Pure ground-glass nodules: are they really indolent?

Predicting Invasiveness of Lung Adenocarcinoma at Chest CT with Deep Learning Ternary Classification Models

Background Preoperative discrimination of preinvasive, minimally invasive, and invasive adenocarcinoma at CT informs clinical management decisions but may be challenging for classifying pure ground-glass nodules (pGGNs). Deep learning (DL) may improve ternary classification. Purpose To determine whether a strategy that includes an adjudication approach can enhance the performance of DL ternary classification models in predicting the invasiveness of adenocarcinoma at chest CT and maintain performance in classifying pGGNs. Materials and Methods In this retrospective study, six ternary models for classifying preinvasive, minimally invasive, and invasive adenocarcinoma were developed using a multicenter data set of lung nodules. The DL-based models were progressively modified through framework optimization, joint learning, and an adjudication strategy (simulating a multireader approach to resolving discordant nodule classifications), integrating two binary classification models with a ternary classification model to resolve discordant classifications sequentially. The six ternary models were then tested on an external data set of pGGNs imaged between December 2019 and January 2021. Diagnostic performance including accuracy, specificity, and sensitivity was assessed. The χ2 test was used to compare model performance in different subgroups stratified by clinical confounders. Results A total of 4929 nodules from 4483 patients (mean age, 50.1 years ± 9.5 [SD]; 2806 female) were divided into training (n = 3384), validation (n = 579), and internal (n = 966) test sets. A total of 361 pGGNs from 281 patients (mean age, 55.2 years ± 11.1 [SD]; 186 female) formed the external test set. The proposed strategy improved DL model performance in external testing (P < .001). For classifying minimally invasive adenocarcinoma, the accuracy was 85% and 79%, sensitivity was 75% and 63%, and specificity was 89% and 85% for the model with adjudication (model 6) and the model without (model 3), respectively. Model 6 showed a relatively narrow range (maximum minus minimum) across diagnostic indexes (accuracy, 1.7%; sensitivity, 7.3%; specificity, 0.9%) compared with the other models (accuracy, 0.6%-10.8%; sensitivity, 14%-39.1%; specificity, 5.5%-17.9%). Conclusion Combining framework optimization, joint learning, and an adjudication approach improved DL classification of adenocarcinoma invasiveness at chest CT. Published under a CC BY 4.0 license. Supplemental material is available for this article. See also the editorial by Sohn and Fields in this issue.

Arc concave sign on thin-section computed tomography：A novel predictor for invasive pulmonary adenocarcinoma in pure ground-glass nodules

OBJECTIVE

We aimed to investigate the risk factors of invasive pulmonary adenocarcinoma, especially to report and validate the use of our newly identified arc concave sign in predicting invasiveness of pure ground-glass nodules (pGGNs).

METHODS

From January 2015 to August 2018, we retrospectively enrolled 302 patients with 306 pGGNs ≤ 20 mm pathologically confirmed (141 preinvasive lesions and 165 invasive lesions). Arc concave sign was defined as smooth and sunken part of the edge of the lesion on thin-section computed tomography (TSCT). The degree of arc concave sign was expressed by the arc chord distance to chord length ratio (AC-R); deep arc concave sign was defined as AC-R larger than the optimal cut-off value. Logistic regression analysis was used to identify the independent risk factors of invasiveness.

RESULTS

Arc concave sign was observed in 65 of 306 pGGNs (21.2 %), and deep arc concave sign (AC-R > 0.25) were more common in invasive lesions (P = 0.008). Under microscope, interlobular septal displacements were found at tumour surface. Multivariate analysis indicated that irregular shape (OR, 3.558; CI: 1.374-9.214), presence of deep arc concave sign (OR, 3.336; CI: 1.013-10.986), the largest diameter > 10.1 mm (OR, 4.607; CI: 2.584-8.212) and maximum density > -502 HU (OR, 6.301; CI: 3.562-11.148) were significant independent risk factors of invasive lesions.

CONCLUSIONS

Arc concave sign on TSCT is caused by interlobular septal displacement. The degree of arc concave sign can reflect the invasiveness of pGGNs. Invasive lesions can be effectively distinguished from preinvasive lesions by the presence of deep arc concave sign, irregular shape, the largest diameter > 10.1 mm and maximum density > -502 HU in pGGNs ≤ 20 mm.