Identification of pulmonary adenocarcinoma and benign lesions in isolated solid lung nodules based on a nomogram of intranodal and perinodal CT radiomic features

Establishing predictive models for malignant and inflammatory pulmonary nodules using clinical data and CT imaging features

Background

The detection of pulmonary nodules has become increasingly common; however, accurate qualitative diagnosis remains a clinical challenge. This study sought to distinguish between malignant and inflammatory solid lung nodules using clinical data and computed tomography (CT) imaging features.

Methods

A total of 948 patients with pulmonary nodules who underwent surgery or percutaneous biopsy from four centers were included in the study. The patients were divided into the following four groups based on nodule diameter: Group 1: nodules ≤10 mm; Group 2: nodules >10 and ≤20 mm; Group 3: nodules >20 and ≤30 mm; and Group 4: all nodules. The independent risk factors were identified and merged by univariate and multivariate analyses in the four groups to establish four models. The overall performance of the four models was evaluated using the area under the curve (AUC) of the receiver operating characteristic curve. Differences between Models 1-3 and Model 4 were compared using the DeLong test.

Results

Of the nodules, 638 were classified as malignant and 310 as inflammatory. The patients with malignant and inflammatory nodules had median ages of 64.3±9.8 and 56.0±11.9 years, respectively (P<0.001). To build the four models, 17 features were identified, of which 2 were clinical features and 15 were imaging features. Notably, the frequency of lobulation, age, multiple lesions, and satellite lesions was relatively high in the four models. The AUC, accuracy, sensitivity, and specificity of Models 1-4 were 0.861 (0.803-0.921), 73.5%, 81.0%, and 78.9%; 0.902 (0.873-0.931), 82.8%, 74.7%, and 88.0%; 0.943 (0.914-0.972), 90.5%, 87.3%, and 89.7%; and 0.921 (0.903-0.940), 84.7%, 83.1%, and 86.8%; respectively. However, there were no statistically significant differences between Models 1-3 and Model 4.

Conclusions

Our novel subgrouping models were able to effectively distinguish between inflammatory and malignant lung nodules using a reduced feature set. Our models could facilitate the accurate diagnosis of patients with potentially malignant lesions.

Risk factors for malignant solid pulmonary nodules: a meta-analysis

BACKGROUND

Previous studies have indicated that clinical and imaging features may assist in distinguishing between benign and malignant solid lung nodules. Yet, the specific characteristics in question continue to be debated. This meta-analysis aims to identify risk factors for malignant solid lung nodules, thereby supporting informed clinical decision-making.

METHODS

A comprehensive search of databases including PubMed, Embase, Web of Science, Cochrane Library, Scopus, Wanfang, CNKI, VIP, and CBM was conducted up to October 6, 2024. Only publications in Chinese or English were considered. Data analysis was performed using Stata 16.0 software.

RESULTS

This analysis included 32 studies, comprising 7758 solid pulmonary nodules, of which 3359 were benign and 4399 were malignant. It was found that the incidence of spiculate signs in malignant solid pulmonary nodules (MSPN) was higher than in benign solid pulmonary nodules (BSPN) [OR = 3.06, 95% CI (2.35, 3.98), P < 0.05. Additionally, increases were observed in the incidences of vascular convergence[OR = 16.57, 95% CI (8.79, 31.24), P < 0.05], lobulated signs [OR = 5.17, 95% CI (3.83, 6.98)], air bronchogram sign[OR = 2.96, 95% CI (1.62, 5.41), P < 0.05], pleura traction sign [OR = 2.33, 95% CI (1.65, 3.29), P < 0.05], border blur [OR = 2.94, 95% CI (1.47, 5.85), P < 0.05], vacuole signs [OR = 5.25, 95% CI (2.66, 10.37), P < 0.05], and family history of cancer [OR = 3.85, 95% CI (2.43, 6.12), P < 0.05] compared to BSPN. Older age[OR = 1.06, 95% CI (1.04, 1.07), P < 0.05], higher prevalence in females [OR = 2.98, 95% CI (2.27, 3.92), P < 0.05], larger nodule diameters [OR = 1.25, 95% CI (1.13, 1.38), P < 0.05], and lower incidence of calcification [OR = 0.21, 95% CI (0.10, 0.48), P < 0.05] were also associated with MSPN. No significant differences were found between MSPN and BSPN regarding CEA and emphysema (all P > 0.05).

CONCLUSIONS

This meta-analysis highlights that spiculate sign, vascular convergence sign, lobulated sign, diameter, border blur, vacuole sign, age, gender, family history of cancer, pleura traction, air bronchogram sign, and calcification are significant markers for predicting malignancy in SPNs, potentially influencing clinical management. However, further well-designed, large-scale studies are needed to confirm these findings.

