A radiomics study to predict invasive pulmonary adenocarcinoma appearing as pure ground-glass nodules

Integrating machine learning and bioinformatics approaches for identifying novel diagnostic gene biomarkers in colorectal cancer

This study aimed to identify diagnostic gene biomarkers for colorectal cancer (CRC) by analyzing differentially expressed genes (DEGs) in tumor and adjacent normal samples across five colon cancer gene-expression profiles (GSE10950, GSE25070, GSE41328, GSE74602, GSE142279) from the Gene Expression Omnibus (GEO) database. Intersecting identified DEGs with the module with the highest correlation to gene expression patterns of tumor samples in the gene co-expression network analysis revealed 283 overlapped genes. Centrality measures were calculated for these genes in the reconstructed STRING protein-protein interaction network. Applying LASSO logistic regression, eleven genes were ultimately recognized as candidate diagnostic genes. Among these genes, the area under the receiver operating characteristic curve (AUROC) values for nine genes (CDC25B, CDK4, IQGAP3, MMP1, MMP7, SLC7A5, TEAD4, TRIB3, and UHRF1) surpassed the threshold of 0.92 in both the training and validation sets. We evaluated the diagnostic performance of these genes with four machine learning algorithms: random forest (RF), support vector machines (SVM), artificial neural network (ANN), and gradient boosting machine (GBM). In the testing dataset (GSE21815 and GSE106582), the AUROC scores were greater than 0.95 for all of the machine learning algorithms, indicating the high diagnostic performance of the nine genes. Besides, these nine genes are also significantly correlated to twelve immune cells, namely Mast cells activated, Macrophages M0, M1, and M2, Neutrophils, T cells CD4 memory activated, T cells follicular helper, T cells CD8, T cells CD4 memory resting, B cells memory, Plasma cells, and Mast cells resting (P < 0.05). These results strongly suggest that all of the nine genes have the potential to serve as reliable diagnostic biomarkers for CRC.

Habitat Imaging With Tumoral and Peritumoral Radiomics for Prediction of Lung Adenocarcinoma Invasiveness on Preoperative Chest CT: A Multicenter Study

BACKGROUND. Tumor growth processes result in spatial heterogeneity, with the development of tumor subregions (i.e., habitats) having unique biologic characteristics. OBJECTIVE. The purpose of our study was to develop and validate a habitat model combining tumor and peritumoral radiomic features on chest CT for predicting invasiveness of lung adenocarcinoma. METHODS. This retrospective study included 1156 patients (mean age, 57.5 years; 464 men, 692 women), from three centers and a public dataset, who underwent chest CT before lung adenocarcinoma resection (variable date ranges across datasets). Patients from one center formed training (n = 500) and validation (n = 215) sets; patients from the other sources formed three external test sets (n = 249, 113, 79). For each patient, a single nodule was manually segmented on chest CT. The nodule segmentation was combined with an automatically generated 4-mm peritumoral region into a whole-volume volume of interest (VOI). A gaussian mixture model (GMM) identified voxel clusters with similar first-order energy across patients. GMM results were used to divide each patient's whole-volume VOI into multiple habitats, which were defined consistently across patients. Radiomic features were extracted from each habitat. After feature selection, a habitat model was developed for predicting invasiveness, with the use of pathologic assessment as a reference. An integrated model was constructed, combining features extracted from habitats and whole-volume VOIs. Model performance was evaluated, including in subgroups based on nodule density (pure ground-glass, part-solid, and solid). The code for habitat imaging and model construction is publicly available (https://github.com/Shangyoulan/Habitat/). RESULTS. Invasive cancer was diagnosed in 626 of 1156 patients. GMM identified four as the optimal number of voxel clusters and thus of per-patient tumor habitats. The habitat model had an AUC of 0.932 in the validation set and 0.881, 0.880, and 0.764 in the three external test sets. The integrated model had an AUC of 0.947 in the validation set and 0.936, 0.908, and 0.800 in the three external test sets. In the three external test sets combined, across nodule densities, AUCs for the habitat model were 0.836-0.869 and for the integrated model were 0.846-0.917. CONCLUSION. Habitat imaging combining tumoral and peritumoral radiomic features could help predict lung adenocarcinoma invasiveness. Prediction is improved when combining information on tumor subregions and the tumor overall. CLINICAL IMPACT. The findings may aid personalized preoperative assessments to guide clinical decision-making in lung adenocarcinoma.

