A Multi-Classification Model for Predicting the Invasiveness of Lung Adenocarcinoma Presenting as Pure Ground-Glass Nodules

The identification of hub genes associated with pure ground glass nodules using weighted gene co-expression network analysis

BACKGROUND

Whether there are invasive components in pure ground glass nodules(pGGNs) in the lungs is still a huge challenge to forecast. The objective of our study is to investigate and identify the potential biomarker genes for pure ground glass nodule(pGGN) based on the method of bioinformatics analysis.

METHODS

To investigate differentially expressed genes (DEGs), firstly the data obtained from the gene expression omnibus (GEO) database was used.Next Weighted gene co-expression network analysis (WGCNA) investigate the co-expression network of DEGs. The black key module was chosen as the key one in correlation with pGGN. Gene Ontology (GO) and Kyoto Encyclopedia of Genes and Genomes (KEGG) pathways analyses were done. Then STRING was uesd to create a protein-protein interaction (PPI) network, and the chosen module genes were analyzed by Cytoscape software.In addition the polymerase chain reaction (PCR) was used to evaluate the value of these hub genes in pGGN patients' tumor tissues compared to controls.

RESULTS

A total of 4475 DEGs were screened out from GSE193725, then 225 DEGs were identified in black key module, which were found to be enriched for various functions and pathways, such as extracellular exosome, vesicle, ribosome and so on. Among these DEGs, 6 overlapped hub genes with high degrees of stress method were selected. These hub genes include RPL4, RPL8, RPLP0, RPS16, RPS2 and CCT3.At last relative expression levels of CCT3 and RPL8 mRNA were both regulated in pGGN patients' tumor tissues compared to controls.

CONCLUSIONS

To summarize, the determined DEGs, pathways, modules, and overlapped hub genes can throw light on the potential molecular mechanisms of pGGN.

Invasiveness identification in pure ground-glass nodules: exploring the generalizability of radiomics based on external validation and stress testing

PURPOSE

This study aimed to apply external validation and stress tests to evaluate the generalizability of radiomics models built using various machine-learning methods for identifying the invasiveness of lung adenocarcinomas manifesting as pure ground-glass nodules (pGGNs).

METHODS

This retrospective study enrolled 495 patients (514 pGGNs) confirmed as lung adenocarcinomas by postoperative pathology from three centers. All nodules were included in the primary cohort (randomly divided into training and test cohorts), two external validation cohorts, and two stress test cohorts. Six machine-learning radiomics models were constructed in the training cohort using the optimal features. Performance of radiomics models and clinical models were compared in primary cohort and external validation cohorts. The stress tests included stratified performance evaluation and shifted performance evaluation and contrastive evaluation under three single-condition modification settings. The predictive performance was validated by area under curve (AUC) of receiver operating characteristic (ROC).

RESULTS

Of the six radiomics models, the best logistic regression (LR) model was able to maintain high differential diagnostic capability (AUC: 0.849 ± 0.049) and good stability (relative standard deviation, 5.719%), but it showed poorer performance (AUC = 0.835) than the clinical model (AUC = 0.862) in the external validation cohort E1. The stress tests suggested LR model had no significant difference in performance between subgroups after stratification and had good consistency in the predictions before and after the three transformations (Kappa = 0.960, 0.840, and 0.933, respectively; p < 0.05, all).

CONCLUSION

The rigorous testing procedure facilitates the selection of high-performance radiomics models with good clinical generalizability.

Effective Invasiveness Recognition of Imbalanced Data by Semi-Automated Segmentations of Lung Nodules

Over the past few decades, recognition of early lung cancers was researched for effective treatments. In early lung cancers, the invasiveness is an important factor for expected survival rates. Hence, how to effectively identify the invasiveness by computed tomography (CT) images became a hot topic in the field of biomedical science. Although a number of previous works were shown to be effective on this topic, there remain some problems unsettled still. First, it needs a large amount of marked data for a better prediction, but the manual cost is high. Second, the accuracy is always limited in imbalance data. To alleviate these problems, in this paper, we propose an effective CT invasiveness recognizer by semi-automated segmentation. In terms of semi-automated segmentation, it is easy for doctors to mark the nodules. Just based on one clicked pixel, a nodule object in a CT image can be marked by fusing two proposed segmentation methods, including thresholding-based morphology and deep learning-based mask region-based convolutional neural network (Mask-RCNN). For thresholding-based morphology, an initial segmentation is derived by adaptive pixel connections. Then, a mathematical morphology is performed to achieve a better segmentation. For deep learning-based mask-RCNN, the anchor is fixed by the clicked pixel to reduce the computational complexity. To incorporate advantages of both, the segmentation is switched between these two sub-methods. After segmenting the nodules, a boosting ensemble classification model with feature selection is executed to identify the invasiveness by equalized down-sampling. The extensive experimental results on a real dataset reveal that the proposed segmentation method performs better than the traditional segmentation ones, which can reach an average dice improvement of 392.3%. Additionally, the proposed ensemble classification model infers better performances than the compared method, which can reach an area under curve (AUC) improvement of 5.3% and a specificity improvement of 14.3%. Moreover, in comparison with the models with imbalance data, the improvements of AUC and specificity can reach 10.4% and 33.3%, respectively.

