Prediction of visceral pleural invasion of clinical stage I lung adenocarcinoma using thoracoscopic images and deep learning

PURPOSE

To develop deep learning models using thoracoscopic images to identify visceral pleural invasion (VPI) in patients with clinical stage I lung adenocarcinoma, and to verify if these models can be applied clinically.

METHODS

Two deep learning models, one based on a convolutional neural network (CNN) and the other based on a vision transformer (ViT), were applied and trained via 463 images (VPI negative: 269 images, VPI positive: 194 images) captured from surgical videos of 81 patients. Model performances were validated via an independent test dataset containing 46 images (VPI negative: 28 images, VPI positive: 18 images) from 46 test patients.

RESULTS

The areas under the receiver operating characteristic curves of the CNN-based and ViT-based models were 0.77 and 0.84 (p = 0.304), respectively. The accuracy, sensitivity, specificity, and positive and negative predictive values were 73.91, 83.33, 67.86, 62.50, and 86.36% for the CNN-based model and 78.26, 77.78, 78.57, 70.00, and 84.62% for the ViT-based model, respectively. These models' diagnostic abilities were comparable to those of board-certified thoracic surgeons and tended to be superior to those of non-board-certified thoracic surgeons.

CONCLUSION

The deep learning model systems can be utilized in clinical applications via data expansion.

Nomogram using intratumoral and peritumoral radiomics for the preoperative prediction of visceral pleural invasion in clinical stage IA lung adenocarcinoma

BACKGROUND

Accurate prediction of visceral pleural invasion (VPI) in lung adenocarcinoma before operation can provide guidance and help for surgical operation and postoperative treatment. We investigate the value of intratumoral and peritumoral radiomics nomograms for preoperatively predicting the status of VPI in patients diagnosed with clinical stage IA lung adenocarcinoma.

METHODS

A total of 404 patients from our hospital were randomly assigned to a training set (n = 283) and an internal validation set (n = 121) using a 7:3 ratio, while 81 patients from two other hospitals constituted the external validation set. We extracted 1218 CT-based radiomics features from the gross tumor volume (GTV) as well as the gross peritumoral tumor volume (GPTV5, 10, 15), respectively, and constructed radiomic models. Additionally, we developed a nomogram based on relevant CT features and the radscore derived from the optimal radiomics model.

RESULTS

The GPTV10 radiomics model exhibited superior predictive performance compared to GTV, GPTV5, and GPTV15, with area under the curve (AUC) values of 0.855, 0.842, and 0.842 in the three respective sets. In the clinical model, the solid component size, pleural indentation, solid attachment, and vascular convergence sign were identified as independent risk factors among the CT features. The predictive performance of the nomogram, which incorporated relevant CT features and the GPTV10-radscore, outperformed both the radiomics model and clinical model alone, with AUC values of 0.894, 0.828, and 0.876 in the three respective sets.

CONCLUSIONS

The nomogram, integrating radiomics features and CT morphological features, exhibits good performance in predicting VPI status in lung adenocarcinoma.

Prediction of Pleural Lavage Cytology According to Thin-Section Computed Tomography in Non-Small-Cell Lung Cancer

BACKGROUND

Although the positive rate of preresection pleural lavage cytology (PLC) is low, it is an important indicator of poor prognosis for non-small-cell lung cancer patients with frequent pleural dissemination (PD) recurrence. Thin-section computed tomography (TSCT) can reveal relationships between a primary tumor and the pleura at 1 to 2 mm intervals, and this is associated with visceral pleural invasion (VPI). However, its association with PLC remains unclear. Therefore, we aimed to improve PLC efficiency and predict PD recurrence by understanding the relationship between PLC and preoperative TSCT findings.

PATIENTS AND METHODS

Between January 2014 and December 2018, we reviewed 978 patients with non-small-cell lung cancer who underwent PLC tests during complete resection surgery. Preoperative TSCT findings were evaluated, and factors with the highest specificity (proportion of patients with radiologically to pathologically diagnosed positive PLC) were investigated. We also evaluated their relationships with VPI and PD recurrence.

RESULTS

PLC positive was identified in 55 (5.6%) of the 978 patients. The two TSCT findings predicting PLC results, "the absence of pleural findings," ie, tumor not attached to pleura or without pleural tag, and "consolidation-to-tumor ratio ≤0.5", had a specificity of 100% (95% confidence interval: 90.4%-100%); additionally, all cases with these findings were VPI negative and had no PD recurrence. And 24% of the cohort had either of these findings.

CONCLUSION

The absence of pleural findings and/or consolidation-to-tumor ratio ≤0.5 of primary tumor on preoperative TSCT can predict PLC negativity with very high probability; therefore, PLC can be omitted for such patients.

Diagnostic performance and prognostic value of CT-defined visceral pleural invasion in early-stage lung adenocarcinomas

OBJECTIVES

To analyze the diagnostic performance and prognostic value of CT-defined visceral pleural invasion (CT-VPI) in early-stage lung adenocarcinomas.

METHODS

Among patients with clinical stage I lung adenocarcinomas, half of patients were randomly selected for a diagnostic study, in which five thoracic radiologists determined the presence of CT-VPI. Probabilities for CT-VPI were obtained using deep learning (DL). Areas under the receiver operating characteristic curve (AUCs) and binary diagnostic measures were calculated and compared. Inter-rater agreement was assessed. For all patients, the prognostic value of CT-VPI by two radiologists and DL (using high-sensitivity and high-specificity cutoffs) was investigated using Cox regression.

