Multilevel Contextual 3-D CNNs for False Positive Reduction in Pulmonary Nodule Detection

By Qi-Yan Dou, Hao Chen, Lequan Yu, Jing Qin, P. Heng. IEEE Transactions on Biomedical Engineering, 2017

506 citations recorded by the source corpus.

Subfields: Computer Vision and Pattern Recognition, Pulmonary and Respiratory Medicine, Radiology, Nuclear Medicine and Imaging

View Paper: https://www.semanticscholar.org/paper/2c8f979c0dc3d9ee1e00570792ce2ce22382ce66

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Computer Vision and Pattern Recognition

In Pulmonary and Respiratory Medicine

In Radiology, Nuclear Medicine and Imaging

Citations in the corpus

Understanding Adversarial Attacks on Deep Learning Based Medical Image Analysis Systems (2019, background): “, 2016) or 3D CNN(Dou et al., 2017) to extract deep features to detect and classify nodules (Wang et al.”
DeepLesion: automated mining of large-scale lesion annotations and universal lesion detection with deep learning (2018, background): “7 – 9 Instead, they reflect the relative performance of different types and sizes.”
Deep multi-view learning methods: A review (2021, background): “[54] propose a contextual 3D CNNs by combing multi-level information for pulmonary nodule detection.”
Knowledge-based Collaborative Deep Learning for Benign-Malignant Lung Nodule Classification on Chest CT (2019, methodology): “Second, although it is straightforward to design 3D CNN for medical image analysis [31], [35], [36], extending the use of 2D CNN to the analysis of volumetric medical images on a slice-by-slice basis, together with data augmentation, enables us to have more training samples [29], [30], [37], [38].”
Automated Lung Nodule Detection and Classification Using Deep Learning Combined with Multiple Strategies (2019, background): “Therefore, the ﬁnal decision regarding early-stage lung cancer diagnosis should be performed by using multiple strategies, because approximately 60–80% of lung cancers are diagnosed at advance stages.”
Deep learning in medical imaging and radiation therapy. (2018, methodology): “Combined with various data augmentation methods, it is possible to generate sufficient number of samples to train 3D CNNs. Examples of using 3D patches can be found for the detection of pulmonary nodules in chest CT 169 and for the detection of lacunar strokes in brain MRI.”
Cancer Diagnosis Using Deep Learning: A Bibliographic Review (2019, methodology): “As observed in the research study by Dou et al., they formed a model with CNN, which dealt with 3D images directly instead of mapping them into a 2D model [56].”
Recent advances and clinical applications of deep learning in medical image analysis (2021, background): “In the radiology domain, the intrinsic 3D spatial context information among volumetric images (e.g. CT scans) has been utilized in many studies (Roth et al., 2016; Dou et al., 2017; Yan et al., 2018a; Liao et al., 2019).”
3D Deep Learning on Medical Images: A Review (2020, methodology): “[90] exploited 3D CNN with multilevel contextual information for the false-positive reduction in pulmonary nodules in volumetric CT scans.”