A Texture-Based Probabilistic Approach for Lung Nodule Segmentation

Producing consistent segmentations of lung nodules in CT scans is a persistent problem of image processing algorithms. Many hard-segmentation approaches are proposed in the literature, but soft segmentation of lung nodules remains largely unexplored. In this paper, we propose a classification-based approach based on pixel-level texture features that produces soft (probabilistic) segmentations. We tested this classifier on the publicly available Lung Image Database Consortium (LIDC) dataset. We further refined the classification results with a post-processing algorithm based on the variability index. The algorithm performed well on nodules not adjacent to the chest wall, producing a soft overlap between radiologists’ based segmentation and computer-based segmentation of 0.52. In the long term, these soft segmentations will be useful for representing the uncertainty in nodule boundaries that is manifest in radiological image segmentations.

• Type: Journal
• Year: 2011
• Where: ICIAR
• Authors: Olga Zinoveva, Dmitry Zinovev, Stephen A. Siena, Daniela Stan Raicu, Jacob D. Furst, Samuel G. Armato III
• Keywords: ICIAR 2011, Image Analysis, Image Processing Algorithms, Lung Nodules, Segmentation Approaches