Can quantitative peritumoral CT radiomics features predict the prognosis of patients with non-small cell lung cancer? A systematic review

Radiomics-based hybrid model for predicting radiation pneumonitis: A systematic review and meta-analysis

PURPOSE

This study reviewed and meta-analyzed evidence on radiomics-based hybrid models for predicting radiation pneumonitis (RP). These models are crucial for improving thoracic radiotherapy plans and mitigating RP, a common complication of thoracic radiotherapy. We examined and compared the RP prediction models developed in these studies with the radiomics features employed in RP models.

METHODS

We systematically searched Google Scholar, Embase, PubMed, and MEDLINE for studies published up to April 19, 2024. Sixteen studies met the inclusion criteria. We compared the RP prediction models developed in these studies and the radiomics features employed.

RESULTS

Radiomics, as a single-factor evaluation, achieved an area under the receiver operating characteristic curve (AUROC) of 0.73, accuracy of 0.69, sensitivity of 0.64, and specificity of 0.74. Dosiomics achieved an AUROC of 0.70. Clinical and dosimetric factors showed lower performance, with AUROCs of 0.59 and 0.58. Combining clinical and radiomic factors yielded an AUROC of 0.78, while combining dosiomic and radiomics factors produced an AUROC of 0.81. Triple combinations, including clinical, dosimetric, and radiomics factors, achieved an AUROC of 0.81. The study identifies key radiomics features, such as the Gray Level Co-occurrence Matrix (GLCM) and Gray Level Size Zone Matrix (GLSZM), which enhance the predictive accuracy of RP models.

CONCLUSIONS

Radiomics-based hybrid models are highly effective in predicting RP. These models, combining traditional predictive factors with radiomic features, particularly GLCM and GLSZM, offer a clinically feasible approach for identifying patients at higher RP risk. This approach enhances clinical outcomes and improves patient quality of life.

PROTOCOL REGISTRATION

The protocol of this study was registered on PROSPERO (CRD42023426565).

EfficientNet-Based System for Detecting EGFR-Mutant Status and Predicting Prognosis of Tyrosine Kinase Inhibitors in Patients with NSCLC

We aimed to develop and validate a deep learning-based system using pre-therapy computed tomography (CT) images to detect epidermal growth factor receptor (EGFR)-mutant status in patients with non-small cell lung cancer (NSCLC) and predict the prognosis of advanced-stage patients with EGFR mutations treated with EGFR tyrosine kinase inhibitors (TKI). This retrospective, multicenter study included 485 patients with NSCLC from four hospitals. Of them, 339 patients from three centers were included in the training dataset to develop an EfficientNetV2-L-based model (EME) for predicting EGFR-mutant status, and the remaining patients were assigned to an independent test dataset. EME semantic features were extracted to construct an EME-prognostic model to stratify the prognosis of EGFR-mutant NSCLC patients receiving EGFR-TKI. A comparison of EME and radiomics was conducted. Additionally, we included patients from The Cancer Genome Atlas lung adenocarcinoma dataset with both CT images and RNA sequencing data to explore the biological associations between EME score and EGFR-related biological processes. EME obtained an area under the curve (AUC) of 0.907 (95% CI 0.840-0.926) on the test dataset, superior to the radiomics model (P = 0.007). The EME and radiomics fusion model showed better (AUC, 0.941) but not significantly increased performance (P = 0.895) compared with EME. In prognostic stratification, the EME-prognostic model achieved the best performance (C-index, 0.711). Moreover, the EME-prognostic score showed strong associations with biological pathways related to EGFR expression and EGFR-TKI efficacy. EME demonstrated a non-invasive and biologically interpretable approach to predict EGFR status, stratify survival prognosis, and correlate biological pathways in patients with NSCLC.

