Lepidic Predominant Pulmonary Lesions (LPL): CT-based Distinction From More Invasive Adenocarcinomas Using 3D Volumetric Density and First-order CT Texture Analysis

CT morphological features and histogram parameters to predict micropapillary or solid components in stage IA lung adenocarcinoma

Objectives

This study aimed to construct prediction models based on computerized tomography (CT) signs, histogram and morphology features for the diagnosis of micropapillary or solid (MIP/SOL) components of stage IA lung adenocarcinoma (LUAC) and to evaluate the models' performance.

Methods

This clinical retrospective study included image data of 376 patients with stage IA LUAC based on postoperative pathology, admitted to Putian First Hospital from January 2019 to June 2023. According to the presence of MIP/SOL components in postoperative pathology, patients were divided into MIP/SOL+ and MIP/SOL- groups. Cases with tumors ≤ 3 cm and ≤ 2 cm were separately analyzed. Each subgroup of patients was then randomly divided into a training set and a test set in a ratio of 7:3. The training set was used to build the prediction model, and the test set was used for internal validation.

Results

For tumors ≤ 3 cm, ground-glass opacity (GGO) [odds ratio (OR) = 0.244; 95% confidence interval (CI): 0.103-0.569; p = 0.001], entropy (OR = 1.748; 95% CI: 1.213-2.577; p = 0.004), average CT value (OR = 1.002; 95% CI: 1.000-1.004; p = 0.002), and kurtosis (OR = 1.240; 95% CI: 1.023-1.513; p = 0.030) were independent predictors of MIP/SOL components of stage IA LUAC. The area under the ROC curve (AUC) of the nomogram prediction model for predicting MIP/SOL components was 0.816 (95% CI: 0.756-0.877) in the training set and 0.789 (95% CI: 0.689-0.889) in the test set. In contrast, for tumors ≤ 2 cm, kurtosis was no longer an independent predictor. The nomogram prediction model had an AUC of 0.811 (95% CI: 0.731-0.891) in the training set and 0.833 (95% CI: 0.733-0.932) in the test set.

Conclusion

For tumors ≤ 3 cm and ≤ 2 cm, GGO, average CT value, and entropy were the same independent influencing factors in predicting MIP/SOL components of stage IA LUAC. The nomogram prediction models have potential diagnostic value for identifying MIP/SOL components of early-stage LUAC.

Establishment and visualization of a model based on high-resolution CT qualitative and quantitative features for prediction of micropapillary or solid components in invasive lung adenocarcinoma

OBJECTIVE

To predict the existence of micropapillary or solid components in invasive adenocarcinoma, a model was constructed using qualitative and quantitative features in high-resolution computed tomography (HRCT).

METHODS

Through pathological examinations, 176 lesions were divided into two groups depending on the presence or absence of micropapillary and/or solid components (MP/S): MP/S- group (n = 128) and MP/S + group (n = 48). Multivariate logistic regression analyses were used to identify independent predictors of the MP/S. Artificial intelligence (AI)-assisted diagnostic software was used to automatically identify the lesions and extract corresponding quantitative parameters on CT images. The qualitative, quantitative, and combined models were constructed according to the results of multivariate logistic regression analysis. The receiver operating characteristic (ROC) analysis was conducted to evaluate the discrimination capacity of the models with the area under the curve (AUC), sensitivity, and specificity calculated. The calibration and clinical utility of the three models were determined using the calibration curve and decision curve analysis (DCA), respectively. The combined model was visualized in a nomogram.

RESULTS

The multivariate logistic regression analysis using both qualitative and quantitative features indicated that tumor shape (P =  0.029 OR =  4.89; 95% CI 1.175-20.379), pleural indentation (P = 0.039 OR =  1.91; 95% CI 0.791-4.631), and consolidation tumor ratios (CTR) (P < 0.001; OR = 1.05; 95% CI 1.036-1.070) were independent predictors for MP/S + . The areas under the curve (AUC) of the qualitative, quantitative, and combined models in predicting MP/S + were 0.844 (95% CI 0.778-0.909), 0.863 (95% CI 0.803-0.923), and 0.880 (95% CI 0.824-0.937). The combined model of AUC was the most superior and statistically better than qualitative model.

CONCLUSION

The combined model could assist doctors to evaluate patient's prognoses and devise personalized diagnostic and treatment protocols for patients.