RESULTS

In 681 patients (median age, 65 years [interquartile range, 58-71]; 382 women), pathologic VPI was positive in 130 patients. For the diagnostic study (n = 339), the pooled AUC of five radiologists was similar to that of DL (0.78 vs. 0.79; p = 0.76). The binary diagnostic performance of radiologists was variable (sensitivity, 45.3-71.9%; specificity, 71.6-88.7%). Inter-rater agreement was moderate (weighted Fleiss κ, 0.51; 95%CI: 0.43-0.55). For overall survival (n = 680), CT-VPI by radiologists (adjusted hazard ratio [HR], 1.27 and 0.99; 95%CI: 0.84-1.92 and 0.63-1.56; p = 0.26 and 0.97) or DL (HR, 1.44 and 1.06; 95%CI: 0.86-2.42 and 0.67-1.68; p = 0.17 and 0.80) was not prognostic. CT-VPI by an attending radiologist was prognostic only in radiologically solid tumors (HR, 1.82; 95%CI: 1.07-3.07; p = 0.03).

CONCLUSION

The diagnostic performance and prognostic value of CT-VPI are limited in clinical stage I lung adenocarcinomas. This feature may be applied for radiologically solid tumors, but substantial reader variability should be overcome.

CLINICAL RELEVANCE STATEMENT

Although the diagnostic performance and prognostic value of CT-VPI are limited in clinical stage I lung adenocarcinomas, this parameter may be applied for radiologically solid tumors with appropriate caution regarding inter-reader variability.

KEY POINTS

• Use of CT-defined visceral pleural invasion in clinical staging should be cautious, because prognostic value of CT-defined visceral pleural invasion remains unexplored. • Diagnostic performance and prognostic value of CT-defined visceral pleural invasion varied among radiologists and deep learning. • Role of CT-defined visceral pleural invasion in clinical staging may be limited to radiologically solid tumors.

A CT-based deep learning model: visceral pleural invasion and survival prediction in clinical stage IA lung adenocarcinoma

Pathologic visceral pleural invasion (VPI) in patients with early-stage lung cancer can result in the upstaging of T1 to T2, in addition to having implications for surgical resection and prognostic outcomes. This study was designed with the goal of establishing and validating a CT-based deep learning (DL) model capable of predicting VPI status and stratifying patients based on their prognostic outcomes. In total, 2077 patients from three centers with pathologically confirmed clinical stage IA lung adenocarcinoma were enrolled. DL signatures were extracted with a 3D residual neural network. DL model was able to effectively predict VPI status. VPI predicted by the DL models, as well as pathologic VPI, was associated with shorter disease-free survival. The established deep learning signature provides a tool capable of aiding the accurate prediction of VPI in patients with clinical stage IA lung adenocarcinoma, thus enabling prognostic stratification.

Predicting visceral pleural invasion in lung adenocarcinoma presenting as part-solid density utilizing a nomogram model combined with radiomics and clinical features

BACKGROUND

To develop and validate a preoperative nomogram model combining the radiomics signature and clinical features for preoperative prediction of visceral pleural invasion (VPI) in lung nodules presenting as part-solid density.

METHODS

We retrospectively reviewed 156 patients with pathologically confirmed invasive lung adenocarcinomas after surgery from January 2016 to August 2019. The patients were split into training and validation sets by a ratio of 7:3. The radiomic features were extracted with the aid of FeAture Explorer Pro (FAE). A CT-based radiomics model was constructed to predict the presence of VPI and internally validated. Multivariable regression analysis was conducted to construct a nomogram model, and the performance of the models were evaluated with the area under the receiver operating characteristic curve (AUC) and compared with each other.

RESULTS

The enrolled patients were split into training (n = 109) and validation sets (n = 47). A total of 806 features were extracted and the selected 10 optimal features were used in the construction of the radiomics model among the 707 stable features. The AUC of the nomogram model was 0.888 (95% CI: 0.762-0.961), which was superior to the clinical model (0.787, 95% CI: 0.643-0.893; p = 0.049) and comparable to the radiomics model (0.879, 95% CI: 0.751-0.965; p > 0.05). The nomogram model achieved a sensitivity of 90.5% and a specificity of 76.9% in the validation dataset.

CONCLUSIONS

The nomogram model could be considered as a noninvasive method to predict VPI with either highly sensitive or highly specific diagnoses depending on clinical needs.

Using CT imaging features to predict visceral pleural invasion of non-small-cell lung cancer

AIM

To examine the diagnostic performance of different models based on computed tomography (CT) imaging features in differentiating the invasiveness of non-small-cell lung cancer (NSCLC) with multiple pleural contact types.

MATERIALS AND METHODS

A total of 1,573 patients with NSCLC (tumour size ≤3 cm) were included retrospectively. The clinical and pathological data and preoperative imaging features of these patients were investigated and their relationships with visceral pleural invasion (VPI) were compared statistically. Multivariate logistic regression was used to eliminate confounding factors and establish different predictive models.

RESULTS

By univariate analysis and multivariable adjustment, surgical history, tumour marker (TM), number of pleural tags, length of solid contact and obstructive inflammation were identified as independent risk predictors of pleural invasiveness (p=0.014, 0.003, <0.001, <0.001, and 0.017, respectively). In the training group, comparison of the diagnostic efficacy between the combined model including these five independent predictors and the image feature model involving the latter three imaging predictors were as follows: sensitivity of 88.9% versus 77% and specificity of 73.5% versus 84.1%, with AUC of 0.868 (95% CI: 0.848-0.886) versus 0.862 (95% CI: 0.842-0.880; p=0.377). In the validation group, the sensitivity and specificity of these two models were as follow: the combined model, 93.5% and 74.3%, the imaging feature model, 77.4% and 81.3%, and their areas under the curve (AUCs) were both 0.884 (95% CI: 0.842-0.919). The best cut-off value of length of solid contact was 7.5 mm (sensitivity 68.9%, specificity 75.5%).