CT and MRI bimodal radiomics for predicting EGFR status in NSCLC patients with brain metastases: A multicenter study

BACKGROUND

Leveraging the radiomics information from non-small cell lung cancer (NSCLC) primary lesion and brain metastasis (BM) to develop and validate a bimodal radiomics nomogram that can accurately predict epidermal growth factor receptor (EGFR) status.

METHODS

A total of 309 NSCLC patients with BM from three independent centers were recruited. Among them, the patients of Center I were randomly allocated into the training and internal test cohorts in a 7:3 ratio. Meanwhile, the patients from Center Ⅱ and Center Ⅲ collectively constitute the external test cohort. All chest CT and brain MRI images of each patient were obtained for image registration and sequence combination within a single modality. After image preprocessing, 1037 radiomics features were extracted from each single sequence. Six machine learning algorithms were used to construct radiomics signatures for CT and MRI respectively. The best CT and MRI radiomics signatures were fitted to establish the bimodal radiomics nomogram for predicting the EGFR status.

RESULTS

The contrast-enhanced (CE) eXtreme gradient boosting (XG Boost) and T2-weighted imaging (T2WI) + T1-weighted contrast-enhanced imaging (T1CE) random forest models were chosen as the radiomics signature representing primary lesion and BM. Both models were found to be independent predictors of EGFR mutation. The bimodal radiomics nomogram, which incorporated CT radiomics signature and MRI radiomics signature, demonstrated a good calibration and discrimination in the internal test cohort [area under curve (AUC), 0.866; 95 % confidence intervals (CI), 0.778-0.950) and the external test cohort (AUC, 0.818; 95 % CI, 0.691-0.938).

CONCLUSIONS

Our CT and MRI bimodal radiomics nomogram could timely and accurately evaluate the likelihood of EGFR mutation in patients with limited access to necessary materials, thus making up for the shortcoming of plasma sequencing and promoting the advancement of precision medicine.

Development of a nomogram-based model incorporating radiomic features from follow-up longitudinal lung CT images to distinguish invasive adenocarcinoma from benign lesions: a retrospective study

PURPOSE

To develop and validate a radiomic model for differentiating pulmonary invasive adenocarcinomas from benign lesions based on follow-up longitudinal CT images.

METHODS

This is a retrospective study including 336 patients (161 with invasive adenocarcinomas and 175 with benign lesions) who underwent baseline (T0) and follow-up (T1) CT scans from January 2016 to June 2022. The patients were randomized in a 7:3 ratio into training and test sets. Radiomic features were extracted from lesion volumes of interest on longitudinal CT images at T0 and T1. Differences in radiomic features between T1 and T0 were defined as delta-radiomic features. Logistic regression was used to build models based on clinicoradiological (CR), T0, T1, and delta radiomic features and compute signatures. Finally, a nomogram based on the CR, T0, T1 and delta signatures was constructed. Model performance was evaluated for calibration, discrimination, and clinical utility.

RESULTS

The T1 radiomic model was superior to the other independent models. In the training set, it had an area under the curve (AUC) of 0.858), superior to the CR model (AUC 0.694), the T0 radiomic model (AUC 0.825), and the delta radiomic model (AUC 0.734). In the test set, it had an AUC of 0.817, again outperforming the CR model (AUC 0.578), the T0 radiomic model (AUC 0.789), and the delta radiomic model (AUC 0.647). The nomogram incorporating the CR, T0, T1 and delta signatures showed the best predictive performance in both the training (AUC: 0.906) and test sets (AUC: 0.856), and it exhibited excellent fit with calibration curves. Decision curve analysis provided additional validation of the clinical utility of the nomogram.

CONCLUSION

A nomogram utilizing radiomic features extracted from longitudinal CT images can enhance the discriminative capability between pulmonary invasive adenocarcinomas and benign lesions.

Predictive value of radiomic features extracted from primary lung adenocarcinoma in forecasting thoracic lymph node metastasis: a systematic review and meta-analysis

BACKGROUND

The application of radiomics in thoracic lymph node metastasis (LNM) of lung adenocarcinoma is increasing, but diagnostic performance of radiomics from primary tumor to predict LNM has not been systematically reviewed. Therefore, this study sought to provide a general overview regarding the methodological quality and diagnostic performance of using radiomic approaches to predict the likelihood of LNM in lung adenocarcinoma.

METHODS

Studies were gathered from literature databases such as PubMed, Embase, the Web of Science Core Collection, and the Cochrane library. The Radiomic Quality Score (RQS) and the Quality Assessment of Diagnostic Accuracy Studies-2 (QUADAS-2) were both used to assess the quality of each study. The pooled sensitivity, specificity, and area under the curve (AUC) of the best radiomics models in the training and validation cohorts were calculated. Subgroup and meta-regression analyses were also conducted.

