Objectives. Current lung cancer screening protocols primarily evaluate pulmonary nodules, yet often neglect the malignancy risk associated with small nodules (≤10 mm). This study endeavors to optimize the management of pulmonary nodules in this population by devising and externally validating a Multimodal Integrated Feature Neural Network (MIFNN). We hypothesize that the fusion of deep learning algorithms with morphological nodule features will significantly enhance diagnostic accuracy.Materials and Methods. Data were retrospectively collected from the Lung Nodule Analysis 2016 (LUNA16) dataset and four local centers in Beijing, China. The study includes patients with small pulmonary nodules (≤10 mm). We developed a neural network, termed MIFNN, that synergistically combines computed tomography (CT) images and morphological characteristics of pulmonary nodules. The network is designed to acquire clinically relevant deep learning features, thereby elevating the diagnostic accuracy of existing models. Importantly, the network\'s simple architecture and use of standard screening variables enable seamless integration into standard lung cancer screening protocols.Results. In summary, the study analyzed a total of 382 small pulmonary nodules (85 malignant) from the LUNA16 dataset and 101 small pulmonary nodules (33 malignant) obtained from four specialized centers in Beijing, China, for model training and external validation. Both internal and external validation metrics indicate that the MIFNN significantly surpasses extant state-of-the-art models, achieving an internal area under the curve (AUC) of 0.890 (95% CI: 0.848-0.932) and an external AUC of 0.843 (95% CI: 0.784-0.891).Conclusion. The MIFNN model significantly enhances the diagnostic accuracy of small pulmonary nodules, outperforming existing benchmarks by Zhanget alwith a 6.34% improvement for nodules less than 10 mm. Leveraging advanced integration techniques for imaging and clinical data, MIFNN increases the efficiency of lung cancer screenings and optimizes nodule management, potentially reducing false positives and unnecessary biopsies.Clinical relevance statement. The MIFNN enhances lung cancer screening efficiency and patient management for small pulmonary nodules, while seamlessly integrating into existing workflows due to its reliance on standard screening variables.

BACKGROUND: The early detection of benign and malignant lung tumors enabled patients to diagnose lesions and implement appropriate health measures earlier, dramatically improving lung cancer patients\' quality of living. Machine learning methods performed admirably when recognizing small benign and malignant lung nodules. However, exploration and investigation are required to fully leverage the potential of machine learning in distinguishing between benign and malignant small lung nodules.
OBJECTIVE: The aim of this study was to develop and evaluate the ResNet50-Ensemble Voting model for detecting the benign and malignant nature of small pulmonary nodules (<20 mm) based on CT images.
METHODS: In this study, 834 CT imaging data from 396 patients with small pulmonary nodules were gathered and randomly assigned to the training and validation sets in an 8:2 ratio. ResNet50 and VGG16 algorithms were utilized to extract CT image features, followed by XGBoost, SVM, and Ensemble Voting techniques for classification, for a total of ten different classes of machine learning combinatorial classifiers. Indicators such as accuracy, sensitivity, and specificity were used to assess the models. The collected features are also shown to investigate the contrasts between them.
RESULTS: The algorithm we presented, ResNet50-Ensemble Voting, performed best in the test set, with an accuracy of 0.943 (0.938, 0.948) and sensitivity and specificity of 0.964 and 0.911, respectively. VGG16-Ensemble Voting had an accuracy of 0.887 (0.880, 0.894), with a sensitivity and specificity of 0.952 and 0.784, respectively.
CONCLUSIONS: Machine learning models that were implemented and integrated ResNet50-Ensemble Voting performed exceptionally well in identifying benign and malignant small pulmonary nodules (<20 mm) from various sites, which might help doctors in accurately diagnosing the nature of early-stage lung nodules in clinical practice.

UNASSIGNED: With the increasing number of small pulmonary nodules detected, effective localization of pulmonary nodules has become an issue. The goal of this study is to determine the safety and feasibility of a newly developed augmented reality navigation technology for intraoperative localization of small pulmonary nodules.
UNASSIGNED: We conducted a prospective single-center feasibility study of a novel augmented reality navigation system and lung localization (LungBrella) marker on ten patients between July and October 2020. For augmented reality navigation-guided localization, a preoperative chest computed tomography scan was performed to generate 3-dimensional (3D) virtual images and individualized localization plan, which were uploaded into Hololens (a head-mounted augmented reality device). Under the guidance of established procedure plan displayed by HoloLens, localization marker was placed in operating room. Segmentectomy or wedge resection was subsequently performed. The primary endpoint was the localization procedure success rate, and the secondary endpoints were localization time, operation time, and complications.
UNASSIGNED: Localization was successful in seven of the ten procedures. Due to different reasons, failures were noted in three cases, after which immediate adjustments were made. In the successful cases, the LungBrella marker was positioned at a median of 5.8 mm (range, 0-10 mm) from the edge of the nodule. Median localization time was 9.4 min (range, 5-19 min), and median operation time was 172.9 min (range, 105-200 min). There were no complications during the entire process.
UNASSIGNED: This exploratory study suggests that augmented reality navigation-guided pulmonary nodule localization is a safe and feasible technique (ClinicalTrials.gov identifier, NCT04211051).

