CT and CEA-based machine learning model for predicting malignant pulmonary nodules

Application of a nomogram from coagulation-related biomarkers and C1q and total bile acids in distinguishing advanced and early-stage lung cancer

BACKGROUND

This study aimed to establish a nomogram to distinguish advanced- and early-stage lung cancer based on coagulation-related biomarkers and liver-related biomarkers.

METHODS

A total of 306 patients with lung cancer and 172 patients with benign pulmonary disease were enrolled. Subgroup analyses based on histologic type, clinical stage, and neoplasm metastasis status were carried out and multivariable logistic regression analysis was applied. Furthermore, a nomogram model was developed and validated with bootstrap resampling.

RESULTS

The concentrations of complement C1q, fibrinogen, and D-dimers, fibronectin, inorganic phosphate, and prealbumin were significantly changed in lung cancer patients compared to benign pulmonary disease patients. Multiple regression analysis based on subgroup analysis of clinical stage showed that compared with early-stage lung cancer, female (P < 0.001), asymptomatic admission (P = 0.001), and total bile acids (P = 0.011) were negatively related to advanced lung cancer, while C1q (P = 0.038), fibrinogen (P < 0.001), and D-dimers (P = 0.001) were positively related. A nomogram model based on gender, symptom, and the levels of total bile acids, C1q, fibrinogen, and D-dimers was constructed for distinguishing advanced lung cancer and early-stage lung cancer, with an area under the receiver operating characteristic curve of 0.919. The calibration curve for this nomogram revealed good predictive accuracy (P-Hosmer-Lemeshow = 0.697) between the predicted probability and the actual probability.

CONCLUSIONS

We developed a nomogram based on gender, symptom, and the levels of fibrinogen, D-dimers, total bile acids, and C1q that can individually distinguish early- and advanced-stage lung cancer.

Comparison of serum from lung cancer patients and from patients with benign lung nodule using FTIR spectroscopy

Lungcancer remains the leading cause of cancer related deaths in worldwide. Earlydiagnosis oflungcancer can significantly improve survival rate. However, due to its close resemblance to the malignant nodules, the possible existence of benign nodules often leads to erroneous decisions. The aim of this study was to explore whether fourier transform infrared (FTIR) spectroscopy could improve the accuracy of early diagnosis of lung cancer by distinguishing lung cancer patients' (LCP') serum from patients with benign lung nodules' (PBLN') serum. In this study, A1243+1081/A1652+1539 ratio in LCP group was increased significantly compared with that in PBLN group, indicating that the ratio could be used to distinguish the serum of LCP from that of PBLN. In addition, the ratios of A2926/A2969, A1744/A2926+2859, A2926+2859/A1652+1539 were also increased significantly in LCP group compared with that in PBLN group. These findings suggest that FTIR spectroscopy might be a potentially effective method for the early diagnosis of lung cancer.

Developing a multi-institutional nomogram for assessing lung cancer risk in patients with 5-30 mm pulmonary nodules: a retrospective analysis

Background

The diagnosis of benign and malignant solitary pulmonary nodules based on personal experience has several limitations. Therefore, this study aims to establish a nomogram for the diagnosis of benign and malignant solitary pulmonary nodules using clinical information and computed tomography (CT) results.

Methods

Retrospectively, we collected clinical and CT characteristics of 1,160 patients with pulmonary nodules in Guang'an People's Hospital and the hospital affiliated with North Sichuan Medical College between 2019 and 2021. Among these patients, data from 773 patients with pulmonary nodules were used as the training set. We used the least absolute shrinkage and selection operator (LASSO) to optimize clinical and imaging features and performed a multivariate logistic regression to identify features with independent predictive ability to develop the nomogram model. The area under the receiver operating characteristic curve (AUC), C-index, decision curve analysis, and calibration plot were used to evaluate the performance of the nomogram model in terms of predictive ability, discrimination, calibration, and clinical utility. Finally, data from 387 patients with pulmonary nodules were utilized for validation.

Results

In the training set, the predictors for the nomogram were gender, density of the nodule, nodule diameter, lobulation, calcification, vacuole, vascular convergence, bronchiole, and pleural traction, selected through LASSO and logistic regression analysis. The resulting model had a C-index of 0.842 (95% CI [0.812-0.872]) and AUCs of 0.842 (95% CI [0.812-0.872]). In the validation set, the C-index was 0.856 (95% CI [0.811-0.901]), and the AUCs were 0.844 (95% CI [0.797-0.891]). Results from the calibration curve and clinical decision curve analyses indicate that the nomogram has a high fit and clinical benefit in both the training and validation sets.

Conclusion

The establishment of a nomogram for predicting the benign or malignant diagnosis of solitary pulmonary nodules by this study has shown good efficacy. Such a nomogram may help to guide the diagnosis, follow-up, and treatment of patients.

Genetic susceptibility loci of lung cancer are associated with malignant risk of pulmonary nodules and improve malignancy diagnosis based on CEA levels

Objective

The heightened prevalence of pulmonary nodules (PN) has escalated its significance as a public health concern. While the precise identification of high-risk PN carriers for malignancy remains an ongoing challenge, genetic variants hold potentials as determinants of disease susceptibility that can aid in diagnosis. Yet, current understanding of the genetic loci associated with malignant PN (MPN) risk is limited.