Interpretable CT radiomics model for invasiveness prediction in patients with ground-glass nodules

AIM

To evaluate the performance of an interpretable computed tomography (CT) radiomic model in predicting the invasiveness of ground-glass nodules (GGNs).

MATERIALS AND METHODS

The study was conducted retrospectively from 1 August 2017 to 1 August 2022, at three different centres. Two hundred and thirty patients with GGNs were enrolled at centre I as a training cohort. Centres II (n=157) and III (n=156) formed two external validation cohorts. Radiomics features extracted based on CT were reduced by a coarse-fine feature screening strategy. A radiomic model was developed through the use of the LASSO (least absolute shrinkage and selection operator) and XGBoost algorithms. Then, a radiological model was established through multivariate logistic regression analysis. Finally, the interpretability of the model was explored using SHapley Additive exPlanations (SHAP).

RESULTS

The radiomic XGBoost model outperformed the radiomic logistic model and radiological model in assessing the invasiveness of GGNs. The area under the curve (AUC) values for the radiomic XGBoost model were 0.885 (95% confidence interval [CI] 0.836-0.923), 0.853 (95% CI 0.790-0.906), and 0.838 (95% CI 0.773-0.902) in the training and the two external validation cohorts, respectively. The SHAP method allowed for both a quantitative and visual representation of how decisions were made using a given model for each individual patient. This can provide a deeper understanding of the decision-making mechanisms within the model and the factors that contribute to its prediction effectiveness.

CONCLUSIONS

The present interpretable CT radiomics model has the potential to preoperatively evaluate the invasiveness of GGNs. Furthermore, it can provide personalised, image-based clinical-decision support.

Machine learning-based CT radiomics model to discriminate the primary and secondary intracranial hemorrhage

It is challenging to distinguish between primary and secondary intracranial hemorrhage (ICH) purely by imaging data, and the two forms of ICHs are treated differently. This study aims to evaluate the potential of CT-based machine learning to identify the etiology of ICHs and compare the effectiveness of two regions of interest (ROI) sketching methods. A total of 1702 radiomic features were extracted from the CT brain images of 238 patients with acute ICH. We used the Select K Best method, least absolute shrinkage, and selection operator logistic regression to select the most discriminable features with a support vector machine to build a classifier model. Then, a ten-fold cross-validation strategy was employed to evaluate the performance of the classifier. From all quantitative CT-based imaging features obtained by two sketch methods, eighteen features were selected respectively. The radiomics model outperformed radiologists in distinguishing between primary and secondary ICH in both the volume of interest and the three-layer ROI sketches. As a result, a machine learning-based CT radiomics model can improve the accuracy of identifying primary and secondary ICH. A three-layer ROI sketch can identify primary versus secondary ICH based on the CT radiomics method.

Establishment and evaluation of a CT-based radiomic model for AIDS-associated pulmonary cryptococcosis

Background

Establish a CT-based diagnostic radiomic model for AIDS complicated with pulmonary cryptococcosis and evaluate the diagnostic efficacy of this model.

Methods

This retrospective study enrolled 98 AIDS patients with pulmonary cryptococcosis and 103 AIDS patients with other infections or neoplastic lesions, comprising a total of 699 lesions. Patients were randomly divided into a training group and test group at a ratio of 2.75:1. Features from all lesions, cavity lesions and solid nodule lesions were extracted, and two kinds of radiomic models (6 types) were established. ROC curves were drawn, and the sensitivity and specificity were calculated to compare the SVM model and LR model, radiologists’ empirical diagnoses and the combination of these empirical diagnoses with the radiomic model.