BACKGROUND: A tracheal foreign body is a common airway aspiration that creates an emergency, which often causes unobserved respiratory problems and requires management. Iatrogenic tracheal foreign bodies are rarely observed, which results in tracheal obstruction. If the foreign body were removed from the tracheobronchial system, it would save lives. A similar case of a tracheal foreign body was focused on, which was caused by medical glue used during preoperative computed tomography localization of pulmonary nodules.
METHODS: The foreign body was deposited in the right upper bronchi, accidentally discovered after anesthesia when a double-lumen tube was located by fiber bronchoscopy. Following a video-assisted thoracoscopic surgery, the foreign body was removed using a respiratory endoscopy without subsequent adverse consequences for the patient.
CONCLUSIONS: There is a risk of complications from iatrogenic airway foreign bodies for preoperative localization of pulmonary nodules by injecting cyanoacrylate glue.

Hybrid operating rooms (HOR) have been increasingly used for image-guided lung surgery, and most surgical teams have used percutaneous localization for small pulmonary nodules. We evaluated the feasibility and safety of augmented fluoroscopic bronchoscopy localization under endotracheal tube intubation general anaesthesia followed by thoracoscopic surgery as a single-stage procedure in ab HOR.
We retrospectively reviewed clinical records of patients who underwent single-stage augmented fluoroscopic bronchoscopy localization under general anaesthesia followed by thoracoscopic surgery in an HOR between August 2020 and March 2022.
Single-stage localization and resection were performed for 85 nodules in 74 patients. The median nodule size was 8 mm [interquartile range (IQR), 6-9 mm], and the median distance from the pleural space was 10.9 mm (IQR, 8-20 mm). All nodules were identifiable on cone-beam computed tomography images and marked transbronchially with indigo carmine dye (median markers per lesion: 3); microcoils were placed for deep margins in 16 patients. The median localization time was 30 min (IQR 23-42 min), and the median fluoroscopy duration was 3.3 min (IQR 2.2-5.3 min). The median radiation exposure (expressed as the dose area product) was 4303.6 μGym2 (IQR 2879.5-6268.7 μGym2). All nodules were successfully marked and resected, and the median global operating room time was 178.5 min (IQR 153.5-204 min). There were no localization-related complications, and the median length of postoperative stay was 1 day (IQR, 1-2 days).
Single-stage augmented fluoroscopic bronchoscopy localization under general anaesthesia followed by thoracoscopic surgery was feasible and safe.

OBJECTIVE: This study aimed to describe a new localization technique developed using an anchor with a scaled suture (AWSS) system and to characterize the localization results and post-operative outcomes to evaluate its safety and effectiveness.
METHODS: This retrospective study was conducted at our centre from October 2020 to December 2021. In total, 328 small pulmonary nodules (sPNs) who underwent pre-operative computed tomography (CT)-guided AWSS system localization followed by wedge resection by video-assisted thoracoscopic surgery (VATS) were enrolled in this study.
RESULTS: CT-guided AWSS system implantations targeting 328 sPNs were successfully performed. The time spent performing localization was 12.4 ± 4.9 min. After puncture localization, the incidences of pneumothorax, pulmonary haemorrhage, and chest pain were 19.2% (63/328), 25.9% (85/328), and 0.9% (3/328), respectively. The incidence of overall complications was 42.7%. According to the CIRSE classification, there were no major complications. The median localization-VATS interval time was 7 h (range, 1-75 h). In 328 cases (100%), the location of the lesion was determined by palpation of the four-paw anchor in the lung and was successfully resected by VATS, and the correct diagnosis was obtained.
CONCLUSIONS: In this series, CT-guided pre-operative localization of pulmonary nodules with the AWSS system was safe and had a high positioning accuracy and success rate.

UNASSIGNED: The incidence, severity and associated risk factors of acute pain after preoperative needle localization of pulmonary nodules are poorly characterized. We therefore conducted a cross-sectional study to quantify the acute pain induced by preoperative needle localization of small pulmonary nodules before video-assisted thoracoscopic surgery (VATS).
UNASSIGNED: We conducted this study at Shanghai Chest Hospital from September 2021 through December 2021. Eligible patients were between 18 and 75 years old and had small pulmonary nodules requiring preoperative CT-guided needle localization. The intensity of acute pain was assessed using the visual analogue scale (VAS) after preoperative needle localization. A VAS score ≥4 cm indicated moderate to severe pain. Patient demographics and CT-guided localization factors were collected to identify significant predictors associated with moderate to severe pain.
UNASSIGNED: A total of 300 patients were included in the final analysis, with a mean (SD) age of 51 (SD =12) years old; 63% were female. Moderate to severe pain occurred in 50.8% of patients during deep breathing and 45.7% of patients during movement. Multivariate logistic regression analysis showed that multiple localization needles [multiple needle localizations vs. single needle localization, odds ratio (OR): 2.363, 95% confidence interval (CI): 1.157-4.825, P=0.018] and the specific location of needle puncture on the chest wall were significant predictors of moderate to severe pain after CT-guided needle localization (lateral chest wall vs. anterior chest wall OR: 2.235, 95% CI: 1.106-4.518, P=0.025; posterior chest wall vs. anterior chest wall OR: 1.198, 95% CI: 0.611-2.349, P=0.599).
UNASSIGNED: In adult patients receiving hookwire CT-guided localization, moderate to severe pain was common. Avoiding the localization route through lateral chest wall may be helpful and pharmacological medications or regional blockade is necessitated in high-risk population.