CONCLUSIONS

The image feature model showed great potential in predicting pleural invasiveness, and had comparable diagnostic efficacy compared with the combined model containing clinical data.

Predicting pleural invasion of invasive lung adenocarcinoma in the adjacent pleura by imaging histology

The aim of the present study was to develop a non-invasive method based on histological imaging and clinical features for predicting the preoperative status of visceral pleural invasion (VPI) in patients with lung adenocarcinoma (LUAD) located near the pleura. VPI is associated with a worse prognosis of LUAD; therefore, early and accurate detection is critical for effective treatment planning. A total of 112 patients with preoperative computed tomography presentation of adjacent pleura and postoperative pathological findings confirmed as invasive LUAD were retrospectively enrolled. Clinical and histological imaging features were combined to develop a preoperative VPI prediction model and validate the model's efficacy. Finally, a nomogram for predicting LUAD was established and validated using a logistic regression algorithm. Both the clinical signature and radiomics signature (Rad signature) exhibited a perfect fit in the training cohort. The clinical signature was overfitted in the testing cohort, whereas the Rad signature showed a good fit. To combine clinical and radiomics signatures for optimal performance, a nomogram was created using the logistic regression algorithm. The results indicated that this approach had the highest predictive performance, with an area under the curve of 0.957 for the clinical signature and 0.900 for the Rad signature. In conclusion, histological imaging and clinical features can be combined in columnar maps to predict the preoperative VPI status of patients with adjacent pleural infiltrative lung carcinoma.

Correlations between iodine uptake, invasive CT features and pleural invasion in adenocarcinomas with pleural contact

Pleural contact in lung cancers does not always imply pleural invasion (PI). This study was designed to determine whether specific invasive CT characteristics or iodine uptake can aid in the prediction of PI. The sample population comprised patients with resected solid lung adenocarcinomas between April 2019 and May 2022. All participants underwent a contrast enhanced spectral CT scan. Two proficient radiologists independently evaluated the CT features and iodine uptake. Logistic regression analyses were employed to identify predictors for PI, via CT features and iodine uptake. To validate the improved diagnostic efficiency, accuracy analysis and ROC curves were subsequently used. A two-tailed P value of less than 0.05 was considered statistically significant. We enrolled 97 consecutive patients (mean age, 61.8 years ± 10; 48 females) in our study. The binomial logistic regression model revealed that a contact length > 10 mm (OR 4.80, 95% CI 1.92, 11.99, p = 0.001), and spiculation sign (OR 2.71, 95% CI 1.08, 6.79, p = 0.033) were independent predictors of PI, while iodine uptake was not. Enhanced sensitivity (90%) and a greater area under the curve (0.73) were achieved by integrating the two aforementioned CT features in predicting PI. We concluded that the combination of contact length > 10 mm and spiculation sign can enhance the diagnostic performance of PI.

Differentiation of pulmonary solid nodules attached to the pleura detected by thin-section CT

BACKGROUND

Pulmonary solid pleura-attached nodules (SPANs) are not very commonly detected and thus not well studied and understood. This study aimed to identify the clinical and CT characteristics for differentiating benign and malignant SPANs.

RESULTS

From January 2017 to March 2023, a total of 295 patients with 300 SPANs (128 benign and 172 malignant) were retrospectively enrolled. Between benign and malignant SPANs, there were significant differences in patients' age, smoking history, clinical symptoms, CT features, nodule-pleura interface, adjacent pleural change, peripheral concomitant lesions, and lymph node enlargement. Multivariate analysis revealed that smoking history (odds ratio [OR], 2.016; 95% confidence interval [CI], 1.037-3.919; p = 0.039), abutting the mediastinal pleura (OR, 3.325; 95% CI, 1.235-8.949; p = 0.017), nodule diameter (> 15.6 mm) (OR, 2.266; 95% CI, 1.161-4.423; p = 0.016), lobulation (OR, 8.922; 95% CI, 4.567-17.431; p < 0.001), narrow basement to pleura (OR, 6.035; 95% CI, 2.847-12.795; p < 0.001), and simultaneous hilar and mediastinal lymph nodule enlargement (OR, 4.971; 95% CI, 1.526-16.198; p = 0.008) were independent predictors of malignant SPANs, and the area under the curve (AUC) of this model was 0.890 (sensitivity, 82.0%, specificity, 77.3%) (p < 0.001).

CONCLUSION

In patients with a smoking history, SPANs abutting the mediastinal pleura, having larger size (> 15.6 mm in diameter), lobulation, narrow basement, or simultaneous hilar and mediastinal lymph nodule enlargement are more likely to be malignant.

CRITICAL RELEVANCE STATEMENT

The benign and malignant SPANs have significant differences in clinical and CT features. Understanding the differences between benign and malignant SPANs is helpful for selecting the high-risk ones and avoiding unnecessary surgical resection.

KEY POINTS

• The solid pleura-attached nodules (SPANs) are closely related to the pleura. • Relationship between nodule and pleura and pleural changes are important for differentiating SPANs. • Benign SPANs frequently have broad pleural thickening or embed in thickened pleura. • Smoking history and lesions abutting the mediastinal pleura are indicators of malignant SPANs. • Malignant SPANs usually have larger diameters, lobulation signs, narrow basements, and lymphadenopathy.

[Research Progress of Relationship between Pleural Deformation and Visceral Pleural Invasion in Lung Cancer Manifesting as Ground-glass Opacity]

Visceral pleural invasion (VPI) is one of the negative prognostic factors of non-small cell lung cancer (NSCLC). With the popularization of computed tomography (CT) screening for lung cancer, more and more ground-glass nodule (GGN) have been found. However, it remains unclear whether the relationship between the pleural deformation of lung cancer manifesting as ground-glass opacity (GGO) and VPI affects the effect of sub-lobectomy, which is reviewed in this paper.
.