Methods

A frequency-matched case-control study was performed, comprising 247 MPN cases and 412 benign NP (BNP) controls. We genotyped 11 established susceptibility loci for lung cancer in a Chinese cohort. Loci associated with MPN risk were utilized to compute a polygenic risk score (PRS). This PRS was subsequently incorporated into the diagnostic evaluation of MPNs, with emphasis on serum tumor biomarkers.

Results

Loci rs10429489G>A, rs17038564A>G, and rs12265047A>G were identified as being associated with an increased risk of MPNs. The PRS, formulated from the cumulative risk effects of these loci, correlated with the malignant risk of PNs in a dose-dependent fashion. A high PRS was found to amplify the MPN risk by 156% in comparison to a low PRS [odds ratio (OR)=2.56, 95% confidence interval (95% CI), 1.40-4.67]. Notably, the PRS was observed to enhance the diagnostic accuracy of serum carcinoembryonic antigen (CEA) in distinguishing MPNs from BPNs, with diagnostic values rising from 0.716 to 0.861 across low- to high-PRS categories. Further bioinformatics investigations pinpointed rs10429489G>A as an expression quantitative trait locus.

Conclusions

Loci rs10429489G>A, rs17038564A>G, and rs12265047A>G contribute to MPN risk and augment the diagnostic precision for MPNs based on serum CEA concentrations.

MSM-ViT: A multi-scale MobileViT for pulmonary nodule classification using CT images

BACKGROUND

Accurate classification of benign and malignant pulmonary nodules using chest computed tomography (CT) images is important for early diagnosis and treatment of lung cancer. In terms of natural image classification, the VIT-based model has greater advantages in extracting global features than the traditional CNN model. However, due to the small image dataset and low image resolution, it is difficult to directly apply the Vit-based model to pulmonary nodule classification.

OBJECTIVE

To propose and test a new Vit-based MSM-ViT model aiming to achieve good performance in classifying pulmonary nodules.

METHODS

In this study, CNN structure was used in the task of classifying pulmonary nodules to compensate for the poor generalization of ViT structure and the difficulty in extracting multi-scale features. First, sub-pixel fusion was designed to improve the ability of the model to extract tiny features. Second, multi-scale local features were extracted by combining dilated convolution with ordinary convolution. Finally, MobileViT module was used to extract global features and predict them at the spatial level.

RESULTS

CT images involving 442 benign nodules and 406 malignant nodules were extracted from LIDC-IDRI data set to verify model performance, which yielded the best accuracy of 94.04% and AUC value of 0.9636 after 10 cross-validations.

CONCLUSION

The proposed new model can effectively extract multi-scale local and global features. The new model performance is also comparable to the most advanced models that use 3D volume data training, but its occupation of video memory (training resources) is less than 1/10 of the conventional 3D models.

A nomogram diagnostic prediction model of pancreatic metastases of small cell lung carcinoma based on clinical characteristics, radiological features and biomarkers

Objective

To investigate clinical characteristics, radiological features and biomarkers of pancreatic metastases of small cell lung carcinoma (PM-SCLC), and establish a convenient nomogram diagnostic predictive model to differentiate PM-SCLC from pancreatic ductal adenocarcinomas (PDAC) preoperatively.

Methods

A total of 299 patients with meeting the criteria (PM-SCLC n=93; PDAC n=206) from January 2016 to March 2022 were retrospectively analyzed, including 249 patients from hospital 1 (training/internal validation cohort) and 50 patients from hospital 2 (external validation cohort). We searched for meaningful clinical characteristics, radiological features and biomarkers and determined the predictors through multivariable logistic regression analysis. Three models: clinical model, CT imaging model, and combined model, were developed for the diagnosis and prediction of PM-SCLC. Nomogram was constructed based on independent predictors. The receiver operating curve was undertaken to estimate the discrimination.

Results

Six independent predictors for PM-SCLC diagnosis in multivariate logistic regression analysis, including clinical symptoms, CA199, tumor size, parenchymal atrophy, vascular involvement and enhancement type. The nomogram diagnostic predictive model based on these six independent predictors showed the best performance, achieved the AUCs of the training cohort (n = 174), internal validation cohort (n = 75) and external validation cohort (n = 50) were 0.950 (95%CI, 0.917-0.976), 0.928 (95%CI, 0.873-0.971) and 0.976 (95%CI, 0.944-1.00) respectively. The model achieved 94.50% sensitivity, 83.20% specificity, 86.80% accuracy in the training cohort and 100.00% sensitivity, 80.40% specificity, 86.70% accuracy in the internal validation cohort and 100.00% sensitivity, 88.90% specificity, 87.50% accuracy in the external validation cohort.

Conclusion

We proposed a noninvasive and convenient nomogram diagnostic predictive model based on clinical characteristics, radiological features and biomarkers to preoperatively differentiate PM-SCLC from PDAC.