Predictors of Invasive Adenocarcinomas among Pure Ground-Glass Nodules Less Than 2 cm in Diameter

Discrimination of invasive lung adenocarcinoma from Lung-RADS category 2 nonsolid nodules through visual assessment: a retrospective study

OBJECTIVES

Invasive adenocarcinomas (IADs) have been identified among nonsolid nodules (NSNs) assigned as Lung Imaging Reporting and Data System (Lung-RADS) category 2. This study used visual assessment for differentiating IADs from noninvasive lesions (NILs) in this category.

METHODS

This retrospective study included 222 patients with 242 NSNs, which were resected after preoperative computed tomography (CT)-guided dye localization. Visual assessment was performed by using the lung and bone window (BW) settings to classify NSNs into BW-visible (BWV) and BW-invisible (BWI) NSNs. In addition, nodule size, shape, border, CT attenuation, and location were evaluated and correlated with histopathological results. Logistic regression was performed for multivariate analysis. A p value of < 0.05 was considered statistically significant.

RESULTS

A total of 242 NSNs (mean diameter, 7.6 ± 2.8 mm), including 166 (68.6%) BWV and 76 (31.4%) BWI NSNs, were included. IADs accounted for 31% (75) of the nodules. Only 4 (5.3%) IADs were identified in the BWI group and belonged to the lepidic-predominant (n = 3) and acinar-predominant (n = 1) subtypes. In univariate analysis for differentiating IADs from NILs, the nodule size, shape, CT attenuation, and visual classification exhibited statistical significance. Nodule size and visual classification were the significant predictors for IAD in multivariate analysis with logistic regression (p < 0.05). The sensitivity, specificity, positive predictive value, and negative predictive value of visual classification in IAD prediction were 94.7%, 43.1%, 42.8%, and 94.7%, respectively.

CONCLUSIONS

The window-based visual classification of NSNs is a simple and objective method to discriminate IADs from NILs.

CLINICAL RELEVANCE STATEMENT

The present study shows that using the bone window to classify nonsolid nodules helps discriminate invasive adenocarcinoma from noninvasive lesions.

KEY POINTS

• Evidence has shown the presence of lung adenocarcinoma in Lung-RADS category 2 nonsolid nodules. • Nonsolid nodules are classified into the bone window-visible and the bone window-invisible nonsolid nodules, and this classification differentiates invasive adenocarcinoma from noninvasive lesions. • The Lung-RADS category 2 nonsolid nodules are unlikely invasive adenocarcinoma if they show nonvisualization in the bone window.

Clinical Outcomes of Resected Pure Ground-Glass, Heterogeneous Ground-Glass, and Part-Solid Pulmonary Nodules

