ObjectiveTo explore the application value of CT-guided microcoil localization in pulmonary nodule (diameter≤15 mm) surgery.MethodsThe clinical data of 175 patients with pulmonary nodules who underwent single utility port video-assisted thoracoscopic surgery at Nanjing Drum Tower Hospital from August 2018 to December 2019 were retrospectively analyzed. According to whether CT-guided coil localization was performed before operation, they were divided into a locating group and a non-locating group. There were 84 patients (34 males, 50 females, aged 57.8±8.8 years) in the locating group and 91 patients (46 males, 45 females, aged 57.6±10.8 years) in the non-locating group. The localization success rate, localization time, incidence of complications, surgical and postoperative conditions were analyzed between the two groups.ResultsAll 84 patients in the locating group were successfully located, and localization time was 19.0±3.6 minutes. Among them, 19 (22.6%) patients had a small pneumothorax, 4 (4.8%) pulmonary hemorrhage and 2 (2.4%) coil shift; 6 (7.1%) patients had mild pain, 3 (3.6%) moderate pain and 1 (1.2%) severe pain. Sex (P=0.181), age (P=0.673), nodule location (P=0.167), nature of lesion (P=0.244), rate of conversion to thoracotomy (P=0.414), rate of disposable resection of nodules (P=0.251) and postoperative hospital stay (P=0.207) were similar between the two groups. There were significant differences in nodule size (P<0.001), nature of nodule (P<0.001), the shortest distance from nodule to pleura (P<0.001), operation time (P<0.001), lung volume by wedge resection (P=0.031), number of staplers (P<0.001) and total hospitalization costs (P<0.001) between the two groups.ConclusionCT-guided microcoil localization has the characteristics of high success rate, and is simple, practicable, effective, safe and minimally invasive. Preoperative CT-guided microcoil localization has important clinical application value for small pulmonary nodules, especially those with small size, deep location and less solid components. It can effectively shorten the operation time, reduce surgical trauma and lower hospitalization costs, which is a preoperative localization technique worthy of popularization.
ObjectiveTo explore the clinical application of the comprehensive guidance technologies, such as cone beam computed tomography (CBCT), virtual bronchoscopic navigation (VBN), and superimposed high-frequency jet ventilator for respiratory control in the biopsy of peripheral pulmonary nodules (PPNs). MethodsThe clinical information of 3 patients with PPNs diagnosed by CBCT combined with VBN and superimposed high frequency superposition jet ventilator in Shanghai Changhai Hospital were retrospectively analyzed. Results Clinical data of 3 patients were collected. The average diameter of PPNs was (25.3±0.3) mm with various locations in left and right lung. The first nodule was located in the apex of the left upper lung, and the biopsy was benign without malignant cells. The lesion was not enlarged during the 5-year follow-up. The second one was located in the left lingual lung, and the postoperative pathology was confirmed as mucosa-associated lymphoma. The third one was located in the anterior segment of the right upper lung. After the failure of endobronchial procedure, percutaneous PPNs biopsy under CBCT combined with VBN was performed, and the pathological diagnosis was confirmed as primary lung adenocarcinoma. Postoperative pneumothorax complication occurred in the third patient with right lung compression rate approximately 20%. ConclusionsThe application of CBCT, combined with VBN and the superimposed high frequency jet ventilator for respiratory control can potentially improve the accuracy and safety in the diagnosis of PPNs. Multi-center clinical trials are needed to verify its further clinical application.
