Biologic Pathways Underlying Prognostic Radiomics Phenotypes from Paired MRI and RNA Sequencing in Glioblastoma

Impact of intensity standardisation and ComBat batch size on clinical-radiomic prognostic models performance in a multi-centre study of patients with glioblastoma

PURPOSE

To assess the effect of different intensity standardisation techniques (ISTs) and ComBat batch sizes on radiomics survival model performance and stability in a heterogenous, multi-centre cohort of patients with glioblastoma (GBM).

METHODS

Multi-centre pre-operative MRI acquired between 2014 and 2020 in patients with IDH-wildtype unifocal WHO grade 4 GBM were retrospectively evaluated. WhiteStripe (WS), Nyul histogram matching (HM), and Z-score (ZS) ISTs were applied before radiomic feature (RF) extraction. RFs were realigned using ComBat and minimum batch size (MBS) of 5, 10, or 15 patients. Cox proportional hazards models for overall survival (OS) prediction were produced using five different selection strategies and the impact of IST and MBS was evaluated using bootstrapping. Calibration, discrimination, relative explained variation, and model fit were assessed. Instability was evaluated using 95% confidence intervals (95% CIs), feature selection frequency and calibration curves across the bootstrap resamples.

RESULTS

One hundred ninety-five patients were included. Median OS = 13 (95% CI: 12-14) months. Twelve to fourteen unique MRI protocols were used per MRI sequence. HM and WS produced the highest relative increase in model discrimination, explained variation and model fit but IST choice did not greatly impact on stability, nor calibration. Larger ComBat batches improved discrimination, model fit, and explained variation but higher MBS (reduced sample size) reduced stability (across all performance metrics) and reduced calibration accuracy.

CONCLUSION

Heterogenous, real-world GBM data poses a challenge to the reproducibility of radiomics. ComBat generally improved model performance as MBS increased but reduced stability and calibration. HM and WS tended to improve model performance.

KEY POINTS

Question ComBat harmonisation of RFs and intensity standardisation of MRI have not been thoroughly evaluated in multicentre, heterogeneous GBM data. Findings The addition of ComBat and ISTs can improve discrimination, relative model fit, and explained variance but degrades the calibration and stability of survival models. Clinical relevance Radiomics risk prediction models in real-world, multicentre contexts could be improved by ComBat and ISTs, however, this degrades calibration and prediction stability and this must be thoroughly investigated before patients can be accurately separated into different risk groups.

Decoding Glioblastoma Heterogeneity: Neuroimaging Meets Machine Learning

Recent advancements in neuroimaging and machine learning have significantly improved our ability to diagnose and categorize isocitrate dehydrogenase (IDH)-wildtype glioblastoma, a disease characterized by notable tumoral heterogeneity, which is crucial for effective treatment. Neuroimaging techniques, such as diffusion tensor imaging and magnetic resonance radiomics, provide noninvasive insights into tumor infiltration patterns and metabolic profiles, aiding in accurate diagnosis and prognostication. Machine learning algorithms further enhance glioblastoma characterization by identifying distinct imaging patterns and features, facilitating precise diagnoses and treatment planning. Integration of these technologies allows for the development of image-based biomarkers, potentially reducing the need for invasive biopsy procedures and enabling personalized therapy targeting specific pro-tumoral signaling pathways and resistance mechanisms. Although significant progress has been made, ongoing innovation is essential to address remaining challenges and further improve these methodologies. Future directions should focus on refining machine learning models, integrating emerging imaging techniques, and elucidating the complex interplay between imaging features and underlying molecular processes. This review highlights the pivotal role of neuroimaging and machine learning in glioblastoma research, offering invaluable noninvasive tools for diagnosis, prognosis prediction, and treatment planning, ultimately improving patient outcomes. These advances in the field promise to usher in a new era in the understanding and classification of IDH-wildtype glioblastoma.

MRI-based machine learning reveals proteasome subunit PSMB8-mediated malignant glioma phenotypes through activating TGFBR1/2-SMAD2/3 axis

Gliomas are the most prevalent and aggressive neoplasms of the central nervous system, representing a major challenge for effective treatment and patient prognosis. This study identifies the proteasome subunit beta type-8 (PSMB8/LMP7) as a promising prognostic biomarker for glioma. Using a multiparametric radiomic model derived from preoperative magnetic resonance imaging (MRI), we accurately predicted PSMB8 expression levels. Notably, radiomic prediction of poor prognosis was highly consistent with elevated PSMB8 expression. Our findings demonstrate that PSMB8 depletion not only suppressed glioma cell proliferation and migration but also induced apoptosis via activation of the transforming growth factor beta (TGF-β) signaling pathway. This was supported by downregulation of key receptors (TGFBR1 and TGFBR2). Furthermore, interference with PSMB8 expression impaired phosphorylation and nuclear translocation of SMAD2/3, critical mediators of TGF-β signaling. Consequently, these molecular alterations resulted in reduced tumor progression and enhanced sensitivity to temozolomide (TMZ), a standard chemotherapeutic agent. Overall, our findings highlight PSMB8's pivotal role in glioma pathophysiology and its potential as a prognostic marker. This study also demonstrates the clinical utility of MRI radiomics for preoperative risk stratification and pre-diagnosis. Targeted inhibition of PSMB8 may represent a therapeutic strategy to overcome TMZ resistance and improve glioma patient outcomes.

MIPD: Molecules, Imagings, and Clinical Phenotype Integrated Database

Due to tumor heterogeneity, a subset of patients fails to benefit from current treatment strategies. However, an integrated analysis of imaging features, genetic molecules, and clinical phenotypes can characterize tumor heterogeneity, enabling the development of more personalized treatment approaches. Despite its potential, cross-modal databases remain underexplored. To address this gap, we established a comprehensive database encompassing 9965 genes, 5449 proteins, 1121 metabolites, 283 pathways, 854 imaging features, and 73 clinical factors from colorectal cancer patients. This database identifies significantly distinct molecules and imaging features associated with clinical phenotypes and provides survival analysis based on these features. Additionally, it offers genetic molecule annotations, comparative expression levels between tumor and normal tissues, imaging features linked to genetic molecules, and imaging-based models for predicting gene expression levels. Furthermore, the database highlights correlations between genetic molecules, clinical factors, and imaging features. In summary, we present MIPD (Molecules, Imaging, and Clinical Phenotype Correlation Database), a user-friendly, interactive, and specialized platform accessible at http://corgenerf.com. MIPD facilitates the interpretability of cross-modal data by providing query, browse, search, visualization, and download functionalities, thereby offering a valuable resource for advancing precision medicine in colorectal cancer. Database URL: http://corgenerf.

Unsupervised machine learning analysis of optical coherence tomography radiomics features for predicting treatment outcomes in diabetic macular edema

This study aimed to identify distinct clusters of diabetic macular edema (DME) patients with differential anti-vascular endothelial growth factor (VEGF) treatment outcomes using an unsupervised machine learning (ML) approach based on radiomic features extracted from pre-treatment optical coherence tomography (OCT) images. Retrospective data from 234 eyes with DME treated with three anti-VEGF therapies between January 2020 and March 2024 were collected from two clinical centers. Radiomic analysis was conducted on pre-treatment OCT images. Following principal component analysis (PCA) for dimensionality reduction, two unsupervised clustering methods (K-means and hierarchical clustering) were applied. Baseline characteristics and treatment outcomes were compared across clusters to assess clustering efficacy. Feature selection employed a three-stage pipeline: exclusion of collinear features (Pearson's r > 0.8); sequential filtering through ANOVA (P < 0.05) and Boruta algorithm (500 iterations); multivariate stepwise regression (entry criteria: univariate P < 0.1) to identify outcome-associated predictors. From 1165 extracted radiomic features, four distinct DME clusters were identified. Cluster 4 exhibited a significantly lower incidence of residual/recurrent DME (RDME) (34.29%) compared to Clusters 1-3 (P = 0.003, P = 0.005 and P = 0.002, respectively). This cluster also demonstrated the highest proportion of eyes (71.43%) with best-corrected visual acuity (BCVA) exceeding 20/63 (P = 0.003, P = 0.005 and P = 0.002, respectively). Multivariate analysis identified logarithm_gldm_DependenceVariance as an independent risk factor for RDME (OR 1.75, 95% CI 1.28-2.40; P < 0.001), while Wavelet-LH_Firstorder_Mean correlated with worse visual outcomes (OR 8.76, 95% CI 1.22-62.84; P = 0.031). Unsupervised ML leveraging pre-treatment OCT radiomics successfully stratifies DME eyes into clinically distinct subgroups with divergent therapeutic responses. These quantitative features may serve as non-invasive biomarkers for personalized outcome prediction and retinal pathology assessment.

