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

TL;DR

This paper introduces a modified 3D U-Net model for joint lung nodule segmentation and texture classification, achieving top results in a medical imaging challenge and supporting follow-up recommendations.

Contribution

It presents a novel neural network architecture for simultaneous nodule segmentation and texture classification, along with an ensemble model for follow-up prediction.

Findings

Achieved best nodule segmentation in LNDb challenge

Effective joint segmentation and texture classification

Ensemble model improved follow-up recommendations

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.