Deep Residual 3D U-Net for Joint Segmentation and Texture Classification of Nodules in Lung

Abstract

In this work we present a method for lung nodules segmentation, their texture classification and subsequent follow-up recommendation from the CT image of lung. Our method consists of neural network model based on popular U-Net architecture family but modified for the joint nodule segmentation and its texture classification tasks and an ensemble-based model for the follow-up recommendation. This solution was evaluated within the LNDb medical imaging challenge and produced the best nodule segmentation result on the final leaderboard.

10 pages, 5 figures, 2 tables, accepted for publication at ICIAR 2020 (LNDb Grand Challenge)

References in corpus (6)

• Very Deep Convolutional Networks for Large-Scale Image Recognition
• Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift
• Generalised Dice overlap as a deep learning loss function for highly unbalanced segmentations
• Submanifold Sparse Convolutional Networks
• Superhuman Accuracy on the SNEMI3D Connectomics Challenge
• An Adaptive and Momental Bound Method for Stochastic Learning