Value of CT-Based Deep Learning Model in Differentiating Benign and Malignant Solid Pulmonary Nodules ≤ 8 mm

RATIONALE AND OBJECTIVES

We examined the effectiveness of computed tomography (CT)-based deep learning (DL) models in differentiating benign and malignant solid pulmonary nodules (SPNs) ≤ 8 mm.

MATERIALS AND METHODS

The study patients (n = 719) were divided into internal training, internal validation, and external validation cohorts; all had small SPNs and had undergone preoperative chest CTs and surgical resection. We developed five DL models incorporating features of the nodule and five different peri-nodular regions with the Multiscale Dual Attention Network (MDANet) to differentiate benign and malignant SPNs. We selected the best-performing model, which was then compared to four conventional algorithms (VGG19, ResNet50, ResNeXt50, and DenseNet121). Furthermore, another five DL models were constructed using MDANet to distinguish benign tumors from inflammatory nodules and the one performed best was selected out.

RESULTS

Model 4, which incorporated the nodule and 15 mm peri-nodular region, best differentiated benign and malignant SPNs. The model had an area under the curve (AUC), accuracy, recall, precision, and F1-score of 0.730, 0.724, 0.711, 0.705, and 0.707 in the external validation cohort. Model 4 also performed better than the other four conventional algorithms. Model 8, which incorporated the nodule and 10 mm peri-nodular region, was the best model for distinguishing benign tumors from inflammatory nodules. The model had an AUC, accuracy, recall, precision, and F1-score of 0.871, 0.938, 0.863, 0.904, and 0.882 in the external validation cohort.

CONCLUSION

The study concludes that CT-based DL models built with MDANet can accurately discriminate among small benign and malignant SPNs, benign tumors and inflammatory nodules.

Radiomics-based prediction of nonalcoholic fatty liver disease following pancreatoduodenectomy

PURPOSE

Predicting nonalcoholic fatty liver disease (NAFLD) following pancreaticoduodenectomy (PD) is challenging, which delays therapeutic intervention and makes its prevention difficult. We conducted this study to assess the potential application of preoperative computed tomography (CT) radiomics for predicting NAFLD.

METHODS

The subjects of this retrospective study were 186 patients with PD from a single institution. We extracted the predictors of NAFLD after PD statistically from conventional clinical and radiomic features of the estimated remnant pancreas and whole liver region on preoperative nonenhanced CT images. Based on these predictors, we developed a machine-learning predictive model, which integrated clinical and radiomic features. A comparative model used only clinical features as predictors.

RESULTS

The incidence of NAFLD after PD was 43.5%. The variables of the clinicoradiomic model included one shape feature of the pancreas, two texture features of the liver, and sex; the variables of the clinical model were age, sex, and chemoradiotherapy. The accuracy%, precision%, recall%, F1 score, and area under the curve of the two models were 75.0, 72.7, 66.7, 69.6, and 0.80; and 69.6, 68.4, 54.2, 60.5, and 0.69, respectively.

CONCLUSIONS

Preoperative CT-derived radiomic features from the pancreatic and liver regions are promising for the prediction of NAFLD post-PD. Using these features enhances the predictive model, enabling earlier intervention for high-risk patients.

A distributed feature selection pipeline for survival analysis using radiomics in non-small cell lung cancer patients

Predictive modelling of cancer outcomes using radiomics faces dimensionality problems and data limitations, as radiomics features often number in the hundreds, and multi-institutional data sharing is ()often unfeasible. Federated learning (FL) and feature selection (FS) techniques combined can help overcome these issues, as one provides the means of training models without exchanging sensitive data, while the other identifies the most informative features, reduces overfitting, and improves model interpretability. Our proposed FS pipeline based on FL principles targets data-driven radiomics FS in a multivariate survival study of non-small cell lung cancer patients. The pipeline was run across datasets from three institutions without patient-level data exchange. It includes two FS techniques, Correlation-based Feature Selection and LASSO regularization, and Cox Proportional-Hazard regression with Overall Survival as endpoint. Trained and validated on 828 patients overall, our pipeline yielded a radiomic signature comprising "intensity-based energy" and "mean discretised intensity". Validation resulted in a mean Harrell C-index of 0.59, showcasing fair efficacy in risk stratification. In conclusion, we suggest a distributed radiomics approach that incorporates preliminary feature selection to systematically decrease the feature set based on data-driven considerations. This aims to address dimensionality challenges beyond those associated with data constraints and interpretability concerns.

