3D-CNN with residual sub-blocks for automatic detection of lung nodules from temporal subtraction images.

Temporal subtraction (TS) technique is one of computer aided diagnosis (CAD) systems. A TS image is obtained by subtracting a previous image, which are warped to match between the structures of the previous image and one of a current image, from the current image. TS technique removes normal structures and enhances interval changes. However, many subtraction artifacts that can be detected as false positives still remain on a TS image. In this paper, we propose 3D-CNNs with residual sub-blocks based on 3D-VGG16-like architecture for detection of nodules accurately from TS images.