ObjectiveTo establish and internally validate a predictive model for poorly differentiated adenocarcinoma based on CT imaging and tumor marker results. MethodsPatients with solid and partially solid lung nodules who underwent lung nodule surgery at the Department of Thoracic Surgery, the Affiliated Brain Hospital of Nanjing Medical University in 2023 were selected and randomly divided into a training set and a validation set at a ratio of 7:3. Patients' CT features, including average density value, maximum diameter, pleural indentation sign, and bronchial inflation sign, as well as patient tumor marker results, were collected. Based on postoperative pathological results, patients were divided into a poorly differentiated adenocarcinoma group and a non-poorly differentiated adenocarcinoma group. Univariate analysis and logistic regression analysis were performed on the training set to establish the predictive model. The receiver operating characteristic (ROC) curve was used to evaluate the model's discriminability, the calibration curve to assess the model's consistency, and the decision curve to evaluate the clinical value of the model, which was then validated in the validation set. ResultsA total of 299 patients were included, with 103 males and 196 females, with a median age of 57.00 (51.00, 67.25) years. There were 211 patients in the training set and 88 patients in the validation set. Multivariate analysis showed that carcinoembryonic antigen (CEA) value [OR=1.476, 95%CI (1.184, 1.983), P=0.002], cytokeratin 19 fragment antigen (CYFRA21-1) value [OR=1.388, 95%CI (1.084, 1.993), P=0.035], maximum tumor diameter [OR=6.233, 95%CI (1.069, 15.415), P=0.017], and average density [OR=1.083, 95%CI (1.020, 1.194), P=0.040] were independent risk factors for solid and partially solid lung nodules as poorly differentiated adenocarcinoma. Based on this, a predictive model was constructed with an area under the ROC curve of 0.896 [95%CI (0.810, 0.982)], a maximum Youden index corresponding cut-off value of 0.103, sensitivity of 0.750, and specificity of 0.936. Using the Bootstrap method for 1000 samplings, the calibration curve predicted probability was consistent with actual risk. Decision curve analysis indicated positive benefits across all prediction probabilities, demonstrating good clinical value. ConclusionFor patients with solid and partially solid lung nodules, preoperative use of CT to measure tumor average density value and maximum diameter, combined with tumor markers CEA and CYFRA21-1 values, can effectively predict whether it is poorly differentiated adenocarcinoma, allowing for early intervention.
ObjectiveTo evaluate the diagnostic value of endobronchial ultrasound technology in combination with LungPoint virtual navigation system for pulmonary peripheral nodules. MethodsRetrospective analysis of 317 patients with peripheral pulmonary nodules who underwent endobronchial ultrasound at the endoscopy center of Shanghai Pulmonary Hospital from January 2021 to March 2022 was used as the study population. They were divided into the endobronchial ultrasound group (EBUS-GS group) and the virtual navigation combined with endobronchial ultrasound group (VBN+EBUS-GS group) according to whether the path was planned with the LungPoint virtual navigation system preoperatively or not. The diagnostic rate, bronchoscopic arrival rate, arrival time, operation time and complications were compared between the EBUS-GS group and the VBN+EBUS-GS group, and the factors associated with the diagnostic rate of endobronchial ultrasound were analyzed. ResultsThere were 101 malignant nodules and 216 benign nodules. The mean size of lung nodules was (1.9±0.7) cm and (1.8±0.6) cm in the EBUS-GS and VBN+EUBS-GS groups, respectively (P>0.05); The time to reach the lesions was 7 (5 - 9) and 4 (3 - 5) min, and the total operation time was 18 (16 - 20) and 16 (14 - 18) min, respectively (P<0.05). The arrival rates of endobronchial ultrasound in the two groups was 82.6% and 98.1% (P<0.05), respectively. The overall diagnostic rate, malignant nodule diagnostic rate and benign nodule diagnostic rate of the two groups were 61.3% vs. 64.8%, 67.9% vs. 68.6% and 57.6% vs. 63.1% respectively (P>0.05). There was one pneumothorax in the EBUS-GS group after examination (0.6%, 1/155). No complications such as hemoptysis or infection occurred in all patients. ConclusionsLungPoint virtual navigation can significantly improve the arrival rate of lesions under endobronchial ultrasound, significantly reduce the arrival time of endobronchial ultrasound to the lesions and the total operation time, which is beneficial to improve the efficiency of clinical examination.