RESULTS

Seventeen studies with 159 to 1202 patients each were enrolled between the years of 2018 to 2022, of which ten studies had sufficient data for the quantitative evaluation. The percentage of RQS was between 11.1% and 44.4% and most of the studies were considered to have a low risk of bias and few applicability concerns in QUADAS-2. Pyradiomics and logistic regression analysis were the most commonly used software and methods for radiomics feature extraction and selection, respectively. In addition, the best prediction models in seventeen studies were mainly based on radiomics features combined with non-radiomics features (semantic features and/or clinical features). The pooled sensitivity, specificity, and AUC of the training cohorts were 0.84 (95% confidence interval (CI) [0.73-0.91]), 0.88 (95% CI [0.81-0.93]), and 0.93(95% CI [0.90-0.95]), respectively. For the validation cohorts, the pooled sensitivity, specificity, and AUC were 0.89 (95% CI [0.82-0.94]), 0.86 (95% CI [0.74-0.93]) and 0.94 (95% CI [0.91-0.96]), respectively.

CONCLUSIONS

Radiomic features based on the primary tumor have the potential to predict preoperative LNM of lung adenocarcinoma. However, radiomics workflow needs to be standardized to better promote the applicability of radiomics.

TRIAL REGISTRATION

CRD42022375712.

Development of a combined radiomics and CT feature-based model for differentiating malignant from benign subcentimeter solid pulmonary nodules

BACKGROUND

We aimed to develop a combined model based on radiomics and computed tomography (CT) imaging features for use in differential diagnosis of benign and malignant subcentimeter (≤ 10 mm) solid pulmonary nodules (SSPNs).

METHODS

A total of 324 patients with SSPNs were analyzed retrospectively between May 2016 and June 2022. Malignant nodules (n = 158) were confirmed by pathology, and benign nodules (n = 166) were confirmed by follow-up or pathology. SSPNs were divided into training (n = 226) and testing (n = 98) cohorts. A total of 2107 radiomics features were extracted from contrast-enhanced CT. The clinical and CT characteristics retained after univariate and multivariable logistic regression analyses were used to develop the clinical model. The combined model was established by associating radiomics features with CT imaging features using logistic regression. The performance of each model was evaluated using the area under the receiver-operating characteristic curve (AUC).

RESULTS

Six CT imaging features were independent predictors of SSPNs, and four radiomics features were selected after a dimensionality reduction. The combined model constructed by the logistic regression method had the best performance in differentiating malignant from benign SSPNs, with an AUC of 0.942 (95% confidence interval 0.918-0.966) in the training group and an AUC of 0.930 (0.902-0.957) in the testing group. The decision curve analysis showed that the combined model had clinical application value.

CONCLUSIONS

The combined model incorporating radiomics and CT imaging features had excellent discriminative ability and can potentially aid radiologists in diagnosing malignant from benign SSPNs.

RELEVANCE STATEMENT

The model combined radiomics features and clinical features achieved good efficiency in predicting malignant from benign SSPNs, having the potential to assist in early diagnosis of lung cancer and improving follow-up strategies in clinical work.

KEY POINTS

• We developed a pulmonary nodule diagnostic model including radiomics and CT features. • The model yielded the best performance in differentiating malignant from benign nodules. • The combined model had clinical application value and excellent discriminative ability. • The model can assist radiologists in diagnosing malignant from benign pulmonary nodules.

Endoscopic Technologies for Peripheral Pulmonary Lesions: From Diagnosis to Therapy

Peripheral pulmonary lesions (PPLs) are frequent incidental findings in subjects when performing chest radiographs or chest computed tomography (CT) scans. When a PPL is identified, it is necessary to proceed with a risk stratification based on the patient profile and the characteristics found on chest CT. In order to proceed with a diagnostic procedure, the first-line examination is often a bronchoscopy with tissue sampling. Many guidance technologies have recently been developed to facilitate PPLs sampling. Through bronchoscopy, it is currently possible to ascertain the PPL's benign or malignant nature, delaying the therapy's second phase with radical, supportive, or palliative intent. In this review, we describe all the new tools available: from the innovation of bronchoscopic instrumentation (e.g., ultrathin bronchoscopy and robotic bronchoscopy) to the advances in navigation technology (e.g., radial-probe endobronchial ultrasound, virtual navigation, electromagnetic navigation, shape-sensing navigation, cone-beam computed tomography). In addition, we summarize all the PPLs ablation techniques currently under experimentation. Interventional pulmonology may be a discipline aiming at adopting increasingly innovative and disruptive technologies.