BACKGROUND. Increased (but not definitively solid) attenuation within pure ground-glass nodules (pGGNs) may indicate invasive adenocarcinoma and the need for resection rather than surveillance. OBJECTIVE. The purpose of this study was to compare the clinical outcomes among resected pGGNs, heterogeneous ground-glass nodules (GGNs), and part-solid nodules (PSNs). METHODS. This retrospective study included 469 patients (335 female patients and 134 male patients; median age, 68 years [IQR, 62.5-73.5 years]) who, between January 2012 and December 2020, underwent resection of lung adenocarcinoma that appeared as a subsolid nodule on CT. Two radiologists, using lung windows, independently classified each nodule as a pGGN, a heterogeneous GGN, or a PSN, resolving discrepancies through discussion. A heterogeneous GGN was defined as a GGN with internal increased attenuation not quite as dense as that of pulmonary vessels, and a PSN was defined as having an internal solid component with the same attenuation as that of the pulmonary vessels. Outcomes included pathologic diagnosis of invasive adenocarcinoma, 5-year recurrence rates (locoregional or distant), and recurrence-free survival (RFS) and overall survival (OS) over 7 years, as analyzed by Kaplan-Meier and Cox proportional hazards regression analyses, with censoring of patients with incomplete follow-up. RESULTS. Interobserver agreement for nodule type, expressed as a kappa coefficient, was 0.69. Using consensus assessments, 59 nodules were pGGNs, 109 were heterogeneous GGNs, and 301 were PSNs. The frequency of invasive adenocarcinoma was 39.0% in pGGNs, 67.9% in heterogeneous GGNs, and 75.7% in PSNs (for pGGNs vs heterogeneous GGNs, p < .001; for pGGNs vs PSNs, p < .001; and for heterogeneous GGNs vs PSNs, p = .28). The 5-year recurrence rate was 0.0% in patients with pGGNs, 6.3% in those with heterogeneous GGNs, and 10.8% in those with PSNs (for pGGNs vs heterogeneous GGNs, p = .06; for pGGNs vs PSNs, p = .02; and for heterogeneous GGNs vs PSNs, p = .18). At 7 years, RFS was 97.7% in patients with pGGNs, 82.0% in those with heterogeneous GGNs, and 79.4% in those with PSNs (for pGGNs vs heterogeneous GGNs, p = .02; for pGGNs vs PSNs, p = .006; and for heterogeneous GGNs vs PSNs, p = .40); OS was 98.0% in patients with pGGNs, 84.6% in those with heterogeneous GGNs, and 82.9% in those with PSNs (for pGGNs vs heterogeneous GGNs, p = .04; for pGGNs vs PSNs, p = .01; and for heterogeneous GGNs vs PSNs, p = .50). CONCLUSION. Resected pGGNs had excellent clinical outcomes. Heterogeneous GGNs had relatively worse outcomes, more closely resembling outcomes for PSNs. CLINICAL IMPACT. The findings support surveillance for truly homogeneous pGGNs versus resection for GGNs showing internal increased attenuation even if not having a true solid component.

Bubble-like lucency in pulmonary ground glass nodules on computed tomography: a specific pattern of air-containing space for diagnosing neoplastic lesions

PURPOSE

To investigate the computed tomography (CT) characteristics of air-containing space and its specific patterns in neoplastic and non-neoplastic ground glass nodules (GGNs) for clarifying their significance in differential diagnosis.

MATERIALS AND METHODS

From January 2015 to October 2022, 1328 patients with 1,350 neoplastic GGNs and 462 patients with 465 non-neoplastic GGNs were retrospectively enrolled. Their clinical and CT data were analyzed and compared with emphasis on revealing the differences of air-containing space and its specific patterns (air bronchogram and bubble-like lucency [BLL]) between neoplastic and non-neoplastic GGNs and their significance in differentiating them.

RESULTS

Compared with patients with non-neoplastic GGNs, female was more common (P < 0.001) and lesions were larger (P < 0.001) in those with neoplastic ones. Air bronchogram (30.1% vs. 17.2%), and BLL (13.0% vs. 2.6%) were all more frequent in neoplastic GGNs than in non-neoplastic ones (each P < 0.001), and the BLL had the highest specificity (93.6%) in differentiation. Among neoplastic GGNs, the BLL was more frequently detected in the larger (14.9 ± 6.0 mm vs. 11.4 ± 4.9 mm, P < 0.001) and part-solid (15.3% vs. 10.7%, P = 0.011) ones, and its incidence significantly increased along with the invasiveness (9.5-18.0%, P = 0.001), whereas no significant correlation was observed between the occurrence of BLL and lesion size, attenuation, or invasiveness.

CONCLUSION

The air containing space and its specific patterns are of great value in differentiating GGNs, while BLL is a more specific and independent sign of neoplasms.

The Role of Artificial Intelligence in Coronary Calcium Scoring in Standard Cardiac Computed Tomography and Chest Computed Tomography With Different Reconstruction Kernels

PURPOSE

To assess the correlation of coronary calcium score (CS) obtained by artificial intelligence (AI) with those obtained by electrocardiography gated standard cardiac computed tomography (CCT) and nongated chest computed tomography (ChCT) with different reconstruction kernels.

