Risk Stratification of Lung Nodules Using 3D CNN-Based Multi-task Learning

Abstract

Risk stratification of lung nodules is a task of primary importance in lung cancer diagnosis. Any improvement in robust and accurate nodule characterization can assist in identifying cancer stage, prognosis, and improving treatment planning. In this study, we propose a 3D Convolutional Neural Network (CNN) based nodule characterization strategy. With a completely 3D approach, we utilize the volumetric information from a CT scan which would be otherwise lost in the conventional 2D CNN based approaches. In order to address the need for a large amount for training data for CNN, we resort to transfer learning to obtain highly discriminative features. Moreover, we also acquire the task dependent feature representation for six high-level nodule attributes and fuse this complementary information via a Multi-task learning (MTL) framework. Finally, we propose to incorporate potential disagreement among radiologists while scoring different nodule attributes in a graph regularized sparse multi-task learning. We evaluated our proposed approach on one of the largest publicly available lung nodule datasets comprising 1018 scans and obtained state-of-the-art results in regressing the malignancy scores.

Accepted for publication at Information Processing in Medical Imaging (IPMI) 2017

Cited by in corpus (15)

• A Survey on Incorporating Domain Knowledge into Deep Learning for Medical Image Analysis
• Lung and Pancreatic Tumor Characterization in the Deep Learning Era: Novel Supervised and Unsupervised Learning Approaches
• Diagnostic Classification Of Lung Nodules Using 3D Neural Networks
• Reinventing 2D Convolutions for 3D Images
• Gated-Dilated Networks for Lung Nodule Classification in CT scans
• Probabilistic Radiomics: Ambiguous Diagnosis with Controllable Shape Analysis
• A Biologically Interpretable Two-stage Deep Neural Network (BIT-DNN) For Vegetation Recognition From Hyperspectral Imagery
• Learning Tumor Growth via Follow-Up Volume Prediction for Lung Nodules
• Interpretable Medical Image Classification using Prototype Learning and Privileged Information
• DARWIN: A Highly Flexible Platform for Imaging Research in Radiology
• Hierarchical Classification of Pulmonary Lesions: A Large-Scale Radio-Pathomics Study
• Crowd disagreement about medical images is informative
• Plot2API: Recommending Graphic API from Plot via Semantic Parsing Guided Neural Network
• Multi-task Ensembles with Crowdsourced Features Improve Skin Lesion Diagnosis
• Primary Tumor Origin Classification of Lung Nodules in Spectral CT using Transfer Learning