The "solid" component within subsolid nodules: imaging definition, display, and correlation with invasiveness of lung adenocarcinoma, a comparison of CT histograms and subjective evaluation

Differential diagnosis of benign and lung adenocarcinoma presenting as larger solid nodules and masses based on multiscale CT radiomics

PURPOSE

To develop a better radiomic model for the differential diagnosis of benign and lung adenocarcinoma lesions presenting as larger solid nodules and masses based on multiscale computed tomography (CT) radiomics.

MATERIALS AND METHODS

This retrospective study enrolled 205 patients with solid nodules and masses from Center 1 between January 2010 and February 2022 and Center 2 between January 2019 and February 2022. After applying the inclusion and exclusion criteria, we retrospectively enrolled 165 patients from two centers and assigned them to the training dataset (n = 115) or the test dataset (n = 50). Radiomics features were extracted from volumes of interest on CT images. A gradient boosting decision tree (GBDT) was used for data dimensionality reduction to perform the final feature selection. Four models were developed using clinical data, conventional imaging features and radiomics features, namely, the clinical and image model (CIM), the plain CT radiomics model (PRM), the enhanced CT radiomics model (ERM) and the combined model (CM). Model performance was evaluated to determine the best model for identifying benign and lung adenocarcinoma presenting as larger solid nodules and masses.

RESULTS

In the training dataset, the areas under the curve (AUCs) for the CIM, PRM, ERM, and CM were 0.718, 0.806, 0.819, and 0.917, respectively. The differential diagnostic capability of the ERM was better than that of the PRM and the CIM. The CM was optimal. Intermediate and junior radiologists and respiratory physicians achieved improved obviously diagnostic results with the radiomics model. The senior radiologists showed slight improved diagnostic results after using the radiomics model.

CONCLUSION

Radiomics may have the potential to be used as a noninvasive tool for the differential diagnosis of benign and lung adenocarcinoma lesions presenting as larger solid nodules and masses.

Comparative analysis of three-dimensional and two-dimensional models for predicting the malignancy probability of subsolid nodules

AIM

To construct three-dimensional (3D) and two-dimensional (2D) models to predict the malignancy probability of subsolid nodules (SSNs) and compare their effectiveness.

MATERIALS AND METHODS

A total of 371 SSNs from 332 patients, collected between January 2020 and January 2024, were included in the study. The SSNs were divided into a training set for constructing the models and a test set for validating the models. Models were developed using binary logistic backward regression, based on factors that showed significant differences in univariate analyses. The performance of the models was assessed using the area under the curve (AUC) of the receiver operating characteristic (ROC). The AUCs of different models were compared using the DeLong test.

RESULTS

The AUCs for the two 3D models, one 2D model, and the Brock model were 0.785 (0.733-0.836), 0.776 (0.723-0.829), 0.764 (0.710-0.818), and 0.738 (0.679-0.798) in the training set. In the test set, these AUCs were 0.817 (0.706-0.928), 0.796 (0.679-0.913), 0.771 (0.647-0.895), and 0.790 (0.678-0.903). The two 3D models demonstrated statistically significant differences from the Brock model in the training set (P=0.024 and P=0.046). None of the four models showed significant differences in the test set (all P>0.05).

CONCLUSION

The 3D models outperform both the 2D model and the Brock model in predicting the malignancy probability of SSNs, and the 3D model incorporating volume, mean CT attenuation value, and lobulation as factors performed the best.

The solid component within part-solid nodules: 3-dimensional quantification, correlation with the malignant grade of nonmucinous pulmonary adenocarcinomas, and comparisons with 2-dimentional measures and semantic features in low-dose computed tomography

BACKGROUND

There is no consensus on 3-dimensional (3D) quantification method for solid component within part-solid nodules (PSNs). This study aimed to find the optimal attenuation threshold for the 3D solid component proportion in low-dose computed tomography (LDCT), namely the consolidation/tumor ratio of volume (CTRV), basing on its correlation with the malignant grade of nonmucinous pulmonary adenocarcinomas (PAs) according to the 5th edition of World Health Organization classification. Then we tested the ability of CTRV to predict high-risk nonmucinous PAs in PSNs, and compare its performance with 2-dimensional (2D) measures and semantic features.