PATIENTS AND METHODS

Seventy-six patients received standard CCT and ChCT simultaneously. We compared CS obtained in 4 groups: CS CCT , by the traditional method from standard CCT, 25 cm field of view, 3 mm slice thickness, and kernel filter convolution 12 (FC12); CS AICCT , by AI from the standard CCT; CS ChCTsoft , by AI from the non-gated CCT, 40 cm field of view, 3 mm slice thickness, and a soft kernel FC02; and CS ChCTsharp , by AI from CCT image with same parameters for CS ChCTsoft except for using a sharp kernel FC56. Statistical analyses included Spearman rank correlation coefficient (ρ), intraclass correlation (ICC), Bland-Altman plots, and weighted kappa analysis (κ).

RESULTS

The CS AICCT was consistent with CS CCT (ρ = 0.994 and ICC of 1.00, P < 0.001) with excellent agreement with respect to cardiovascular (CV) risk categories of the Agatston score (κ = 1.000). The correlation between CS ChCTsoft and CS ChCTsharp was good (ρ = 0.912, 0.963 and ICC = 0.929, 0.948, respectively, P < 0.001) with a tendency of underestimation (Bland-Altman mean difference and 95% upper and lower limits of agreements were 329.1 [-798.9 to 1457] and 335.3 [-651.9 to 1322], respectively). The CV risk category agreement between CS ChCTsoft and CS ChCTsharp was moderate (κ = 0.556 and 0.537, respectively).

CONCLUSIONS

There was an excellent correlation between CS CCT and CS AICCT , with excellent agreement between CV risk categories. There was also a good correlation between CS CCT and CS obtained by ChCT albeit with a tendency for underestimation and moderate accuracy in terms of CV risk assessment.

Low-dose CT screening among never-smokers with or without a family history of lung cancer in Taiwan: a prospective cohort study

BACKGROUND

In Taiwan, lung cancers occur predominantly in never-smokers, of whom nearly 60% have stage IV disease at diagnosis. We aimed to assess the efficacy of low-dose CT (LDCT) screening among never-smokers, who had other risk factors for lung cancer.

METHODS

The Taiwan Lung Cancer Screening in Never-Smoker Trial (TALENT) was a nationwide, multicentre, prospective cohort study done at 17 tertiary medical centres in Taiwan. Eligible individuals had negative chest radiography, were aged 55-75 years, had never smoked or had smoked fewer than 10 pack-years and stopped smoking for more than 15 years (self-report), and had one of the following risk factors: a family history of lung cancer; passive smoke exposure; a history of pulmonary tuberculosis or chronic obstructive pulmonary disorders; a cooking index of 110 or higher; or cooking without using ventilation. Eligible participants underwent LDCT at baseline, then annually for 2 years, and then every 2 years up to 6 years thereafter, with follow-up assessments at each LDCT scan (ie, total follow-up of 8 years). A positive scan was defined as a solid or part-solid nodule larger than 6 mm in mean diameter or a pure ground-glass nodule larger than 5 mm in mean diameter. Lung cancer was diagnosed through invasive procedures, such as image-guided aspiration or biopsy or surgery. Here, we report the results of 1-year follow-up after LDCT screening at baseline. The primary outcome was lung cancer detection rate. The p value for detection rates was estimated by the χ2 test. Univariate and multivariable logistic regression analyses were used to assess the association between lung cancer incidence and each risk factor. The sensitivity, specificity, positive predictive value (PPV), and negative predictive value (NPV) of LDCT screening were also assessed. This study is registered with ClinicalTrials.gov, NCT02611570, and is ongoing.

