ObjectiveTo study the feasibility and safety of CT-guided preoperative Hookwire localization of pulmonary nodules in clinical application.MethodsClinical data of 102 patients who were scheduled to undergo surgical treatment for pulmonary nodules from June 2015 to April 2020 in the North Ward of Thoracic Surgery Department of Ruijin Hospital were retrospectively analyzed. There were 38 males and 64 females, aged 23-82 (53.2±12.8) years.ResultsAll 102 patients with pulmonary nodules underwent CT-guided preoperative Hookwire localization successfully, with a localization success rate of 100.0%. The localization time was 27.0 (11-67) min; the number of times to adjust the angle during the positioning process was 6.9 (3-14); the needle depth of the positioning needle was 41.5 (16.3-69.1) mm. A total of 48 (47.1%) patients had a small amount of bleeding in the lung tissue in the positioning area after positioning; 53 (51.9%) patients had a small amount of pneumothorax after positioning; 16 (15.7%) patients were found that the positioning needle completely shedded from the lung tissue in the subsequent surgery. One patient was transferred to open thoracotomy because of extensive dense adhesion in the thorax, and the remaining 101 patients were operated on under thoracoscopy. Postoperative pathology showed that 5 (4.9%) patients were adenocarcinoma in situ, 28 (27.5%) were microinvasive adenocarcinoma, 36 (35.3%) patients were invasive carcinoma and 32 (31.3%) patients were benign lesions. No patients had complications or adverse events related to preoperative positioning.ConclusionPreoperative CT-guided localization of Hookwire intrapulmonary nodules is safe and effective, and can meet the intraoperative localization needs of thoracic surgeons in most clinical situations, and is not inferior to other preoperative localization methods currently used in clinics.
This study aims to explore the clinical value of the computer-aided diagnosis (CAD) system for early detection of the pulmonary nodules on digital chest X-ray. A total of 100 cases of digital chest radiographs with pulmonary nodules of 5-20 mm diameter were selected from Pictures Archiving and Communication System (PACS) database in West China Hospital of Sichuan University were enrolled into trial group, and other 200 chest radiographs without pulmonary nodules as control group. All cases were confirmed by CT examination. Firstly, these cases were diagnosed by 5 different-seniority doctors without CAD, and after three months, these cases were re-diagnosed by the 5 doctors with CAD. Subsequently, the diagnostic results were analyzed by using SPSS statistical methods. The results showed that the sensitivity and specificity for detecting pulmonary nodules tended to be improved by using the CAD system, especially for specificity, but there was no significant difference before and after using CAD system.
ObjectiveTo explore clinical strategies of early diagnosis and treatment of solitary pulmonary nodules (SPN), and define the importance of biological tumor markers, preoperative CT-guided localization with the combination of methylene blue and hookwire system, and video-assisted thoracoscopic surgery (VATS)for early diagnosis and treatment of SPN. MethodsWe retrospectively analyzed clinical records of 70 SPN patients in Department of Thoracic Surgery of Taixing People's Hospital from January 2011 to February 2014. There were 33 male and 37 female patients with their age of 32-87 (59.74±2.04)years. Preoperatively, patients' medical history, heart, lung, liver and kidney function, sputum cytology and bronchoscopic biopsy results were combined with biological tumor markers to make a preliminary differential diagnosis between benign or malignant SPN and surgical risk evaluation. For SPN less than 1 cm or too small for accurate intraoperative localization, CT-guided localization with the combination of methylene blue and hookwire system was routinely performed half an hour before the operation. For SPN large enough for accurate intraoperative localization, wedge resection of SPN and surrounding lung tissue was directly performed with VATS. Intraoperative frozen-section examination of resected lung specimens was preformed. If the pathological diagnosis was malignant, conventional VATS lobectomy/segmentectomy and lymphadenectomy were performed. If the pathological diagnosis was benign, the operation was then completed. Long-term follow-up was performed for SPN patients, especially patients with early-stage lung cancer. ResultsThere was no in-hospital death or postoperative bronchopleural fistula in this study. Postoperatively, there were 2 patients with pneumonia, 3 patients with pneumothorax and 1 patient with wound infection, who were all cured or improved after proper treatment. Among the 70 patients, 11 patients acquired pathological diagnosis via preoperative lung needle biopsy. Among the other 59 patients, 12 patients with eccentric SPN acquired pathological diagnosis via intraoperative biopsy, and 47 patients underwent SPN resection with VATS. Pathological diagnosis included adenocarcinoma in 19 patients, squamous cell carcinoma in 9 patients, bronchioloalveolar carcinoma in 3 patients, adenosquamous carcinoma in 2 patients, inflammatory pseudotumor in 11 patients, tuberculoma in 4 patients, granuloma in 5 patients, sclerosing hemangioma in 2 patients, lung metastasis from breast cancer in 1 patient, lung metastasis from colon cancer in 1 patient, lung metastasis from thyroid cancer in 1 patient, and lung metastasis from stomach cancer in 1 patient. All the 70 patients (100%)were followed up for a mean duration of 2-34 months, and there was no late death during follow-up. One patient with adenocarcinoma of the right upper lobe had cerebral metastasis 18 months after operation, and had been receiving radiotherapy. All the other patients had a good quality of life. ConclusionAbove clinical strategies are accurate for early diagnosis and minimally invasive treatment of SPN with good postoperative recovery and short-term outcomes.
