Search

Abstract Background Accurate prediction of visceral pleural invasion (VPI) in lung adenocarcinoma before operation can provide guidance and help for surgical operation and postoperative treatment. We investigate the value of intratumoral and peritumoral radiomics nomograms for preoperatively predicting the status of VPI in patients diagnosed with clinical stage IA lung adenocarcinoma. Methods A total of 404 patients from our hospital were randomly assigned to a training set (n = 283) and an internal validation set (n = 121) using a 7:3 ratio, while 81 patients from two other hospitals constituted the external validation set. We extracted 1218 CT-based radiomics features from the gross tumor volume (GTV) as well as the gross peritumoral tumor volume (GPTV5, 10, 15), respectively, and constructed radiomic models. Additionally, we developed a nomogram based on relevant CT features and the radscore derived from the optimal radiomics model. Results The GPTV10 radiomics model exhibited superior predictive performance compared to GTV, GPTV5, and GPTV15, with area under the curve (AUC) values of 0.855, 0.842, and 0.842 in the three respective sets. In the clinical model, the solid component size, pleural indentation, solid attachment, and vascular convergence sign were identified as independent risk factors among the CT features. The predictive performance of the nomogram, which incorporated relevant CT features and the GPTV10-radscore, outperformed both the radiomics model and clinical model alone, with AUC values of 0.894, 0.828, and 0.876 in the three respective sets. Conclusions The nomogram, integrating radiomics features and CT morphological features, exhibits good performance in predicting VPI status in lung adenocarcinoma.

Purpose: It is vital to develop noninvasive approaches with high accuracy to discriminate the preserved ratio impaired spirometry (PRISm) group from the chronic obstructive pulmonary disease (COPD) groups. Radiomics has emerged as an image analysis technique. This study aims to develop and confirm the new radiomics-based noninvasive approach to discriminate these two groups. Methods: Totally 1066 subjects from 4 centers were included in this retrospective research, and classified into training, internal validation or external validation sets. The chest computed tomography (CT) images were segmented by the fully automated deep learning segmentation algorithm (Unet231) for radiomics feature extraction. We established the radiomics signature (Rad-score) using the least absolute shrinkage and selection operator algorithm, then conducted ten-fold cross-validation using the training set. Last, we constructed a radiomics signature by incorporating independent risk factors using the multivariate logistic regression model. Model performance was evaluated by receiver operating characteristic (ROC) curve, calibration curve, and decision curve analyses (DCA). Results: The Rad-score, including 15 radiomic features in whole-lung region, which was suitable for diffuse lung diseases, was demonstrated to be effective for discriminating between PRISm and COPD. Its diagnostic accuracy was improved through integrating Rad-score with a clinical model, and the area under the ROC (AUC) were 0.82(95 %CI 0.79–0.86), 0.77(95 %CI 0.72–0.83) and 0.841(95 %CI 0.78–0.91) for training, internal validation and external validation sets, respectively. As revealed by analysis, radiomics nomogram showed good fit and superior clinical utility. Conclusions: The present work constructed the new radiomics-based nomogram and verified its reliability for discriminating between PRISm and COPD.