METHODS

A total of 313 consecutive patients with 326 PSNs, who underwent LDCT within one month before surgery and were pathologically diagnosed with nonmucinous PAs, were retrospectively enrolled and were divided into training and testing cohorts according to scanners. The CTRV were automatically generated by setting a series of attenuation thresholds from - 400 to 50 HU with an interval of 50 HU. The Spearman's correlation was used to evaluate the correlation between the malignant grade of nonmucinous PAs and semantic, 2D, and 3D features in the training cohort. The semantic, 2D, and 3D models to predict high-risk nonmucinous PAs were constructed using multivariable logistic regression and validated in the testing cohort. The diagnostic performance of these models was evaluated by the area under curve (AUC) of receiver operating characteristic curve.

RESULTS

The CTRV at attenuation threshold of -250 HU (CTRV_- 250HU) showed the highest correlation coefficient among all attenuation thresholds (r = 0.655, P < 0.001), which was significantly higher than semantic, 2D, and other 3D features (all P < 0.001). The AUCs of CTRV_- 250HU to predict high-risk nonmucinous PAs were 0.890 (0.843-0.927) in the training cohort and 0.832 (0.737-0.904) in the testing cohort, which outperformed 2D and semantic models (all P < 0.05).

CONCLUSIONS

The optimal attenuation threshold was - 250 HU for solid component volumetry in LDCT, and the derived CTRV_- 250HU might be valuable for the risk stratification and management of PSNs in lung cancer screening.

Tumour-pleura relationship on CT is a risk factor for occult lymph node metastasis in peripheral clinical stage IA solid adenocarcinoma

OBJECTIVES

To investigate whether the tumour-pleura relationship on computed tomography (CT) is a risk factor for occult lymph node metastasis (OLNM) in peripheral clinical stage IA solid adenocarcinoma.

METHODS

A total of 232 patients were included in the study. The tumour-pleura relationship was divided into four types: type 1, the tumour was unrelated to the pleura; type 2, the tumour was not in contact with the pleura, and one or more linear or striated pleural tags were visible; type 3, the tumour was not in contact with the pleura, and one or more linear or striated pleural tags with soft tissue component at the pleural end were visible; and type 4, the tumour was in contact with the pleura. Univariate and multivariate logistic regression analyses were used to identify the predictive factors, including the tumour-pleura relationship, clinical factors, conventional CT findings, and pathology-reported visceral pleural invasion, for OLNM.

RESULTS

Type 3 and 4 tumour-pleura relationships were more likely to have visceral pleural invasion than type 1 and 2 tumour-pleura relationships (p < 0.001). Univariate and multivariate logistic regression analyses revealed that the type 3 or 4 tumour-pleura relationship (OR: 3.261, p = 0.026), carcinoembryonic antigen level (OR: 3.361, p = 0.006), cytokeratin 19 fragments level (OR: 2.539, p = 0.025), and mediastinal window tumour size (OR: 1.078, p = 0.020) were predictive factors for OLNM.

CONCLUSIONS

The type 3 or 4 tumour-pleura relationship is correlated with a greater risk of OLNM in peripheral clinical stage IA solid adenocarcinoma.

KEY POINTS

• The tumour-pleura relationship on CT is a risk factor for occult lymph node metastasis in peripheral clinical stage IA solid adenocarcinoma. • Other risk factors for OLNM include CEA level, CYFRA level, and mediastinal window tumour size. • Pathology-reported visceral pleural invasion is not a risk factor for OLNM.

Diagnosis of Invasive Lung Adenocarcinoma Based on Chest CT Radiomic Features of Part-Solid Pulmonary Nodules: A Multicenter Study