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%.
Abstract： Objective To explore the approach of clinical diagnosis and treatment strategy for patients with small pulmonary nodules （SPN）≤ 1.0 cm in size on CT. Methods We retrospectively analyzed the clinical records of 39 patients with SPN less than 1.0 cm in size who underwent lung resection at Nanjing Drum Tower Hospital from January 2005 to June 2011. There were 23 males and 16 females. Their age ranged from 31-74 （51.0±7.4） years. Nine patients had cough and sputum and other patients had no symptom. All the patients were found to have SPN less than 1.0（0.8±0.1）cm in size but not associated with hilum and mediastinal lymphadenectasis in chest CT and X-ray. The results of their sputum cytology and electronic bronchoscope were all negative. All the patients had no histologic evidence and underwent pulmonary function test prior to operation. Eleven patients had positron emission tomography/computer tomography （PET/CT）or single-photon emission computed tomography （SPECT）which was all negative. Thirteen patients underwent video-assisted minithoracotomy（VAMT） and 26 patients underwent video-assisted thoracoscopic surgery （VATS）. Results The average operation time was 121.0±48.0 min. Patients after partial lung resection were discharged 4～5 d postoperatively, and patients after lobectomy were discharged 7 d postoperatively. All the patients had no postoperative complications. Twenty one patients were identified as lung malignancy by postoperative pathology, including 9 patients with adenocarcinoma, 7 patients with bronchioloalveolar carcinoma, 1 patient with small cell lung carcinoma, and 4 patients with pulmonary metastasis. Eighteen patients had benign lesions including 4 patients with sclerosing hemangioma, 4 patients with inflammatory pseudotumor, 2 patients with pneumonia, 3 patients with granuloma, 2 patients with tuberculosis, and 3 patients with pulmonary lymph node hyperplasia. The SPN were located in left upper lobe in 11 patients, left lower lobe in 6 patients, right upper lobe in 14 patients, right middle lobe in 1 patient, and right lower lobe in 7 patients. Conclusion The diagnosis of SPN ≤1.0 cm in size on CT should consider malignance in the first step to avoid treatment delay. Patients may have a 3-month observation period to receive selective antibiotic treatment, chest CT and X-ray review after 2 to 4 weeks. CT- guided hook-wire fixation is useful to help in precise lesion localization for surgical resection. VATS and VAMT are common and effective methods for the diagnosis and treatment for SPN.