Pathological components and CT imaging analysis of the area adjacent pleura within the pure ground-glass nodules with pleural deformation in invasive lung adenocarcinoma

Background

Pleural deformation is associated with the invasiveness of lung adenocarcinoma(LAC). Our study focused on the pathological components of the area adjacent pleura in pulmonary pure ground-glass nodules(pGGNs) with pleural deformations(P-pGGNs) confirmed to be invasive LAC without visceral pleural invasion (VPI) pathologically.

Methods

Computed tomography(CT) imaging features of nodules and pathological components of the area adjacent pleura were analyzed and recorded. Statistical analysis was performed for subgroups of P-pGGNs.

Results

The 81 enrolled patients with 81 P-pGGNs were finally involved in the analysis. None of solid/micropapillary group and none of VPI was observed, 54 alveoli/lepidics and 27 acinar/papillarys were observed. In P-pGGN with acinar/papillary components of the area adjacent pleura, invasive adenocarcinoma (IAC) was more common compared to minimally invasive adenocarcinoma (MIA, 74.07% vs. 25.93%; p < 0.001). The distance in alveoli/lepidic group was significantly larger (1.50 mm vs. 0.00 mm; p < 0.001) and the depth was significantly smaller (2.00 mm vs. 6.00 mm; p < 0.001) than that in acinar/papillary group. The CT attenuation value, maximum diameter and maximum vertical diameter was valuable to distinguish acinar/papillary group form alveoli/lepidic group(p < 0.05). The type d pleural deformation was the common pleural deformation in IAC(p = 0.028).

Conclusions

The pathological components of the area adjacent pleura in P-pGGN without VPI confirmed to be invasive LAC could included alveoli/lepidics and acinar/papillarys. Some CT indicators that can identify the pathological invasive components of the area adjacent pleura in P-pGGNs.

Supplementary Information

The online version contains supplementary material available at 10.1186/s12885-022-10043-2.

Predictive Value of 18 F-FDG PET/MRI for Pleural Invasion in Solid and Subsolid Lung Adenocarcinomas Smaller Than 3 cm

BACKGROUND

Positron emission tomography (PET)/MRI combines the characteristics of metabolism imaging and high soft tissue resolution, and could provide high diagnostic efficacy for assessment of pleural invasion (PI) of lung cancer.

PURPOSE

To investigate the application of ¹⁸ F-fluorodeoxyglucose (FDG) PET/MRI for predicting PI of lung cancer with the maximum diameter ≤3 cm.

STUDY TYPE

Prospective.

POPULATION

A total of 44 patients with non-small cell lung cancer (NSCLC), age from 39 to 79 years old, including 19 (56.82%) females.

FIELD STRENGTH/SEQUENCE

A 3-T, hybrid PET/MRI including axial fast spin echo respiratory-triggered T2 fat-suppressed imaging (T2FS) and echo planar imaging diffusion-weighted imaging (DWI).

ASSESSMENT

The maximum standardized uptake value (SUVmax) of all lesions was measured on PET images. Localized effusion outside the contact between the nodules and the pleura on T2FS and signal at the contact between the nodules and the pleura on DWI were evaluated by experienced physicians through visual assessment of the MRI sequences.

STATISTICAL TESTS

Three models (models 1-3) were developed, incorporating CT, CT and PET, PET and MRI features, and Lasso regression was used in feature selection. The receiver operating characteristic (ROC) curve for PI diagnosis was visualized for each model, and the area under the curve (AUC) was calculated. The DeLong test was used to compare the different AUCs. A P value < 0.05 was considered statistically significant.

RESULTS

The AUC of models 1-3 was 0.762, 0.829, and 0.915, respectively. The DeLong test showed a statistically significant difference between the AUCs of model 1 vs. model 3, while the differences between the AUCs of model 1 vs. model 2 (P = 0.253) and model 2 vs. model 3 (P = 0.075) were not statistically significant.

DATA CONCLUSION

¹⁸ F-FDG PET/MRI might show high predictive value for lung adenocarcinoma smaller than 3 cm with PI.

EVIDENCE LEVEL

1 TECHNICAL EFFICACY: Stage 2.

A radiomics nomogram for invasiveness prediction in lung adenocarcinoma manifesting as part-solid nodules with solid components smaller than 6 mm

Objective

To investigate whether radiomics can help radiologists and thoracic surgeons accurately predict invasive adenocarcinoma (IAC) manifesting as part-solid nodules (PSNs) with solid components <6 mm and provide a basis for rational clinical decision-making.

Materials and Methods

In total, 1,210 patients (mean age ± standard deviation: 54.28 ± 11.38 years, 374 men and 836 women) from our hospital and another hospital with 1,248 PSNs pathologically diagnosed with adenocarcinoma in situ (AIS), minimally invasive adenocarcinoma (MIA), or IAC were enrolled in this study. Among them, 1,050 cases from our hospital were randomly divided into a derivation set (n = 735) and an internal validation set (n = 315), 198 cases from another hospital were used for external validation. Each labeled nodule was segmented, and 105 radiomics features were extracted. Least absolute shrinkage and selection operator (LASSO) was used to calculate Rad-score and build the radiomics model. Multivariable logistic regression was conducted to identify the clinicoradiological predictors and establish the clinical-radiographic model. The combined model and predictive nomogram were developed based on identified clinicoradiological independent predictors and Rad-score using multivariable logistic regression analysis. The predictive performances of the three models were compared via receiver operating characteristic (ROC) curve analysis. Decision curve analysis (DCA) was performed on both the internal and external validation sets to evaluate the clinical utility of the nomogram.

