China lung cancer screening (CLUS) version 2.0 with new techniques implemented: Artificial intelligence, circulating molecular biomarkers and autofluorescence bronchoscopy.

OBJECTIVE: The present study, CLUS version 2.0, was conducted to evaluate the performance of new techniques in improving the implementation of lung cancer screening and to validate the efficacy of LDCT in reducing lung cancer-specific mortality in a high-risk Chinese population. METHODS: From July 2018 to February 2019, high-risk participants from six screening centers in Shanghai were enrolled in our study. Artificial intelligence, circulating molecular biomarkers and autofluorescencebronchoscopy were applied during screening. RESULTS: A total of 5087 eligible high-risk participants were enrolled in the study; 4490 individuals were invited, and 4395 participants (97.9%) finally underwent LDCT detection. Positive screening results were observed in 857 (19.5%) participants. Solid nodules represented 53.6% of all positive results, while multiple nodules were the most common location type (26.8%). Up to December 2020, 77 participants received lung resection or biopsy, including 70 lung cancers, 2 mediastinal tumors, 1 tracheobronchial tumor, 1 malignant pleural mesothelioma and 3 benign nodules. Lung cancer patients accounted for 1.6% of all the screened participants, and 91.4% were in the early stage (stage 0-1). CONCLUSIONS: LDCT screening can detect a high proportion of early-stage lung cancer patients in a Chinese high-risk population. The utilization of new techniques would be conducive to improving the implementation of LDCT screening.

Longitudinal prediction of lung nodule invasiveness by sequential modelling with common clinical computed tomography (CT) measurements: a prediction accuracy study.

Background: Accurate preoperative prediction of the invasiveness of lung nodules on computed tomography (CT) can avoid unnecessary invasive procedures and costs for low-risk patients. While previous studies approached this task using cross-sectional data, this study aimed to utilize the commonly available longitudinal data of lung nodules through sequential modelling based on long short-term memory (LSTM) networks. Methods: We retrospectively included 171 patients with lung nodules that were followed-up at least once and pathologically diagnosed with adenocarcinoma for model development. Pathological diagnosis was the gold standard for deciding lung nodule invasiveness. For each nodule, a handful of semantic features, including size intensity and interval since first discovery, were obtained from an arbitrary number of CT scans available to individual patients and used as input variables to pre-operatively predict nodule invasiveness. The LSTM-based classifier was optimized by extensive experiments and compared to logistic regression (LR) as baseline with five-fold cross-validation. Results: The best LSTM-based classifier, capable of receiving data from an arbitrary number of time points, achieved better preoperative prediction of lung nodule invasiveness [area under the curve (AUC), 0.982; accuracy, 0.924; sensitivity, 0.946; specificity, 0.881] than the best LR (AUC, 0.947; accuracy, 0.906; sensitivity, 0.938; specificity, 0.847) classifier. Conclusions: The longitudinal data of lung nodules, though unevenly spaced and varying in length, can be well modeled by the LSTM, allowing for the accurate prediction of nodule invasiveness. Given that the input variables of the sequential modelling consist of a few semantic features that are easily obtained and interpreted by clinicians, our approach is worthy further investigation for the optimal management of lung nodules.

Augmented reality-assisted localization of solitary pulmonary nodules for precise sublobar lung resection: a preliminary study using an animal model.

BACKGROUND: Accurate localization of early lung cancer, manifested as solitary pulmonary nodules (SPNs) on computed tomography (CT), is critical in sublobar lung resection. The AR-assisted localization of SPNs was evaluated using a pig animal model. METHODS: A Microsoft HoloLens AR system was used. First, a plastic thoracic model was used for the pilot study. Three female 12 months 45 kg Danish Landrace Pigs were then used for the animal study. Thirty natural pulmonary structures, such as lymphonodus and bifurcated bronchioles or bronchial vessels, were chosen as simulated SPNs. The average angle between the actual puncturing needle and the expected path, the average distance between the puncture point and the plan point, and the difference between the actual puncturing depth and expected depth were recorded, and the accuracy rate was calculated. RESULTS: The point selected in the plastic thoracic model could be hit accurately with the assistance from the AR system in the pilot study. Moreover, the average angle between the actual puncturing needle and the expected path was 14.52°±6.04°. Meanwhile, the average distance between the puncture point and the expected point was 8.74±5.07 mm, and the difference between the actual and expected depths was 9.42±7.95 mm. Puncturing within a 1 cm3 area around the SPN using a hook-wire was considered a successful hit. The puncture accuracy was calculated. The average hit rate within a spherical area with a diameter of 1 cm range was 76.67%, and within a diameter of 2 cm range was 100%. CONCLUSIONS: The HoloLens AR-assisted localization of SPNs may become a promising technique to improve the surgical treatment of early-stage lung cancer. Here, we evaluated its feasibility in an animal model. Nevertheless, its safety and effectiveness require further investigation in clinical trials.