ObjectiveTo analyze the value of structured electronic medical records for pulmonary nodules in increasing the ability of outpatient service and hospital management by resident physicians.MethodsWe included 40 trainees [94 males and 26 females aged 22-31 (26.45±2.81) years] who were trained in the standardized training base for surgical residents in our hospital from January 2018 to January 2021. The trainees were randomly divided into two groups including a structured group using the structured electronic medical record for pulmonary nodule and an unstructured group using unstructured electronic medical record designed by our department. The time of completing hospitalization records and first-time course records, the quality of course records, the accuracy of issuing admission orders, the quality of teaching rounds, and patient’s satisfaction between the two groups were analyzed and compared.Results(1) The average time in the structured group to complete inpatient medical records was significantly shorter than that of the unstructured group (53.61±8.12 min vs. 84.25±16.09 min, P<0.010); the average time in the structured group to complete the first-time course record was shorter than that of the unstructured group (13.20±5.43 min vs. 27.51±8.62 min, P<0.010), and there was a significant statistical difference between the two groups. (2) The overall teaching round quality score of the students in the structured group was significantly higher than that in the unstructured group (84.21±15.61 vs. 70.91±12.28, P<0.010). (3) The score of the medical record writing quality of the structured group was significantly higher than that of the unstructured group (80.25±9.22 vs. 74.22±5.40, P<0.010).ConclusionThe structured electronic medical record specific for pulmonary nodules can effectively improve the training efficiency in the standardized training of surgical residents, improve the clinical ability to deal with pulmonary nodules, improve the integrity and accuracy of key clinical data collected by students, and improve doctor-patient relationship.
Objective To explore the clinical value of artificial intelligence (AI) quantitative parameters in distinguishing pathological grades of stageⅠ invasive adenocarcinoma (IAC). Methods Clinical data of patients with clinical stageⅠ IAC admitted to Yantaishan Hospital Affiliated to Binzhou Medical University from October 2018 to May 2023 were retrospectively analyzed. Based on the 2021 WHO pathological grading criteria for lung adenocarcinoma, IAC was divided into gradeⅠ, grade Ⅱ, and grade Ⅲ. The differences in parameters among the groups were compared, and logistic regression analysis was used to evaluate the predictive efficacy of AI quantitative parameters for grade Ⅲ IAC patients. Parameters were screened using least absolute shrinkage and selection operator (LASSO) regression analysis. Three machine learning models were constructed based on these parameters to predict grade Ⅲ IAC and were internally validated to assess their efficacy. Nomograms were used for visualization. ResultsA total of 261 IAC patients were included, including 101 males and 160 females, with an average age of 27-88 (61.96±9.17) years. Six patients had dual primary lesions, and different lesions from the same patient were analyzed as independent samples. There were 48 patients of gradeⅠ IAC, 89 patients of grade Ⅱ IAC, and 130 patients of grade Ⅲ IAC. There were statitical differences in the AI quantitive parameters such as consolidation/tumor ratio (CTR), ect among the three goups. (P<0.05). Univariate analysis showed that the differences in all variables except age were statistically significant (P<0.05) between the group gradeⅠ+grade Ⅱand the group grade Ⅲ . Multivariate analysis suggested that CTR and CT standard deviation were independent risk factors for identifying grade Ⅲ IAC, and the two were negatively correlated. Grade Ⅲ IAC exhibited advanced TNM staging, more pathological high-risk factors, higher lymph node metastasis rate, and higher proportion of advanced structure. CTR was positively correlated with the proportion of advanced structures in all patients. This correlation was also observed in grade Ⅲ but not in gradeⅠand grade ⅡIAC. CTR and CT median value were selected by using LASSO regression. Logistic regression, random forest, and XGBoost models were constructed and validated, among which, the XGBoost model demonstrated the best predictive performance. Conclusion Cautious consideration should be given to grade Ⅲ IAC when CTR is higher than 39.48% and CT standard deviation is less than 122.75 HU. The XGBoost model based on combined CTR and CT median value has good predictive efficacy for grade Ⅲ IAC, aiding clinicians in making personalized clinical decisions.
