Lung nodule segmentation via level set machine learning
Published in
arXiv.org(2019)External Links:
TL
TL;DR
This work introduces an extension of the vanilla level set image segmentation method where the velocity function is learned from data via machine learning regression methods, rather than manually designed, which mitigates the tedious design process of the velocity term from the standard method.
Abstract
Lung cancer has the highest mortality rate of all cancers in both men and women. The algorithmic detection, characterization, and diagnosis of abnormalities found in chest CT scan images can potentially aid radiologists by providing additional medical information to consider in their assessment. Lung nodule segmentation, i.e., the algorithmic delineation of the lung nodule surface, is a fundamental component of an automated nodule analysis pipeline. We introduce an extension of the vanilla level set image segmentation method where the velocity function is learned from data via machine learning regression methods, rather than manually designed. This mitigates the tedious design process of the velocity term from the standard method. We apply the method to image volumes of lung nodules from CT scans in the publicly available LIDC dataset, obtaining an average intersection over union score of 0.7185($\pm$0.1114).
References39 items
1
SciPy 1.0: fundamental algorithms for scientific computing in Python
2
Central focused convolutional neural networks: Developing a data-driven model for lung nodule segmentation
3
3-D Active Contour Segmentation Based on Sparse Linear Combination of Training Shapes (SCoTS)
4
Lung nodule malignancy classification using only radiologist-quantified image features as inputs to statistical learning algorithms: probing the Lung Image Database Consortium dataset with two statistical learning methods
5