Results

The AUCs of senior radiologist for all lesions and cavity lesions were lower than those of the SVM and LR models. The diagnostic efficacy of primary radiologist was lower than that of both of the other model types. The diagnostic efficacy of the LR model was relatively stable, with the highest diagnostic efficiency of the 3 model/radiologist groups. The AUCs of intermediate radiologist in combination with the LR radiomic model for all lesions, nodular lesions and cavity lesions were 0.88, 0.84, and 0.9, respectively, which were the highest among all models and radiologists.

Conclusions

The CT-based radiomic LR model of AIDS-associated pulmonary cryptococcosis exhibits good diagnostic performance, which was similar to that of senior radiologists and higher than that of the primary radiologist. With the help of a radiomic model, radiologists can achieve improved diagnostic accuracy compared to that when only an empirical diagnosis is used.

Supplementary Information

The online version contains supplementary material available at 10.1186/s12880-022-00910-6.

Identidication of novel biomarkers in non-small cell lung cancer using machine learning

Lung cancer is one of the leading causes of cancer-related deaths worldwide, and non-small cell lung cancer (NSCLC) accounts for a large proportion of lung cancer cases, with few diagnostic and therapeutic targets currently available for NSCLC. This study aimed to identify specific biomarkers for NSCLC. We obtained three gene-expression profiles from the Gene Expression Omnibus database (GSE18842, GSE21933, and GSE32863) and screened for differentially expressed genes (DEGs) between NSCLC and normal lung tissue. Enrichment analyses were performed using Gene Ontology, Disease Ontology, and the Kyoto Encyclopedia of Genes and Genomes. Machine learning methods were used to identify the optimal diagnostic biomarkers for NSCLC using least absolute shrinkage and selection operator logistic regression, and support vector machine recursive feature elimination. CIBERSORT was used to assess immune cell infiltration in NSCLC and the correlation between biomarkers and immune cells. Finally, using western blot, small interfering RNA, Cholecystokinin-8, and transwell assays, the biological functions of biomarkers with high predictive value were validated. A total of 371 DEGs (165 up-regulated genes and 206 down-regulated genes) were identified, and enrichment analysis revealed that these DEGs might be linked to the development and progression of NSCLC. ABCA8, ADAMTS8, ASPA, CEP55, FHL1, PYCR1, RAMP3, and TPX2 genes were identified as novel diagnostic biomarkers for NSCLC. Monocytes were the most visible activated immune cells in NSCLC. The knockdown of the TPX2 gene, a biomarker with a high predictive value, inhibited A549 cell proliferation and migration. This study identified eight potential diagnostic biomarkers for NSCLC. Further, the TPX2 gene may be a therapeutic target for NSCLC.

Radiomics for differentiating minimally invasive adenocarcinoma from precursor lesions in pure ground-glass opacities on chest computed tomography

OBJECTIVE

To explore the correlation between radiomic features and the pathology of pure ground-glass opacities (pGGOs), we established a radiomics model for predicting the pathological subtypes of minimally invasive adenocarcinoma (MIA) and precursor lesions.

METHODS

CT images of 1521 patients with lung adenocarcinoma or precursor lesions appearing as pGGOs on CT in our hospital (The Third Affiliated Hospital of Sun Yat-sen University) from January 2015 to March 2021 were analyzed retrospectively and selected based on inclusion and exclusion criteria. pGGOs were divided into an atypical adenomatous hyperplasia (AAH)/adenocarcinoma in situ (AIS) group and an MIA group. Radiomic features were extracted from the original and preprocessed images of the region of interest. ANOVA and least absolute shrinkage and selection operator feature selection algorithm were used for feature selection. Logistic regression algorithm was used to construct radiomics prediction model. Receiver operating characteristic curves were used to evaluate the classification efficiency.

