Visual discrimination of screen-detected persistent from transient subsolid nodules: An observer study

Construction and validation of a predictive model of invasive adenocarcinoma in pure ground-glass nodules less than 2 cm in diameter

OBJECTIVES

In this study, we aimed to develop a multiparameter prediction model to improve the diagnostic accuracy of invasive adenocarcinoma in pulmonary pure glass nodules.

METHOD

We included patients with pulmonary pure glass nodules who underwent lung resection and had a clear pathology between January 2020 and January 2022 at the Qilu Hospital of Shandong University. We collected data on the clinical characteristics of the patients as well as their preoperative biomarker results and computed tomography features. Thereafter, we performed univariate and multivariate logistic regression analyses to identify independent risk factors, which were then used to develop a prediction model and nomogram. We then evaluated the recognition ability of the model via receiver operating characteristic (ROC) curve analysis and assessed its calibration ability using the Hosmer-Lemeshow test and calibration curves. Further, to assess the clinical utility of the nomogram, we performed decision curve analysis.

RESULT

We included 563 patients, comprising 174 and 389 cases of invasive and non-invasive adenocarcinoma, respectively, and identified seven independent risk factors, namely, maximum tumor diameter, age, serum amyloid level, pleural effusion sign, bronchial sign, tumor location, and lobulation. The area under the ROC curve was 0.839 (95% CI: 0.798-0.879) for the training cohort and 0.782 (95% CI: 0.706-0.858) for the validation cohort, indicating a relatively high predictive accuracy for the nomogram. Calibration curves for the prediction model also showed good calibration for both cohorts, and decision curve analysis showed that the clinical prediction model has clinical utility.

CONCLUSION

The novel nomogram thus constructed for identifying invasive adenocarcinoma in patients with isolated pulmonary pure glass nodules exhibited excellent discriminatory power, calibration capacity, and clinical utility.

Software-based quantitative CT analysis to predict the growth trend of persistent nonsolid pulmonary nodules: a retrospective study

PURPOSE

Persistent nonsolid nodules (NSNs) usually exhibit an indolent course and may remain stable for several years; however, some NSNs grow quickly and require surgical excision. Therefore, identifying quantitative features capable of early discrimination between growing and nongrowing NSNs is becoming a crucial aspect of radiological analysis. The main purpose of this study was to evaluate the performance of an open-source software (ImageJ) to predict the future growth of NSNs detected in a Caucasian (Italian) population.

MATERIAL AND METHODS

We retrospectively selected 60 NSNs with an axial diameter of 6-30 mm scanned with the same acquisition-reconstruction parameters and the same computed tomography (CT) scanner. Software-based analysis was performed on thin-section CT images using ImageJ. For each NSNs, several quantitative features were extracted from the baseline CT images. The relationships of NSN growth with quantitative CT features and other categorical variables were analyzed using univariate and multivariable logistic regression analyses.

RESULTS

In multivariable analysis, only the skewness and linear mass density (LMD) were significantly associated with NSN growth, and the skewness was the strongest predictor of growth. In receiver operating characteristic curve analyses, the optimal cutoff values of skewness and LMD were 0.90 and 19.16 mg/mm, respectively. The two predictive models that included the skewness, with or without LMD, exhibited an excellent power for predicting NSN growth.

CONCLUSION

According to our results, NSNs with a skewness value > 0.90, specifically those with a LMD > 19.16 mg/mm, should require closer follow-up due to their higher growth potential, and higher risk of becoming an active cancer.

Features for Predicting Absorbable Pulmonary Solid Nodules as Depicted on Thin-Section Computed Tomography

Purpose

To investigate the clinical and computed tomography (CT) characteristics of absorbable pulmonary solid nodules (PSNs) and to clarify CT features for distinguishing absorbable PSNs from malignant ones.

Materials and Methods

From January 2015 to February 2021, a total of 316 patients with 348 PSNs (171 absorbable and 177 size-matched malignant) were retrospectively enrolled. Their clinical and CT data were analyzed and compared to determine CT features for predicting absorbable PSNs.

Results

Between absorbable and malignant PSNs, there were significant differences in patients' age, lesions' locations, shapes, homogeneity, borders, distance from the pleura, vacuoles, air bronchograms, lobulation, spiculation, halo sign, multiple concomitant nodules and pleural indentation (each P < 0.05). Multivariate analysis revealed that the independent predictors of absorbable PSNs were the following: patient age ≤55 years (OR, 2.660; 95% CI, 1.432-4.942; P = 0.002), homogeneous density (OR, 2.487; 95% CI, 1.107-5.590; P = 0.027), ill-defined border (OR, 5.445; 95% CI, 1.661-17.846; P = 0.005), halo sign (OR, 3.135; 95% CI, 1.154-8.513; P = 0.025), multiple concomitant nodules (OR, 8.700; 95% CI, 4.401-17.197; P<0.001), and abutting pleura (OR, 3.759; 95% CI, 1.407-10.044; P = 0.008). The indicators for malignant PSNs were the following: lobulation (OR, 3.904; 95% CI, 1.956-7.791; P<0.001), spiculation (OR, 4.980; 95% CI, 2.202-11.266, P<0.001), and pleural indentation (OR, 4.514; 95% CI, 1.223-16.666; P = 0.024).