FINDINGS

Between Dec 1, 2015, and July 31, 2019, 12 011 participants (8868 females) were enrolled, of whom 6009 had a family history of lung cancer. Among 12 011 LDCT scans done at baseline, 2094 (17·4%) were positive. Lung cancer was diagnosed in 318 (2·6%) of 12 011 participants (257 [2·1%] participants had invasive lung cancer and 61 [0·5%] had adenocarcinomas in situ). 317 of 318 participants had adenocarcinoma and 246 (77·4%) of 318 had stage I disease. The prevalence of invasive lung cancer was higher among participants with a family history of lung cancer (161 [2·7%] of 6009 participants) than in those without (96 [1·6%] of 6002 participants). In participants with a family history of lung cancer, the detection rate of invasive lung cancer increased significantly with age, whereas the detection rate of adenocarcinoma in situ remained stable. In multivariable analysis, female sex, a family history of lung cancer, and age older than 60 years were associated with an increased risk of lung cancer and invasive lung cancer; passive smoke exposure, cumulative exposure to cooking, cooking without ventilation, and a previous history of chronic lung diseases were not associated with lung cancer, even after stratification by family history of lung cancer. In participants with a family history of lung cancer, the higher the number of first-degree relatives affected, the higher the risk of lung cancer; participants whose mother or sibling had lung cancer were also at an increased risk. A positive LDCT scan had 92·1% sensitivity, 84·6% specificity, a PPV of 14·0%, and a NPV of 99·7% for lung cancer diagnosis.

INTERPRETATION

TALENT had a high invasive lung cancer detection rate at 1 year after baseline LDCT scan. Overdiagnosis could have occurred, especially in participants diagnosed with adenocarcinoma in situ. In individuals who do not smoke, our findings suggest that a family history of lung cancer among first-degree relatives significantly increases the risk of lung cancer as well as the rate of invasive lung cancer with increasing age. Further research on risk factors for lung cancer in this population is needed, particularly for those without a family history of lung cancer.

FUNDING

Ministry of Health and Welfare of Taiwan.

The predictive value of computed tomography value on high-resolution images in differentiating invasive from indolent lung adenocarcinoma

Background

Invasive adenocarcinoma (IA) has a worse prognosis and different clinical management strategies compared to indolent lung adenocarcinoma including adenocarcinoma in situ (AIS) and minimally IA (MIA). The purpose of this study was to evaluate the predictive value of computed tomography (CT) value in differentiating invasive from indolent lung adenocarcinoma.

Methods

The pathological diagnoses and imaging data of confirmed lung adenocarcinomas manifested as lung nodules with homogeneous internal density which were surgically resected between August 2021 and July 2022 were retrospectively analyzed. Differences in CT values between invasive and indolent lung adenocarcinomas were compared in the primary cohort (n=766), and receiver operating characteristic (ROC) curve analysis was used to determine the optimal cut-off value. The predictive performance of the cut-off value was evaluated in the validation cohort (n=341).

Results

A total of 1,107 lung nodules from 1,014 patients were included in the total cohort. The CT values had a significant difference between invasive and indolent lung adenocarcinomas (P<0.001). Using the primary cohort, we determined the optimal cut-off value of -415 Hounsfield units (HU) of the CT value based on ROC curve, which showed good discrimination between IA and AIS/MIA in both the primary and validation cohorts (sensitivity, 85.98% and 87.42%, specificity, 87.67% and 84.74%, respectively).

Conclusions

The CT value of >-415 HU could be an effective predictor of invasive lung adenocarcinoma, thereby providing an appropriate clinical decision guide.

Predicting the Invasiveness of Pulmonary Adenocarcinomas in Pure Ground-Glass Nodules Using the Nodule Diameter: A Systematic Review, Meta-Analysis, and Validation in an Independent Cohort