Clinical features and prognostic nomogram development for cancer-specific death in patients with dual primary lung cancer: a population-based study from SEER database

OBJECTIVE

This study aimed to develop a concise and valid clinical prediction model to assess the survival prognostic risk of cancer-specific death in patients with dual primary lung cancer (DPLC).

DATA SOURCE

Surveillance, epidemiology, and end results (SEER) database.

DESIGN

A retrospective population-based study.

METHODS

Data of DPLC patients from the database from 1992 to 2020 were collected. The number of DPLC patients was determined based on the first primary LC (FPLC) and second primary LC (SPLC), and patients were randomly assigned to a training set and a testing set in a 7:3 ratio. The primary endpoint was cancer-specific survival (CSS). Kaplan-Meier survival analysis was performed to construct survival curves. Cox analysis and bilateral stepwise regression were used to analyze prognostic factors for cancer-specific death in patients and establish the nomogram. The discriminative ability of the nomogram was assayed by C-index and calibration curves, decision-making ability was assessed by decision curve analysis (DCA), and nomogram performance was measured by receiver operating characteristic (ROC) curves.

RESULTS

This study included 997 DPLC patients, divided into a training set (n = 698) and a testing set (n = 299) in a 7:3 ratio. Age, gender, histological type, surgery, chemotherapy, T stage, N stage, and tumor size were identified as risk factors affecting CSS in DPLC patients (P < 0.05) and were utilized to establish a nomogram. The C-index of the nomogram in the training set was 0.671, and the AUC values of ROC curves for 1-year, 3-year, and 5-year survival rates were 0.84, 0.78, and 0.74, respectively. The C-index of the testing set was 0.644, and the AUC values were 0.72, 0.74, and 0.75, respectively. Calibration curves for both sets were close to the diagonal line, indicating good predictive ability of the nomogram. DCA curves demonstrated the good decision-making ability of the nomogram.

CONCLUSION

This study revealed the clinical features of DPLC patients and developed an effective nomogram for predicting CSS, which can assist clinicians in making accurate and personalized clinical decisions regarding patient treatment.

Prediction of EGFR-TP53 genes co-mutations in patients with lung adenocarcinoma (LUAD) by 18F-FDG PET/CT radiomics

PURPOSE

This retrospective study was undertaken to assess the predictive efficacy of 18F-FDG PET/CT -derived radiomic features concerning the co-mutation status of epidermal growth factor receptor (EGFR) and TP53 in LUAD.

METHODS

A cohort of 150 LUAD patients underwent pretreatment 18F-FDG PET/CT scans with known mutation status of EGFR and TP53 were collected. The feature extraction based on their PET/CT images utilized the Pyradiomics package based on the 3D Slicer. The optimal radiomic features were selected through correlation analysis and the Gradient Boosting Decision Tree (GBDT) algorithm, followed by the construction of the radiomic model. The clinical model incorporated meaningful clinical variables, whereas the complex model integrated both the radiomic and clinical models. The area under the receiver operating characteristic curve (AUC) facilitated the comparison of prediction performance across the three models. The DCA gauged the clinical utility of these models.

RESULTS

The patient cohort was randomly allocated into a training set (n = 105) and a validation set (n = 45) in a 7:3 ratio. Eleven PET and eleven CT optimal radiomic features were selected to construct the radiomic model. The model showed a good ability to discriminate the co-occurrence of EGFR and TP53, with AUC equal to 0.850 in the training set, and 0.748 in the validation set, compared with 0.750 and 0.626 for the clinical model. The complex model exhibited the highest AUC values, with 0.880 and 0.794 in both sets, but there were no significant differences compared to the radiomic model. The DCA revealed favorable clinical value.

CONCLUSION

Integrated MRI radiomics, tumor microenvironment, and clinical risk factors for improving survival prediction in patients with glioblastomas

PURPOSE

To construct a comprehensive model for predicting the prognosis of patients with glioblastoma (GB) using a radiomics method and integrating clinical risk factors, tumor microenvironment (TME), and imaging characteristics.

MATERIALS AND METHODS

In this retrospective study, we included 148 patients (85 males and 63 females; median age 53 years) with isocitrate dehydrogenase-wildtype GB between January 2016 and April 2022. Patients were randomly divided into the training (n = 104) and test (n = 44) sets. The best feature combination related to GB overall survival (OS) was selected using LASSO Cox regression analyses. Clinical, radiomics, clinical-radiomics, clinical-TME, and clinical-radiomics-TME models were established. The models' concordance index (C-index) was evaluated. The survival curve was drawn using the Kaplan-Meier method, and the prognostic stratification ability of the model was tested.

RESULTS

LASSO Cox analyses were used to screen the factors related to OS in patients with GB, including MGMT (hazard ratio [HR] = 0.642; 95% CI 0.414-0.997; P = 0.046), TERT (HR = 1.755; 95% CI 1.095-2.813; P = 0.019), peritumoral edema (HR = 1.013; 95% CI 0.999-1.027; P = 0.049), tumor purity (TP; HR = 0.982; 95% CI 0.964-1.000; P = 0.054), CD163 + tumor-associated macrophages (TAMs; HR = 1.049; 95% CI 1.021-1.078; P < 0.001), CD68 + TAMs (HR = 1.055; 95% CI 1.018-1.093; P = 0.004), and the six radiomics features. The clinical-radiomics-TME model had the best survival prediction ability, the C‑index was 0.768 (0.717-0.819). The AUC of 1‑, 2‑, and 3‑year OS prediction in the test set was 0.842, 0.844, and 0.795, respectively.

CONCLUSION

The clinical-radiomics-TME model is the most effective for predicting the survival of patients with GB. Radiomics features, TP, and TAMs play important roles in the prognostic model.

Early prediction of progression-free survival of patients with locally advanced nasopharyngeal carcinoma using multi-parametric MRI radiomics

PURPOSE

Prognostic prediction plays a pivotal role in guiding personalized treatment for patients with locoregionally advanced nasopharyngeal carcinoma (LANPC). However, few studies have investigated the incremental value of functional MRI to the conventional MRI-based radiomic models. Here, we aimed to develop a radiomic model including functional MRI to predict the prognosis of LANPC patients.

METHODS

One hundred and twenty-six patients (training dataset, n = 88; validation dataset, n = 38) with LANPC were retrospectively included. Radiomic features were extracted from T1-weighted imaging (T1WI), T2-weighted imaging (T2WI), contrast-enhanced T1WI (cT1WI), and diffusion-weighted imaging (DWI). Pearson correlation analysis and recursive feature elimination or Relief were used for identifying features associated with progression-free survival (PFS). Five machine learning algorithms with cross-validation were compared to develop the optimal single-layer and fusion radiomic models. Clinical and combined models were developed via multivariate Cox regression model.

RESULTS

The clinical model based on TNM stage achieved a C-index of 0.544 in the validation dataset. The fusion radiomic model, incorporating DWI-, T1WI-, and cT1WI-derived imaging features, yielded the highest C-index of 0.788, outperforming DWI-based (C-index = 0.739), T1WI-based (C-index = 0.734), cT1WI-based (C-index = 0.722), and T1WI plus cT1WI-based models (C-index = 0.747) in predicting PFS. The fusion radiomic model yielded the C-index of 0.786 and 0.690 in predicting distant metastasis-free survival and overall survival, respectively. However, the addition of TNM stage to the fusion radiomic model could not improve the predictive power.