Radiomics for identifying lung adenocarcinomas with predominant lepidic growth manifesting as large pure ground-glass nodules on CT images

Purpose

To explore the value of radiomics in the identification of lung adenocarcinomas with predominant lepidic growth in pure ground-glass nodules (pGGNs) larger than 10 mm.

Methods

We retrospectively analyzed CT images of 204 patients with large pGGNs (≥ 10 mm) pathologically diagnosed as minimally invasive adenocarcinomas (MIAs), lepidic predominant adenocarcinomas (LPAs), and non-lepidic predominant adenocarcinomas (NLPAs). All pGGNs in the two groups (MIA/LPA and NLPA) were randomly divided into training and test cohorts. Forty-seven patients from another center formed the external validation cohort. Baseline features, including clinical data and CT morphological and quantitative parameters, were collected to establish a baseline model. The radiomics model was built with the optimal radiomics features. The combined model was developed using the rad_score and independent baseline predictors. The performance of the models was evaluated using the area under the receiver operating characteristic curve (AUC) and compared using the DeLong test. The differential diagnosis performance of the models was compared with three radiologists (with 20+, 10+, and 3 years of experience) in the test cohort.

Results

The radiomics (training AUC: 0.833; test AUC: 0.804; and external validation AUC: 0.792) and combined (AUC: 0.849, 0.820, and 0.775, respectively) models performed better for discriminating than the baseline model (AUC: 0.756, 0.762, and 0.725, respectively) developed by tumor location and mean CT value of the whole nodule. The DeLong test showed that the AUCs of the combined and radiomics models were significantly increased in the training cohort. The highest AUC value of the radiologists was 0.600.

Conclusion

The application of CT radiomics improved the identification performance of lung adenocarcinomas with predominant lepidic growth appearing as pGGNs larger than 10 mm.

[Research Progress in 3D-reconstruction Based Imaging Analysis in Partial Solid Pulmonary Nodule]

The incidence and mortality of lung cancer rank first among all malignant tumors in China. With the popularization of high resolution computed tomography (CT) in clinic, chest CT has become an important means of clinical screening for early lung cancer and reducing the mortality of lung cancer. Imaging findings of early lung adenocarcinoma often show partial solid nodules with ground glass components. With the development of imaging, the relationship between the imaging features of some solid nodules and their prognosis has attracted more and more attention. At the same time, with the development of 3D-reconstruction technology, clinicians can improve the accuracy of diagnosis and treatment of such nodules.This article focuses on the traditional imaging analysis of partial solid nodules and the imaging analysis based on 3D reconstruction, and systematically expounds the advantages and disadvantages of both.
.

Inter-Reader Variability of Volumetric Subsolid Pulmonary Nodule Radiomic Features

OBJECTIVE

To evaluate the inter-observer consistency for subsolid pulmonary nodule radiomic features.

MATERIALS AND METHODS

Subsolid nodules were selected by reviewing radiology reports of CT examinations performed December 1, 2015 to April 1, 2016. Patients with CTs at two time points were included in this study. There were 55 patients with subsolid nodules, of whom 14 had two nodules. Of 69 subsolid nodules, 66 were persistent at the second time point, yielding 135 lesions for segmentation. Two thoracic radiologists and an imaging fellow segmented the lesions using a semi-automated volumetry algorithm (Syngo.via Vb20, Siemens). Coefficient of variation (CV) was used to assess consistency of 91 quantitative measures extracted from the subsolid nodule segmentations, including first and higher order texture features. The accuracy of segmentation was visually graded by an experienced thoracic radiologist. Influencing factors on radiomic feature consistency and segmentation accuracy were assessed using generalized estimating equation analyses and the Exact Mann-Whitney test.

RESULTS

Mean patient age was 71 (38-93 years), with 39 women and 16 men. Mean nodule volume was 1.39mL, range .03-48.2mL, for 135 nodules. Several radiomic features showed high inter-reader consistency (CV<5%), including entropy, uniformity, sphericity, and spherical disproportion. Descriptors such as surface area and energy had low consistency across inter-reader segmentations (CV>10%). Nodule percent solid component and attenuation influenced inter-reader variability of some radiomic features. The presence of contrast did not significantly affect the consistency of subsolid nodule radiomic features. Near perfect segmentation, within 5% of actual nodule size, was achieved in 68% of segmentations, and very good segmentation, within 25% of actual nodule size, in 94%. Morphologic features including nodule margin and shape (each p <0.01), and presence of air bronchograms (p = 0.004), bubble lucencies (p = 0.02) and broad pleural contact (p < 0.01) significantly affected the probability of near perfect segmentation. Stroke angle (p = 0.001) and length (p < 0.001) also significantly influenced probability of near perfect segmentation.

