Marginal radiomics features as imaging biomarkers for pathological invasion in lung adenocarcinoma

• Published in: European radiology Vol. 30; no. 5; pp. 2984 - 2994
• Main Authors: Cho, Hwan-ho, Lee, Geewon, Lee, Ho Yun, Park, Hyunjin
• Format: Journal Article
• Language: English
• Published: Berlin/Heidelberg Springer Berlin Heidelberg 01.05.2020; Springer Nature B.V
• Subjects: Adenocarcinoma; Adenocarcinoma in Situ - diagnostic imaging; Adenocarcinoma in Situ - pathology; Adenocarcinoma in Situ - surgery; Adenocarcinoma of Lung - diagnostic imaging; Adenocarcinoma of Lung - pathology; Adenocarcinoma of Lung - surgery; Adult; Aged; Aged, 80 and over; Area Under Curve; Artificial intelligence; Biomarkers; Classifiers; Computed tomography; Computer engineering; Diagnostic Radiology; Distribution functions; Female; Health sciences; Humans; Identification methods; Imaging; Imaging Informatics and Artificial Intelligence; Internal Medicine; Interventional Radiology; Invasiveness; Lung cancer; Lung Neoplasms - diagnostic imaging; Lung Neoplasms - pathology; Lung Neoplasms - surgery; Lungs; Male; Margins of Excision; Medical imaging; Medicine; Medicine & Public Health; Middle Aged; Neoplasm Invasiveness - diagnostic imaging; Neoplasm Invasiveness - pathology; Neuroradiology; Nodules; Radiology; Radiomics; Regularization; Retrospective Studies; Support Vector Machine; Support vector machines; Surgery; Thoracic surgery; Tomography, X-Ray Computed - methods; Training; Ultrasound; Lung adenocarcinoma; Tumor microenvironment; Quantitative evaluation; Classification; Machine learning
• ISSN: 0938-7994; 1432-1084; 1432-1084
• DOI: 10.1007/s00330-019-06581-2

Objectives Lung adenocarcinomas which manifest as ground-glass nodules (GGNs) have different degrees of pathological invasion and differentiating among them is critical for treatment. Our goal was to evaluate the addition of marginal features to a baseline radiomics model on computed tomography (CT) images to predict the degree of pathologic invasiveness. Methods We identified 236 patients from two cohorts (training, n = 189; validation, n = 47) who underwent surgery for GGNs. All GGNs were pathologically confirmed as adenocarcinoma in situ (AIS), minimally invasive adenocarcinoma (MIA), or invasive adenocarcinoma (IA). The regions of interest were semi-automatically annotated and 40 radiomics features were computed. We selected features using L1-norm regularization to build the baseline radiomics model. Additional marginal features were developed using the cumulative distribution function (CDF) of intratumoral intensities. An improved model was built combining the baseline model with CDF features. Three classifiers were tested for both models. Results The baseline radiomics model included five features and resulted in an average area under the curve (AUC) of 0.8419 (training) and 0.9142 (validation) for the three classifiers. The second model, with the additional marginal features, resulted in AUCs of 0.8560 (training) and 0.9581 (validation). All three classifiers performed better with the added features. The support vector machine showed the most performance improvement (AUC improvement = 0.0790) and the best performance was achieved by the logistic classifier (validation AUC = 0.9825). Conclusion Our novel marginal features, when combined with a baseline radiomics model, can help differentiate IA from AIS and MIA on preoperative CT scans. Key Points • Our novel marginal features could improve the existing radiomics model to predict the degree of pathologic invasiveness in lung adenocarcinoma.