Multicenter, prospective, observational study of a novel technique for preoperative pulmonary nodule localization.

OBJECTIVES: Minimally invasive surgery provides an ideal method for pathologic diagnosis and curative intent of small pulmonary nodules (SPNs); however, the main problem with thoracoscopic resection is the difficulty in locating the nodules. The goal of this study was to determine the safety and feasibility of a new localization technique tailored for SPNs. METHODS: A computed tomography (CT)-guided technique, which has a tri-colored suture and claw with 4 fishhook-shaped hooks, was designed to localize SPN preoperatively. Then a multicenter, prospective study was conducted to evaluate the safety and feasibility of this device. The primary endpoints included safety (asymptomatic/symptomatic pneumothorax or parenchymal hemorrhage, and unanticipated adverse effects) and success rate (precise placement and device fracture, displacement, or dislodgement). The secondary endpoints included feasibility (duration of the localization procedure and device fracture or fault) and patient comfort (pain). RESULTS: A total of 90 SPNs were localized from 80 patients. Overall, no symptomatic complications requiring medical intervention, with the exception of asymptomatic pneumothorax (n = 7 [7.8%]) and lung hemorrhages (n = 5 [5.6%]), were observed. The device was successfully placed without dislodgment or movement in 87 of 90 lesions (96.7%). The median nodule size was 0.70 cm (range, 0.30-1.0 cm). The median duration of the procedure was 15 minutes (range, 7-36 minutes). No patient complained of notable pain during or after the procedure. CONCLUSIONS: This new device for SPNs is safe, and has a high success rate, feasibility and good tolerance.

Prediction of pathologic stage in non-small cell lung cancer using machine learning algorithm based on CT image feature analysis.

PURPOSE: To explore imaging biomarkers that can be used for diagnosis and prediction of pathologic stage in non-small cell lung cancer (NSCLC) using multiple machine learning algorithms based on CT image feature analysis. METHODS: Patients with stage IA to IV NSCLC were included, and the whole dataset was divided into training and testing sets and an external validation set. To tackle imbalanced datasets in NSCLC, we generated a new dataset and achieved equilibrium of class distribution by using SMOTE algorithm. The datasets were randomly split up into a training/testing set. We calculated the importance value of CT image features by means of mean decrease gini impurity generated by random forest algorithm and selected optimal features according to feature importance (mean decrease gini impurity > 0.005). The performance of prediction model in training and testing sets were evaluated from the perspectives of classification accuracy, average precision (AP) score and precision-recall curve. The predictive accuracy of the model was externally validated using lung adenocarcinoma (LUAD) and lung squamous cell carcinoma (LUSC) samples from TCGA database. RESULTS: The prediction model that incorporated nine image features exhibited a high classification accuracy, precision and recall scores in the training and testing sets. In the external validation, the predictive accuracy of the model in LUAD outperformed that in LUSC. CONCLUSIONS: The pathologic stage of patients with NSCLC can be accurately predicted based on CT image features, especially for LUAD. Our findings extend the application of machine learning algorithms in CT image feature prediction for pathologic staging and identify potential imaging biomarkers that can be used for diagnosis of pathologic stage in NSCLC patients.

Response of the temporomandibular joint tissue of rats to rheumatoid arthritis induction methods.

BACKGROUND/PURPOSE: The pathogenesis of rheumatoid arthritis (RA)-related temporomandibular joint (TMJ) disorder remains unclear. Studies have reported the change of the TMJ after complete Freund's adjuvant (CFA) injection, which is consistent with osteoarthritis. However, few studies have reported that the tissue response of the TMJ in collagen-induced arthritis (CIA) can mimic RA. The present study was aimed to investigate the TMJ response in rat models by CFA-induced arthritis and CIA to verify the proper RA-related TMJ arthritis rat model. MATERIALS AND METHODS: In total, 24 rats were randomly divided into four groups: (1) control group; (2) type I collagen injection group; (3) CFA-induced arthritis group; and (4) CIA group. Drugs were injected on Day 0, and the rats were sacrificed on Days 7 and 35. Next, TMJ tissue was collected for hematoxylin and eosin staining, and inflammatory gene (IL-1ß and MMP3) expression was investigated. RESULTS: Compared with the control group, the type I collagen injection group confirmed the negative inflammatory response through hematoxylin and eosin staining and IL-1ßand MMP3 expression. Although CFA-induced arthritis and CIA groups showed inflammatory response (P < 0.05) compared with the control group, histological changes were different. The 7-day CFA-induced arthritis group showed adaptive changes and partly recovered after 35 days of induction. In contrast, 7- and 35-day CIA groups underwent a degenerative process. CONCLUSION: Considering the study limitations, the CIA method is a proper method to study the mechanism of RA-related TMJ arthritis.