CONCLUSIONS

The inter-observer consistency of radiomic features for subsolid pulmonary nodules varies, with high consistency for several features, including sphericity, spherical disproportion, and first and higher order entropy, and normalized non-uniformity. Nodule morphology influences the consistency of subsolid nodule radiomic features, and the accuracy of subsolid nodule segmentation.

Investigating the association between ground-glass nodules glucose metabolism and the invasive growth pattern of early lung adenocarcinoma

Background

To explore the association between the glucose metabolism level of lung ground-glass nodules (GGNs), as revealed by ¹⁸F-flurodeoxyglucose positron emission tomography/computed tomography (¹⁸F-FDG PET/CT) imaging, and the invasive pathological growth pattern of early lung adenocarcinoma.

Methods

We retrospectively analyzed patients who underwent PET/CT examination and surgical resection due to persistent GGNs, which were confirmed to be early lung adenocarcinoma by postoperative pathology examination. After adjusting for confounding factors and performing stratified analysis, we explored the association between the maximum standard uptake value of PET (SUVmax) and the invasive pathological growth pattern of early stage lung adenocarcinoma.

Results

The proportions of invasive adenocarcinoma (INV) in the SUVmax of Tertile 1, Tertile 2, and Tertile 3 were 52.7%, 73.3%, and 87.1%, respectively. After adjusting for potential confounding factors, the risk of INV gradually increased as the GGN SUVmax increased [odds ratio (OR): 1.520, 95% confidence interval (CI): 1.044-2.213, P=0.029]. This trend was statistically significant (OR: 1.678, 95% CI: 1.064-2.647, P=0.026), especially in Tertile 3 vs. Tertile 1 (OR: 4.879, 95% CI: 1.349-17.648, P=0.016). Curve fitting showed that the SUVmax and INV risk were linearly and positively associated. The association was consistent in different subgroups based on GGN number, type, shape, edge, bronchial sign, vacuole sign, pleural depression sign, diameters, and consolidation-to-tumor ratio, suggesting that there was no significant interaction between different grouping parameters and the association (P for interaction range = 0.129-0.909).

Conclusions

In FDG PET, the glucose metabolism level (SUVmax) of lung GGNs is independently associated with INV risk, and this association is linear and positive.

Assessing invasiveness of subsolid lung adenocarcinomas with combined attenuation and geometric feature models

The aim of this study was to develop and test multiclass predictive models for assessing the invasiveness of individual lung adenocarcinomas presenting as subsolid nodules on computed tomography (CT). 227 lung adenocarcinomas were included: 31 atypical adenomatous hyperplasia and adenocarcinomas in situ (class H1), 64 minimally invasive adenocarcinomas (class H2) and 132 invasive adenocarcinomas (class H3). Nodules were segmented, and geometric and CT attenuation features including functional principal component analysis features (FPC1 and FPC2) were extracted. After a feature selection step, two predictive models were built with ordinal regression: Model 1 based on volume (log) (logarithm of the nodule volume) and FPC1, and Model 2 based on volume (log) and Q.875 (CT attenuation value at the 87.5% percentile). Using the 200-repeats Monte-Carlo cross-validation method, these models provided a multiclass classification of invasiveness with discriminative power AUCs of 0.83 to 0.87 and predicted the class probabilities with less than a 10% average error. The predictive modelling approach adopted in this paper provides a detailed insight on how the value of the main predictors contribute to the probability of nodule invasiveness and underlines the role of nodule CT attenuation features in the nodule invasiveness classification.

Solid Indeterminate Nodules with a Radiological Stability Suggesting Benignity: A Texture Analysis of Computed Tomography Images Based on the Kurtosis and Skewness of the Nodule Volume Density Histogram

Background

The number of incidental findings of pulmonary nodules using imaging methods to diagnose other thoracic or extrathoracic conditions has increased, suggesting the need for in-depth radiological image analyses to identify nodule type and avoid unnecessary invasive procedures.

Objectives

The present study evaluated solid indeterminate nodules with a radiological stability suggesting benignity (SINRSBs) through a texture analysis of computed tomography (CT) images.