PURPOSETo investigate the value of clinical characteristics and radiological features for predicting spread through air spaces (STAS) in patients with clinical stage IA non-small cell lung cancer (NSCLC).METHODSA total of 336 patients with NSCLC from our hospital were randomly divided into two groups, i.e., the training cohort (n = 236) and the internal validation cohort (n = 100) (7:3 ratio). Furthermore, 69 patients from two other hospitals were collected as the external validation cohort. Eight clinical patient characteristics were recorded, and 20 tumor radiological features were quantitatively measured and qualitatively analyzed. In the training cohort, the differences in clinical characteristics and radiological features were compared using univariate and multivariate analysis. A nomogram was created, and the predictive efficacy of the model was evaluated in the validation cohorts. The receiver operating characteristic curve and area under the curve (AUC) value were used to evaluate the discriminative ability of the model. In addition, the Hosmer–Lemeshow test and calibration curve were used to evaluate the goodness-of-fit of the model, and the decision curve was used to analyze the model’s clinical application value.RESULTSThe best predictors included gender, the carcinoembryonic antigen (CEA), consolidation-to-tumor ratio (CTR), density type, and distal ribbon sign. Among these, the tumor density type [odds ratio (OR): 6.738] and distal ribbon sign (OR: 5.141) were independent risk factors for predicting the STAS status. Moreover, three different STAS prediction models were constructed, i.e., a clinical, radiological, and combined model. The clinical model comprised gender and the CEA, the radiological model included the CTR, density type, and distal ribbon sign, and the combined model comprised the above two models. A DeLong test results revealed that the combined model was superior to the clinical model in all three cohorts and superior to the radiological model in the external validation cohort; the cohort AUC values were 0.874, 0.822, and 0.810, respectively. The results also showed that the combined model had the highest diagnostic efficacy among the models. The Hosmer–Lemeshow test showed that the combined model showed a good fit in all three cohorts, and the calibration curve showed that the predicted probability value of the combined model was in good agreement with the actual STAS status. Finally, the decision curve showed that the combined model had a better clinical application value than the clinical and radiological models.CONCLUSIONThe nomogram created in this study, based on clinical characteristics and radiological features, has a high diagnostic efficiency for predicting the STAS status in patients with clinical stage IA NSCLC and may support the creation of personalized treatment strategies before surgery.

PURPOSETo assess the quantification accuracy of pulmonary nodules using virtual monoenergetic images (VMIs) derived from spectral-detector computed tomography (CT) under an ultra-low-dose scan protocol.METHODSA chest phantom consisting of 12 pulmonary nodules was scanned using spectral-detector CT at 100 kVp/10 mAs, 100 kVp/20 mAs, 120 kVp/10 mAs, and 120 kVp/30 mAs. Each scanning protocol was repeated three times. Each CT scan was reconstructed utilizing filtered back projection, hybrid iterative reconstruction, iterative model reconstruction (IMR), and VMIs of 40–100 keV. The signal-to-noise ratio and air noise of images, absolute differences, and absolute percentage measurement errors (APEs) of the diameter, density, and volume of the four scan protocols and ten reconstruction images were compared.RESULTSWith each fixed reconstruction image, the four scanning protocols exhibited no significant differences in APEs for diameter and density (all P > 0.05). Of the four scan protocols and ten reconstruction images, APEs for nodule volume had no significant differences (all P > 0.05). At 100 kVp/10 mAs, APEs for density using IMR were the lowest (APE-mean: 6.69), but no significant difference was detected between VMIs at 50 keV (APE-mean: 11.69) and IMR (P = 0.666). In the subgroup analysis, at 100 kVp/10 mAs, there were no significant differences between VMIs at 50 keV and IMR in diameter and density (all P > 0.05). The radiation dose at 100 kVp/10 mAs was reduced by 77.8% compared with that at 120 kVp/30 mAs.CONCLUSIONCompared with IMR, reconstruction at 100 kVp/10 mAs and 50 keV provides a more accurate quantification of pulmonary nodules, and the radiation dose is reduced by 77.8% compared with that at 120 kVp/30 mAs, demonstrating great potential for ultra-low-dose spectral-detector CT.

