Objective To investigate the accuracy of 18F-FDG positron emission tomography/computed tomography (PET/CT) combined with CT three-dimensional reconstruction (CT-3D) in the differential diagnosis of benign and malignant pulmonary nodules. Methods The clinical data of patients who underwent pulmonary nodule surgery in the Department of Thoracic Surgery, Northern Jiangsu People's Hospital from July 2020 to August 2021 were retrospectively analyzed. The preoperative 18F-FDG PET/CT and chest enhanced CT-3D and other imaging data were extracted. The parameters with diagnostic significance were screened by the area under the receiver operating characteristic (ROC) curve (AUC). Three prediction models, including PET/CT prediction model (MOD PET), CT-3D prediction model (MOD CT-3D), and PET/CT combined CT-3D prediction model (MOD combination), were established through binary logistic regression, and the diagnostic performance of the models were validated by ROC curve. Results A total of 125 patients were enrolled, including 57 males and 68 females, with an average age of 61.16±8.57 years. There were 46 patients with benign nodules, and 79 patients with malignant nodules. A total of 2 PET/CT parameters and 5 CT-3D parameters were extracted. Two PET/CT parameters, SUVmax≥1.5 (AUC=0.688) and abnormal uptake of hilar/mediastinal lymph node metabolism (AUC=0.671), were included in the regression model. Among the CT-3D parameters, CT value histogram peaks (AUC=0.694) and CT-3D morphology (AUC=0.652) were included in the regression model. Finally, the AUC of the MOD PET was verified to be 0.738 [95%CI (0.651, 0.824)], the sensitivity was 74.7%, and the specificity was 60.9%; the AUC of the MOD CT-3D was 0.762 [95%CI (0.677, 0.848)], the sensitivity was 51.9%, and the specificity was 87.0%; the AUC of the MOD combination was 0.857 [95%CI (0.789, 0.925)], the sensitivity was 77.2%, the specificity was 82.6%, and the differences were statistically significant (P<0.001). Conclusion 18F-FDG PET/CT combined with CT-3D can improve the diagnostic performance of pulmonary nodules, and its specificity and sensitivity are better than those of single imaging diagnosis method. The combined prediction model is of great significance for the selection of surgical timing and surgical methods for pulmonary nodules, and provides a theoretical basis for the application of artificial intelligence in the pulmonary nodule diagnosis.
Automatic detection of pulmonary nodule based on computer tomography (CT) images can significantly improve the diagnosis and treatment of lung cancer. However, there is a lack of effective interactive tools to record the marked results of radiologists in real time and feed them back to the algorithm model for iterative optimization. This paper designed and developed an online interactive review system supporting the assisted diagnosis of lung nodules in CT images. Lung nodules were detected by the preset model and presented to doctors, who marked or corrected the lung nodules detected by the system with their professional knowledge, and then iteratively optimized the AI model with active learning strategy according to the marked results of radiologists to continuously improve the accuracy of the model. The subset 5−9 dataset of the lung nodule analysis 2016(LUNA16) was used for iteration experiments. The precision, F1-score and MioU indexes were steadily improved with the increase of the number of iterations, and the precision increased from 0.213 9 to 0.565 6. The results in this paper show that the system not only uses deep segmentation model to assist radiologists, but also optimizes the model by using radiologists' feedback information to the maximum extent, iteratively improving the accuracy of the model and better assisting radiologists.
The precise localization of pulmonary nodules has become an important technical key point in the treatment of pulmonary nodules by thoracoscopic surgery, which is a guarantee for safe margin and avoiding removal of too much normal lung parenchyma. With the development of medical technology and equipment, the methods of locating pulmonary nodules are also becoming less trauma and convenience. There are currently a number of methods applied to the preoperative or intraoperative localization of pulmonary nodules, including preoperative percutaneous puncture localization, preoperative transbronchial localization, intraoperative palpation localization, intraoperative ultrasound localization, and localization according to anatomy. The most appropriate localization method should be selected according to the location of the nodule, available equipment, and surgeon’s experience. According to the published literatures, we have sorted out a variety of different theories and methods of localization of pulmonary nodules in this article, summarizing their advantages and disadvantages for references.
