DeepLung: 3D Deep Convolutional Nets for Automated Pulmonary Nodule Detection and Classification
This work addresses lung cancer diagnosis for medical imaging, offering an automated tool that could assist radiologists, though it is incremental as it builds on existing 3D network architectures.
The authors tackled automated lung cancer diagnosis from CT scans by developing DeepLung, a system that uses 3D deep convolutional networks for nodule detection and classification, achieving performance comparable to experienced doctors on the LIDC-IDRI dataset.
In this work, we present a fully automated lung CT cancer diagnosis system, DeepLung. DeepLung contains two parts, nodule detection and classification. Considering the 3D nature of lung CT data, two 3D networks are designed for the nodule detection and classification respectively. Specifically, a 3D Faster R-CNN is designed for nodule detection with a U-net-like encoder-decoder structure to effectively learn nodule features. For nodule classification, gradient boosting machine (GBM) with 3D dual path network (DPN) features is proposed. The nodule classification subnetwork is validated on a public dataset from LIDC-IDRI, on which it achieves better performance than state-of-the-art approaches, and surpasses the average performance of four experienced doctors. For the DeepLung system, candidate nodules are detected first by the nodule detection subnetwork, and nodule diagnosis is conducted by the classification subnetwork. Extensive experimental results demonstrate the DeepLung is comparable to the experienced doctors both for the nodule-level and patient-level diagnosis on the LIDC-IDRI dataset.