Use of CT radiomics to differentiate minimally invasive adenocarcinomas and invasive adenocarcinomas presenting as pure ground-glass nodules larger than 10 mm

Abstract

This study aimed to develop a model based on radiomics features extracted from computed tomography (CT) images to effectively differentiate between minimally invasive adenocarcinomas (MIAs) and invasive adenocarcinomas (IAs) manifesting as pure ground-glass nodules (pGGNs) larger than 10 mm. Method: This retrospective study included patients who underwent surgical resection for persistent pGGN between November 2012 and June 2018 and diagnosed with MIAs or IAs. The patients were randomly assigned to the training and test cohorts. The correlation coefficient method and the least absolute shrinkage and selection operator (LASSO) method were applied to select radiomics features useful for constructing a model whose performance was assessed by the area under the receiver operating characteristic curve (AUC-ROC). The radiomics model was compared to a standard CT model (shape, volume and mean CT value of the largest crosssection) and the combined radiomics-standard CT model using univariate and multivariate logistic regression analysis.Results: The radiomics model showed better discriminative ability (training AUC, 0.879; test AUC, 0.877) than the standard CT model (training AUC, 0.820; test AUC, 0.828). The combined model (training AUC, 0.879; test AUC, 0.870) did not demonstrate improved performance compared with the radiomics model. Radiomics_score was an independent predictor of invasiveness following multivariate logistic analysis. Conclusions: For pGGNs larger than 10 mm, the radiomics model demonstrated superior diagnostic performance in differentiating between IAs and MIAs, which may be useful to clinicians for diagnosis and treatment selection.

Consecutive Serial Non-Contrast CT Scan-Based Deep Learning Model Facilitates the Prediction of Tumor Invasiveness of Ground-Glass Nodules

“…Previous studies have reported that the size of GGNs is a critical risk factor for potential invasiveness (3)(4)(5)21). Lee et al found that the optimal cutoff size for preinvasive lesions was less than 10 mm (sensitivity, 53.33%; specificity, 100%) in a pure GGN cohort; this could be used as a selection criterion to identify patients suitable for sublobar resection (25).…”

“…Most previous CT-based quantitative studies have used single screening images to estimate the invasiveness of GGNs on the basis of size, density, and mass volume (4,5). However, there are known limitations to this approach owing to inter-and intraobserver variability in morphological features of GGNs.…”

Development and Validation of a Radiomics Nomogram for Differentiating Pulmonary Cryptococcosis and Lung Adenocarcinoma in Solitary Pulmonary Solid Nodule

“…When the value of l was 0.0118, and log(l) = −1.9293, an optimal subset with 24 non-zero features was yielded. Radiomics converts traditional medical images, applying advanced computational methodologies, into exploitable data information that cannot be captured by the naked eye and carries out high-throughput quantitative analysis on them (26)(27)(28)(29)(30)(31). To our knowledge, this is the first study to classify PC and LAC manifesting a solitary pulmonary solid nodule based on advanced radiomics technology.…”

Structured Reporting of Lung Cancer Staging: A Consensus Proposal

“…However, it is necessary to point out that all SR sections are independent from each other, so that the Patient Clinical Data and Clinical Evaluation sections are optional and may be filled in or not upon user choice, although they were conceived with the aim of creating databases. In fact, the possibility of collecting all these data could allow the creation of a large database, not only for epidemiological studies, but also in the highest conception of radiology, to lay the foundations for radiomics studies [34][35][36][37]. Radiology reports should be rich in data that could potentially be pooled, analyzed and correlated with patient outcomes, thereby assisting future clinical and imaging guidelines.…”