articleTop 1% cited

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

IEEE Transactions on Biomedical Engineering · 2016 · Vol. 64(7) · pp. 1558–1567

Qi Dou✉(Chinese University of Hong Kong)Hao Chen(Chinese University of Hong Kong)Lequan Yu(Chinese University of Hong Kong)Jing Qin(Hong Kong Polytechnic University)Pheng‐Ann Heng(Chinese University of Hong Kong)

View via DOI Publisher page

Abstract

While our method is tailored for pulmonary nodule detection, the proposed framework is general and can be easily extended to many other 3-D object detection tasks from volumetric medical images, where the targeting objects have large variations and are accompanied by a number of hard mimics.

Lung Cancer Diagnosis and Treatment COVID-19 diagnosis using AI Radiomics and Machine Learning in Medical ImagingComputer sciencePattern recognition (psychology)Artificial intelligenceReduction (mathematics)Convolutional neural networkNodule (geology)ENCODEMedical imagingMathematicsBiology

MeSH terms

Machine LearningAlgorithmsSolitary Pulmonary NoduleDiagnostic ErrorsFalse Positive ReactionsHumansPattern Recognition, AutomatedRadiographic Image Interpretation, Computer-AssistedSensitivity and SpecificityTomography, X-Ray ComputedReproducibility of ResultsNeural Networks, ComputerImaging, Three-Dimensional