The nodule diameter was commonly used to predict the invasiveness of pulmonary adenocarcinomas in pure ground-glass nodules (pGGNs). However, the diagnostic performance and optimal cut-off values were inconsistent. We conducted a meta-analysis to evaluate the diagnostic performance of the nodule diameter for predicting the invasiveness of pulmonary adenocarcinomas in pGGNs and validated the cut-off value of the diameter in an independent cohort. Relevant studies were searched through PubMed, MEDLINE, Embase, and the Cochrane Library, from inception until December 2022. The inclusion criteria comprised studies that evaluated the diagnostic accuracy of the nodule diameter to differentiate invasive adenocarcinomas (IAs) from non-invasive adenocarcinomas (non-IAs) in pGGNs. A bivariate mixed-effects regression model was used to obtain the diagnostic performance. Meta-regression analysis was performed to explore the heterogeneity. An independent sample of 220 pGGNs (82 IAs and 128 non-IAs) was enrolled as the validation cohort to evaluate the performance of the cut-off values. This meta-analysis finally included 16 studies and 2564 pGGNs (761 IAs and 1803 non-IAs). The pooled area under the curve, the sensitivity, and the specificity were 0.85 (95% confidence interval (CI), 0.82-0.88), 0.82 (95% CI, 0.78-0.86), and 0.73 (95% CI, 0.67-0.78). The diagnostic performance was affected by the measure of the diameter, the reconstruction matrix, and patient selection bias. Using the prespecified cut-off value of 10.4 mm for the mean diameter and 13.2 mm for the maximal diameter, the mean diameter showed higher sensitivity than the maximal diameter in the validation cohort (0.85 vs. 0.72, p < 0.01), while there was no significant difference in specificity (0.83 vs. 0.86, p = 0.13). The nodule diameter had adequate diagnostic performance in differentiating IAs from non-IAs in pGGNs and could be replicated in a validation cohort. The mean diameter with a cut-off value of 10.4 mm was recommended.

Correlation Between Intranodular Vessels and Tumor Invasiveness of Lung Adenocarcinoma Presenting as Ground-glass Nodules: A Deep Learning 3-Dimensional Reconstruction Algorithm-based Quantitative Analysis on Noncontrast Computed Tomography Images

PURPOSE

To evaluate the role of quantitative features of intranodular vessels based on deep learning in distinguishing pulmonary adenocarcinoma invasiveness.

MATERIALS AND METHODS

This retrospective study included 512 confirmed ground-glass nodules from 474 patients with 241 precursor glandular lesions (PGL), 126 minimally invasive adenocarcinomas (MIA), and 145 invasive adenocarcinomas (IAC). The pulmonary blood vessels were reconstructed on noncontrast computed tomography images using deep learning-based region-segmentation and region-growing techniques. The presence of intranodular vessels was evaluated based on the automatic calculation of vessel prevalence, vascular categories, and vessel volume percentage. Further comparisons were made between different invasive groups by the Mantel-Haenszel χ 2 test, χ 2 test, and analysis of variance.

RESULTS

The detection rate of intranodular vessels in PGL (33.2%) was significantly lower than that of MIA (46.8%, P = 0.011) and IAC (55.2%, P < 0.001), while the vascular categories were similar (all P > 0.05). Vascular changes were more common in IAC and MIA than in PGL, mainly in increased vessel volume percentage (12.4 ± 19.0% vs. 6.3 ± 13.1% vs. 3.9 ± 9.4%, P < 0.001). The average intranodular artery and vein volume percentage of IAC (7.5 ± 14.0% and 5.0 ± 10.1%) was higher than that of PGL (2.1 ± 6.9% and 1.7 ± 5.8%) and MIA (3.2 ± 9.1% and 3.1 ± 8.7%), with statistical significance (all P < 0.05).

CONCLUSIONS

The quantitative analysis of intranodular vessels on noncontrast computed tomography images demonstrated that the ground-glass nodules with increased internal vessel prevalence and volume percentages had higher possibility of tumor invasiveness.

Editorial: Bio-Pathological Markers in the Diagnosis and Therapy of Cancer

Identifying novel biomarkers with diagnostic, prognostic and predictive value in terms of therapeutic response is a current topic in the clinical practice of oncologists, pathologists and medical researchers in general [...].

Correlations Between Inflammatory Cell Infiltration and Relative Density and the Boundary Manifestation of Pulmonary Non-Neoplastic Ground Glass Nodules

Purpose

To investigate the influence factors for the various boundary manifestations of pulmonary non-neoplastic ground glass nodules (GGNs) on computed tomography (CT).

Materials and Methods

From January 2015 to March 2022, a total of 280 patients with 318 non-neoplastic GGNs were enrolled. The correlations between degree of inflammatory cell infiltration and relative density (ΔCT) and the boundary manifestations of lesions were evaluated, respectively.