UNASSIGNED: In our previous study, we developed a 4-hook claw-suture localization device for pulmonary nodule resection, which acheived satifisfactory results. Following this, we conducted this single-center, open-label, randomized clinical trial to compare the success rate and complication rate of this novel localization device and currently widely-used hookwire.
UNASSIGNED: Patients with small pulmonary nodules (0.4-1 cm) who received preoperative localization and thoracoscopic resection at Shanghai Chest Hospital were randomly assigned (1:2 ratio, via computer-generated randomized numbers) to undergo localization using either a novel claw-suture system (claw group) or classical (hookwire group) localization device. The primary endpoint of this study was localization success rate, and the secondary endpoints included complications, localization-related time, and pain.
UNASSIGNED: A total of 411 patients were randomly assigned to the claw group (n=136) or the hookwire group (n=275) before thoracoscopic resection of small pulmonary nodules and analyzed. Compared with the hookwire group, the claw group had a significantly higher success rate (133/136, 97.8% vs. 254/275, 92.4%, P=0.027), less asymptomatic hemorrhage (16.9% vs. 37.5%, P=0.003) and pleural reaction (0% vs. 5.1%, P=0.017), as well as better pain alleviation 10 min after localization (measured using the difference between two visual analog scale scores, 0.84±0.98 vs. 0.35±0.79, P<0.001). In contrast, the hookwire group was associated with a shorter localization procedure duration than the claw group (7.2±2.9 vs. 14.4±6.6 min, P<0.001). In the multiple localization subgroup, the claw group compared to the hookwire group also achieved higher success (32/33, 97.0% vs. 70/86, 81.4%) and less pleural reaction (0% vs. 16.3%).
UNASSIGNED: The new claw-suture localization device is superior to traditional hookwire, with a higher success rate, fewer complications, and better patient tolerance for preoperative localization of small pulmonary nodules.
UNASSIGNED: Chinese Clinical Trial Registry ChiCTR1900027346.

UNASSIGNED: Intraoperative identification of small pulmonary nodules has been an important technical issue. We aimed to develop a new localization method which is much safer and simple procedure compared with conventional methods.
UNASSIGNED: This was a retrospective study including patients with resected peripheral pulmonary nodules between November 2017 and April 2021 at Teikyo University School of Medicine, and Saitama Cardiovascular and Respiratory Center. All surgical procedure was wedge resection, and the tumor size was equal to or less than 20 mm which were detected by cone-beam computed tomography (CBCT; Philips Allura Xper FD 20, Philips). Some metal clips were put on several places of visceral pleura, where the target lesion was sandwiched by marking clips (sandwich marking technique). CBCT detected both the target lesion and metal clips, and video-assisted thoracoscopic surgery (VATS) was performed. Radiological and pathological findings were analyzed, and the correlation coefficient of tumor size was examined among pre-, intra-, and post-operative tumor sizes.
UNASSIGNED: The average age of 90 patients was 65.2 years, and 47 were male (52.2%). All procedure was wedge resection including twelve bi-wedge resections, and one hundred nine peripheral pulmonary lesions were obtained by sandwich marking technique. The detection rate was 100%, and there was no marking-related complication.
UNASSIGNED: All small peripheral pulmonary lesions were successfully detected and resected by using CBCT with no marking-related complication. Sandwich marking technique was demonstrated to provide safe, reliable, and simple localization procedure for small peripheral pulmonary lesions.

Preoperative localization holds promise for overcoming the limitations of video-assisted thoracoscopic surgery (VATS) in the treatment of impalpable lung nodules. The purpose of this study was to assess the safety and efficacy of cone-beam computed tomography (CBCT)-guided localization using near-infrared (NIR) marking. Between 2017 and 2021, patients presenting with a solitary pulmonary nodule (SPN) who had undergone CBCT-guided lesion localization with indocyanine green (ICG) in a hybrid operating room were included. The primary outcomes were the efficacy of localization and the occurrence of complications. The study cohort consisted of 175 patients with the mean age of 58.76 years. The mean size and depth of the 175 SPNs were 8.34 mm and 5.3 mm, respectively. The mean time required for lesion marking was 14.71 min. Upon thoracoscopic inspection, the NIR tattoo was detected in the vast majority of the study participants (98.3%). An utility thoracotomy to allow digital palpation was required in two of the three patients in whom the tattoo was not identifiable. The perioperative survival rate was 100%, and the mean length of hospital stay was 3.09 days. We conclude that needle localization with ICG injection is a safe and feasible technique to localize SPNs prior to resection.