Memory-Augmented Capsule Network for Adaptable Lung Nodule Classification
- 12 January 2021
- journal article
- research article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Medical Imaging
- Vol. 40 (10), 2869-2879
- https://doi.org/10.1109/tmi.2021.3051089
Abstract
Computer-aided diagnosis (CAD) systems must constantly cope with the perpetual changes in data distribution caused by different sensing technologies, imaging protocols, and patient populations. Adapting these systems to new domains often requires significant amounts of labeled data for re-training. This process is labor-intensive and time-consuming. We propose a memory-augmented capsule network for the rapid adaptation of CAD models to new domains. It consists of a capsule network that is meant to extract feature embeddings from some high-dimensional input, and a memory-augmented task network meant to exploit its stored knowledge from the target domains. Our network is able to efficiently adapt to unseen domains using only a few annotated samples. We evaluate our method using a large-scale public lung nodule dataset (LUNA), coupled with our own collected lung nodules and incidental lung nodules datasets. When trained on the LUNA dataset, our network requires only 30 additional samples from our collected lung nodule and incidental lung nodule datasets to achieve clinically relevant performance (0.925 and 0.891 area under receiving operating characteristic curves (AUROC), respectively). This result is equivalent to using two orders of magnitude less labeled training data while achieving the same performance. We further evaluate our method by introducing heavy noise, artifacts, and adversarial attacks. Under these severe conditions, our network’s AUROC remains above 0.7 while the performance of state-of-the-art approaches reduce to chance level.Funding Information
- National Science Foundation (1910973)
This publication has 39 references indexed in Scilit:
- Computer-aided detection system for lung cancer in computed tomography scans: Review and future prospectsBioMedical Engineering OnLine, 2014
- Reduced Lung-Cancer Mortality with Low-Dose Computed Tomographic ScreeningThe New England Journal of Medicine, 2011
- The Lung Image Database Consortium (LIDC) and Image Database Resource Initiative (IDRI): A Completed Reference Database of Lung Nodules on CT ScansMedical Physics, 2011
- The National Lung Screening Trial: Overview and Study DesignRadiology, 2011
- Adapting Visual Category Models to New DomainsLecture Notes in Computer Science, 2010
- Guidelines for Management of Small Pulmonary Nodules Detected on CT Scans: A Statement from the Fleischner SocietyRadiology, 2005
- Introduction to the Special Issue on Meta-LearningMachine Learning, 2004
- Pulmonary Nodules at Chest CT: Effect of Computer-aided Diagnosis on Radiologists’ Detection PerformanceRadiology, 2004
- Learning to Learn: Introduction and OverviewPublished by Springer Science and Business Media LLC ,1998
- Long Short-Term MemoryNeural Computation, 1997