Conclusion

In patients younger than 55 years, PSNs with homogeneous density, ill-defined border, halo sign, multiple concomitant nodules, and abutting pleura should be highly suspected as absorbable ones.

CT-Detected Subsolid Nodules: A Predictor of Lung Cancer Development at Another Location?

The purpose of this case-cohort study was to investigate whether the frequency and computed tomography (CT) features of pulmonary nodules posed a risk for the future development of lung cancer (LC) at a different location. Patients scanned between 2004 and 2012 at two Dutch academic hospitals were cross-linked with the Dutch Cancer Registry. All patients who were diagnosed with LC by 2014 and a random selection of LC-free patients were considered. LC patients who were determined to be LC-free at the time of the scan and all LC-free patients with an adequate scan were included. The nodule count and types (solid, part-solid, ground-glass, and perifissural) were recorded per scan. Age, sex, and other CT measures were included to control for confounding factors. The cohort included 163 LC patients and 1178 LC-free patients. Cox regression revealed that the number of ground-glass nodules and part-solid nodules present were positively correlated to future LC risk. The area under the receiver operating curve of parsimonious models with and without nodule type information were 0.827 and 0.802, respectively. The presence of subsolid nodules in a clinical setting may be a risk factor for future LC development in another pulmonary location in a dose-dependent manner. Replication of the results in screening cohorts is required for maximum utility of these findings.

Discrimination between transient and persistent subsolid pulmonary nodules on baseline CT using deep transfer learning

OBJECTIVES

To develop and validate a deep learning model to discriminate transient from persistent subsolid nodules (SSNs) on baseline CT.

METHODS

A cohort of 1414 SSNs, consisting of 319 transient SSNs in 168 individuals and 1095 persistent SSNs in 816 individuals, were identified on chest CT. The cohort was assigned by examination date into a development set of 996 SSNs, a tuning set of 212 SSNs, and a validation set of 206 SSNs. Our model was built by transfer learning, which was transferred from a well-performed deep learning model for pulmonary nodule classification. The performance of the model was compared with that of two experienced radiologists. Each nodule was categorized by Lung CT Screening Reporting and Data System (Lung-RADS) to further evaluate the performance and the potential clinical benefit of the model. Two methods were employed to visualize the learned features.

RESULTS

Our model achieved an AUC of 0.926 on the validation set with an accuracy of 0.859, a sensitivity of 0.863, and a specificity of 0.858, and outperformed the radiologists. The model performed the best among Lung-RADS 2 nodules and maintained well performance among Lung-RADS 4 nodules. Feature visualization demonstrated the model's effectiveness in extracting features from images.

CONCLUSIONS

The transfer learning model presented good performance on the discrimination between transient and persistent SSNs. A reliable diagnosis on nodule persistence can be achieved at baseline CT; thus, an early diagnosis as well as better patient care is available.

KEY POINTS

• Deep learning can be used for the discrimination between transient and persistent subsolid nodules. • A transfer learning model can achieve good performance when it is transferred from a model with a similar task. • With the assistance of deep learning model, a reliable diagnosis on nodule persistence can be achieved at baseline CT, which can bring a better patient care strategy.

Two nomograms based on CT features to predict tumor invasiveness of pulmonary adenocarcinoma and growth in pure GGN: a retrospective analysis

PURPOSE

The aim of the study is to construct two nomograms for predicting the invasive extent of pulmonary adenocarcinoma and nodule growth in patients with pulmonary pure ground-glass nodules (pGGN).

METHOD

Consecutive patients with pGGNs (n = 172) were retrospectively studied at one institution, formed the development cohort in predicting IPAs' nomogram. A separate cohort of patients with pGGNs (n = 116) from another institution was used for validation. For the predicting growth nomogram, the primary cohort of patients with pGGNs (n = 80) was from the former institution. We developed the nomogram for predicting IPA using binary logistic regression model, and a Cox multivariable model for the growth nomogram. We assessed nomogram model performance by calibration and discrimination (C-index).