Results

The radiomics model showed superior predictive performance than the clinical-radiographic model in both internal and external validation sets (Az values, 0.884 vs. 0.810, p = 0.001; 0.924 vs. 0.855, p < 0.001, respectively). The combined model showed comparable predictive performance to the radiomics model (Az values, 0.887 vs. 0.884, p = 0.398; 0.917 vs. 0.924, p = 0.271, respectively). The clinical application value of the nomogram developed based on the Rad-score, maximum diameter, and lesion shape was confirmed, and DCA demonstrated that application of the Rad-score would be beneficial for radiologists predicting invasive lesions.

Conclusions

Radiomics has the potential as an independent diagnostic tool to predict the invasiveness of PSNs with solid components <6 mm.

A Nomogram Combined Radiomics and Clinical Features as Imaging Biomarkers for Prediction of Visceral Pleural Invasion in Lung Adenocarcinoma

Objectives

To develop and validate a nomogram model based on radiomics features for preoperative prediction of visceral pleural invasion (VPI) in patients with lung adenocarcinoma.

Methods

A total of 659 patients with surgically pathologically confirmed lung adenocarcinoma underwent CT examination. All cases were divided into a training cohort (n = 466) and a validation cohort (n = 193). CT features were analyzed by two chest radiologists. CT radiomics features were extracted from CT images. LASSO regression analysis was applied to determine the most useful radiomics features and construct radiomics score (radscore). A nomogram model was developed by combining the optimal clinical and CT features and the radscore. The model performance was evaluated using ROC analysis, calibration curve and decision curve analysis (DCA).

Results

A total of 1316 radiomics features were extracted. A radiomics signature model with a selection of the six optimal features was developed to identify patients with or without VPI. There was a significant difference in the radscore between the two groups of patients. Five clinical features were retained and contributed as clinical feature models. The nomogram combining clinical features and radiomics features showed improved accuracy, specificity, positive predictive value, and AUC for predicting VPI, compared to the radiomics model alone (specificity: training cohort: 0.89, validation cohort: 0.88, accuracy: training cohort: 0.84, validation cohort: 0.83, AUC: training cohort: 0.89, validation cohort: 0.89). The calibration curve and decision curve analyses suggested that the nomogram with clinical features is beyond the traditional clinical and radiomics features.

Conclusion

A nomogram model combining radiomics and clinical features is effective in non-invasively prediction of VPI in patients with lung adenocarcinoma.

The combination of computed tomography features and circulating tumor cells increases the surgical prediction of visceral pleural invasion in clinical T1N0M0 lung adenocarcinoma

Background

Visceral pleural invasion (VPI) is a clinical manifestation associated with a poor prognosis, and diagnosing it preoperatively is highly imperative for successful sublobar resection of these peripheral tumors. We evaluated the roles of computed tomography (CT) features and circulating tumor cells (CTCs) for improving VPI detection in patients with clinical T1N0M0 invasive lung adenocarcinoma.

Methods

Three hundred and ninety-one patients were reviewed retrospectively in this study, of which 234 presented with a pleural tag or pleural contact on CT images. CTCs positive for the foliate receptors were enriched and analyzed prior to surgery. Logistic regression analyses were performed to assess the association of CT features and CTCs with VPI, and the receiver operating characteristic (ROC) curve was generated to compare the predictive power of these variables.

Results

Patients mostly underwent either segmentectomies (18.9%) or lobectomies (79.0%). Only 49 of the 234 patients with pleural involvement on CT showed pathologically confirmed VPI. Multivariate logistic regression analysis revealed that CTC level ≥10.42 FU/3 mL was a significant VPI risk factor for invasive adenocarcinoma cases ≤30 mm [adjusted odds ratio (OR) =4.62, 95% confidence interval (CI): 2.05–10.44, P<0.001]. Based on CT features, subgroup analyses showed that the solid portion size was a statistically significant independent predictor of VPI for these peripheral nodules with pleural tag, while the solid portion length of the interface was an independent predictor of pleural contact. The receiver operating curve analyses showed that the combination of CTC and CT features were highly predictive of VPI [area under the curve (AUC) =0.921 for pleural contact and 0.862 for the pleural tag, respectively].

Conclusions

CTC, combined with CT features of pleural tag or pleural contact, could significantly improve VPI detection in invasive lung adenocarcinomas at clinical T1N0M0 stage prior to the patient’s surgery.

The value of CT radiomics features to predict visceral pleural invasion in ≤3 cm peripheral type early non-small cell lung cancer

OBJECTIVE

To investigate predictive value of CT-based radiomics features on visceral pleural invasion (VPI) in ≤3.0 cm peripheral type early non-small cell lung cancer (NSCLC).

METHODS

A total of 221 NSCLC cases were collected. Among them, 115 are VPI-positive and 106 are VPI-negative. Using a stratified random sampling method, 70% cases were assigned to training dataset (n = 155) and 30% cases (n = 66) were assigned to validation dataset. First, CT findings, imaging features, clinical data and pathological findings were retrospectively analyzed, the size, location and density characteristics of nodules and lymph node status, the relationship between lesions and pleura (RAP) were assessed, and their mean CT value and the shortest distance between lesions and pleura (DLP) were measured. Next, the minimum redundancy-maximum relevance (mRMR) and least absolute shrinkage and selection operator (LASSO) features were extracted from the imaging features. Then, CT imaging prediction model, texture feature prediction model and joint prediction model were built using multifactorial logistic regression analysis method, and the area under the ROC curve (AUC) was applied to evaluate model performance in predicting VPI.

RESULTS

Mean diameter, density, fractal relationship with pleura, and presence of lymph node metastasis were all independent predictors of VPI. When applying to the validation dataset, the CT imaging model, texture feature model, and joint prediction model yielded AUC = 0.882, 0.824 and 0.894, respectively, indicating that AUC of the joint prediction model was the highest (p < 0.05).