Results

Nongranulomatous nodules (283, 89.0%) with fibrous tissue proliferation and/or inflammatory cells as the predominant pathological findings were the most common non-neoplastic GGNs, followed by granulomatous nodules (28, 8.8%). Among nongranulomatous GGNs, cases with more and less/no inflammatory cells were 15 (10.9%) and 122 (89.1%) in 137 well-defined ones with smooth margin, 16 (24.6%) and 49 (75.4%) in 65 well-defined ones with coarse margin, 43 (91.5%) and 4 (8.5%) in 47 ill-defined ones with higher ΔCT (>151HU), and 4 (11.8%) and 30 (88.2%) in 34 ill-defined ones with lower ΔCT (< 151HU). The proportion of cases with more inflammatory cells in well-defined nodules was similar to that in ill-defined ones with lower ΔCT (P = 0.587) but significantly lower than that in ill-defined ones with higher ΔCT (P < 0.001). Among the granulomatous nodules, ill-defined cases with higher ΔCT (16, 57.1%) were the most common, and they (7/8, 87.5%) frequently had changes during short-term follow-up.

Conclusion

Nongranulomatous nodules are the most common non-neoplastic GGNs, their diverse boundary manifestations closely correlate with degree of inflammatory cell infiltration and density difference.

A predictive nomogram for lymph node metastasis in part-solid invasive lung adenocarcinoma: A complement to the IASLC novel grading system

Background

The International Association for the Study of Lung Cancer (IASLC) proposed a novel grading system for invasive lung adenocarcinoma, but lymphatic invasion was not evaluated. Meanwhile, the scope of lymph node dissection in part-solid invasive lung adenocarcinoma (PSILA) is still controversial. Therefore, this study aims to explore preoperative risk factors for lymph node metastasis in PSILA, to provide reference for intraoperative dissection of lymph nodes.

Methods

From 2018 to 2020, clinical data of patients (stage cN0) consecutively diagnosed as PSILA were retrospectively analyzed and classified according to the novel grading system. Logistic regression was conducted to screen the clinicopathological factors of lymph node metastasis in PSILA.

Results

A large cohort of 960 patients with PSILA who underwent lobectomy or sub-lobectomy were enrolled. By logistic regression analyses, solid part size, bronchial cutoff sign, spiculation, and carbohydrate antigen 199 (CA199) were eventually identified as independent risk factors for lymph node metastasis, based on which a nomogram was built to preoperatively predict the risk of lymph node metastasis [area under the receiver operating characteristic curve (AUC)=0.858; concordance index = 0.857; best cutoff, 0.027]. This suggests that intraoperative systematic lymph node dissection is recommended when the predicted risk value exceeds 0.027. Reproducibility of the novel grading system was verified.

Conclusions

The novel IASLC grading system was applicative in real world. The nomogram for preoperative prediction of lymph node metastasis may provide reference for the lymph node dissection strategy during PSILA surgeries.

Correlation Analysis of Computed Tomography Features and Pathological Types of Multifocal Ground-Glass Nodular Lung Adenocarcinoma

To investigate the correlation between computed tomography (CT) image characteristics of multiple lung ground-glass nodules (GGNs) and pathological classification, the CT image data of multiple lung GGN patients confirmed by pathology (n = 132) in our hospital were collected. The imaging features of GGNs were analyzed by qualified physicians, including lesion size (diameter, volume, and mass), location, CT values (mean and relative CT values), lesion morphology (round and irregular), marginal structure (pagination and burr), internal structure (bronchial inflation sign), and adjacent structure (pleural depression). CT imaging analysis was performed for the subtype of infiltrating adenocarcinoma (IAC). In CT findings, GGNs were greatly different from adenomatous hyperplasia (AAH), pure GGN adenocarcinoma in situ (AIS), and microinvasive adenocarcinoma (MIA) in terms of marginal structure, lesion morphology, internal structure, adjacent structure, and size (P < 0.05). The mean and relative CT values of mural adenocarcinoma, acinar adenocarcinoma, and papillary adenocarcinoma of IAC subtypes were greatly different from those of AAH/AIS/MIA (P < 0.05). In summary, the CT images of GGNs can be used as the basis for the differentiation of AAH, AIS, and MIA early noninvasive types and IAC invasive types, and the CT value of the IAC subtype can be used as the basis for the classification and differentiation of IAC pathological subtypes.