Differentiation of testicular seminomas from nonseminomas based on multiphase CT radiomics combined with machine learning: A multicenter study

BACKGROUND

Differentiating seminomas from nonseminomas is crucial for formulating optimal treatment strategies for testicular germ cell tumors (TGCTs). Therefore, our study aimed to develop and validate a clinical-radiomics model for this purpose.

METHODS

In this study, 221 patients with TGCTs confirmed by pathology from four hospitals were enrolled and classified into training (n = 126), internal validation (n = 55) and external test (n = 40) cohorts. Radiomics features were extracted from the CT images. After feature selection, we constructed a clinical model, radiomics models and clinical-radiomics model with different machine learning algorithms. The top-performing model was chosen utilizing receiver operating characteristic (ROC) curve analysis. Decision curve analysis (DCA) was also conducted to assess its practical utility.

RESULTS

Compared with those of the clinical and radiomics models, the clinical-radiomics model demonstrated the highest discriminatory ability, with AUCs of 0.918 (95 % CI: 0.870 - 0.966), 0.909 (95 % CI: 0.829 - 0.988) and 0.839 (95 % CI: 0.709 - 0.968) in the training, validation and test cohorts, respectively. Moreover, DCA confirmed that the combined model had a greater net benefit in predicting seminomas and nonseminomas.

CONCLUSION

The clinical-radiomics model serves as a potential tool for noninvasive differentiation between testicular seminomas and nonseminomas, offering valuable guidance for clinical treatment.

Development and External Validation of an MRI-based Radiomics Nomogram to Distinguish Circumscribed Astrocytic Gliomas and Diffuse Gliomas: A Multicenter Study

RATIONALE AND OBJECTIVES

The 5th edition of the World Health Organization classification of tumors of the Central Nervous System (WHO CNS) has introduced the term "diffuse" and its counterpart "circumscribed" to the category of gliomas. This study aimed to develop and validate models for distinguishing circumscribed astrocytic gliomas (CAGs) from diffuse gliomas (DGs).

MATERIALS AND METHODS

We retrospectively analyzed magnetic resonance imaging (MRI) data from patients with CAGs and DGs across three institutions. After tumor segmentation, three volume of interest (VOI) types were obtained: VOItumor and peritumor, VOIwhole, and VOIinterface. Clinical and combined models (incorporating radiomics and clinical features) were also established. To address imbalances in training dataset, Synthetic Minority Oversampling Technique was employed.

RESULTS

A total of 475 patients (DGs: n = 338, CAGs: n = 137) were analyzed. The VOIinterface model demonstrated the best performance for differentiating CAGs from DGs, achieving an area under the curve (AUC) of 0.806 and area under the precision-recall curve (PRAUC)of 0.894 in the cross-validation set. Using analysis of variance (ANOVA) feature selector and Support Vector Machine (SVM) classifier, seven features were selected. The model achieved an AUC and AUPRC of 0.912 and 0.972 in the internal validation dataset, and 0.897 and 0.930 in the external validation dataset. The combined model, incorporating interface radiomics and clinical features, showed improved performance in the external validation set, with an AUC of 0.94 and PRAUC of 0.959.

CONCLUSION

Radiomics models incorporating the peritumoral area demonstrate greater potential for distinguishing CAGs from DGs compared to intratumoral models. These findings may hold promise for evaluating tumor nature before surgery and improving clinical management of glioma patients.