Objective To analyze the benign-malignant outcomes of pulmonary nodules in surgical patients and their influencing factors, and provide evidence and ideas for optimizing and improving the integrated management model of pulmonary nodules. Methods From October to December 2023, a convenience sampling method was used to select patients who underwent lung surgery at West China Hospital, Sichuan University between July 2022 and June 2023 for this study. The malignancy rate of postoperative pathological results of pulmonary nodules and its influencing factors were analyzed using univariate analysis and multiple logistic regression. Results A total of 4600 surgical patients with pulmonary nodules were included, with a malignancy rate of 88.65% (4078/4600) and a benign rate of 11.35% (522/4600). Univariate analysis showed significant differences in malignancy rates among different genders, ages, methods of pulmonary nodule detection, and smoking histories (P<0.05); however, no significant difference was found regarding place of birth or family history of lung cancer (P>0.05). Multiple logistic regression analysis indicated that females [odds ratio (OR)=1.533, 95% confidence interval (CI) (1.271, 1.850)], older age groups [61-75 vs. ≤30 years: OR=1.640, 95%CI (1.021, 2.634); >75 vs. ≤30 years: OR=2.690, 95%CI (1.062, 6.814)], and pulmonary nodules detected during physical examinations [OR=1.286, 95%CI (1.064, 1.554)] were high-risk factors for malignancy, with statistical significance (P<0.05). Conclusion In the integrated management of pulmonary nodules, it is crucial not to overlook females or older patients, as they may be more significant influencing factors than smoking; furthermore, lung examinations are effective means of early detection of malignant lung tumors and are worth promoting and popularizing.
ObjectiveTo investigate the diagnostic value of tuberculosis T cell spot test (T-SPOT.TB) and erythrocyte sedimentation rate (ESR) test in the diagnosis of simple pulmonary nodules in Xinjiang.MethodsA retrospective analysis of 72 patients with asymptomatic simple pulmonary nodules in the Department of Thoracic Surgery, the First Affiliated Hospital of Xinjiang Medical University from October 2017 to July 2019 was performed. According to the pathological results, the patients were divided into a tuberculoma group [n=23, including 14 males and 9 females, aged 37-84 (56.91±12.73) years] and a lung cancer group [n=49, including 31 males and 18 females, aged 34-83 (61.71±10.15) years]. The predictive value of T-SPOT.TB and ESR results for the diagnosis of simple pulmonary nodules was evaluated.ResultsThe positive rate of T-SPOT.TB in the tuberculoma group (69.60%) was higher than that in the lung cancer group (42.90%) (χ2=5.324, P=0.021), with a sensitivity of 69.56% and specificity of 57.14%; the positive ESR was 47.80% in the tuberculoma group and 59.20% in the lung cancer group, and no statistical difference was found between the two groups (χ2=0.981, P=0.322), with a sensitivity of 47.82% and specificity of 40.81%; the area under receiver operating characteristic curve (AUC) was 0.618, the 95% confidence interval of AUC was (0.479, 0.758), and the Youden’s index was 0.267 with a sensitivity of 69.60% and specificity of 57.10%. Difference in the T-SPOT.TB and ESR test results was statistically significant (χ2=4.986, P=0.026), but the correlation between the tests was weak with a Pearson contingency coefficient of 0.199. ESR results in patients with different ages were statistically different (χ2=7.343, P=0.025), but the correlation between age and ESR results was weak with a Pearson contingency coefficient of 0.239; T-SPOT.TB results in patients with different ages were not statistically different (χ2=0.865, P=0.649), and the correlation between age and ESR results was weak with a Pearson contingency coefficient of 0.084.ConclusionThe diagnostic value of T-SPOT.TB and ESR tests is small in the diagnosis of simple pulmonary nodules.
