End-to-End Lung Nodule Detection Framework with Model-Based Feature Projection Block

This paper proposes novel end-to-end framework for detecting suspicious pulmonary nodules in chest CT scans. The method’s core idea is a new nodule segmentation architecture with model-based feature projection block on three-dimensional convolutions. acts as preliminary extractor two-dimensional U-Net-like convolutional network. Using the proposed approach along an axial, coronal, and sagittal analysis makes it possible to abandon widely used false positives reduction step. method achieves SOTA LUNA2016 0.959 average sensitivity, 0.936 sensitivity if false-positive level per scan 1/4. describes represents experimental results well ablation studies. code of model available at https://github.com/Botkin-AI/feature-projection-block.