MRI-Based Texture Analysis for Preoperative Prediction of BRAF V600E Mutation in Papillary Thyroid Carcinoma

Purpose

BRAF V600E mutation can compensate for the low detection rate by fine-needle aspiration (FNA) and is related to aggressiveness and lymph node metastasis. This study aimed to investigate the relationship between texture analysis features based on magnetic resonance imaging (MRI) and mutations.

Methods

Retrospective analysis was performed on patients with postoperative pathology confirmed papillary thyroid carcinoma (PTC) from 2017 to 2021. One thousand one hundred and thirty-two texture features were extracted from T2-weighted imaging (T2WI) and contrast-enhanced T1-weighted imaging (CE-T1WI) separately by outlining the tumor volume of interest (VOI). Univariate, minimum redundancy maximum relevance (mRMR), and multivariate analyses were used for feature selection to construct 3 models (T2WI, CE-T1WI, and combined model) to predict mutation. The reproducibility between observers was evaluated by intraclass correlation coefficient (ICC). Receiver operating characteristic (ROC) analysis was used to assess the performance of models. The diagnostic performance of the optimal cut-off value of models were calculated and validated by 10-fold cross-validation.

Results

A total of 80 PTCs (22 BRAF V600E wild-type and 58 BRAF V600E mutant) were included in our study. Good interobserver agreement was found on texture features we selected (all ICCs >0.75). The area under the ROC curves (AUCs) for the T2WI model, CE-T1WI model, and combined model were 0.83 (95% CI: 0.75-0.91), 0.83 (95% CI: 0.73-0.90), and 0.88 (95% CI: 0.81-0.94), respectively. The accuracy, sensitivity, specificity, PPV, and NPV were 0.776, 0.679, 0.905, 0.905, and 0.679 for the T2WI model at a cut-off value of 0.674; 0.755, 0.750, 0.762, 0.808, and 0.696 for the CE-T1WI model at a cut-off value of 0.573; 0.816, 0.893, 0.714, 0.806, and 0.833 for the combined model at a cut-off value of 0.420.

Conclusion

MRI-based texture analysis could be a potential method for predicting BRAF V600E mutation in PTC preoperatively.

A multi-classification model for non-small cell lung cancer subtypes based on independent subtask learning

PURPOSE

The non-small cell lung cancer (NSCLC) can be divided into adenocarcinoma (ADC), squamous cell carcinoma (SCC), large cell carcinoma (LCC), and not otherwise specified (NOS), which is crucial for clinical decision-making. However, current related researches are rare for the complex multi-classification of NSCLC, mainly due to the serious data imbalance, the difficulty to unify the feature space, and the complicated decision boundary among multiple subtypes. The machine learning method of traditional "one-vs-one" (OVO) is difficult to solve these problems and achieve good results.

METHODS

To this end, we propose a novel independent subtask learning (ISTL) method to better carry out the multi-classification task. Specifically, it includes four pertinent strategies: (1) independent data expansion; (2) independent feature selection (IFS); (3) independent model construction; and (4) a novel voting strategy: majority voting combined with Bayesian prior. We performed experiments using 1036 CT scans (ADC:SCC:LCC:NOS = 600:268:105:63) collected from eight international databases, and the data acquisition was highly complex and diverse.

RESULTS

The experimental results showed that the ISTL method obtained an accuracy of 0.812 on the independent test cohort, which significantly improved the performance of multi-classification compared with the traditional OVO-support vector machine (0.691) and OVO-random forest (0.710) models. After the IFS, six selected feature sets of six binary tasks are obviously different, indicating that the ISTL method has better interpretability to distinguish the multiple NSCLC subtypes. The results of a further auxiliary contrast experiment showed that four pertinent strategies were all effective.

CONCLUSION

Our work indicates that the ISTL method can effectively perform multi-classification of NSCLC subtypes with better interpretability for clinical computer-aided detection and has the potential to be applied in a wide range of multi-classification studies.