CONCLUSION

The fusion radiomic model demonstrates favorable performance in predicting survival outcomes in LANPC patients, surpassing TNM staging alone. Integration of DWI-derived features into conventional MRI radiomic models could enhance predictive accuracy.

An MRI Radiogenomic Signature to Characterize the Transcriptional Heterogeneity Associated with Prognosis and Biological Functions in Glioblastoma

BACKGROUND

The study sought to establish a radiogenomic signature to evaluate the transcriptional heterogeneity that reflects the prognosis and tumour-related biological functions of patients with glioblastoma.

METHODS

Transcriptional subclones were identified via fully unsupervised deconvolution of RNA sequencing. A genomic prognostic risk score was developed from transcriptional subclone proportions in the development dataset (n = 532) and independently verified in the testing dataset (n = 225). Multimodal magnetic resonance imaging (MRI) analysis involved feature extraction from three distinct anatomical regions across four imaging sequences. Key features were selected to construct a radiogenomic signature predictive of the genomic risk score in the radiogenomic dataset (n = 99), with subsequent survival analysis conducted in the image testing dataset (n = 233).

RESULTS

A total of 8 transcriptional subclones were identified, of which the metabolic pathway subclone and spinocerebellar ataxia subclone were independent risk factors for overall survival. The genomic risk score effectively differentiated patient subgroups with divergent survival outcomes in both development (p < 0.001) and testing datasets (p = 0.0003). Nineteen radiomic features were selected to construct a radiogenomic signature, with these features being linked to hallmark cancer pathways and the malignant behaviours of cancer cells. The radiogenomic signature predicted overall survival in the image testing dataset (hazard ratios (HR) = 1.67, p = 0.011).

CONCLUSIONS

A prognostic radiogenomic signature was established and verified to characterize transcriptional subclones with underlying biological functions in glioblastoma.

Machine learning prediction model for functional prognosis of acute ischemic stroke based on MRI radiomics of white matter hyperintensities

OBJECTIVE

The purpose of the current study is to explore the value of a nomogram that integrates clinical factors and MRI white matter hyperintensities (WMH) radiomics features in predicting the prognosis at 90 days for patients with acute ischemic stroke (AIS).

METHODS

A total of 202 inpatients with acute anterior circulation ischemic stroke from the Department of Neurology, Xuzhou Central Hospital between September 2023 and March 2024 were retrospectively enrolled. Inpatient clinical data and cranial MRI images were acquired. In this study, the sample was randomly divided into a training cohort comprising 141 cases and a validation cohort of 61 cases in a 7:3 ratio. WMH lesions on fluid-attenuated inversion recovery (FLAIR) sequences were automatically segmented and manually adjusted using Matlab and ITK-SNAP software. The segmentation led to the identification of total white matter hyperintensity (TWMH), periventricular white matter hyperintensity (PWMH), and deep white matter hyperintensity (DWMH). Subsequently, radiomics features were meticulously extracted from these three distinct regions of interest (ROIs). Radiomic models for the three ROIs were developed using six machine learning algorithms. The clinical model was built by identifying clinical risk factors through univariate and multivariate logistic regression analyses. A combined model was subsequently developed incorporating the best radiomics model with significant clinical factors. To illustrate these risk factors, a graphical representation known as a nomogram was devised.

RESULTS

Age, previous stroke history, coronary artery disease, admission blood glucose levels, homocysteine levels, and infarct volume were identified as independent clinical predictors of AIS prognosis. A total of 16, 21, and 22 radiomics features were selected from TWMH, PWMH, and DWMH, respectively. The TWMH radiomics model using the SVM classifier exhibited the best predictive performance for AIS prognosis, achieving a sensitivity of 90.0%, a specificity of 81.3%, an accuracy of 85.3%, and an AUC of 0.916 in the validation set. The combined model outperformed both the clinical and radiomics models, exhibiting exceptional predictive capabilities with a validation cohort sensitivity of 89.3%, specificity of 84.8%, accuracy of 86.9%, and AUC of 0.939.

CONCLUSION

The FLAIR sequence-based WMH radiomics approach demonstrates effective prediction of the 90-day functional prognosis in patients with AIS. The integration of TWMH radiomics and clinical factors in a combined model exhibits superior performance. This innovative model shows potential in aiding clinicians to enhance their assessment of patient prognosis and tailor personalized treatment strategies.

CLINICAL TRIAL NUMBER

Not applicable.

MRI radiomics based on machine learning in high-grade gliomas as a promising tool for prediction of CD44 expression and overall survival

We aimed to predict CD44 expression and assess its prognostic significance in patients with high-grade gliomas (HGG) using non-invasive radiomics models based on machine learning. Enhanced magnetic resonance imaging, along with the corresponding gene expression and clinicopathological data, was downloaded from online database. Kaplan-Meier survival curves, univariate and multivariate COX analyses, and time-dependent receiver operating characteristic were used to assess the prognostic value of CD44. Following the screening of radiomic features using repeat least absolute shrinkage and selection operator, two radiomics models were constructed utilizing logistic regression and support vector machine for validation purposes. The results indicated that CD44 protein levels were higher in HGG compared to normal brain tissues, and CD44 expression emerged as an independent biomarker of diminished overall survival (OS) in patients with HGG. Moreover, two predictive models based on seven radiomic features were built to predict CD44 expression levels in HGG, achieving areas under the curves (AUC) of 0.809 and 0.806, respectively. Calibration and decision curve analysis validated the fitness of the models. Notably, patients with high radiomic scores presented worse OS (p < 0.001). In summary, our results indicated that the radiomics models effectively differentiate CD44 expression level and OS in patients with HGG.

Radiomics in glioma: emerging trends and challenges

Radiomics is a promising neuroimaging technique for extracting and analyzing quantitative glioma features. This review discusses the application, emerging trends, and challenges associated with using radiomics in glioma. Integrating deep learning algorithms enhances various radiomics components, including image normalization, region of interest segmentation, feature extraction, feature selection, and model construction and can potentially improve model accuracy and performance. Moreover, investigating specific tumor habitats of glioblastomas aids in a better understanding of glioblastoma aggressiveness and the development of effective treatment strategies. Additionally, advanced imaging techniques, such as diffusion-weighted imaging, perfusion-weighted imaging, magnetic resonance spectroscopy, magnetic resonance fingerprinting, functional MRI, and positron emission tomography, can provide supplementary information for tumor characterization and classification. Furthermore, radiomics analysis helps understand the glioma immune microenvironment by predicting immune-related biomarkers and characterizing immune responses within tumors. Integrating multi-omics data, such as genomics, transcriptomics, proteomics, and pathomics, with radiomics, aids the understanding of the biological significance of the underlying radiomics features and improves the prediction of genetic mutations, prognosis, and treatment response in patients with glioma. Addressing challenges, such as model reproducibility, model generalizability, model interpretability, and multi-omics data integration, is crucial for the clinical translation of radiomics in glioma.

Establishment of a predictive nomogram for breast cancer lympho-vascular invasion based on radiomics obtained from digital breast tomography and clinical imaging features

BACKGROUND

To develop a predictive nomogram for breast cancer lympho-vascular invasion (LVI), based on digital breast tomography (DBT) data obtained from intra- and peri-tumoral regions.

METHODS

One hundred ninety-two breast cancer patients were enrolled in this retrospective study from 2 institutions, in which Institution 1 served as the basis for training (n = 113) and testing (n = 49) sets, while Institution 2 served as the external validation set (n = 30). Tumor regions of interest (ROI) were manually-delineated on DBT images, in which peri-tumoral ROI was defined as 1 mm around intra-tumoral ROI. Radiomics features were extracted, and logistic regression was used to construct intra-, peri-, and intra- + peri-tumoral radiomics models. Patient clinical data was analyzed by both uni- and multi-variable logistic regression analyses to identify independent risk factors for the non-radiomics clinical imaging model, and the combination of both the most optimal radiomics and clinical imaging models comprised the comprehensive model. The best-performing model out of the 3 types (radiomics, clinical imaging, comprehensive) was identified using receiver operating characteristic (ROC) curve analysis, and used to construct the predictive nomogram.