ObjectiveTo analyze the independent risk factors affecting complications of preoperative CT-guided Hookwire localization of pulmonary nodules, and establish and validate a nomogram risk prediction model. MethodsClinical data of patients who underwent thoracoscopic lung surgery with preoperative CT-guided Hookwire localization at the Department of Thoracic Surgery, Affiliated Nanjing Brain Hospital, Nanjing Medical University from January 2023 to October 2023 were collected. Patients were divided into a complication group and a non-complication group according to whether they had complications. The clinical data of the two groups were compared by univariate analysis and multivariate binary logistic regression analysis to determine the independent risk factors causing complications during localization, and a nomogram prediction model was established. The discrimination of the model was evaluated by receiver operating characteristic (ROC) curve, and the consistency between predicted events and actual results was evaluated by calibration curve. ResultsA total of 300 patients were included, including 143 males and 157 females, aged 24-68 (46.00±22.81) years. Univariate analysis showed that there were statistically significant differences in age, number and location of nodules, preoperative anxiety score, history of chronic obstructive pulmonary disease (COPD), number of needle adjustments, pain score, and distance between the tip of the localization needle and the visceral pleura between the two groups (P<0.05). Multivariate binary logistic regression analysis suggested that pain score [OR=1.253, 95%CI (1.094, 1.434), P=0.001], age [OR=1.020, 95%CI (1.000, 1.042), P=0.049], history of COPD [OR=3.281, 95%CI (1.751, 6.146), P<0.001], number of nodules [OR=1.667, 95%CI (1.221, 2.274), P=0.001], preoperative anxiety score [OR=1.061, 95%CI (1.031, 1.092), P<0.001], number of needle adjustments [OR=1.832, 95%CI (1.263, 2.658), P=0.001], and distance between the needle tip and the visceral pleura [OR=1.759, 95%CI (1.373, 2.254), P<0.001] were associated with localization complications. The area under the ROC curve for the modeling group was 0.825, and that for the validation group was 0.845. Hosmer-Lemeshow test showed that there was no statistically significant difference between the ideal curve of the model fitting curve and that of the modeling group and internal validation group, indicating good goodness of fit (χ2=6.488, P=0.593). ConclusionAdvanced age, multiple nodules, preoperative anxiety, history of COPD, multiple needle adjustments, severe pain during localization, and long distance between the tip of the localization needle and the visceral pleura are independent risk factors for complications of lung nodule localization, and the prediction model based on these factors has good predictive performance.
Objective To explore the efficacy of a novel detection technique of circulating tumor cells (CTCs) to identify benign and malignant lung nodules. Methods Nanomagnetic CTC detection based on polypeptide with epithelial cell adhesion molecule (EpCAM)-specific recognition was performed on enrolled patients with pulmonary nodules. There were 73 patients including 48 patients with malignant lesions as a malignant group and 25 patients with benign lesion as a benign group. There were 13 males and 35 females at age of 57.0±11.9 years in the malignant group and 11 males and 14 females at age of 53.1±13.2 years in the benign group. e calculated the differential diagnostic efficacy of CTC count, and conducted subgroup analysis according to the consolidation-tumor ratio, while compared with PET/CT on the efficacy. Results CTC count of the malignant group was significantly higher than that of the benign group (0.50/ml vs. 0.00/ml, P<0.05). Subgroup analysis according to consolidation tumor ratio (CTR) revealed that the difference was statistically significant in pure ground glass (pGGO) nodules 1.00/mlvs. 0.00/ml, P<0.05), but not in part-solid or pure solid nodules. For pGGO nodules, the area under the receiver operating characteristic (ROC) curve of CTC count was 0.833, which was significantly higher than that of maximum of standardized uptake value (SUVmax) (P<0.001). Its sensitivity and specificity was 80.0% and 83.3%, respectively. Conclusion The peptide-based nanomagnetic CTC detection system can differentiate malignant tumor and benign lesions in pulmonary nodules presented as pGGO. It is of great clinical potential as a noninvasive, nonradiating method to identify malignancies in pulmonary nodules.
Lung cancer has brought tough challenges to human health due to its high incidence and mortality rate in the current practice. Nowadays, computed tomography (CT) imaging is still the most preferred diagnostic tool for early screening of lung cancer. However, a great challenge brought from accumulative CT imaging data can not meet the demand of the current clinical practice. As a novel kind of artificial intelligence technique aimed to deal with medical images, a computer-aided diagnosis has been found to provide useful auxiliary information, attenuate the workload of doctors, and significantly improve the efficiency and accuracy for clinical diagnosis of lung cancer. Therefore, an effective combination of computer-aided techniques and CT imaging has increasingly become an active area of investigation in early diagnosis of lung cancer. This review aims to summarize the latest progress on the diagnostic value of computer-aided technology with regard to early stage lung cancer from the perspectives of machine learning and deep learning.
The widespread application of low-dose computed tomography (LDCT) has significantly increased the detection of pulmonary small nodules, while accurate prediction of their growth patterns is crucial to avoid overdiagnosis or underdiagnosis. This article reviews recent research advances in predicting pulmonary nodule growth based on CT imaging, with a focus on summarizing key factors influencing nodule growth, such as baseline morphological parameters, dynamic indicators, and clinical characteristics, traditional prediction models (exponential and Gompertzian models), and the applications and limitations of radiomics-based and deep learning models. Although existing studies have achieved certain progress in predicting nodule growth, challenges such as small sample sizes and lack of external validation persist. Future research should prioritize the development of personalized and visualized prediction models integrated with larger-scale datasets to enhance predictive accuracy and clinical applicability.