CONCLUSION

The study demonstrates that the joint prediction model containing CT morphological features and texture features enables to predict the presence of VPI in early NSCLC preoperatively at the highest level.

CT texture analysis-based nomogram for the preoperative prediction of visceral pleural invasion in cT1N0M0 lung adenocarcinoma: an external validation cohort study

AIM

To develop a nomogram based on computed tomography (CT) texture analysis for the preoperative prediction of visceral pleural invasion in patients with cT1N0M0 lung adenocarcinoma.

MATERIALS AND METHODS

A dataset of chest CT containing lung nodules was collected from two institutions, and all surgically resected nodules were classified pathologically based on the presence of visceral pleural invasion. Each nodule on the CT image was segmented automatically by artificial-intelligence software and its CT texture features were extracted. The dataset was divided into training and external validation cohorts according to the institution, and a nomogram for predicting visceral pleural invasion was developed and validated.

RESULTS

Of a total of 313 patients enrolled from two independent institutions, 63 were diagnosed with visceral pleural invasion. Three-dimensional (3D) CT long diameter, skewness, and sphericity, and chronic obstructive pulmonary disease were identified as independent predictors for visceral pleural invasion by multivariable logistic regression. The nomogram based on multivariable logistic regression showed great discriminative ability, as indicated by a C-index of 0.890 (95% confidence interval [CI]: 0.867-0.914) and 0.864 (95% CI: 0.817-0.911) for the training and external validation cohorts, respectively. Additionally, calibration of the nomogram revealed good predictive ability, as indicated by the Brier score (0.108 and 0.100 for the training and external validation cohorts, respectively).

CONCLUSIONS

A nomogram was developed that could compute the probability of visceral pleural invasion in patients with cT1N0M0 lung adenocarcinoma with good calibration and discrimination. The nomogram has potential as a reliable tool for clinical evaluation and decision-making.

Sublobar Resection in Stage IA Non-Small Cell Lung Cancer: Role of Preoperative CT Features in Predicting Pathologic Lymphovascular Invasion and Postoperative Recurrence

BACKGROUND. Prognostic factors on preoperative CT in stage IA non-small cell lung cancer (NSCLC) may help select patients for sublobar resection or lobectomy. OBJECTIVE. The purpose of this study was to identify CT features predictive of pathologic lymphovascular invasion (LVI) in stage IA NSCLC and to evaluate the features' prognostic value in patients who undergo sublobar resection. METHODS. This retrospective study included 904 patients (mean age, 62.0 years; 453 men, 451 women) who underwent lobectomy (n = 574) or sublobar resection (n = 330) for stage IA NSCLC. Two thoracic radiologists independently evaluated findings on pre-operative chest CT and then resolved discrepancies. Recurrences were identified from medical record review. Multivariable logistic regression was used to identify independent predictors of pathologic LVI. Multivariable Cox proportional hazards models were used to identify prognostic features. Interreader agreement was assessed. RESULTS. Pathologic LVI was present in 10.2% (92/904) of patients. It was present only in solid-dominant part-solid nodules (PSNs) and solid nodules and only in nodules with a solid portion diameter over 10 mm. Among solid-dominant PSNs and solid nodules with a solid portion diameter over 10 mm, independent (p < .05) predictors of pathologic LVI were peritumoral interstitial thickening (odds ratio [OR], 13.22) and pleural contact (defined as pleural contact measuring over one-quarter of the circumference of the nodule's solid portion) (OR, 2.45). Also among such nodules, peritumoral interstitial thickening achieved 80.4% sensitivity, 76.7% specificity, and 77.4% accuracy; pleural contact achieved 35.9% sensitivity, 82.5% specificity, and 74.3% accuracy; and presence of either feature achieved 90.2% sensitivity, 64.3% specificity, and 68.9% accuracy for predicting pathologic LVI. In patients undergoing sublobar resection, after adjusting for T category and operative type, recurrence-free survival (RFS) was independently (p < .05) predicted by solid-dominant PSN or solid nodule with a solid portion diameter over 10 mm also showing peritumoral interstitial thickening (hazard ratio [HR], 5.37) or also showing either peritumoral interstitial thickening or pleural contact (HR, 6.05). The interreader agreement kappa values were 0.67 for peritumoral interstitial thickening and 0.77 for pleural contact. CONCLUSION. Pathologic LVI occurred only in solid-dominant PSNs and solid nodules with solid portion over 10 mm. Among such nodules, peritumoral interstitial thickening and pleural contact independently predicted pathologic LVI and RFS. CLINICAL IMPACT. CT features may help select patients with stage IA NSCLC for sublobar resection rather than more extensive surgery.

Ultrasound-Guided Percutaneous Core Needle Biopsy of Peripheral Pulmonary Nodules ≤ 2 cm: Diagnostic Performance, Safety and Influence Factors

Purpose

To evaluate diagnostic performance and safety of ultrasound-guided needle biopsy in the diagnosis of peripheral pulmonary nodules (PPLs) ≤ 2 cm, and the influence factors of sample adequacy and safety.

Materials and Methods

194 patients (99 men, 95 women; mean age, 56.2 ± 13.7 years) who received biopsy for PPLs ≤ 2 cm between January 2014 to January 2019 were included. Variables including patient demographics, lesion location, lesion size, presence of lesion necrosis, presence of emphysema on CT, patient position, biopsy needle size and number of needle passes were recorded. Univariate analysis and multivariate logistic regression analysis were performed to explore the influence factor of sample adequacy and safety.