RESULTS

The most optimal radiomics model was the intra- + peri-tumoral model, and 3 independent risk factors for LVI, maximum tumor diameter (odds ratio [OR] = 1.486, 95% confidence interval [CI] = 1.082-2.041, P = 0.014), suspicious malignant calcification (OR = 2.898, 95% CI = 1.232 ~ 6.815, P = 0.015), and axillary lymph node (ALN) metastasis (OR = 3.615, 95% CI = 1.642-7.962, P < 0.001) were identified by the clinical imaging model. Furthermore, the comprehensive model was the most accurate in predicting LVI occurrence, with areas under the curve (AUCs) of 0.889, 0.916, and 0.862, for, respectively, the training, testing and external validation sets, compared to radiomics (0.858, 0.849, 0.844) and clinical imaging (0.743, 0.759, 0.732). The resulting nomogram, incorporating radiomics from the intra- + peri-tumoral model, as well as maximum tumor diameter, suspicious malignant calcification, and ALN metastasis, had great correspondence with actual LVI diagnoses under the calibration curve, and was of high clinical utility under decision curve analysis.

CONCLUSIONS

The predictive nomogram, derived from both radiomics and clinical imaging features, was highly accurate in identifying future LVI occurrence in breast cancer, demonstrating its potential as an assistive tool for clinicians to devise individualized treatment regimes.

Tumour surface regularity predicts survival and benefit from gross total resection in IDH-wildtype glioblastoma patients

OBJECTIVES

To evaluate the ability of sphericity in glioblastomas (GBMs) for predicting overall survival (OS) and the survival benefit from gross tumour resection (GTR).

METHODS

Preoperative MRI scans were retrospectively analysed in IDH-wildtype GBM patients from two datasets. After MRI preprocessing and tumour segmentation, tumour sphericity was calculated based on the tumour core region. The prognostic value of tumour surface regularity was evaluated via Kaplan-Meier (K-M) plots, univariate and multivariate Cox proportional hazards analyses. In different surface regularity subgroups, the OS benefit from GTR was evaluated via K-M plots and the restricted mean survival time (RMST).

RESULTS

This study included 367 patients (median age, 62.0 years [IQR, 54.5-70.5 years]) in the discovery cohort and 475 patients (median age, 63.6 years [IQR, 56.2-71.3 years]) in the validation cohort. Sphericity was an independent predictor of OS in the discovery (p = 0.022, hazard ratio (HR) = 1.45, 95% confidence interval (CI) 1.06-1.99) and validation groups (p = 0.007, HR = 1.38, 95% CI: 1.09-1.74) according to multivariate analysis. Age, extent of resection, and surface regularity composed a prognostic model that separated patients into subgroups with distinct prognoses. Patients in the surface-irregular subgroup benefited from GTR, but patients in the surface-regular subgroup did not in the discovery (p < 0.001 vs. p = 0.056) and validation datasets (p < 0.001 vs. p = 0.11).

CONCLUSIONS

The high surface regularity of IDH-wildtype GBM is significantly correlated with better OS and does not benefit substantially from GTR.

CRITICAL RELEVANCE STATEMENT

The proposed imaging marker has the potential to increase the survival prediction efficacy for IDH-wildtype glioblastomas (GBMs), offering a valuable indicator for clinical decision-making.

KEY POINTS

Sphericity is an independent prognostic factor in IDH-wildtype glioblastomas (GBMs). High sphericity in IDH-wildtype GBM is significantly correlated with better survival. GBM patients with low sphericity could receive survival benefits from gross tumour resection.

Survival and immune microenvironment prediction of glioma based on MRI imaging genomics method: a retrospective observational study

Glioma is characterized by high heterogeneity and poor prognosis. Attempts have been made to understand its diversity in both genetic expressions and radiomic characteristics, while few integrated the two omics in predicting survival of glioma. This study was intended to investigate the connection between glioma imaging and genome, and examine its predictive value in glioma mortality risk and tumor immune microenvironment (TIME). Clinical, transcriptomics and radiomics data were obtained from public datasets and patients in our center. Correlation analysis between gene expression and radiomic feature (RF) was performed, followed by survival analysis to select RF-related genes (RFRGs) and gene expression-related RFs (GRRFs). After that, RFRGs and GRRFs were used to construct mortality risk prediction model of all glioma and isocitrate dehydrogenase (IDH) wild type (WT) glioma. The association between RFRGs and TIME was explored. Six cohorts composed of 1,754 glioma patients were included. Thirty-five genes and eighty-two RFs demonstrated high correlation with each other. Gene score based on RFRGs was independent predictor of both glioma (P < 0.05) and IDH-WT glioma (P < 0.05). Same score based on GRRFs was also able to stratify risk of both glioma (P < 0.0001) and IDH-WT glioma (P < 0.0001), with nomograms constructed separately. The TIME of gliomas predicted with RFRGs' score found mismatched risk of death with immune response. RFRGs and GRRFs were able to predict glioma mortality risk and TIME. Further studies could validate our results and explore this genome-imaging interactions.

Whole slide image based prognosis prediction in rectal cancer using unsupervised artificial intelligence

BACKGROUND

Rectal cancer is a common cancer worldwide and lacks effective prognostic markers. The development of prognostic markers by computational pathology methods has attracted increasing attention. This paper aims to construct a prognostic signature from whole slide images for predicting progression-free survival (PFS) of rectal cancer through an unsupervised artificial intelligence algorithm.

METHODS

A total of 238 patients with rectal cancer from two datasets were collected for the development and validation of the prognostic signature. A tumor detection model was built by transfer learning. Then, on the basis of the tumor patches recognized by the tumor detection model, a convolutional autoencoder model was built for decoding the tumor patches into deep latent features. Next, on the basis of the deep latent features, the tumor patches were divided into different clusters. The cluster number and other hyperparameters were optimized by a nested cross-validation method. The percentage of each cluster from the patient's tumor patches, which is hereafter called PCF, was calculated for prognostic signature construction. The prognostic signature was constructed by Cox proportional hazard regression with L2 regularization. Finally, bioinformatic analysis was performed to explore the underlying biological mechanisms of the PCFs.

RESULTS

The accuracy of the tumor detection model in distinguishing tumor patches from non-tumor patches achieved 99.3%. The optimal cluster number was determined to be 9. Therfore, 9 PCFs were calculated to construct the prognostic signature. The prognostic signature achieved a concordance index of 0.701 in the validation cohort. The Kaplan-Meier survival curves showed the prognostic signature had good risk stratification ability. Through the bioinformatic analysis, several PCF-associated genes were identified. These genes were enriched in various gene ontology terms.

CONCLUSION

The developed prognostic signature can effectively predict PFS in patients with rectal cancer and exploration of the underlying biological mechanisms may help to promote its clinical translation.

Metabolic checkpoints in glioblastomas: targets for new therapies and non-invasive detection

Glioblastoma (GBM) is a highly malignant tumor of the central nervous system that remains intractable despite advancements in current tumor treatment modalities, including immunotherapy. In recent years, metabolic checkpoints (aberrant metabolic pathways underlying the immunosuppressive tumor microenvironment) have gained attention as promising therapeutic targets and sensitive biomarkers across various cancers. Here, we briefly review the existing understanding of tumor metabolic checkpoints and their implications in the biology and management of GBM. Additionally, we discuss techniques that could evaluate metabolic checkpoints of GBM non-invasively, thereby potentially facilitating neo-adjuvant treatment and dynamic surveillance.

18F-FDG PET/CT-based habitat radiomics combining stacking ensemble learning for predicting prognosis in hepatocellular carcinoma: a multi-center study

BACKGROUND

This study aims to develop habitat radiomic models to predict overall survival (OS) for hepatocellular carcinoma (HCC), based on the characterization of the intratumoral heterogeneity reflected in 18F-FDG PET/CT images.

METHODS

A total of 137 HCC patients from two institutions were retrospectively included. First, intratumoral habitats were achieved by a two-step unsupervised clustering process based on k-means clustering. Second, a total of 4032 radiomic features were extracted based on each habitat, including 2016 PET-based and 2016 CT-based radiomic features. Then, after feature selection, the stacking ensemble learning approach which combined six machine learning classifiers as the first-level learners with Cox proportional hazards regression as the second-level learner, was employed to build multiple radiomic models. Finally, the optimal model was selected based on the calculation of the C-index, and a combined model integrating with a clinical model was also constructed to identify the potentially complementary effect.