Background Solid components of part-solid nodules (PSNs) at CT are reflective of invasive adenocarcinoma, but studies describing radiomic features of PSNs and the perinodular region are lacking. Purpose To develop and to validate radiomic signatures diagnosing invasive lung adenocarcinoma in PSNs compared with the Brock, clinical-semantic features, and volumetric models. Materials and Methods This retrospective multicenter study (https://ClinicalTrials.gov, NCT03872362) included 291 patients (median age, 60 years; interquartile range, 55-65 years; 191 women) from January 2013 to October 2017 with 297 PSN lung adenocarcinomas split into training (n = 229) and test (n = 68) data sets. Radiomic features were extracted from the different regions (gross tumor volume [GTV], solid, ground-glass, and perinodular). Random-forest models were trained using clinical-semantic, volumetric, and radiomic features, and an online nodule calculator was used to compute the Brock model. Performances of models were evaluated using standard metrics such as area under the curve (AUC), accuracy, and calibration. The integrated discrimination improvement was applied to assess model performance changes after the addition of perinodular features. Results The radiomics model based on ground-glass and solid features yielded an AUC of 0.98 (95% confidence interval [CI]: 0.96, 1.00) on the test data set, which was significantly higher than the Brock (AUC, 0.83 [95% CI: 0.72, 0.94]; P = .007), clinical-semantic (AUC, 0.90 [95% CI: 0.83, 0.98]; P = .03), volumetric GTV (AUC, 0.87 [95% CI: 0.78, 0.96]; P = .008), and radiomics GTV (AUC, 0.88 [95% CI: 0.80, 0.96]; P = .01) models. It also achieved the best accuracy (93% [95% CI: 84%, 98%]). Both this model and the model with added perinodular features showed good calibration, whereas adding perinodular features did not improve the performance (integrated discrimination improvement, -0.02; P = .56). Conclusion Separating ground-glass and solid CT radiomic features of part-solid nodules was useful in diagnosing the invasiveness of lung adenocarcinoma, yielding a better predictive performance than the Brock, clinical-semantic, volumetric, and radiomics gross tumor volume models. Online supplemental material is available for this article. See also the editorial by Nishino in this issue. Published under a CC BY 4.0 license.

Development and clinical application of deep learning model for lung nodules screening on CT images

Lung cancer screening based on low-dose CT (LDCT) has now been widely applied because of its effectiveness and ease of performance. Radiologists who evaluate a large LDCT screening images face enormous challenges, including mechanical repetition and boring work, the easy omission of small nodules, lack of consistent criteria, etc. It requires an efficient method for helping radiologists improve nodule detection accuracy with efficiency and cost-effectiveness. Many novel deep neural network-based systems have demonstrated the potential for use in the proposed technique to detect lung nodules. However, the effectiveness of clinical practice has not been fully recognized or proven. Therefore, the aim of this study to develop and assess a deep learning (DL) algorithm in identifying pulmonary nodules (PNs) on LDCT and investigate the prevalence of the PNs in China. Radiologists and algorithm performance were assessed using the FROC score, ROC-AUC, and average time consumption. Agreement between the reference standard and the DL algorithm in detecting positive nodules was assessed per-study by Bland-Altman analysis. The Lung Nodule Analysis (LUNA) public database was used as the external test. The prevalence of NCPNs was investigated as well as other detailed information regarding the number of pulmonary nodules, their location, and characteristics, as interpreted by two radiologists.

Solitary solid pulmonary nodules: a CT-based deep learning nomogram helps differentiate tuberculosis granulomas from lung adenocarcinomas

OBJECTIVES

To evaluate the differential diagnostic performance of a computed tomography (CT)-based deep learning nomogram (DLN) in identifying tuberculous granuloma (TBG) and lung adenocarcinoma (LAC) presenting as solitary solid pulmonary nodules (SSPNs).

METHODS

Routine CT images of 550 patients with SSPNs were retrospectively obtained from two centers. A convolutional neural network was used to extract deep learning features from all lesions. The training set consisted of data for 218 patients. The least absolute shrinkage and selection operator logistic regression was used to create a deep learning signature (DLS). Clinical factors and CT-based subjective findings were combined in a clinical model. An individualized DLN incorporating DLS, clinical factors, and CT-based subjective findings was constructed to validate the diagnostic ability. The performance of the DLN was assessed by discrimination and calibration using internal (n = 140) and external validation cohorts (n = 192).

RESULTS

DLS, gender, age, and lobulated shape were found to be independent predictors and were used to build the DLN. The combination showed better diagnostic accuracy than any single model evaluated using the net reclassification improvement method (p < 0.05). The areas under the curve in the training, internal validation, and external validation cohorts were 0.889 (95% confidence interval [CI], 0.839-0.927), 0.879 (95% CI, 0.813-0.928), and 0.809 (95% CI, 0.746-0.862), respectively. Decision curve analysis and stratification analysis showed that the DLN has potential generalization ability.