Objective To analyze risk factors of malignancy in patients with small pulmonary nodules （diameter ≤2 cm） using univariate analysis and multivariate logistic regression，and establish a mathematical prediction model to estimatethe probability of malignancy. Methods Clinical data of 147 patients with small pulmonary nodules who underwentsurgical resection with definite postoperative pathological diagnosis from January 2005 to September 2012 in the 161st Central Hospital of PLA were retrospectively analyzed. There were 84 male and 63 female patients with their age of 31-78（56.2±10.1） years. Univariate analysis using Chi-square test or t test was performed to analyze risk factors including patientage，gender，symptoms，history and quantity of smoking，history of heavy drinking，history of tumor，tumor site，diameter，lobulation，spiculation，pleural indentation，ground-glass opacity，cavity，enlarged hilar and mediastinal lymph nodes.Independent predictors of malignancy were screened with multivariate logistic regression analysis. A mathematical predictionmodel was built to estimate the probability of malignancy and then examined. Results Univariate analysis showed that there was statistical difference in patient age（t=7.146，P＜0.001），heavy smoking history（χ2=6.169，P=0.013），nodule diameter（t=3.375，P=0.001），spiculation（χ2=5.609，P=0.018），lobulation（χ2=5.675，P=0.017），and pleural indentation（χ2=12.994，P＜0.001）between benign and malignant small pulmonary nodule groups. Multivariate logistic regression analysis showed that patient age （OR=1.110，P=0.000），nodule diameter （OR=2.050，P=0.029），lobulation （OR=1.672，P=0.045），spiculation（OR=2.054，P=0.032） and pleural indentation（OR=4.090，P=0.024）were independent predictors of malignancy in patients with small pulmonary nodules （P＜0.05） . The mathematical prediction model to estimate the probability of malignancy was：Logit （P） =ez/ （1 ＋ ez），Z=-6.657 ＋ （0.104×age） ＋ （0.718×diameter） ＋ （0.720×spiculation） ＋（0.514×lobulation） ＋ （1.409×pleural indentation），and e was natural logarithm. Both Hosmer-Lemeshow test （χ2=1.802，P=0.986） and maximum likelihood ratio test （Cox-Snell R2=0.310，Nagelkerke R2=0.443） showed satisfactory goodness of fit. The diagnostic accuracy was 85.71%，sensitivity was 87.50%，specificity was 81.40%，positive predictive value was 91.92%，and negative predictive value was 72.92% when the cut-off value was 0.58. Conclusions Patient age，nodule diameter，spiculation，lobulation and pleural indentation are independent predictors of malignancy in patients with small pulmonary nodules. The mathematical prediction model can accurately estimate the probability of malignancy for patients with small pulmonary nodules.
In thoracoscopic pulmonary nodule resection surgery, precise preoperative planning is crucial. Artificial intelligence (AI)-assisted three-dimensional (3D) reconstruction technologies have shown great potential in this area. AI-assisted 3D reconstruction technologies can provide accurate, personalized models of the pulmonary vasculature and bronchial anatomy, assisting surgeons in detailed surgical planning and thus enhancing the precision and safety of surgeries. This article reviews the application progress of AI-assisted 3D reconstruction technologies in pulmonary nodule surgery, including their applications in preoperative diagnosis, surgical planning, and intraoperative navigation, as well as the advancements in AI-assisted 3D reconstruction technologies. It analyzes the technical features of all kinds of 3D reconstruction methods, their clinical applications, and the challenges they face.
ObjectiveTo explore the clinical utility and safety of electromagnetic navigation bronchoscopy (ENB)-guided microwave ablation (MWA) in the patients with inoperable high-risk pulmonary nodules.MethodsClinical data of patients who were diagnosed with inoperable pulmonary nodules highly suspected as malignant tumors and treated with ENB-guided MWA in Zhongshan Hospital, Fudan University from December 2019 to September 2020 were retrospectively collected and analyzed to evaluate the efficacy and safety of the procedure. There were 6 males and 3 females aged 72.0 (59.5-77.0) years.ResultsTotally ENB-guided MWA was performed in 9 patients with 12 lesions. All patients suffered from at least one chronic comorbidity. The inoperable reasons included poor pulmonary function (55.6%), comorbidities of other organs which made the surgery intolerable (33.3%), multiple lesions in different lobes or segments (22.2%), personal wills (22.2%) and advanced in age (11.1%). The median diameter of nodules was 13.5 (9.5-22.0) mm and the median distance from the edge of nodules to pleura was 5.3 (1.8-16.3) mm. Bronchoscope maneuver to the targeted lesions was manipulated according to navigation pathway under visual and X-ray guidance and confirmed with radial ultrasound probe. Rapid on-site evaluation also helped with primary pathological confirmation of biopsy specimen. Among all the lesions, 4 adenocarcinoma, 1 non-small cell lung cancer-not otherwise specified and 2 inflammatory lesions were reported in postoperative pathological diagnosis, while no malignant cells were found in 5 specimens. The ablation success rate was 83.3% (10/12). For the two off-targeted lesions, percutaneous ablations were performed as salvage treatment subsequently. The median hospitalization time was 3.0 (2.0-3.0) days and no short-term complications were reported in these patients.ConclusionENB-guided MWA is a safe and effective procedure for patients with high-risk pulmonary nodules when thoracic surgery cannot be tolerated.
The robotic bronchoscopy system is a new technology for lung lesion location, biopsy and interventional therapy. Its safety and effectiveness have been clinically proven. Based on many advanced technologies carried by the robotic bronchoscopy system, it is more intelligent, convenient and stable when clinicians perform bronchoscopy operations. It has higher accuracy and diagnostic rates, and less complications than bronchoscopy with the assistance of magnetic navigation and ordinary bronchoscopy. This article gave a review of the progress of robotic bronchoscopy systems, and a prospect of the combination with artificial intelligence.
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.