A quantitative analysis of imaging features in lung CT images using the RW-T hybrid segmentation model

Lung cancer is the leading cause of cancer death worldwide. A lung nodule is the most common symptom of lung cancer. The analysis of lung cancer relies heavily on the segmentation of nodules, which aids in optimal treatment planning. However, because there are several lung nodules, accurate segmentation remains challenging. We propose an RW-T hybrid approach capable of segmenting all types of nodules, primarily externally attached nodules (juxta-pleural and juxta-vascular), and estimate the effect of nodule segmentation techniques to assess the quantitative Computer Tomography (CT) imaging features in lung adenocarcinoma. On 301 lung CT images from 40 patients with lung adenocarcinoma cases from the LungCT- Diagnosis dataset publicly available in The Cancer Imaging Archive, we used a random-walk strategy and a thresholding method to implement nodule segmentation (TCIA). We extracted two quantitative CT features from the segmented nodule using morphological techniques: convexity and entropy scores. The proposed method's resultant segmented nodules are compared to the single-click ensemble segmentation method and validated using ground-truth segmented nodules. Our proposed segmentation approach had a high level of agreement with ground truth delineations, with a dice-similarity coefficient of 0.7884, compared to single-click ensemble segmentation, with a dice-similarity metric of 0.6407.