RESULTS

Three spatially distinct habitats were identified in the two cohorts. Among a total of 30 stacking ensemble learning models established based on different combinations of 5 types of segmented volumes of interest (VOIs) with 6 types of classifiers, the MLP-Cox-habitat-2 model was selected as the optimal radiomic model with a C-index of 0.702 in the external validation cohort. Furthermore, the combined model integrating the optimal radiomic model with the clinical model achieved an improved C-index of 0.747. Consistently, the combined model outperformed the other models for OS prediction, with a time-dependent AUC of 0.835, 0.828, and 0.800 in the 1-year, 2-year, and 3-year OS, respectively.

CONCLUSION

18F-FDG PET/CT-based habitat radiomics outperformed traditional radiomics in OS prediction for HCC, with a further improved predictive power by integrating with the clinical model. The optimal combined habitat model was potentially promising in guiding individualized treatment for HCC.

TRIAL REGISTRATION

This study was a retrospective study, so it was free from registration.

Prediction of acute pancreatitis severity based on early CT radiomics

BACKGROUND

This study aims to develop and validate an integrated predictive model combining CT radiomics and clinical parameters for early assessment of acute pancreatitis severity.

METHODS

A retrospective cohort of 246 patients with acute pancreatitis was analyzed, with a 70%-30% split for training and validation groups. CT image segmentation was performed using ITK-SNAP, followed by the extraction of radiomics features. The stability of the radiomics features was assessed through inter-observer Intraclass Correlation Coefficient analysis. Feature selection was carried out using univariate analysis and least absolute shrinkage and selection operator (LASSO) regression with 10-fold cross-validation. A radiomics model was constructed through logistic regression to compute the radiomics score. Concurrently, univariate and multivariate logistic regression were employed to identify independent clinical risk factors for the clinical model. The radiomics score and clinical variables were integrated into a combined model, which was visualized with a nomogram. Model performance and net clinical benefit were evaluated through the area under the receiver operating characteristic curve (AUC), the DeLong test, and decision curve analysis.

RESULTS

A total of 913 radiomics features demonstrated satisfactory consistency. Eight features were selected for the radiomics model. Serum calcium, C-reactive protein, and white blood cell count were identified as independent clinical predictors. The AUC of the radiomics model was 0.871 (95% CI, 0.793-0.949) in the training cohort and 0.859 (95% CI, 0.751-0.967) in the validation cohort. The clinical model achieved AUCs of 0.833 (95% CI, 0.756-0.910) and 0.810 (95% CI, 0.692-0.929) for the training and validation cohorts, respectively. The combined model outperformed both the radiomics and clinical models, with an AUC of 0.905 (95% CI, 0.837-0.973) in the training cohort and 0.908 (95% CI, 0.824-0.992) in the validation cohort. The DeLong test confirmed superior predictive performance of the combined model over both the radiomics and clinical models in the training cohort, and over the clinical model in the validation cohort. Decision curve analysis further demonstrated that the combined model provided greater net clinical benefit than the radiomics or clinical models alone.

CONCLUSION

The clinical-radiomics model offers a novel tool for the early prediction of acute pancreatitis severity, providing valuable support for clinical decision-making.

Prognostic value of FDX1, the cuprotosis key gene, and its prediction models across imaging modalities and histology

BACKGROUND

Cuprotosis has been identified as a novel way of cell death. The key regulator ferredoxin 1 (FDX1) was explored via pan-cancer analysis, and its prediction models were proposed across seven malignancies and two imaging modalities.

METHODS

The prognostic value of FDX1 was explored via 1654 cases of 33 types of cancer in the Cancer Genome Atlas database. The MRI cohort of hepatocellular carcinoma in the First Affiliated Hospital of Fujian Medical University, and CT and MRI images from the Cancer Imaging Archive, REMBRANDT and Duke databases were exploited to formulate radiomic models to predict FDX1 expression. After segmentation of volumes of interest and feature extraction, the recursive feature elimination algorithm was used to screen features, logistic regression was used to model features, immunohistochemistry staining with FDX1 antibody was performed to test the radiomic model.

RESULTS

FDX1 was found to be prognostic in various types of cancer. The area under the receiver operating characteristic curve of radiomic models to predict FDX1 expression reached 0.825 (95% CI = 0.739-0.911). Cross-tissue compatibility was confirmed in pan-cancer validation and test cohorts. Mechanistically, the radiomic score was significantly correlated with various immunosuppressive genes and gene mutations. The radiomic score was also found to be an independent prognostic factor, making it a potentially actionable biomarker in the clinical setting.

CONCLUSIONS

The expression of FDX1 could be non-invasively predicted via radiomics. The radiomic patterns with biological and clinical relevance across histology and modalities could have a broad impact on a larger population of patients.

Radiomic Features as Artificial Intelligence Prognostic Models in Glioblastoma: A Systematic Review and Meta-Analysis

BACKGROUND

Glioblastoma, the predominant primary tumor among all central nervous systems, accounts for around 80% of cases. Prognosis in neuro-oncology involves assessing the disease's progression in different individuals, considering the time between the initial pathological diagnosis and the time until the disease worsens. A noninvasive therapeutic approach called radiomic features (RFs), which involves the application of artificial intelligence in MRI, has been developed to address this issue. This study aims to systematically gather evidence and evaluate the prognosis significance of radiomics in glioblastoma using RFs.

METHODS

We conducted an extensive search across the PubMed, ScienceDirect, EMBASE, Web of Science, and Cochrane databases to identify relevant original studies examining the use of RFs to evaluate the prognosis of patients with glioblastoma. This thorough search was completed on 25 July 2024. Our search terms included glioblastoma, MRI, magnetic resonance imaging, radiomics, and survival or prognosis. We included only English-language studies involving human subjects, excluding case reports, case series, and review studies. The studies were classified into two quality categories: those rated 4-6 were considered moderate-, whereas those rated 7-9 were high-quality using the Newcastle-Ottawa Scale (NOS). Hazard ratios (HRs) and their 95% confidence intervals (CIs) for OS and PFS were combined using random effects models.

RESULTS

In total, 253 studies were found in the initial search across the five databases. After screening the articles, 40 were excluded due to not meeting the eligibility criteria, and we included only 14 studies. All twelve OS and eight PFS trials were considered, involving 1.639 and 747 patients, respectively. The random effects model was used to calculate the pooled HRs for OS and PFS. The HR for OS was 3.59 (95% confidence interval [CI], 1.80-7.17), while the HR for PFS was 4.20 (95% CI, 1.02-17.32).

CONCLUSIONS

An RF-AI-based approach offers prognostic significance for OS and PFS in patients with glioblastoma.

Multicenter radio-multiomic analysis for predicting breast cancer outcome and unravelling imaging-biological connection

Radiomics offers a noninvasive avenue for predicting clinicopathological factors. However, thorough investigations into a robust breast cancer outcome-predicting model and its biological significance remain limited. This study develops a robust radiomic model for prognosis prediction, and further excavates its biological foundation and transferring prediction performance. We retrospectively collected preoperative dynamic contrast-enhanced MRI data from three distinct breast cancer patient cohorts. In FUSCC cohort (n = 466), Lasso was used to select features correlated with patient prognosis and multivariate Cox regression was utilized to integrate these features and build the radiomic risk model, while multiomic analysis was conducted to investigate the model's biological implications. DUKE cohort (n = 619) and I-SPY1 cohort (n = 128) were used to test the performance of the radiomic signature in outcome prediction. A thirteen-feature radiomic signature was identified in the FUSCC cohort training set and validated in the FUSCC cohort testing set, DUKE cohort and I-SPY1 cohort for predicting relapse-free survival (RFS) and overall survival (OS) (RFS: p = 0.013, p = 0.024 and p = 0.035; OS: p = 0.036, p = 0.005 and p = 0.027 in the three cohorts). Multiomic analysis uncovered metabolic dysregulation underlying the radiomic signature (ATP metabolic process: NES = 1.84, p-adjust = 0.02; cholesterol biosynthesis: NES = 1.79, p-adjust = 0.01). Regarding the therapeutic implications, the radiomic signature exhibited value when combining clinical factors for predicting the pathological complete response to neoadjuvant chemotherapy (DUKE cohort, AUC = 0.72; I-SPY1 cohort, AUC = 0.73). In conclusion, our study identified a breast cancer outcome-predicting radiomic signature in a multicenter radio-multiomic study, along with its correlations with multiomic features in prognostic risk assessment, laying the groundwork for future prospective clinical trials in personalized risk stratification and precision therapy.