ObjectiveTo compare the clinical application of empirical thoracoscopic segmentectomy and precise segmentectomy planned by artificial intelligence software, and to provide some reference for clinical segmentectomy. MethodsA retrospective analysis was performed on the patients who underwent thoracoscopic segmentectomy in our department from 2019 to 2022. The patients receiving empirical thoracoscopic segmentectomy from January 2019 to September 2021 were selected as a group A, and the patients receiving precise segmentectomy from October 2021 to December 2022 were selected as a group B. The number of preoperative Hookwire positioning needle, proportion of patients meeting oncology criteria, surgical time, intraoperative blood loss, postoperative chest drainage time, postoperative hospital stay, and number of patients converted to thoracotomy between the two groups were compared. Results A total of 322 patients were collected. There were 158 patients in the group A, including 56 males and 102 females with a mean age of 56.86±8.82 years, and 164 patients in the group B, including 55 males and 109 females with a mean age of 56.69±9.05 years. All patients successfully underwent thoracoscopic segmentectomy, and patients whose resection margin did not meet the oncology criteria were further treated with extended resection or even lobectomy. There was no perioperative death. The number of positioning needles used for segmentectomy in the group A was more than that in the group B [47 (29.7%) vs. 9 (5.5%), P<0.001]. There was no statistical difference in the number of positioning needles used for wedge resection between the two groups during the same period (P=0.572). In the group A, the nodule could not be found in the resection target segment in 3 patients, and the resection margin was insufficient in 10 patients. While in the group B, the nodule could not be found in 1 patient, and the resection margin was insufficient in 3 patients. There was a statistical difference between the two groups [13 (8.2%) vs. 4 (2.4%), P=0.020]. There was no statistical difference between the two groups in terms of surgical time, intraoperative blood loss, duration of postoperative thoracic drainage, postoperative hospital stay, or conversion to open chest surgery (P＞0.05). Conclusion Preoperative surgical planning performed with the help of artificial intelligence software can effectively guide the completion of thoracoscopic anatomical segmentectomy. It can effectively ensure the resection margin of pulmonary nodules meeting the oncological requirements and significantly reduce the number of positioning needles of pulmonary nodules.
Objective To evaluate the value of incremental dynamic enhanced computer tomography (CT) in diagnosis of solitary pulmonary nodules (SPN). Methods The data of 42 cases with SPN who had undergone pulmonary lobectomy were collected retrospectively to find the relationship between character of preoperative dynamic enhanced CT image and postoperative pathologic result. Results All bronchogenic carcinoma showed significant enhancement after intravenous 100 ml iodinated contrast material. The average degree of enhancement of bronchogenic carcinoma during the time 85s and 135s after infusion was significantly different from that of tuberculoma and other benign lesions(Plt;0.05). Conclusion Dynamic enhanced CT is valuable in identifying the malignant nodules from benign nodules. Emphasis should be paid to the lymph nodes in the relative field with dynamic enhanced CT, which is beneficial to the diagnosis of SPN and it is an important predictor of the result of surgical treatment.
ObjectiveTo analyze the effect of indocyanine green (ICG) fluorescence dual-visualization technique on evaluating tumor margins during the thoracoscopic segmentectomy. MethodsA total of 36 patients who underwent thoracoscopic anatomical segmentectomy using ICG fluorescence dual-visualization technique in our hospital from December 2020 to June 2021 were retrospectively included. There were 15 males and 21 females aged from 20 to 69 years. The clinical data of the patients were retrospectively analyzed. ResultsThe ICG fluorescence dual-visualization technique clearly showed the position of lung nodules and the plane boundary line between segments during the operation. There was no ICG-related complication. The average operation time was 98.6±21.3 min, and the average intraoperative bleeding amount was 47.1±35.3 mL, the average postoperative drainage tube placement time was 3.3±2.8 d, the average postoperative hospital stay was 5.4±1.8 d, and the average tumor resection distance was 2.6±0.7 cm. There was no perioperative period death, and one patient suffered a persistent postoperative air leak. ConclusionThe ICG fluorescence dual-visualization technique is safe and feasible for evaluating the tumor margins during thoracoscopic segmentectomy. It simplifies the surgical procedure, shortens the operation time, ensures sufficient tumor margins, and reserves healthy pulmonary parenchyma to the utmost extent, providing reliable technical support for thoracoscopic anatomical segmentectomy.
