Predictive model for the probability of malignancy in solitary pulmonary nodules: a meta-analysis

Prediction of Malignancy and Pathological Types of Solid Lung Nodules on CT Scans Using a Volumetric SWIN Transformer

Lung adenocarcinoma and squamous cell carcinoma are the two most common pathological lung cancer subtypes. Accurate diagnosis and pathological subtyping are crucial for lung cancer treatment. Solitary solid lung nodules with lobulation and spiculation signs are often indicative of lung cancer; however, in some cases, postoperative pathology finds benign solid lung nodules. It is critical to accurately identify solid lung nodules with lobulation and spiculation signs before surgery; however, traditional diagnostic imaging is prone to misdiagnosis, and studies on artificial intelligence-assisted diagnosis are few. Therefore, we introduce a volumetric SWIN Transformer-based method. It is a multi-scale, multi-task, and highly interpretable model for distinguishing between benign solid lung nodules with lobulation and spiculation signs, lung adenocarcinomas, and lung squamous cell carcinoma. The technique's effectiveness was improved by using 3-dimensional (3D) computed tomography (CT) images instead of conventional 2-dimensional (2D) images to combine as much information as possible. The model was trained using 352 of the 441 CT image sequences and validated using the rest. The experimental results showed that our model could accurately differentiate between benign lung nodules with lobulation and spiculation signs, lung adenocarcinoma, and squamous cell carcinoma. On the test set, our model achieves an accuracy of 0.9888, precision of 0.9892, recall of 0.9888, and an F1-score of 0.9888, along with a class activation mapping (CAM) visualization of the 3D model. Consequently, our method could be used as a preoperative tool to assist in diagnosing solitary solid lung nodules with lobulation and spiculation signs accurately and provide a theoretical basis for developing appropriate clinical diagnosis and treatment plans for the patients.

CT radiomics based model for differentiating malignant and benign small (≤20mm) solid pulmonary nodules

Background

Currently, the computed tomography (CT) radiomics-based models, which can evaluate small (≤ 20 mm) solid pulmonary nodules (SPNs) are lacking. This study aimed to develop a CT radiomics-based model that can differentiate between benign and malignant small SPNs.

Methods

This study included patients with small SPNs between January 2019 and November 2021. The participants were then randomly categorized into training and testing cohorts with an 8:2 ratio. CT images of all the patients were analyzed to extract radiomics features. Furthermore, a radiomics scoring model was developed based on the features selected in the training group via univariate and multivariate logistic regression analyses. The testing cohort was then used to validate the developed predictive model.

Results

This study included 210 patients, 168 in the training and 42 in the testing cohorts. Radiomics scores were ultimately calculated based on 9 selected CT radiomics features. Furthermore, traditional CT and clinical risk factors associated with SPNs included lobulation (P < 0.001), spiculation (P < 0.001), and a larger diameter (P < 0.001). The developed CT radiomics scoring model comprised of the following formula: X = -6.773 + 12.0705×radiomics score+2.5313×lobulation (present: 1; no present: 0)+3.1761×spiculation (present: 1; no present: 0)+0.3253×diameter. The area under the curve (AUC) values of the CT radiomics-based model, CT radiomics score, and clinicoradiological score were 0.957, 0.945, and 0.853, respectively, in the training cohort, while that of the testing cohort were 0.943, 0.916, and 0.816, respectively.

Conclusions

The CT radiomics-based model designed in the present study offers valuable diagnostic accuracy in distinguishing benign and malignant SPNs.

18F-FDG PET/CT based model for predicting malignancy in pulmonary nodules: a meta-analysis

BACKGROUND

Several studies to date have reported on the development of positron emission tomography (PET)/computed tomography (CT)-based models intended to effectively distinguish between benign and malignant pulmonary nodules (PNs). This meta-analysis was designed with the goal of clarifying the utility of these PET/CT-based conventional parameter models as diagnostic tools in the context of the differential diagnosis of PNs.

METHODS

Relevant studies published through September 2023 were identified by searching the Web of Science, PubMed, and Wanfang databases, after which Stata v 12.0 was used to conduct pooled analyses of the resultant data.

RESULTS

This meta-analysis included a total of 13 retrospective studies that analyzed 1,731 and 693 malignant and benign PNs, respectively. The respective pooled sensitivity, specificity, PLR, and NLR values for the PET/CT-based studies developed in these models were 88% (95%CI: 0.86-0.91), 78% (95%CI: 0.71-0.85), 4.10 (95%CI: 2.98-5.64), and 0.15 (95%CI: 0.12-0.19). Of these endpoints, the pooled analyses of model sensitivity (I2 = 69.25%), specificity (I2 = 78.44%), PLR (I2 = 71.42%), and NLR (I2 = 67.18%) were all subject to significant heterogeneity. The overall area under the curve value (AUC) value for these models was 0.91 (95%CI: 0.88-0.93). When differential diagnosis was instead performed based on PET results only, the corresponding pooled sensitivity, specificity, PLR, and NLR values were 92% (95%CI: 0.85-0.96), 51% (95%CI: 0.37-0.66), 1.89 (95%CI: 1.36-2.62), and 0.16 (95%CI: 0.07-0.35), with all four being subject to significant heterogeneity (I2 = 88.08%, 82.63%, 80.19%, and 86.38%). The AUC for these pooled analyses was 0.82 (95%CI: 0.79-0.85).

CONCLUSIONS

These results suggest that PET/CT-based models may offer diagnostic performance superior to that of PET results alone when distinguishing between benign and malignant PNs.

Computed tomography-guided biopsy for sub-centimetre pulmonary nodules: a meta-analysis

Introduction

Pulmonary nodules (PNs) with a diameter from 5 to 10 mm exhibit malignancy rates anywhere from 47.5 to 61.5%. Despite the potential danger posed by these lesions, their small size makes the biopsy of these sub-centimetre (≤ 10 mm) PNs under computed tomography (CT) guidance very difficult.

Aim

A meta-analysis was performed with the goal of evaluating the safety and diagnostic utility of CT-guided biopsy procedures for sub-centimetre PNs.

Material and methods

Relevant studies published through April 2023 were identified in the PubMed, Web of Science, and Wanfang databases and used to conduct pooled analyses of selected endpoints, including technical success, diagnostic yield, diagnostic accuracy, pulmonary haemorrhage, and pneumothorax rates.

Results

In total, this meta-analysis incorporated 10 studies in which 1482 patients with sub-centimetre PNs underwent CT-guided biopsy procedures. Among these patients, the respective pooled rates of technical success, diagnostic yield, diagnostic accuracy, pulmonary haemorrhage, and pneumothorax were 90%, 60%, 91%, 11%, and 24%, and significant heterogeneity was detected for all of these endpoints (I2 = 93.6%, 96%, 76.9%, 80.8%, and 93.6%). A substantial difference in diagnostic accuracy was observed when comparing biopsy procedures performed using fine- and core-needle biopsy approaches (85% vs. 95%), whereas the use of the co-axial method or the selected guidance approach (conventional vs. cone-beam CT) had no impact on diagnostic accuracy. Needle type, guidance method, and co-axial method use had no impact on the rates of pulmonary haemorrhage or pneumothorax.

Conclusions

CT-guided biopsy represents a safe and effective means of accurately diagnosing sub-centimetre PNs.