Radiogenomic profiling of global DNA methylation associated with molecular phenotypes and immune features in glioma

BACKGROUND

The radiogenomic analysis has provided valuable imaging biomarkers with biological insights for gliomas. The radiogenomic markers for molecular profile such as DNA methylation remain to be uncovered to assist the molecular diagnosis and tumor treatment.

METHODS

We apply the machine learning approaches to identify the magnetic resonance imaging (MRI) features that are associated with molecular profiles in 146 patients with gliomas, and the fitting models for each molecular feature (MoRad) are developed and validated. To provide radiological annotations for the molecular profiles, we devise two novel approaches called radiomic oncology (RO) and radiomic set enrichment analysis (RSEA).

RESULTS

The generated MoRad models perform well for profiling each molecular feature with radiomic features, including mutational, methylation, transcriptional, and protein profiles. Among them, the MoRad models have a remarkable performance in quantitatively mapping global DNA methylation. With RO and RSEA approaches, we find that global DNA methylation could be reflected by the heterogeneity in volumetric and textural features of enhanced regions in T2-weighted MRI. Finally, we demonstrate the associations of global DNA methylation with clinicopathological, molecular, and immunological features, including histological grade, mutations of IDH and ATRX, MGMT methylation, multiple methylation-high subtypes, tumor-infiltrating lymphocytes, and long-term survival outcomes.

CONCLUSIONS

Global DNA methylation is highly associated with radiological profiles in glioma. Radiogenomic global methylation is an imaging-based quantitative molecular biomarker that is associated with specific consensus molecular subtypes and immune features.

CT-based radiomics nomogram to predict proliferative hepatocellular carcinoma and explore the tumor microenvironment

BACKGROUND

Proliferative hepatocellular carcinomas (HCCs) is a class of aggressive tumors with poor prognosis. We aimed to construct a computed tomography (CT)-based radiomics nomogram to predict proliferative HCC, stratify clinical outcomes and explore the tumor microenvironment.

METHODS

Patients with pathologically diagnosed HCC following a hepatectomy were retrospectively collected from two medical centers. A CT-based radiomics nomogram incorporating radiomics model and clinicoradiological features to predict proliferative HCC was constructed using the training cohort (n = 184), and validated using an internal test cohort (n = 80) and an external test cohort (n = 89). The predictive performance of the nomogram for clinical outcomes was evaluated for HCC patients who underwent surgery (n = 201) or received transarterial chemoembolization (TACE, n = 104). RNA sequencing data and histological tissue slides from The Cancer Imaging Archive database were used to perform transcriptomics and pathomics analysis.

RESULTS

The areas under the receiver operating characteristic curve of the radiomics nomogram to predict proliferative HCC were 0.84, 0.87, and 0.85 in the training, internal test, and external test cohorts, respectively. The radiomics nomogram could stratify early recurrence-free survivals in the surgery outcome cohort (hazard ratio [HR] = 2.25; P < 0.001) and progression-free survivals in the TACE outcome cohort (HR = 2.21; P = 0.03). Transcriptomics and pathomics analysis indicated that the radiomics nomogram was associated with carbon metabolism, immune cells infiltration, TP53 mutation, and heterogeneity of tumor cells.

CONCLUSION

The CT-based radiomics nomogram could predict proliferative HCC, stratify clinical outcomes, and measure a pro-tumor microenvironment.

Biologically interpretable multi-task deep learning pipeline predicts molecular alterations, grade, and prognosis in glioma patients

Deep learning models have been developed for various predictions in glioma; yet, they were constrained by manual segmentation, task-specific design, or a lack of biological interpretation. Herein, we aimed to develop an end-to-end multi-task deep learning (MDL) pipeline that can simultaneously predict molecular alterations and histological grade (auxiliary tasks), as well as prognosis (primary task) in gliomas. Further, we aimed to provide the biological mechanisms underlying the model's predictions. We collected multiscale data including baseline MRI images from 2776 glioma patients across two private (FAHZU and HPPH, n = 1931) and three public datasets (TCGA, n = 213; UCSF, n = 410; and EGD, n = 222). We trained and internally validated the MDL model using our private datasets, and externally validated it using the three public datasets. We used the model-predicted deep prognosis score (DPS) to stratify patients into low-DPS and high-DPS subtypes. Additionally, a radio-multiomics analysis was conducted to elucidate the biological basis of the DPS. In the external validation cohorts, the MDL model achieved average areas under the curve of 0.892-0.903, 0.710-0.894, and 0.850-0.879 for predicting IDH mutation status, 1p/19q co-deletion status, and tumor grade, respectively. Moreover, the MDL model yielded a C-index of 0.723 in the TCGA and 0.671 in the UCSF for the prediction of overall survival. The DPS exhibits significant correlations with activated oncogenic pathways, immune infiltration patterns, specific protein expression, DNA methylation, tumor mutation burden, and tumor-stroma ratio. Accordingly, our work presents an accurate and biologically meaningful tool for predicting molecular subtypes, tumor grade, and survival outcomes in gliomas, which provides personalized clinical decision-making in a global and non-invasive manner.

Predicting progression-free survival in patients with epithelial ovarian cancer using an interpretable random forest model

Prognostic models play a crucial role in providing personalised risk assessment, guiding treatment decisions, and facilitating the counselling of patients with cancer. However, previous imaging-based artificial intelligence models of epithelial ovarian cancer lacked interpretability. In this study, we aimed to develop an interpretable machine-learning model to predict progression-free survival in patients with epithelial ovarian cancer using clinical variables and radiomics features. A total of 102 patients with epithelial ovarian cancer who underwent contrast-enhanced computed tomography scans were enrolled in this retrospective study. Pre-surgery clinical data, including age, performance status, body mass index, tumour stage, venous blood cancer antigen-125 (CA125) level, white blood cell count, neutrophil count, red blood cell count, haemoglobin level, and platelet count, were obtained from medical records. The volume of interest for each tumour was manually delineated slice-by-slice along the boundary. A total of 2074 radiomic features were extracted from the pre- and post-contrast computed tomography images. Optimal radiomic features were selected using the Least Absolute Shrinkage and Selection Operator logistic regression. Multivariate Cox analysis was performed to identify independent predictors of three-year progression-free survival. The random forest algorithm developed radiomic and combined models using four-fold cross-validation. Finally, the Shapley additive explanation algorithm was applied to interpret the predictions of the combined model. Multivariate Cox analysis identified CA-125 levels (P = 0.015), tumour stage (P = 0.019), and Radscore (P < 0.001) as independent predictors of progression-free survival. The combined model based on these factors achieved an area under the curve of 0.812 (95 % confidence interval: 0.802-0.822) in the training cohort and 0.772 (95 % confidence interval: 0.727-0.817) in the validation cohort. The most impactful features on the model output were Radscore, followed by tumour stage and CA-125. In conclusion, the Shapley additive explanation-based interpretation of the prognostic model enables clinicians to understand the reasoning behind predictions better.