RESULTS

The variables selected in binary logistic regression model (lesion size and shape) had a significant effect on identifying IPA from preinvasive lesion. The C-index of the development and validation cohort were 0.819 (95% CI 0.753-0.874) and 0.811 (95% CI 0.728-0.878), respectively. The risk variables (lesion size, blood vessel types) were selected in the multivariable Cox model. The C-index was 0.880 in the development cohort.

CONCLUSION

Our nomograms are reliable prognostic methods that can predict the invasiveness of pulmonary adenocarcinomas and the growth of pure GGN in preoperative.

Tumor Atelectasis Gives Rise to a Solid Appearance in Pulmonary Adenocarcinomas on High-Resolution Computed Tomography

Introduction

Ground-glass opacities in a high-resolution computed tomography (HR-CT) scan correlate, if malignant, with adenocarcinoma in situ. The solid appearance in the HR-CT is often considered indicative of an invasive component. This study aims to compare the radiologic features revealed in the HR-CT and the histologic features of primary adenocarcinomas in resection specimens to find the presence of tumor atelectasis in ground-glass nodules (GGNs) and part-solid and solid nodules.

Methods

HR-CT imaging was evaluated, and lung nodules were classified as GGNs, part-solid nodules, and solid nodules, whereas adenocarcinomas were classified according to WHO classification. Lepidic growth pattern with collapse was considered if there was reduction of air in the histologic section with maintained pulmonary architecture (without signs of pleural or vascular invasion).

Results

Radiologic and histologic features were compared in 47 lesions of 41 patients. The number of GGN, part-solid, and solid nodules were two, eight, and 37, respectively. Lepidic growth pattern with collapse was observed in both GGN, seven of the eight part-solid (88%) and 24 of the 37 solid (65%) lesions. Remarkably, more than 50% of the adenocarcinomas with a solid appearance in HR-CT imaging had a preexisting pulmonary architecture with adenocarcinoma with a predominant lepidic growth pattern. In these cases, the solid component can be explained by tumor-related collapse in vivo (tumor atelectasis on radiologic examination).

Conclusions

Tumor atelectasis is a frequent finding in pulmonary adenocarcinomas and may beside a ground glass opacity also result in a solid appearance in HR-CT imaging. A solid appearance on HR-CT cannot be attributed to invasion alone, as has been the assumption until now.

Whole-Lesion Computed Tomography-Based Entropy Parameters for the Differentiation of Minimally Invasive and Invasive Adenocarcinomas Appearing as Pulmonary Subsolid Nodules

OBJECTIVE

The aim of this study was to investigate the differentiation of computed tomography (CT)-based entropy parameters between minimally invasive adenocarcinoma (MIA) and invasive adenocarcinoma (IAC) lesions appearing as pulmonary subsolid nodules (SSNs).

METHODS

This study was approved by the institutional review board in our hospital. From July 2015 to November 2018, 186 consecutive patients with solitary peripheral pulmonary SSNs that were pathologically confirmed as pulmonary adenocarcinomas (74 MIA and 112 IAC lesions) were included and subdivided into the training data set and the validation data set. Chest CT scans without contrast enhancement were performed in all patients preoperatively. The subjective CT features of the SSNs were reviewed and compared between the MIA and IAC groups. Each SSN was semisegmented with our in-house software, and entropy-related parameters were quantitatively extracted using another in-house software developed in the MATLAB platform. Logistic regression analysis and receiver operating characteristic analysis were performed to evaluate the diagnostic performances. Three diagnostic models including subjective model, entropy model, and combined model were built and analyzed using area under the curve (AUC) analysis.

RESULTS

There were 119 nonsolid nodules and 67 part-solid nodules. Significant differences were found in the subjective CT features among nodule type, lesion size, lobulated shape, and irregular margin between the MIA and IAC groups. Multivariate analysis revealed that part-solid type and lobulated shape were significant independent factors for IAC (P < 0.0001 and P < 0.0001, respectively). Three entropy parameters including Entropy-0.8, Entropy-2.0-32, and Entropy-2.0-64 were identified as independent risk factors for the differentiation of MIA and IAC lesions. The median entropy model value of the MIA group was 0.266 (range, 0.174-0.590), which was significantly lower than the IAC group with value 0.815 (range, 0.623-0.901) (P < 0.0001). Multivariate analysis revealed that the combined model had an excellent diagnostic performance with sensitivity of 88.2%, specificity of 73.0%, and accuracy of 82.1%. The AUC value of the combined model was significantly higher (AUC, 0.869) than that of the subjective model (AUC, 0.809) or the entropy model alone (AUC, 0.836) (P < 0.0001).

CONCLUSIONS

The CT-based entropy parameters could help assess the aggressiveness of pulmonary adenocarcinoma via quantitative analysis of intratumoral heterogeneity. The MIA can be differentiated from IAC accurately by using entropy-related parameters in peripheral pulmonary SSNs.