Lung nodules are the main manifestation of early lung cancer. So accurate detection of lung nodules is of great significance for early diagnosis and treatment of lung cancer. However, the rapid and accurate detection of pulmonary nodules is a challenging task due to the complex background, large detection range of pulmonary computed tomography (CT) images and the different sizes and shapes of pulmonary nodules. Therefore, this paper proposes a multi-scale feature fusion algorithm for the automatic detection of pulmonary nodules to achieve accurate detection of pulmonary nodules. Firstly, a three-layer modular lung nodule detection model was designed on the deep convolutional network (VGG16) for large-scale image recognition. The first-tier module of the network is used to extract the features of pulmonary nodules in CT images and roughly estimate the location of pulmonary nodules. Then the second-tier module of the network is used to fuse multi-scale image features to further enhance the details of pulmonary nodules. The third-tier module of the network was fused to analyze the features of the first-tier and the second-tier module of the network, and the candidate box of pulmonary nodules in multi-scale was obtained. Finally, the candidate box of pulmonary nodules under multi-scale was analyzed with the method of non-maximum suppression, and the final location of pulmonary nodules was obtained. The algorithm is validated by the data of pulmonary nodules on LIDC-IDRI common data set. The average detection accuracy is 90.9%.
ObjectiveTo explore the efficacy of artificial intelligence (AI) detection on pulmonary nodule compared with multidisciplinary team (MDT) in regional medical center.MethodsWe retrospectively analyzed the clinical data of 102 patients with lung nodules in the Xiamen Fifth Hospital from April to December 2020. There were 57 males and 45 females at age of 36-90 (48.8±11.6) years. The preoperative chest CT was imported into AI system to record the detected lung nodules. The detection rate of pulmonary nodules by AI system was calculated, and the sensitivity, specificity of AI in the different diagnosis of benign and malignant pulmonary was calculated and compared with manual film reading by MDT.ResultsA total of 322 nodules were detected by AI software system, and 305 nodules were manually detected by physicians (P<0.05). Among them, 113 pulmonary nodules were diagnosed by pathologist. Thirty-eight of 40 lung cancer nodules were AI high-risk nodules, the sensitivity was 95.0%, and 25 of 73 benign nodules were AI high-risk nodules, the specificity was 65.8%. Lung cancer nodules were correctly diagnosed by MDT, but benign nodules were still considered as lung cancer at the first diagnosis in 10 patients.ConclusionAI assisted diagnosis system has strong performance in the detection of pulmonary nodules, but it can not content itself with clinical needs in the differentiation of benign and malignant pulmonary nodules. The artificial intelligence system can be used as an auxiliary tool for MDT to detect pulmonary nodules in regional medical center.
ObjectiveTo summarize the experience of diagnosis and surgical treatment for solitary pulmonary nodules (SPN). MethodsWe retrospectively analyzed clinical data of 327 patients with video-assisted thoracoscopic surgery (VATS) lung resections and subsequent pathological diagnosis of the SPNs in Daping Hospital from January 2008 through May 2014 year. There were 183 males, 144 females at age of 56.6(20-79) years. ResultsOne way analysis of variance showed that there were significant differences in age, smoking index, diameter, glitches, lobulation, traction of pleural, cavity, vascular convergence, calcification between benign and malignant lesions (P<0.05). Logistic regression analysis revealed that age (P=0.004, OR=1.084), diameter (P<0.001, OR=1.467), glitches (P=0.001, OR=8.754), lobulation (P<0.001, OR=10.424), traction of pleural (P=0.002, OR=6.619) were independent predictors of malignancy in patients with SPN. Operation time was 121.4±47.6 min. Blood loss was 105.3±57.8 ml. Postoperative hospital stay was 7.3±2.4 days. Diagnostic accuracy was 99.7%. Incidence of complication was 0.5%. Five (1.5%) patients were converted to thoracotomy and no perioperative death occurred. ConclusionsAge, diameter, glitches, lobulation, traction of pleural are independent predictors of malignancy in the patients with SPN. VATS is a safe and efficient method for diagnosis and treatment of SPN.