Could the underlying biological basis of prognostic radiomics and deep learning signatures be explored in patients with lung cancer? A systematic review

OBJECTIVES

To summarize the underlying biological correlation of prognostic radiomics and deep learning signatures in patients with lung cancer and evaluate the quality of available studies.

METHODS

This study examined databases including the PubMed, Embase, Web of Science Core Collection, and Cochrane Library, for studies that elaborated on the underlying biological correlation with prognostic radiomics and deep learning signatures based on CT or PET/CT for predicting the prognosis in patients with lung cancer. Information about the patient and radiogenomic analyses was extracted for the included studies. The Radiomics Quality Score (RQS) and the Prediction Model Risk of Bias Assessment Tool were used to assess the quality of these studies.

RESULTS

Twelve studies were included with 7,338 patients from 2014 to 2022. All studies except for one were retrospective. Supervised machine learning was adopted in six studies, and the remaining used unsupervised machine learning methods. Gene sequencing and histopathological data were analyzed by 83.33% and 16.67% of the included studies, respectively. Gene set enrichment analysis and correlation analysis were most used to explore the biological meaning of prognostic signatures. The median RQS for supervised learning articles was 13.5 (range 12-19) and 7.0 (range 5-14) for unsupervised learning articles. The studies included in this report were assessed to have high risk of bias overall.

CONCLUSION

The biological basis for the interpretability of data-driven models mainly focused on genomics and histopathological factors, and it may improve the prognosis of lung cancer with more proper biological interpretation in the future.

The value of intratumoral and peritumoral radiomics features in differentiating early-stage lung invasive adenocarcinoma (≤3 cm) subtypes

Background

The identification of different subtypes of early-stage lung invasive adenocarcinoma before surgery contributes to the precision treatment. Radiomics could be one of the effective and noninvasive identification methods. The value of peritumoral radiomics in predicting the subtypes of early-stage lung invasive adenocarcinoma perhaps clinically useful.

Methods

This retrospective study included 937 lung adenocarcinomas which were randomly divided into the training set (n=655) and testing set (n=282) with a ratio of 7:3. This study used the univariate and multivariate analysis to choose independent clinical predictors. Radiomics features were extracted from 18 regions of interest (1 intratumoral region and 17 peritumoral regions). Independent and conjoint prediction models were constructed based on radiomics and clinical features. The performance of the models was evaluated using receiver operating characteristic (ROC) curves, accuracy (ACC), sensitivity (SEN), and specificity (SPE). Significant differences between areas under the ROC (AUCs) were estimated using in the Delong test.

Results

Patient age, smoking history, carcinoembryonic antigen (CEA), lesion location, length, width and clinic behavior were the independent predictors of differentiating early-stage lung invasive adenocarcinoma (≤3 cm) subtypes. The highest AUC value among the 19 independent models was obtained for the PTV0~+3 radiomics model with 0.849 for the training set and 0.854 for the testing set. As the peritumoral distance increased, the predictive power of the models decreased. The radiomics-clinical conjoint model was statistically significantly different from the other models in the Delong test (P<0.05).

Conclusions

The intratumoral and peritumoral regions contained a wealth of clinical information. The diagnostic efficacy of intra-peritumoral radiomics combined clinical model was further improved, which was particularly important for preoperative staging and treatment decision-making.

Computed Tomography-derived intratumoral and peritumoral radiomics in predicting EGFR mutation in lung adenocarcinoma

OBJECTIVE

To investigate the value of Computed Tomography (CT) radiomics derived from different peritumoral volumes of interest (VOIs) in predicting epidermal growth factor receptor (EGFR) mutation status in lung adenocarcinoma patients.