PURPOSEPreoperative prediction of visceral pleural invasion (VPI) is important because it enables thoracic surgeons to choose appropriate surgical plans. This study aimed to develop and validate a multivariate logistic regression model incorporating the maximum standardized uptake value (SUVmax) and valuable computed tomography (CT) signs for the non-invasive prediction of VPI status in subpleural clinical stage IA lung adenocarcinoma patients before surgery.METHODSA total of 140 patients with subpleural clinical stage IA peripheral lung adenocarcinoma were recruited and divided into a training set (n = 98) and a validation set (n = 42), according to the positron emission tomography/CT examination temporal sequence, with a 7:3 ratio. Next, VPI-positive and VPI-negative groups were formed based on the pathological results. In the training set, the clinical information, the SUVmax, the relationship between the tumor and the pleura, and the CT features were analyzed using univariate analysis. The variables with significant differences were included in the multivariate analysis to construct a prediction model. A nomogram based on multivariate analysis was developed, and its predictive performance was verified in the validation set.RESULTSThe size of the solid component, the consolidation-to-tumor ratio, the solid component pleural contact length, the SUVmax, the density type, the pleural indentation, the spiculation, and the vascular convergence sign demonstrated significant differences between VPI-positive (n = 40) and VPI-negative (n = 58) cases on univariate analysis in the training set. A multivariate logistic regression model incorporated the SUVmax [odds ratio (OR): 1.753, P = 0.002], the solid component pleural contact length (OR: 1.101, P = 0.034), the pleural indentation (OR: 5.075, P = 0.041), and the vascular convergence sign (OR: 13.324, P = 0.025) as the best combination of predictors, which were all independent risk factors for VPI in the training group. The nomogram indicated promising discrimination, with an area under the curve value of 0.892 [95% confidence interval (CI), 0.813–0.946] in the training set and 0.885 (95% CI, 0.748–0.962) in the validation set. The calibration curve demonstrated that its predicted probabilities were in acceptable agreement with the actual probability. The decision curve analysis illustrated that the current nomogram would add more net benefit.CONCLUSIONThe nomogram integrating the SUVmax and the CT features could non-invasively predict VPI status before surgery in subpleural clinical stage IA lung adenocarcinoma patients.

ObjectiveTo develop and validate the model for predicting benign and malignant ground-glass nodules (GGNs) based on the whole-lung baseline CT features deriving from deep learning and radiomics.MethodsThis retrospective study included 385 GGNs from 3 hospitals, confirmed by pathology. We used 239 GGNs from Hospital 1 as the training and internal validation set; 115 and 31 GGNs from Hospital 2 and Hospital 3 as the external test sets 1 and 2, respectively. An additional 32 stable GGNs from Hospital 3 with more than five years of follow-up were used as the external test set 3. We evaluated clinical and morphological features of GGNs at baseline chest CT and extracted the whole-lung radiomics features simultaneously. Besides, baseline whole-lung CT image features are further assisted and extracted using the convolutional neural network. We used the back-propagation neural network to construct five prediction models based on different collocations of the features used for training. The area under the receiver operator characteristic curve (AUC) was used to compare the prediction performance among the five models. The Delong test was used to compare the differences in AUC between models pairwise.ResultsThe model integrated clinical-morphological features, whole-lung radiomic features, and whole-lung image features (CMRI) performed best among the five models, and achieved the highest AUC in the internal validation set, external test set 1, and external test set 2, which were 0.886 (95% CI: 0.841-0.921), 0.830 (95%CI: 0.749-0.893) and 0.879 (95%CI: 0.712-0.968), respectively. In the above three sets, the differences in AUC between the CMRI model and other models were significant (all P < 0.05). Moreover, the accuracy of the CMRI model in the external test set 3 was 96.88%.ConclusionThe baseline whole-lung CT features were feasible to predict the benign and malignant of GGNs, which is helpful for more refined management of GGNs.