RESULTS

129 pGGOs were included. 2107 radiomic features were extracted from each region of interest. 18 radiomic features were eventually selected for model construction. The area under the curve of the radiomics model was 0.884 [95% confidence interval (CI), 0.818-0.949] in the training set and 0.872 (95% CI, 0.756-0.988) in the test set, with a sensitivity of 72.73%, specificity of 88.24% and accuracy of 79.47%. The decision curve indicated that the model had a high net benefit rate.

CONCLUSION

The prediction model for pathological subtypes of MIA and precursor lesions in pGGOs demonstrated a high diagnostic accuracy.

ADVANCES IN KNOWLEDGE

We focused on lesions appearing as pGGOs on CT and revealed the differences in radiomic features between MIA and precursor lesions. We constructed a radiomics prediction model and improved the diagnostic accuracy for the pathology of MIA and precursor lesions.

CT-based radiomics for differentiating invasive adenocarcinomas from indolent lung adenocarcinomas appearing as ground-glass nodules: Asystematic review

PURPOSE

To provide an overview of the available studies investigating the use of computer tomography (CT) radiomics features for differentiating invasive adenocarcinomas (IAC) from indolent lung adenocarcinomas presenting as ground-glass nodules (GGNs), to identify the bias of the studies and to propose directions for future research.

METHOD

PubMed, Embase, Web of Science Core Collection were searched for relevant studies. The studies differentiating IAC from indolent lung adenocarcinomas appearing as GGNs based on CT radiomics features were included. Basic information, patient information, CT-scanner information, technique information and performance information were extracted for each included study. The quality of each study was assessed using the Radiomic Quality Score (RQS) and the Prediction model Risk of Bias Assessment Tool (PROBAST).

RESULTS

Twenty-eight studies were included with patients ranging from 34 to 794. All of them were retrospective. Patients in three studies were from multiple centers. Most studies segmented regions of interest manually. Pyradiomics and AK software were the most frequently used for features extraction. The number of radiomics features extracted varied from 7 to 10329. Logistic regression was the most frequently chosen model. Entropy was identified as radiomics signature in seven studies. The AUC of included studies ranged from 0.77 to 0.98 in 15 validation sets. The percentage RQS ranged from 3% to 50%. According to PROBAST, the overall risk of bias (ROB) was high in 89.3% (25/28) of included studies, unclear in 7.1% (2/28) of included studies, and low in 3.6% (1/28) of included studies. All studies were low concern regarding the applicability of primary studies to the review question.

CONCLUSION

CT radiomics-based model is promising and encouraging in differentiating IAC from indolent lung adenocarcinomas, though they require methodological rigor. Well-designed studies are necessary to demonstrate their validity and standardization of methods and results can prompt their use in daily clinical practice.

Predicting the histological invasiveness of pulmonary adenocarcinoma manifesting as persistent pure ground-glass nodules by ultra-high-resolution CT target scanning in the lateral or oblique body position

Background

Ultra-high-resolution computed tomography (U-HRCT) has improved image quality for displaying the detailed characteristics of disease states and lung anatomy. The purpose of this study was to retrospectively examine whether U-HRCT target scanning in the lateral or oblique body position (protocol G scan) could predict histological invasiveness of pulmonary adenocarcinoma manifesting as pure ground-glass nodules (pGGNs).

Methods

From January 2015 to December 2016, 260 patients with 306 pathologically confirmed pGGNs who underwent preoperative protocol G scans were retrospectively reviewed and analyzed. The U-HRCT findings of preinvasive lesions [atypical adenomatous hyperplasias (AAH) and adenocarcinomas in situ (AIS)] and invasive pulmonary adenocarcinomas [minimally invasive adenocarcinomas (MIA) and invasive adenocarcinomas (IAC)] were manually compared and analyzed using orthogonal multiplanar reformation (MPR) images. The logistic regression model was established to determine variables that could predict the invasiveness of pGGNs. Receiver operating characteristic (ROC) curve analysis was performed to evaluate their diagnostic performance.

