reached 94%, utilizing a modification proposal of a state-of-the-art CNN, called VGG16, and enhancing the training set with LIDC-IDRI dataset. Besides, the proposed modification outperforms in terms of sensitivity several similar researches, which exploit the benefits of transfer learning.

Graphical abstract

Overview of the experiment setup. The two datasets containing nodule representations are combined to evaluate the effectiveness of transfer learning over the traditional approach of training Convolutional Neural Networks from scratch.

中文翻译：

PET/CT 成像中孤立性肺结节的自动分类采用转移学习技术

计算机断层扫描 (CT) 胸部扫描中孤立性肺结节 (SPN) 的早期自动诊断可以为肺癌患者提供早期治疗，并使医生从耗时的程序中解放出来。本研究的目的是在从正电子发射断层扫描和计算机断层扫描 (PET/CT) 系统中提取的 CT 扫描中自动和可靠地表征 SPN。为了完成上述任务，应用了卷积神经网络 (CNN) 的深度学习。通过利用最先进的预训练 CNN 从头开始训练特定 CNN 架构的策略和迁移学习策略进行了比较和评估。为了增强训练集，执行数据增强。公开的 CT 扫描数据库，命名为肺影像数据库联盟和影像数据库资源倡议 (LIDC-IDRI)，也用于进一步扩展训练集并添加到 PET/CT 数据集。结果突出了迁移学习和数据增强对小数据集分类任务的有效性。在 PET/CT 数据集上获得的最佳准确率达到了 94%，利用了最先进的 CNN 的修改建议，称为 VGG16，并使用 LIDC-IDRI 数据集增强了训练集。此外，所提出的修改在敏感性方面优于几个类似的研究，这些研究利用了迁移学习的好处。结果突出了迁移学习和数据增强对小数据集分类任务的有效性。在 PET/CT 数据集上获得的最佳准确率达到了 94%，利用了最先进的 CNN 的修改建议，称为 VGG16，并使用 LIDC-IDRI 数据集增强了训练集。此外，所提出的修改在敏感性方面优于几个类似的研究，这些研究利用了迁移学习的好处。结果突出了迁移学习和数据增强对小数据集分类任务的有效性。在 PET/CT 数据集上获得的最佳准确率达到了 94%，利用了最先进的 CNN 的修改建议，称为 VGG16，并使用 LIDC-IDRI 数据集增强了训练集。此外，所提出的修改在敏感性方面优于几个类似的研究，这些研究利用了迁移学习的好处。