Objective To explore the diagnostic and treatment value of computed tomography (CT)-guided embolization coil localization of pulmonary nodules accurately resected under the thoracoscope. Methods Between October 2015 and October 2016, 40 patients with undiagnosed nodules of 15 mm or less were randomly divided into a no localization group (n=20, 11 males and 9 females with an average age of 60.50±8.27 years) or preoperative coil localization group (n=20, 12 males and 8 females with an average age of 61.35±8.47 years). Coils were placed with the distal end deep to the nodule and the superficial end coiled on the visceral pleural surface with subsequent visualization by video-assisted thoracoscopic (VATS). Nodules were removed by VATS wedge excision using endo staplers. The tissue was sent for rapid pathological examination, and the pulmonary nodules with definitive pathology found at the first time could be defined as the exact excision. Results The age, sex, forced expiratory volume in the first second of expiration, nodule size/depth were similar between two groups. The coil group had a higher rate of accurate resection (100.00% vs. 70.00%, P=0.008), less operation time to nodule excision (35.65±3.38 minvs. 44.38±11.53 min,P=0.003), and reduced stapler firings (3.25±0.85vs. 4.44±1.26,P=0.002) with no difference in total costs. Conclusion Preoperative CT-guided coil localization increases the rate of accurate resection.
The possibility of solitary pulmonary nodules tending to lung cancer is very high in the middle and late stage. In order to detect the middle and late solitary pulmonary nodules, we present a new computer-aided diagnosis method based on the geometric features. The new algorithm can overcome the disadvantage of the traditional algorithm which can't eliminate the interference of vascular cross section. The proposed algorithm was implemented by multiple clustering of the extracted geometric features of region of interest (ROI) through K-means algorithm, including degree of slenderness, similar degree of circle, degree of compactness and discrete degree. The 232 lung CT images were selected from Lung Image Database Consortium (LIDC) database to do contrast experiment. Compared with the traditional algorithm, the detection rate of the new algorithm was 92.3%, and the error rate was 14.8%. At the same time, the detection rate of the traditional algorithm was only 83.9%, and the error rate was 78.2%. The results show that the proposed algorithm can mark the solitary pulmonary nodules more accurately and reduce the error rate due to precluding the disturbance of vessel section.
Artificial intelligence (AI) has been widely used in all walks of life, including healthcare, and has shown great application value in the auxiliary diagnosis of pulmonary nodules in the medical field. In the face of a large amount of lung imaging data, clinicians use AI tools to identify lesions more quickly and accurately, improving work efficiency, but there are still many problems in this field, such as the high false positive rate of recognition, and the difficulty in identifying special types of nodules. Researchers and clinicians are actively developing and using AI tools to promote their continuous evolution and make them better serve human health. This article reviews the clinical application and research progress of AI-assisted diagnosis of pulmonary nodules.
Accurate segmentation of pulmonary nodules is an important basis for doctors to determine lung cancer. Aiming at the problem of incorrect segmentation of pulmonary nodules, especially the problem that it is difficult to separate adhesive pulmonary nodules connected with chest wall or blood vessels, an improved random walk method is proposed to segment difficult pulmonary nodules accurately in this paper. The innovation of this paper is to introduce geodesic distance to redefine the weights in random walk combining the coordinates of the nodes and seed points in the image with the space distance. The improved algorithm is used to achieve the accurate segmentation of pulmonary nodules. The computed tomography (CT) images of 17 patients with different types of pulmonary nodules were selected for segmentation experiments. The experimental results are compared with the traditional random walk method and those of several literatures. Experiments show that the proposed method has good accuracy in the segmentation of pulmonary nodule, and the accuracy can reach more than 88% with segmentation time is less than 4 seconds. The results could be used to assist doctors in the diagnosis of benign and malignant pulmonary nodules and improve clinical efficiency.