Brain gliomas: Diagnostic and therapeutic issues and the prospects of drug-targeted nano-delivery technology

Glioma is the most common intracranial malignant tumor, with severe difficulty in treatment and a low patient survival rate. Due to the heterogeneity and invasiveness of tumors, lack of personalized clinical treatment design, and physiological barriers, it is often difficult to accurately distinguish gliomas, which dramatically affects the subsequent diagnosis, imaging treatment, and prognosis. Fortunately, nano-delivery systems have demonstrated unprecedented capabilities in diagnosing and treating gliomas in recent years. They have been modified and surface modified to efficiently traverse BBB/BBTB, target lesion sites, and intelligently release therapeutic or contrast agents, thereby achieving precise imaging and treatment. In this review, we focus on nano-delivery systems. Firstly, we provide an overview of the standard and emerging diagnostic and treatment technologies for glioma in clinical practice. After induction and analysis, we focus on summarizing the delivery methods of drug delivery systems, the design of nanoparticles, and their new advances in glioma imaging and treatment in recent years. Finally, we discussed the prospects and potential challenges of drug-delivery systems in diagnosing and treating glioma.

A deep learning model based on contrast-enhanced computed tomography for differential diagnosis of gallbladder carcinoma

BACKGROUND

Gallbladder carcinoma (GBC) is highly malignant, and its early diagnosis remains difficult. This study aimed to develop a deep learning model based on contrast-enhanced computed tomography (CT) images to assist radiologists in identifying GBC.

METHODS

We retrospectively enrolled 278 patients with gallbladder lesions (> 10 mm) who underwent contrast-enhanced CT and cholecystectomy and divided them into the training (n = 194) and validation (n = 84) datasets. The deep learning model was developed based on ResNet50 network. Radiomics and clinical models were built based on support vector machine (SVM) method. We comprehensively compared the performance of deep learning, radiomics, clinical models, and three radiologists.

RESULTS

Three radiomics features including LoG_3.0 gray-level size zone matrix zone variance, HHL first-order kurtosis, and LHL gray-level co-occurrence matrix dependence variance were significantly different between benign gallbladder lesions and GBC, and were selected for developing radiomics model. Multivariate regression analysis revealed that age ≥ 65 years [odds ratios (OR) = 4.4, 95% confidence interval (CI): 2.1-9.1, P < 0.001], lesion size (OR = 2.6, 95% CI: 1.6-4.1, P < 0.001), and CA-19-9 > 37 U/mL (OR = 4.0, 95% CI: 1.6-10.0, P = 0.003) were significant clinical risk factors of GBC. The deep learning model achieved the area under the receiver operating characteristic curve (AUC) values of 0.864 (95% CI: 0.814-0.915) and 0.857 (95% CI: 0.773-0.942) in the training and validation datasets, which were comparable with radiomics, clinical models and three radiologists. The sensitivity of deep learning model was the highest both in the training [90% (95% CI: 82%-96%)] and validation [85% (95% CI: 68%-95%)] datasets.

CONCLUSIONS

The deep learning model may be a useful tool for radiologists to distinguish between GBC and benign gallbladder lesions.

Statistical plots in oncologic imaging, a primer for neuroradiologists

The simplest approach to convey the results of scientific analysis, which can include complex comparisons, is typically through the use of visual items, including figures and plots. These statistical plots play a critical role in scientific studies, making data more accessible, engaging, and informative. A growing number of visual representations have been utilized recently to graphically display the results of oncologic imaging, including radiomic and radiogenomic studies. Here, we review the applications, distinct properties, benefits, and drawbacks of various statistical plots. Furthermore, we provide neuroradiologists with a comprehensive understanding of how to use these plots to effectively communicate analytical results based on imaging data.

A preoperative radiogenomic model based on quantitative heterogeneity for predicting outcomes in triple-negative breast cancer patients who underwent neoadjuvant chemotherapy

BACKGROUND

Triple-negative breast cancer (TNBC) is highly heterogeneous, resulting in different responses to neoadjuvant chemotherapy (NAC) and prognoses among patients. This study sought to characterize the heterogeneity of TNBC on MRI and develop a radiogenomic model for predicting both pathological complete response (pCR) and prognosis.

MATERIALS AND METHODS

In this retrospective study, TNBC patients who underwent neoadjuvant chemotherapy at Fudan University Shanghai Cancer Center were enrolled as the radiomic development cohort (n = 315); among these patients, those whose genetic data were available were enrolled as the radiogenomic development cohort (n = 98). The study population of the two cohorts was randomly divided into a training set and a validation set at a ratio of 7:3. The external validation cohort (n = 77) included patients from the DUKE and I-SPY 1 databases. Spatial heterogeneity was characterized using features from the intratumoral subregions and peritumoral region. Hemodynamic heterogeneity was characterized by kinetic features from the tumor body. Three radiomics models were developed by logistic regression after selecting features. Model 1 included subregional and peritumoral features, Model 2 included kinetic features, and Model 3 integrated the features of Model 1 and Model 2. Two fusion models were developed by further integrating pathological and genomic features (PRM: pathology-radiomics model; GPRM: genomics-pathology-radiomics model). Model performance was assessed with the AUC and decision curve analysis. Prognostic implications were assessed with Kaplan‒Meier curves and multivariate Cox regression.

RESULTS

Among the radiomic models, the multiregional model representing multiscale heterogeneity (Model 3) exhibited better pCR prediction, with AUCs of 0.87, 0.79, and 0.78 in the training, internal validation, and external validation sets, respectively. The GPRM showed the best performance for predicting pCR in the training (AUC = 0.97, P = 0.015) and validation sets (AUC = 0.93, P = 0.019). Model 3, PRM and GPRM could stratify patients by disease-free survival, and a predicted nonpCR was associated with poor prognosis (P = 0.034, 0.001 and 0.019, respectively).

CONCLUSION

Multiscale heterogeneity characterized by DCE-MRI could effectively predict the pCR and prognosis of TNBC patients. The radiogenomic model could serve as a valuable biomarker to improve the prediction performance.

Comprehensive quantitative radiogenomic evaluation reveals novel radiomic subtypes with distinct immune pattern in glioma

BACKGROUND

Accurate classification of gliomas is critical to the selection of immunotherapy, and MRI contains a large number of radiomic features that may suggest some prognostic relevant signals. We aim to predict new subtypes of gliomas using radiomic features and characterize their survival, immune, genomic profiles and drug response.

METHODS

We initially obtained 341 images of 36 patients from the CPTAC dataset for the development of deep learning models. Further 1812 images of 111 patients from TCGA_GBM and 152 images of 53 patients from TCGA_LGG were collected for testing and validation. A deep learning method based on Mask R-CNN was developed to identify new subtypes of glioma patients and compared the survival status, immune infiltration patterns, genomic signatures, specific drugs, and predictive models of different subtypes.

RESULTS

200 glioma patients (mean age, 33 years ± 19 [standard deviation]) were enrolled. The accuracy of the deep learning model for identifying tumor regions achieved 88.3 % (98/111) in the test set and 83 % (44/53) in the validation set. The sample was divided into two subtypes based on radiomic features showed different prognostic outcomes (hazard ratio, 2.70). According to the results of the immune infiltration analysis, the subtype with a poorer prognosis was defined as the immunosilencing radiomic (ISR) subtype (n = 43), and the other subtype was the immunoactivated radiomic (IAR) subtype (n = 53). Subtype-specific genomic signatures distinguished celllines into ISR celllines (n = 9) and control celllines (n = 13), and identified eight ISR-specific drugs, four of which were validated by the OCTAD database. Three machine learning-based classifiers showed that radiomic and genomic co-features better predicted the radiomic subtypes of gliomas.

CONCLUSIONS

These findings provide insights into how radiogenomic could identify specific subtypes that predict prognosis, immune and drug sensitivity in a non-invasive manner.

Unveiling divergent treatment prognoses in IDHwt-GBM subtypes through multiomics clustering: a swift dual MRI-mRNA model for precise subtype prediction

BACKGROUND

IDH1-wildtype glioblastoma multiforme (IDHwt-GBM) is a highly heterogeneous and aggressive brain tumour characterised by a dismal prognosis and significant challenges in accurately predicting patient outcomes. To address these issues and personalise treatment approaches, we aimed to develop and validate robust multiomics molecular subtypes of IDHwt-GBM. Through this, we sought to uncover the distinct molecular signatures underlying these subtypes, paving the way for improved diagnosis and targeted therapy for this challenging disease.

