Lung cancer classification and identification framework with automatic nodule segmentation screening using machine learning.

Lung cancer is often a fatal disease. To minimize patient mortality, the ability to identify the nodule malignancy stage from computed tomography (CT) lung scans is critical. Most existing methods rely exclusively on deep learning (DL) networks. However, duplicated structures and insufficient training data make DL-based malignancy diagnosis from CT images time-consuming and imprecise. Additionally, the features that DL networks use to make decisions cannot be recognized. In response to these challenges in previous work, we built an end-to-end conventional machine learning (ML) model called 'NoduleDiag' to classify cancerous CT images and their malignancy stage based on the nodule characteristics observable in CT images that radiologists typically prefer for diagnosis. We also prepared a fully automatic pulmonary nodule segmentation model for implementation during the final stage of diagnosis (after disease-stage identification) and added it to our classification framework as immense practical assistance to radiologists and medical personnel. To the best of our knowledge, this work will be the first all in one computer-assisted diagnosis (CAD) framework with lung cancer classification, automatic malignancy-stage identification and nodule segmentation screening together using conventional ML approaches. Our proposed model classifies nodule malignancy on a scale of 1–5. It achieves 99.65% accuracy, 99.64% sensitivity, 99.76% precision, 99.9% specificity, and 99.91% negative predictive value (NPV) with XGBoost. Our segmentation model uses DeepLabv3+ (weights initialized by ResNet-18), achieving a 99.86% global accuracy, mean boundary F1 (BF) score of 0.976, 0.715 mean IoU and 0.997 weighted IoU. [ABSTRACT FROM AUTHOR]