CONCLUSIONS

The CT-based DLN can preoperatively distinguish between LAC and TBG in patients presenting with SSPNs.

KEY POINTS

• The deep learning nomogram was developed to preoperatively differentiate TBG from LAC in patients with SSPNs. • The performance of the deep learning feature was superior to that of the radiomics feature. • The deep learning nomogram achieved superior performance compared to the deep learning signature, the radiomics signature, or the clinical model alone.

CT Characteristics for Predicting Invasiveness in Pulmonary Pure Ground-Glass Nodules

OBJECTIVE. The objective of our study was to investigate the differences in the CT features of atypical adenomatous hyperplasia (AAH), adenocarcinoma in situ (AIS), minimally invasive adenocarcinoma (MIA), and invasive adenocarcinoma (IA) manifesting as a pure ground-glass nodule (pGGN) with the aim of determining parameters predictive of invasiveness. MATERIALS AND METHODS. A total of 161 patients with 172 pGGNs (14 AAHs, 59 AISs, 68 MIAs, and 31 IAs) were retrospectively enrolled. The following CT features of each histopathologic subtype of nodule were analyzed and compared: lesion location, diameter, area, shape, attenuation, uniformity of density, margin, nodule-lung interface, and internal and surrounding changes. RESULTS. ROC curves revealed that nodule diameter and area (cutoff value, 10.5 mm and 86.5 mm²; sensitivity, 87.1% and 87.1%; specificity, 70.9% and 65.2%) were significantly larger in IAs than in AAHs, AISs, and MIAs (p < 0.001), whereas the latter three were similar in size (p > 0.050). CT attenuation higher than -632 HU in pGGNs indicated invasiveness (sensitivity, 78.8%; specificity, 59.8%). As opposed to noninvasive pGGNs (AAHs and AISs), invasive pGGNs (MIAs and IAs) usually had heterogeneous density, irregular shape, coarse margin, lobulation, spiculation, pleural indentation, and dilated or distorted vessels (each, p < 0.050). Multivariate analysis showed that mean CT attenuation and presence of lobulation were predictors for invasive pGGNs (p ≤ 0.001). CONCLUSION. The likelihood of invasiveness is greater in pGGNs with larger size (> 10.5 mm or > 86.5 mm²), higher attenuation (> -632 HU), heterogeneous density, irregular shape, coarse margin, spiculation, lobulation, pleural indentation, and dilated or distorted vessels.

A cross-modal 3D deep learning for accurate lymph node metastasis prediction in clinical stage T1 lung adenocarcinoma

OBJECTIVES

The evaluation of lymph node (LN) status by radiologists based on preoperative computed tomography (CT) lacks high precision for early lung cancer patients; erroneous evaluations result in inappropriate therapeutic plans and increase the risk of complications. This study aims to develop a cross-modal 3D neural network based on CT images and prior clinical knowledge for accurate prediction of LN metastasis in clinical stage T1 lung adenocarcinoma.

PATIENTS AND METHODS

Five hundred one lung adenocarcinoma patients with clinical stage T1 were enrolled. Data including: corresponding 3D nodule-centered patches of CT; prior clinical features; and pathological labels of LN status were obtained. We proposed a cross-modal deep learning system, which can successfully incorporate prior clinical knowledge and CT images into a 3D neural network to predict LN metastasis. We trained and validated our system with 401 cases and tested its performance with 100 cases. The result was compared with that of the logistic regression integration model, the single deep learning model without prior clinical knowledge integration, radiomics method, and manual evaluation by radiologists.

RESULTS

The model proposed DensePriNet achieved an AUC of 0.926, which is significantly higher than the logistic regression integration model (0.904) single deep learning model (0.880), and radiomics method (0.891). The Matthews Correlation Coefficient (MCC) of DensePriNet (0.705) was significantly higher than manual classification by one senior radiologist (0.534) and one junior radiologist (0.416), respectively.

CONCLUSION

The performance of the single deep learning method is significantly higher than the radiomics method and the radiologists, and integration of prior clinical knowledge into the deep learning model enhance the diagnostic precision of LN status and facilitate the application of precision medicine.