A comparative study for the evaluation of CT-based conventional, radiomic, combined conventional and radiomic, and delta-radiomic features, and the prediction of the invasiveness of lung adenocarcinoma manifesting as ground-glass nodules

AIM

To investigate and compare the performance of conventional, radiomic, combined, and delta-radiomic features to predict the invasiveness of lung adenocarcinoma manifesting as ground-glass nodules (GGNs).

MATERIALS AND METHODS

The present retrospective study included 216 GGNs confirmed surgically as pulmonary adenocarcinomas. All the thin-section computed tomography (CT) images were imported into the software of the United Imaging Intelligence research portal, and radiomic features were extracted with three-dimensional (3D) regions of interest. Least Absolute Shrinkage and Selection Operator was used to select the optimal radiomic features. Four models were constructed, including conventional, radiomic, combined conventional and radiomic, and delta-radiomic models. The receiver operating characteristic curves were built to evaluate the validity of these.

RESULTS

The type, long diameter, shape, margin, vacuole, air bronchus, vascular convergence, and pleural traction exhibited significant differences between pre-invasive lesions (PILs)/minimally invasive adenocarcinoma (MIA), and invasive adenocarcinoma (IA) groups were selected for conventional model building. Nine radiomic features were selected to build the radiomic model. The four models indicated optimal performance (AUC > 0.7). The radiomic and combined models exhibited the highest diagnostic efficiency, and their AUC were 0.89 and 0.88 in the training set, and 0.87 and 0.88 in the validation set, respectively. The delta-radiomic model indicated that the AUC was 0.83 in the training set, and 0.76 in the validation set. Finally, the conventional model exhibited an AUC in the training and validation sets of 0.78 and 0.76.

CONCLUSIONS

The radiomic model and combined model, in particular, and the delta-radiomic model all demonstrated improved diagnostic efficiency in differentiating IA from PIL/MIA than that of the conventional model.

Identification of pathological subtypes of early lung adenocarcinoma based on artificial intelligence parameters and CT signs

Objective: To explore the value of quantitative parameters of artificial intelligence (AI) and computed tomography (CT) signs in identifying pathological subtypes of lung adenocarcinoma appearing as ground-glass nodules (GGNs). Methods: CT images of 224 GGNs from 210 individuals were collected retrospectively and classified into atypical adenomatous hyperplasia (AAH)/adenocarcinoma in situ (AIS), minimally invasive adenocarcinoma (MIA), and invasive adenocarcinoma (IAC) groups. AI was used to identify GGNs and to obtain quantitative parameters, and CT signs were recognized manually. The mixed predictive model based on logistic multivariate regression was built and evaluated. Results: Of the 224 GGNs, 55, 93, and 76 were AAH/AIS, MIA, and IAC, respectively. In terms of AI parameters, from AAH/AIS to MIA, and IAC, there was a gradual increase in two-dimensional mean diameter, three-dimensional mean diameter, mean CT value, maximum CT value, and volume of GGNs (all P<0.0001). Except for the CT signs of the location, and the tumor–lung interface, there were significant differences among the three groups in the density, shape, vacuolar signs, air bronchogram, lobulation, spiculation, pleural indentation, and vascular convergence signs (all P<0.05). The areas under the curve (AUC) of predictive model 1 for identifying the AAH/AIS and MIA and model 2 for identifying MIA and IAC were 0.779 and 0.918, respectively, which were greater than the quantitative parameters independently (all P<0.05). Conclusion: AI parameters are valuable for identifying subtypes of early lung adenocarcinoma and have improved diagnostic efficacy when combined with CT signs.