NoduleNet: Decoupled False Positive Reductionfor Pulmonary Nodule Detection and Segmentation
This work addresses the need for more efficient and accurate computer-aided analysis in medical imaging, specifically for lung cancer screening, though it is incremental as it builds on existing deep learning methods with multi-task training.
The paper tackled the problem of jointly performing pulmonary nodule detection, false positive reduction, and segmentation in chest CT images by proposing NoduleNet, a multi-task 3D deep convolutional neural network, which improved nodule detection accuracy by 10.27% compared to a baseline model.
Pulmonary nodule detection, false positive reduction and segmentation represent three of the most common tasks in the computeraided analysis of chest CT images. Methods have been proposed for eachtask with deep learning based methods heavily favored recently. However training deep learning models to solve each task separately may be sub-optimal - resource intensive and without the benefit of feature sharing. Here, we propose a new end-to-end 3D deep convolutional neural net (DCNN), called NoduleNet, to solve nodule detection, false positive reduction and nodule segmentation jointly in a multi-task fashion. To avoid friction between different tasks and encourage feature diversification, we incorporate two major design tricks: 1) decoupled feature maps for nodule detection and false positive reduction, and 2) a segmentation refinement subnet for increasing the precision of nodule segmentation. Extensive experiments on the large-scale LIDC dataset demonstrate that the multi-task training is highly beneficial, improving the nodule detection accuracy by 10.27%, compared to the baseline model trained to only solve the nodule detection task. We also carry out systematic ablation studies to highlight contributions from each of the added components. Code is available at https://github.com/uci-cbcl/NoduleNet.