Results

There were 213 preinvasive lesions (59 AAHs and 154 AISs) and 93 invasive pulmonary adenocarcinomas (53 MIAs and 40 IACs). Compared with the preinvasive lesions, invasive adenocarcinomas exhibited a larger diameter (13.5 vs. 9.3 mm, P=0.000), higher mean attenuation (-571 vs. -613 HU, P=0.002), higher representative attenuation (-475 vs. -547 HU, P=0.000), lower relative attenuation (-339 vs. -292 HU, P=0.000) and greater frequencies of heterogeneity (P=0.001), air bronchogram (P=0.000), bubble lucency (P=0.000), and pleural indentation (P=0.000). Multiple logistic analysis revealed that larger diameter [odds ratio (OR), 1.328; 95% CI: 1.208-1.461; P=0.000] and higher representative attenuation (OR, 1.005; 95% CI: 1.003-1.007; P=0.000) were significant predictive factors of invasive pulmonary adenocarcinomas from preinvasive lesions. The optimal cut-off value of the maximum diameter for invasive pulmonary adenocarcinomas was larger than 10 mm (sensitivity, 66.7%; specificity, 72.8%).

Conclusions

The imaging features based on protocol G scanning can effectively help predict the histological invasiveness of pGGNs. The maximum diameter and representative attenuation are important parameters for predicting invasiveness.

Machine Learning-Based Multiparametric Magnetic Resonance Imaging Radiomic Model for Discrimination of Pathological Subtypes of Craniopharyngioma

BACKGROUND

Preoperative, noninvasive discrimination of the craniopharyngioma subtypes is important because it influences the treatment strategy.

PURPOSE

To develop a radiomic model based on multiparametric magnetic resonance imaging for noninvasive discrimination of pathological subtypes of craniopharyngioma.

STUDY TYPE

Retrospective.

POPULATION

A total of 164 patients from two medical centers were enrolled in this study. Patients from the first medical center were divided into a training cohort (N = 99) and an internal validation cohort (N = 33). Patients from the second medical center were used as the external independent validation cohort (N = 32).

FIELD STRENGTH/SEQUENCE

Axial T₁ -weighted (T₁ -w), T₂ -weighted (T₂ -w), contrast-enhanced T₁ -weighted (CET₁ -w) on 3.0 T or 1.5 T magnetic resonance scanners.

ASSESSMENT

Pathological subtypes (squamous papillary craniopharyngioma and adamantinomatous craniopharyngioma) were confirmed by surgery and hematoxylin and eosin staining. Optimal radiomic feature selection was performed by SelectKBest, the least absolute shrinkage and selection operator algorithm, and support vector machine (SVM) with a recursive feature elimination algorithm. Models based on each sequence or combinations of sequences were built using a SVM classifier and used to differentiate pathological subtypes of craniopharyngioma in the training cohort, internal validation, and external validation cohorts.

STATISTICAL TESTS

The area under the receiver operating characteristic curve (AUC) was used to assess the diagnostic performance of the radiomic models.

RESULTS

Seven texture features, three from T₁ -w, two from T₂ -w, and two from CET₁ -w, were selected and used to construct the radiomic model. The AUC values of the radiomic model were 0.899, 0.810, and 0.920 in the training cohort, internal and external validation cohorts, respectively. The AUC values of the clinicoradiological model were 0.677, 0.655, and 0.671 in the training cohort, internal and external validation cohorts, respectively.

DATA CONCLUSION

The model based on radiomic features from T₁ -w, T₂ -w, and CET₁ -w has a high discriminatory ability for pathological subtypes of craniopharyngioma.

LEVEL OF EVIDENCE

4 TECHNICAL EFFICACY: 2.