Objective To analyze the imaging features of solitary pulmonary nodules ( SPNs) , and compare the two types of lung cancer prediction models in distinguishing malignancy of SPNs.Methods A retrospective study was performed on the patients admitted to Ruijin Hospital between 2002 and 2009 with newly discovered SPNs. The patients all received pathological diagnosis. The clinical and imaging characteristics were analyzed. Then the diagnostic accuracy of two lung cancer prediction models for distinguishing malignancy of SPNs was evaluated and compared.Results A total of 90 patients were enrolled, of which 32 cases were with benign SPNs, 58 cases were with malignant SPNs. The SPNs could be identified between benign and maligant by the SPN edge features of lobulation ( P lt;0. 05) . The area under ROC curve of VA model was 0. 712 ( 95% CI 0. 606 to 0. 821) . The area under ROC curve of Mayo Clinic model was 0. 753 ( 95% CI 0. 652 to 0. 843) , which was superior to VA model. Conclusions It is meaningful for the identification of benign and maligant SPNs by the obulation sign in CT scan. We can integrate the clinical features and the lung cancer predicting models to guide clinical work.
Objective To construct a "disease-syndrome combination" mathematical representation model for pulmonary nodules based on oral microbiome data, utilizing a multimodal data algorithm framework centered on dynamic systems theory. Furthermore, to compare predictive models under various algorithmic frameworks and validate the efficacy of the optimal model in predicting the presence of pulmonary nodules. MethodsA total of 213 subjects were prospectively enrolled from July 2022 to March 2023 at the Hospital of Chengdu University of Traditional Chinese Medicine, Sichuan Cancer Hospital, and the Chengdu Integrated Traditional Chinese and Western Medicine Hospital. This cohort included 173 patients with pulmonary nodules and 40 healthy subjects. A novel multimodal data algorithm framework centered on dynamic systems theory, termed VAEGANTF (Variational Auto Encoder-Generative Adversarial Network-Transformer), was proposed. Subsequently, based on a multi-dimensional integrated dataset of “clinical features-syndrome elements-microorganisms”, all subjects were divided into training (70%) and testing (30%) sets for model construction and efficacy testing, respectively. Using pulmonary nodules as dependent variables, and combining candidate markers such as clinical features, lesion location, disease nature, and microbial genera, the independent variables were screened based on variable importance ranking after identifying and addressing multicollinearity. Missing values were then imputed, and data were standardized. Eight machine learning algorithms were then employed to construct pulmonary nodule risk prediction models: random forest, least absolute shrinkage and selection operator (LASSO) regression, support vector machine, multilayer perceptron, eXtreme Gradient Boosting (XGBoost), VAE-ViT (Vision Transformer), GAN-ViT, and VAEGANTF. K-fold cross-validation was used for model parameter tuning and optimization. The efficacy of the eight predictive models was evaluated using confusion matrices and receiver operating characteristic (ROC) curves, and the optimal model was selected. Finally, goodness-of-fit testing and decision curve analysis (DCA) were performed to evaluate the optimal model. ResultsThere were no statistically significant differences between the two groups in demographic characteristics such as age and sex. The 213 subjects were randomly divided into training and testing sets (7 : 3), and prediction models were constructed using the eight machine learning algorithms. After excluding potential problems such as multicollinearity, a total of 301 clinical feature information, syndrome elements, and microbial genera markers were included for model construction. The area under the curve (AUC) values of the random forest, LASSO regression, support vector machine, multilayer perceptron, and VAE-ViT models did not reach 0.85, indicating poor efficacy. The AUC values of the XGBoost, GAN-ViT, and VAEGANTF models all reached above 0.85, with the VAEGANTF model exhibiting the highest AUC value (AUC=0.923). Goodness-of-fit testing indicated good calibration ability of the VAEGANTF model, and decision curve analysis showed a high degree of clinical benefit. The nomogram results showed that age, sex, heart, lung, Qixu, blood stasis, dampness, Porphyromonas genus, Granulicatella genus, Neisseria genus, Haemophilus genus, and Actinobacillus genus could be used as predictors. Conclusion The “disease-syndrome combination” risk prediction model for pulmonary nodules based on the VAEGANTF algorithm framework, which incorporates multi-dimensional data features of “clinical features-syndrome elements-microorganisms”, demonstrates better performance compared to other machine learning algorithms and has certain reference value for early non-invasive diagnosis of pulmonary nodules.