ObjectiveThis study aimed to develop effective artificial intelligence (AI) diagnostic models based on CT images of pulmonary nodules only, on descriptional and quantitative clinical or image features, or on a combination of both to differentiate benign and malignant ground-glass nodules (GGNs) to assist in the determination of surgical intervention.MethodsOur study included a total of 867 nodules (benign nodules: 112; malignant nodules: 755) with postoperative pathological diagnoses from two centers. For the diagnostic models to discriminate between benign and malignant GGNs, we adopted three different artificial intelligence (AI) approaches: a) an image-based deep learning approach to build a deep neural network (DNN); b) a clinical feature-based machine learning approach based on the clinical and image features of nodules; c) a fusion diagnostic model integrating the original images and the clinical and image features. The performance of the models was evaluated on an internal test dataset (the “Changzheng Dataset”) and an independent test dataset collected from an external institute (the “Longyan Dataset”). In addition, the performance of automatic diagnostic models was compared with that of manual evaluations by two radiologists on the ‘Longyan dataset’.ResultsThe image-based deep learning model achieved an appealing diagnostic performance, yielding AUC values of 0.75 (95% confidence interval [CI]: 0.62, 0.89) and 0.76 (95% CI: 0.61, 0.90), respectively, on both the Changzheng and Longyan datasets. The clinical feature-based machine learning model performed well on the Changzheng dataset (AUC, 0.80 [95% CI: 0.64, 0.96]), whereas it performed poorly on the Longyan dataset (AUC, 0.62 [95% CI: 0.42, 0.83]). The fusion diagnostic model achieved the best performance on both the Changzheng dataset (AUC, 0.82 [95% CI: 0.71-0.93]) and the Longyan dataset (AUC, 0.83 [95% CI: 0.70-0.96]), and it achieved a better specificity (0.69) than the radiologists (0.33-0.44) on the Longyan dataset.ConclusionThe deep learning models, including both the image-based deep learning model and the fusion model, have the ability to assist radiologists in differentiating between benign and malignant nodules for the precise management of patients with GGNs.

PURPOSE Preoperative prediction of visceral pleural invasion (VPI) is important because it enables thoracic surgeons to choose appropriate surgical plans. This study aimed to develop and validate a multivariate logistic regression model incorporating the maximum standardized uptake value (SUVmax) and valuable computed tomography (CT) signs for the non-invasive prediction of VPI status in subpleural clinical stage IA lung adenocarcinoma patients before surgery. METHODS A total of 140 patients with subpleural clinical stage IA peripheral lung adenocarcinoma were recruited and divided into a training set (n = 98) and a validation set (n = 42), according to the positron emission tomography/CT examination temporal sequence, with a 7:3 ratio. Next, VPI-positive and VPI-negative groups were formed based on the pathological results. In the training set, the clinical information, the SUVmax, the relationship between the tumor and the pleura, and the CT features were analyzed using univariate analysis. The variables with significant differences were included in the multivariate analysis to construct a prediction model. A nomogram based on multivariate analysis was developed, and its predictive performance was verified in the validation set. RESULTS The size of the solid component, the consolidation-to-tumor ratio, the solid component pleural contact length, the SUVmax, the density type, the pleural indentation, the spiculation, and the vascular convergence sign demonstrated significant differences between VPI-positive (n = 40) and VPI-negative (n = 58) cases on univariate analysis in the training set. A multivariate logistic regression model incorporated the SUVmax [odds ratio (OR): 1.753, P = 0.002], the solid component pleural contact length (OR: 1.101, P = 0.034), the pleural indentation (OR: 5.075, P = 0.041), and the vascular convergence sign (OR: 13.324, P = 0.025) as the best combination of predictors, which were all independent risk factors for VPI in the training group. The nomogram indicated promising discrimination, with an area under the curve value of 0.892 [95% confidence interval (CI), 0.813-0.946] in the training set and 0.885 (95% CI, 0.748-0.962) in the validation set. The calibration curve demonstrated that its predicted probabilities were in acceptable agreement with the actual probability. The decision curve analysis illustrated that the current nomogram would add more net benefit. CONCLUSION The nomogram integrating the SUVmax and the CT features could non-invasively predict VPI status before surgery in subpleural clinical stage IA lung adenocarcinoma patients. [ABSTRACT FROM AUTHOR]