ObjectiveTo analyze the results and rationality of the lesion-focused strategy with subsegment as the pulmonary anatomical unit for pulmonary nodules with a diameter of ≤2 cm which require surgery. MethodsClinical data of 246 patients with pulmonary nodules who underwent surgery in the Department of Thoracic Surgery of The First Affiliated Hospital of Nanjing Medical University from January 2017 to October 2018 were retrospectively analyzed, including 76 males and 170 females, with an average age of 53.30±11.82 years. The patients were divided into four groups, a single segmentectomy group, a segmentectomy combined with adjacent subsegmentectomy group, a single subsegmentectomy group and a combined subsegmentectomy group, according to the different surgical approaches, to compare preoperative, intraoperative, and postoperative related data. ResultsThere was no perioperative death. Among the four groups, there was no statistical difference in gender (P=0.163), age (P=0.691), diameter of the nodule (P=0.743), longitudinal position of the nodule (depth ratio, P=0.831), postoperative pulmonary leakage (P=0.752), intraoperative blood loss (P=0.135), pathological type (P=0.951) or TNM stage (P=0.995); there were statistical differences in transverse position of the nodule (P<0.001) and number of subsegments involved (P<0.001). The results of multivariate logistic regression analysis showed that compared with combined subsegmentectomy, the odds ratio (OR) of the lung nodule in segmentectomy combined with adjacent subsegmentectomy as intersegment nodules was 5.759 (95%CI 1.162 to 28.539, P=0.032).Conclusion The surgical strategy of lesion focused and subsegment as anatomical unit is safe and feasible for surgical treatment of pulmonary nodules with diameter ≤2 cm. The transverse position of the nodules is an important factor affecting the choice of surgical method for the middle and lateral nodules with a diameter of ≤2 cm, and the longitudinal location of the nodule is not an influencing factor. For nodules in inner zone, the diameter also is one of the factors influencing the choice of surgical method.
With the widespread adoption of low-dose CT screening and the extensive application of high-resolution CT, the detection rate of sub-centimeter lung nodules has significantly increased. How to scientifically manage these nodules while avoiding overtreatment and diagnostic delays has become an important clinical issue. Among them, lung nodules with a consolidation tumor ratio less than 0.25, dominated by ground-glass shadows, are particularly worthy of attention. The therapeutic challenge for this group is how to achieve precise and complete resection of nodules during surgery while maximizing the preservation of the patient's lung function. The "watershed topography map" is a new technology based on big data and artificial intelligence algorithms. This method uses Dicom data from conventional dose CT scans, combined with microscopic (22-24 levels) capillary network anatomical watershed features, to generate high-precision simulated natural segmentation planes of lung sub-segments through specific textures and forms. This technology forms fluorescent watershed boundaries on the lung surface, which highly fit the actual lung anatomical structure. By analyzing the adjacent relationship between the nodule and the watershed boundary, real-time, visually accurate positioning of the nodule can be achieved. This innovative technology provides a new solution for the intraoperative positioning and resection of lung nodules. This consensus was led by four major domestic societies, jointly with expert teams in related fields, oriented to clinical practical needs, referring to domestic and foreign guidelines and consensus, and finally formed after multiple rounds of consultation, discussion, and voting. The main content covers the theoretical basis of the "watershed topography map" technology, indications, operation procedures, surgical planning details, and postoperative evaluation standards, aiming to provide scientific guidance and exploration directions for clinical peers who are currently or plan to carry out lung nodule resection using the fluorescent microscope watershed analysis method.
ObjectiveTo explore and analyze the risk factors of pleural invasion in patients with small nodular type stage ⅠA pulmonary adenocarcinoma.MethodsFrom June 2016 to December 2017, 168 patients with small nodular type stage ⅠA pulmonary adenocarcinoma underwent surgical resection in the First Affiliated Hospital of Nanjing Medical University. There were 59 males and 109 females aged 58.7±11.5 years ranging from 28 to 83 years. The clinical data were analyzed retrospectively. Single factor Chi-square test and multivariate logistic regression were used to analyze the independent risk factors of pleural invasion.ResultsAmong 168 patients, 20 (11.9%) were pathologically confirmed with pleural invasion and 148 (88.1%) with no pleural invasion. Single factor analysis revealed significant differences (P<0.05) in nodule size, nodule status, pathological type, relation of lesion to pleura (RLP), distance of lesion to pleura (DLP), epidermal growth factor receptor (EGFR) mutation between patients with and without pleural invasion in stage ⅠA pulmonary adenocarcinoma. Logistic multivariate regression analysis showed that significant differences of nodule size, nodule status, RLP, DLP and EGFR mutation existed between the two groups (P<0.05), which were independent risk factors for pleural invasion.ConclusionImageological-pathological-biological characteristics of patients with small nodular type stage ⅠA pulmonary adenocarcinoma are closely related to pleural invasion. The possibility of pleural invasion should be evaluated by combining these parameters in clinical diagnosis and treatment.