A ℓ2, 1 norm regularized multi-kernel learning for false positive reduction in Lung nodule CAD

Lung cancer is one of the main public health issues in developed countries, and early detection of pulmonary nodules is an important clinical indication for early-stage lung cancer diagnosis [1]. Lung nodule refers to lung tissue abnormalities that are roughly spherical with round opacity and a diameter of up to 30 mm. Currently, nodules are mainly detected by one or multiple expert radiologists inspecting CT images of lungs. Recent research, however, shows that inter-reader variability in the detection of nodules by expert radiologists may exist.
Source: Computer Methods and Programs in Biomedicine - Category: Bioinformatics Authors: Source Type: research