MATERIALS AND METHODS

A retrospective cohort of 779 patients who had pathologically confirmed lung adenocarcinoma were enrolled. 640 patients were randomly divided into a training set, a validation set, and an internal testing set (3:1:1), and the remaining 139 patients were defined as an external testing set. The intratumoral VOI (VOI_I) was manually delineated on the thin-slice CT images, and seven peritumoral VOIs (VOI_P) were automatically generated with 1, 2, 3, 4, 5, 10, and 15 mm expansion along the VOI_I. 1454 radiomic features were extracted from each VOI. The t-test, the least absolute shrinkage and selection operator (LASSO), and the minimum redundancy maximum relevance (mRMR) algorithm were used for feature selection, followed by the construction of radiomics models (VOI_I model, VOI_P model and combined model). The performance of the models were evaluated by the area under the curve (AUC).

RESULTS

399 patients were classified as EGFR mutant (EGFR+), while 380 were wild-type (EGFR-). In the training and validation sets, internal and external testing sets, VOI4 (intratumoral and peritumoral 4 mm) model achieved the best predictive performance, with AUCs of 0.877, 0.727, and 0.701, respectively, outperforming the VOI_I model (AUCs of 0.728, 0.698, and 0.653, respectively).

CONCLUSIONS

Radiomics extracted from peritumoral region can add extra value in predicting EGFR mutation status of lung adenocarcinoma patients, with the optimal peritumoral range of 4 mm.

Preoperative CT-based radiomics combined with tumour spread through air spaces can accurately predict early recurrence of stage I lung adenocarcinoma: a multicentre retrospective cohort study

OBJECTIVE

To develop and validate a prediction model for early recurrence of stage I lung adenocarcinoma (LUAD) that combines radiomics features based on preoperative CT with tumour spread through air spaces (STAS).

MATERIALS AND METHODS

The most recent preoperative thin-section chest CT scans and postoperative pathological haematoxylin and eosin-stained sections were retrospectively collected from patients with a postoperative pathological diagnosis of stage I LUAD. Regions of interest were manually segmented, and radiomics features were extracted from the tumour and peritumoral regions extended by 3 voxel units, 6 voxel units, and 12 voxel units, and 2D and 3D deep learning image features were extracted by convolutional neural networks. Then, the RAdiomics Integrated with STAS model (RAISm) was constructed. The performance of RAISm was then evaluated in a development cohort and validation cohort.

RESULTS

A total of 226 patients from two medical centres from January 2015 to December 2018 were retrospectively included as the development cohort for the model and were randomly split into a training set (72.6%, n = 164) and a test set (27.4%, n = 62). From June 2019 to December 2019, 51 patients were included in the validation cohort. RAISm had excellent discrimination in predicting the early recurrence of stage I LUAD in the training cohort (AUC = 0.847, 95% CI 0.762-0.932) and validation cohort (AUC = 0.817, 95% CI 0.625-1.000). RAISm outperformed single modality signatures and other combinations of signatures in terms of discrimination and clinical net benefits.

CONCLUSION

We pioneered combining preoperative CT-based radiomics with STAS to predict stage I LUAD recurrence postoperatively and confirmed the superior effect of the model in validation cohorts, showing its potential to assist in postoperative treatment strategies.

Methodological quality of radiomic-based prognostic studies in gastric cancer: a cross-sectional study

Background

Machine learning radiomics models are increasingly being used to predict gastric cancer prognoses. However, the methodological quality of these models has not been evaluated. Therefore, this study aimed to evaluate the methodological quality of radiomics studies in predicting the prognosis of gastric cancer, summarize their methodological characteristics and performance.

Methods

The PubMed and Embase databases were searched for radiomics studies used to predict the prognosis of gastric cancer published in last 5 years. The characteristics of the studies and the performance of the models were extracted from the eligible full texts. The methodological quality, reporting completeness and risk of bias of the included studies were evaluated using the RQS, TRIPOD and PROBAST. The discrimination ability scores of the models were also compared.