Methods

A total of 100 chest CT scans were evaluated, including 50 cases of SINRSBs and 50 cases of malignant nodules. SINRSB CT scans were performed using the same noncontrast enhanced CT protocol and equipment; the malignant nodule data were acquired from several databases. The kurtosis (KUR) and skewness (SKW) values of these tests were determined for the whole volume of each nodule, and the histograms were classified into two basic patterns: peaks or plateaus.

Results

The mean (MEN) KUR values of the SINRSBs and malignant nodules were 3.37 ± 3.88 and 5.88 ± 5.11, respectively. The receiver operating characteristic (ROC) curve showed that the sensitivity and specificity for distinguishing SINRSBs from malignant nodules were 65% and 66% for KUR values >6, respectively, with an area under the curve (AUC) of 0.709 (p < 0.0001). The MEN SKW values of the SINRSBs and malignant nodules were 1.73 ± 0.94 and 2.07 ± 1.01, respectively. The ROC curve showed that the sensitivity and specificity for distinguishing malignant nodules from SINRSBs were 65% and 66% for SKW values >3.1, respectively, with an AUC of 0.709 (p < 0.0001). An analysis of the peak and plateau histograms revealed sensitivity, specificity, and accuracy values of 84%, 74%, and 79%, respectively.

Conclusions

KUR, SKW, and histogram shape can help to noninvasively diagnose SINRSBs but should not be used alone or without considering clinical data.

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

OBJECTIVE

To validate three proposed definitions of the "solid" component of subsolid nodules, as compared to CT histograms and the use of different window settings, for discriminating the invasiveness of adenocarcinomas in a manner that facilitates routine clinical assessment.

METHODS

We retrospectively analyzed 328 pathologically confirmed lung adenocarcinomas, manifesting as subsolid nodules. Three-dimensional CT histograms were generated by setting 11 CT attenuation intervals from - 400 to 50 HU, at 50 HU intervals, and the voxel percentage within each CT attenuation interval was generated automatically. Three definitions of the "solid" component were proposed, and 10 medium window settings were set to evaluate the "solid" component. The diagnostic performance of the three definitions for identifying invasive adenocarcinoma was compared with that of CT histogram analysis and subjective evaluation with medium window settings.

RESULTS

A parallel diagnosis using five intervals with the largest AUC (AUC ≥ 0.797) demonstrated good differential diagnostic performance, with 78% sensitivity and 73.7% specificity. Definition 2 (visibility in the mediastinum window) yielded higher accuracy (75.6%) than the other two definitions (p < 0.01). A medium window setting of - 50 WL/2 WW gave a larger AUC than the other nine medium window settings as well as definition 2, with 82.5% specificity and 88.5% PPV, which was higher than those of parallel diagnosis with CT histogram and definition 2.

CONCLUSION

Using - 50 WL/2 WW is the optimum approach for evaluating the "solid" component and discriminating invasiveness, superior to using 3D CT histograms and definition 2, and convenient in routine clinical assessment.

KEY POINTS

• - 50 WL/2 WW gave a larger AUC than definition 2. • The specificity of - 50 WL/2 WW was higher than CT histograms. • - 50 WL/2 WW offers the best evaluation of the solid component.

3D convolutional neural network for differentiating pre-invasive lesions from invasive adenocarcinomas appearing as ground-glass nodules with diameters ≤3 cm using HRCT

Background

Identification of pre-invasive lesions (PILs) and invasive adenocarcinomas (IACs) can facilitate treatment selection. This study aimed to develop an automatic classification framework based on a 3D convolutional neural network (CNN) to distinguish different types of lung cancer using computed tomography (CT) data.

Methods

The CT data of 1,545 patients suffering from pre-invasive or invasive lung cancer were collected from Fudan University Shanghai Cancer Center. All of the data were preprocessed through lung mask extraction and 3D reconstruction to adapt to different imaging scanners or protocols. The general flow for the classification framework consisted of nodule detection and cancer classification. The performance of our classification algorithm was evaluated using a receiver operating characteristic (ROC) analysis, with diagnostic results from three experienced radiologists.

Results

The sensitivity, specificity, accuracy, and AUC (area under the ROC curve) values of our proposed automatic classification method were 88.5%, 80.1%, 84.0%, and 89.2%, respectively. The results of the CNN classification method were compared to those of three experienced radiologists. The AUC value of our method (AUC =0.892) was higher than those of all radiologists (radiologist 1: 80.5%; radiologist 2: 83.9%; and radiologist 3: 86.7%).

Conclusions

The 3D CNN-based classification algorithm is a promising tool for the diagnosis of pre-invasive and invasive lung cancer and for the treatment choice decision.