Results

Biopsy specimens were adequate for diagnosis in 161/194 (83%) cases; the diagnostic accuracy was 81.4% (158/194). The overall complication rate was 8.8% (17/194), including pneumothorax, hemoptysis and pleural effusion, which occurred in 2.1% (4/194), 5.2% (10/194), and 1.5% (3/194) of patients, respectively. The incidence of pneumothorax in the 16-gauge-needle group were significantly higher than that of the 18-gauge-needle group (5.6% vs 0%, P=0.018). Adequate sampling of 16-gauge and 18-gauge needles were achieved in 90.3%(65/72) and 78.7%(96/122) cases, respectively. Multivariate logistic regression analysis revealed needle size (16-gauge vs 18-gauge) was an independent influence factors of sample adequacy (P=0.015, odds ratio=3.419). A receiver operating characteristic curve was plotted and the area under the curve was 0.774.

Conclusion

US-guided percutaneous needle biopsy is a feasible and safe technique for small PPLs ≤ 2 cm. Needle size is an independent influence factor of sample adequacy and post-procedure pneumothorax. Sixteen-gauge needle has the advantage of achieving adequate sample for pathological analysis, though the risk of pneumothorax should be alerted.

Prediction of visceral pleural invasion in lung cancer on CT: deep learning model achieves a radiologist-level performance with adaptive sensitivity and specificity to clinical needs

OBJECTIVES

To develop and validate a preoperative CT-based deep learning model for the prediction of visceral pleural invasion (VPI) in early-stage lung cancer.

METHODS

In this retrospective study, dataset 1 (for training, tuning, and internal validation) included 676 patients with clinical stage IA lung adenocarcinomas resected between 2009 and 2015. Dataset 2 (for temporal validation) included 141 patients with clinical stage I adenocarcinomas resected between 2017 and 2018. A CT-based deep learning model was developed for the prediction of VPI and validated in terms of discrimination and calibration. An observer performance study and a multivariable regression analysis were performed.

RESULTS

The area under the receiver operating characteristic curve (AUC) of the model was 0.75 (95% CI, 0.67-0.84), which was comparable to those of board-certified radiologists (AUC, 0.73-0.79; all p > 0.05). The model had a higher standardized partial AUC for a specificity range of 90 to 100% than the radiologists (all p < 0.05). The high sensitivity cutoff (0.245) yielded a sensitivity of 93.8% and a specificity of 31.2%, and the high specificity cutoff (0.448) resulted in a sensitivity of 47.9% and a specificity of 86.0%. Two of the three radiologists provided highly sensitive (93.8% and 97.9%) but not specific (48.4% and 40.9%) diagnoses. The model showed good calibration (p > 0.05), and its output was an independent predictor for VPI (adjusted odds ratio, 1.07; 95% CI, 1.03-1.11; p < 0.001).

CONCLUSIONS

The deep learning model demonstrated a radiologist-level performance. The model could achieve either highly sensitive or highly specific diagnoses depending on clinical needs.

KEY POINTS

• The preoperative CT-based deep learning model demonstrated an expert-level diagnostic performance for the presence of visceral pleural invasion in early-stage lung cancer. • Radiologists had a tendency toward highly sensitive, but not specific diagnoses for the visceral pleural invasion.

Accessory and Incomplete Lung Fissures: Clinical and Histopathologic Implications

OBJECTIVE

This article reviews the anatomy, histology, and disease processes of pulmonary fissures, with emphasis on clinical implications of accessory and incomplete fissures.

CONCLUSION

Accessory and incomplete pulmonary fissures are often overlooked during routine imaging but can have profound clinical importance. Knowledge of fissure anatomy could improve diagnostic accuracy and inform prognosis for oncologists, interventional pulmonologists, and thoracic surgeons.

The new 8th TNM staging system of lung cancer and its potential imaging interpretation pitfalls and limitations with CT image demonstrations

The tumor, node, metastasis (TNM) staging system approved by International Association for the Study of Lung Cancer (IASLC) and the American Joint Committee on Cancer (AJCC) to stage lung cancer was recently revised. The latest revision is the 8th edition published in January, 2017. This new edition made some important changes to the previous edition, including modification of the T classification based on 1 cm increment, downstage of T descriptor including endobronchial tumor disregarding its distance from carina (T2), merging total and partial atelectasis/pneumonitis into the same T category (T2), upstage diaphragmatic invasion to T4, new classification concept of adenocarcinoma in situ and minimally invasive adenocarcinoma for pure and part-solid ground-glass nodules, and further division of extrathoracic metastasis into M1b and M1c based on the number and sites of extrathoracic metastases. Consensus is reached for debating situations not covered in the previous edition of staging system, such as the classification of pancoast tumor based on its invasion depth and staging tumors that extend directly across the fissure as T2a. Classification of multiple sites of pulmonary involvement, including multiple primary lung cancer, separate lung cancer nodules, multiple ground-glass or lepidic lesions, and consolidation, is also discussed. Even though the 8th edition of the TNM lung staging system provides us with more precise classification based on prognostic analysis of each TNM descriptors, there are still some potential limitations and clinical situations that have not yet been clarified in terms of clinical staging by imaging. It is important for radiologists to understand the major changes introduced in the 8th edition of TNM staging and to recognize the potential pitfalls and limitations of imaging interpretation to precisely classify the clinical stage of lung cancer.

Visceral Pleural Invasion in Pulmonary Adenocarcinoma: Differences in CT Patterns between Solid and Subsolid Cancers

PURPOSE

To analyze the incidence and CT patterns of visceral pleural invasion (VPI) in adenocarcinomas on the basis of their CT presentation as solid or subsolid nodules.