Results

Out of 283 identified records, 22 studies met the inclusion criteria. The study endpoints included survival time, treatment response, and recurrence, with reported discriminations ranging between 0.610 and 0.878 in the validation dataset. The mean overall RQS value was 15.32 ± 3.20 (range: 9 to 21). The mean adhered items of the 35 item of TRIPOD checklist was 20.45 ± 1.83. The PROBAST showed all included studies were at high risk of bias.

Conclusion

The current methodological quality of gastric cancer radiomics studies is insufficient. Large and reasonable sample, prospective, multicenter and rigorously designed studies are required to improve the quality of radiomics models for gastric cancer prediction.

Study registration

This protocol was prospectively registered in the Open Science Framework Registry (https://osf.io/ja52b).

Artificial Intelligence in the Diagnosis and Treatment of Pancreatic Cystic Lesions and Adenocarcinoma

Pancreatic cancer is projected to become the second leading cause of cancer-related mortality in the United States by 2030. This is in part due to the paucity of reliable screening and diagnostic options for early detection. Amongst known pre-malignant pancreatic lesions, pancreatic intraepithelial neoplasia (PanIN) and intraductal papillary mucinous neoplasms (IPMNs) are the most prevalent. The current standard of care for the diagnosis and classification of pancreatic cystic lesions (PCLs) involves cross-sectional imaging studies and endoscopic ultrasound (EUS) and, when indicated, EUS-guided fine needle aspiration and cyst fluid analysis. However, this is suboptimal for the identification and risk stratification of PCLs, with accuracy of only 65-75% for detecting mucinous PCLs. Artificial intelligence (AI) is a promising tool that has been applied to improve accuracy in screening for solid tumors, including breast, lung, cervical, and colon cancer. More recently, it has shown promise in diagnosing pancreatic cancer by identifying high-risk populations, risk-stratifying premalignant lesions, and predicting the progression of IPMNs to adenocarcinoma. This review summarizes the available literature on artificial intelligence in the screening and prognostication of precancerous lesions in the pancreas, and streamlining the diagnosis of pancreatic cancer.

Blood- and Imaging-Derived Biomarkers for Oncological Outcome Modelling in Oropharyngeal Cancer: Exploring the Low-Hanging Fruit

Aims: To assess whether CT-based radiomics and blood-derived biomarkers could improve the prediction of overall survival (OS) and locoregional progression-free survival (LRPFS) in patients with oropharyngeal cancer (OPC) treated with curative-intent RT. Methods: Consecutive OPC patients with primary tumors treated between 2005 and 2021 were included. Analyzed clinical variables included gender, age, smoking history, staging, subsite, HPV status, and blood parameters (baseline hemoglobin levels, neutrophils, monocytes, and platelets, and derived measurements). Radiomic features were extracted from the gross tumor volumes (GTVs) of the primary tumor using pyradiomics. Outcomes of interest were LRPFS and OS. Following feature selection, a radiomic score (RS) was calculated for each patient. Significant variables, along with age and gender, were included in multivariable analysis, and models were retained if statistically significant. The models’ performance was compared by the C-index. Results: One hundred and five patients, predominately male (71%), were included in the analysis. The median age was 59 (IQR: 52–66) years, and stage IVA was the most represented (70%). HPV status was positive in 63 patients, negative in 7, and missing in 35 patients. The median OS follow-up was 6.3 (IQR: 5.5–7.9) years. A statistically significant association between low Hb levels and poorer LRPFS in the HPV-positive subgroup (p = 0.038) was identified. The calculation of the RS successfully stratified patients according to both OS (log-rank p < 0.0001) and LRPFS (log-rank p = 0.0002). The C-index of the clinical and radiomic model resulted in 0.82 [CI: 0.80–0.84] for OS and 0.77 [CI: 0.75–0.79] for LRPFS. Conclusions: Our results show that radiomics could provide clinically significant informative content in this scenario. The best performances were obtained by combining clinical and quantitative imaging variables, thus suggesting the potential of integrative modeling for outcome predictions in this setting of patients.