A Coarse-to-fine Morphological Approach With Knowledge-based Rules and Self-adapting Correction for Lung Nodules Segmentation

TL;DR

This paper introduces a novel coarse-to-fine morphological segmentation method with knowledge-based rules and self-adapting correction, achieving high accuracy in lung nodule segmentation across various nodule types and sizes.

Contribution

It presents a new morphological segmentation approach that combines dataset features, knowledge-based principles, and self-adapting correction to improve accuracy and generality in lung nodule segmentation.

Findings

Achieves state-of-the-art DSC scores on public and private datasets.

Independent of nodule type or size, demonstrating broad applicability.

Close to deep learning models' performance with traditional morphological methods.

Abstract

The segmentation module which precisely outlines the nodules is a crucial step in a computer-aided diagnosis(CAD) system. The most challenging part of such a module is how to achieve high accuracy of the segmentation, especially for the juxtapleural, non-solid and small nodules. In this research, we present a coarse-to-fine methodology that greatly improves the thresholding method performance with a novel self-adapting correction algorithm and effectively removes noisy pixels with well-defined knowledge-based principles. Compared with recent strong morphological baselines, our algorithm, by combining dataset features, achieves state-of-the-art performance on both the public LIDC-IDRI dataset (DSC 0.699) and our private LC015 dataset (DSC 0.760) which closely approaches the SOTA deep learning-based models' performances. Furthermore, unlike most available morphological methods that can only segment the isolated and well-circumscribed nodules accurately, the precision of our method is totally independent of the nodule type or diameter, proving its applicability and generality.