MATERIALS AND METHODS

A total of 286 adenocarcinomas in direct contact with a pleural surface, resected at an institution between 2005 and 2016, were included in this retrospective, institutional review board-approved study. CT size and longest contact length with a pleural surface were measured and their ratios computed. Pleural deviation, pleural thickening, spiculations, different pleural tag types, pleural effusion, and the CT appearance of transgression into an adjacent lobe or infiltration of surrounding tissue were evaluated. Fisher exact tests and simple and multiple logistic regression models were used.

RESULTS

Of the 286 nodules, 179 of 286 (62.6%) were solid and 107 of 286 (37.4%) were subsolid. VPI was present in 49 of 286 (17.1%) nodules and was significantly more frequent in solid (44 of 179; 24.6%) than in subsolid nodules (five of 107; 4.7%; P < .001). In solid nodules, multiple regression analysis showed an association of higher contact length-to-size ratio (adjusted odds ratio [OR], 1.02; P = .007) and the presence of multiple pleural tag types (adjusted OR, 5.88; P = .002) with VPI. In subsolid nodules, longer pleural contact length of the solid nodular component (adjusted OR, 1.27; P = .017) and the CT appearance of transgression or infiltration (adjusted OR, 10.75; P = .037) were associated with VPI.

CONCLUSION

During preoperative evaluation of adenocarcinomas for the likelihood of VPI, whether a tumor manifests as a solid or a subsolid nodule is important to consider because the incidence of VPI is significantly higher in solid than in subsolid nodules. In addition, this study showed that the CT patterns associated with VPI differ between solid and subsolid nodules.© RSNA, 2019Supplemental material is available for this article.See also the commentary by Elicker in this issue.

Clinical Significance of Pleural Attachment and Indentation of Subsolid Nodule Lung Cancer

Purpose

Lung cancers presenting as subsolid nodule commonly have peripheral location, making the cancer-pleura relationship noteworthy. We aimed to evaluate the effect of pleural attachment and/or indentation on visceral pleural invasion (VPI) and recurrence-free survival.

Materials and Methods

Patients who underwent curative resection of lung cancer as subsolid nodules from April 2007 to January 2016 were retrospectively evaluated. They were divided into four groups according to their relationship with the pleura. Clinical, radiographical, and pathological findings were analyzed.

Results

Among 404 patients with malignant subsolid nodule, 120 (29.7%) had neither pleural attachment nor indentation, 26 (6.4%) had attachment only, 117 (29.0%) had indentation only, and 141 (34.9%) had both. VPI was observed in nodules of 36 patients (8.9%), but absent in nonsolid nodules and in those without pleural attachment and/or indentation. Compared to subsolid nodules with concurrent pleural attachment and indentation, those with attachment only (odds ratio, 0.12; 95% confidence interval [CI], 0.02 to 0.98) and indentation only (odds ratio, 0.10; 95% CI, 0.03 to 0.31) revealed lower odds of VPI. On subgroup analysis, the size of the solid portion was associated with VPI among those with pleural attachment and indentation (p=0.021). Such high-risk features for VPI were associated with earlier lung cancer recurrence (adjusted hazard ratio, 3.31; 95% CI, 1.58 to 6.91).

Conclusion

Concurrent pleural attachment and indentation are risk factors for VPI, and the odds increase with larger solid portion in subsolid nodules. Considering the risk of recurrence, early surgical resection could be encouraged in these patients.

Pleural contact decreases survival in clinical T1N0M0 lung cancer patients undergoing SBRT

BACKGROUND

Clinical staging, as used for patients treated with stereotactic body radiotherapy (SBRT) for early-stage lung cancer, inadequately accounts for pleural invasion, which is a pathologic criteria. Considering the current situation, we analyzed effects of relationships between tumors and the pleura on treatment outcomes of SBRT for early-stage lung cancer.

MATERIALS AND METHODS

Among consecutive patients treated with SBRT between 2006 and 2017, we retrospectively identified non-small cell lung cancer patients with primary tumor diameters ≤4 cm and N0M0. The relationships between tumors and the pleura were investigated. The effects of these findings on treatment outcomes were analyzed.

RESULTS

We identified 386 patients which met the inclusion criteria. Among these patients, 323 patients were with tumors of 0.1-3.0 cm (T1-size), and 63 patients were with tumors of 3.1-4.0 cm (T2a-size). Among patients with T1-size tumors, 120, 134, and 23 had findings of pleural contact, pleural indentation, and pleural thickening, respectively. When we divided T1-size patients into 2 groups based on pleural contact (contact- or contact+), the 3-year cause-specific mortality and overall survival in patients with T1-size & contact+ were significantly worse than those in patients with T1-size & contact- (17.6% (95% confidence interval (CI), 10.7-25.9%) vs. 6.6% (95% CI, 3.5-11.1%), p < 0.01), and 58.2% (95% CI, 47.6-67.5%) vs. 77.6% (95% CI, 70.5-83.2%), p < 0.01). Local recurrence, regional recurrence, pleural cavity recurrence, and distant metastasis were associated with worse cause-specific mortality and overall survival. On multivariate analysis, pleural contact was associated with cause-specific mortality (hazard ratio (HR), 1.96; 95% CI, 1.09-3.52; p = 0.03) and overall survival (HR, 1.59; 95% CI, 1.08-2.34; p = 0.02).

CONCLUSION

Pleural contact in clinical T1N0M0 lung cancer patients was associated with significantly worse survivals.

Dilemmas in Lung Cancer Staging

The advent of the 8th edition of the lung cancer staging system reflects a further meticulous evidence-based advance in the stratification of the survival of patients with lung cancer. Although addressing many limitations of earlier staging systems, several limitations in staging remain. This article reviews from a radiological perspective the limitations of the current staging system, highlighting the process of TNM restructuring, the residual issues with regards to the assignment of T, N, M descriptors, and their associated stage groupings and how these dilemmas impact guidance of multidisciplinary teams taking care of patients with lung cancer.