METHODS

To identify stable molecular subtypes among 184 IDHwt-GBM patients from TCGA, we used the consensus clustering method to consolidate the results from ten advanced multiomics clustering approaches based on mRNA, lncRNA, and mutation data. We developed subtype prediction models using the PAM and machine learning algorithms based on mRNA and MRI data for enhanced clinical utility. These models were validated in five independent datasets, and an online interactive system was created. We conducted a comprehensive assessment of the clinical impact, drug treatment response, and molecular associations of the IDHwt-GBM subtypes.

RESULTS

In the TCGA cohort, two molecular subtypes, class 1 and class 2, were identified through multiomics clustering of IDHwt-GBM patients. There was a significant difference in survival between Class 1 and Class 2 patients, with a hazard ratio (HR) of 1.68 [1.15-2.47]. This difference was validated in other datasets (CGGA: HR = 1.75[1.04, 2.94]; CPTAC: HR = 1.79[1.09-2.91]; GALSS: HR = 1.66[1.09-2.54]; UCSF: HR = 1.33[1.00-1.77]; UPENN HR = 1.29[1.04-1.58]). Additionally, class 2 was more sensitive to treatment with radiotherapy combined with temozolomide, and this sensitivity was validated in the GLASS cohort. Correspondingly, class 2 and class 1 exhibited significant differences in mutation patterns, enriched pathways, programmed cell death (PCD), and the tumour immune microenvironment. Class 2 had more mutation signatures associated with defective DNA mismatch repair (P = 0.0021). Enriched pathways of differentially expressed genes in class 1 and class 2 (P-adjust < 0.05) were mainly related to ferroptosis, the PD-1 checkpoint pathway, the JAK-STAT signalling pathway, and other programmed cell death and immune-related pathways. The different cell death modes and immune microenvironments were validated across multiple datasets. Finally, our developed survival prediction model, which integrates molecular subtypes, age, and sex, demonstrated clinical benefits based on the decision curve in the test set. We deployed the molecular subtyping prediction model and survival prediction model online, allowing interactive use and facilitating user convenience.

CONCLUSIONS

Molecular subtypes were identified and verified through multiomics clustering in IDHwt-GBM patients. These subtypes are linked to specific mutation patterns, the immune microenvironment, prognoses, and treatment responses.

The prognostic relevance of a gene expression signature in MRI-defined highly vascularized glioblastoma

Background

The vascular heterogeneity of glioblastomas (GB) remains an important area of research, since tumor progression and patient prognosis are closely tied to this feature. With this study, we aim to identify gene expression profiles associated with MRI-defined tumor vascularity and to investigate its relationship with patient prognosis.

Methods

The study employed MRI parameters calculated with DSC Perfusion Quantification of ONCOhabitats glioma analysis software and RNA-seq data from the TCGA-GBM project dataset. In our study, we had a total of 147 RNA-seq samples, which 15 of them also had MRI parameter information. We analyzed the gene expression profiles associated with MRI-defined tumor vascularity using differential gene expression analysis and performed Log-rank tests to assess the correlation between the identified genes and patient prognosis.

Results

The findings of our research reveal a set of 21 overexpressed genes associated with the high vascularity pattern. Notably, several of these overexpressed genes have been previously implicated in worse prognosis based on existing literature. Our log-rank test further validates that the collective upregulation of these genes is indeed correlated with an unfavorable prognosis. This set of genes includes a variety of molecules, such as cytokines, receptors, ligands, and other molecules with diverse functions.

Conclusions

Our findings suggest that the set of 21 overexpressed genes in the High Vascularity group could potentially serve as prognostic markers for GB patients. These results highlight the importance of further investigating the relationship between the molecules such as cytokines or receptors underlying the vascularity in GB and its observation through MRI and developing targeted therapies for this aggressive disease.

Application of artificial intelligence radiomics in the diagnosis, treatment, and prognosis of hepatocellular carcinoma

Hepatocellular carcinoma (HCC) is the most common type of primary liver cancer, with an increasing incidence and poor prognosis. In the past decade, artificial intelligence (AI) technology has undergone rapid development in the field of clinical medicine, bringing the advantages of efficient data processing and accurate model construction. Promisingly, AI-based radiomics has played an increasingly important role in the clinical decision-making of HCC patients, providing new technical guarantees for prediction, diagnosis, and prognostication. In this review, we evaluated the current landscape of AI radiomics in the management of HCC, including its diagnosis, individual treatment, and survival prognosis. Furthermore, we discussed remaining challenges and future perspectives regarding the application of AI radiomics in HCC.

Lymph node metastasis prediction and biological pathway associations underlying DCE-MRI deep learning radiomics in invasive breast cancer

BACKGROUND

The relationship between the biological pathways related to deep learning radiomics (DLR) and lymph node metastasis (LNM) of breast cancer is still poorly understood. This study explored the value of DLR based on dynamic contrast-enhanced magnetic resonance imaging (DCE-MRI) in LNM of invasive breast cancer. It also analyzed the biological significance of DLR phenotype based on genomics.

METHODS

Two cohorts from the Cancer Imaging Archive project were used, one as the training cohort (TCGA-Breast, n = 88) and one as the validation cohort (Breast-MRI-NACT Pilot, n = 57). Radiomics and deep learning features were extracted from preoperative DCE-MRI. After dual selection by principal components analysis (PCA) and relief methods, radiomics and deep learning models for predicting LNM were constructed by the random forest (RF) method. A post-fusion strategy was used to construct the DLR nomograms (DLRNs) for predicting LNM. The performance of the models was evaluated using the receiver operating characteristic (ROC) curve and Delong test. In the training cohort, transcriptome data were downloaded from the UCSC Xena online database, and biological pathways related to the DLR phenotypes were identified. Finally, hub genes were identified to obtain DLR gene expression (RadDeepGene) scores.

RESULTS

DLRNs were based on area under curve (AUC) evaluation (training cohort, AUC = 0.98; validation cohort, AUC = 0.87), which were higher than single radiomics models or GoogLeNet models. The Delong test (radiomics model, P = 0.04; GoogLeNet model, P = 0.01) also validated the above results in the training cohorts, but they were not statistically significant in the validation cohort. The GoogLeNet phenotypes were related to multiple classical tumor signaling pathways, characterizing the biological significance of immune response, signal transduction, and cell death. In all, 20 genes related to GoogLeNet phenotypes were identified, and the RadDeepGene score represented a high risk of LNM (odd ratio = 164.00, P < 0.001).

CONCLUSIONS

DLRNs combining radiomics and deep learning features of DCE-MRI images improved the preoperative prediction of LNM in breast cancer, and the potential biological characteristics of DLRN were identified through genomics.

Machine learning and optical coherence tomography-derived radiomics analysis to predict persistent diabetic macular edema in patients undergoing anti-VEGF intravitreal therapy

BACKGROUND

Diabetic macular edema (DME) is a leading cause of vision loss in patients with diabetes. This study aimed to develop and evaluate an OCT-omics prediction model for assessing anti-vascular endothelial growth factor (VEGF) treatment response in patients with DME.

METHODS

A retrospective analysis of 113 eyes from 82 patients with DME was conducted. Comprehensive feature engineering was applied to clinical and optical coherence tomography (OCT) data. Logistic regression, support vector machine (SVM), and backpropagation neural network (BPNN) classifiers were trained using a training set of 79 eyes, and evaluated on a test set of 34 eyes. Clinical implications of the OCT-omics prediction model were assessed by decision curve analysis. Performance metrics (sensitivity, specificity, F1 score, and AUC) were calculated.

RESULTS

The logistic, SVM, and BPNN classifiers demonstrated robust discriminative abilities in both the training and test sets. In the training set, the logistic classifier achieved a sensitivity of 0.904, specificity of 0.741, F1 score of 0.887, and AUC of 0.910. The SVM classifier showed a sensitivity of 0.923, specificity of 0.667, F1 score of 0.881, and AUC of 0.897. The BPNN classifier exhibited a sensitivity of 0.962, specificity of 0.926, F1 score of 0.962, and AUC of 0.982. Similar discriminative capabilities were maintained in the test set. The OCT-omics scores were significantly higher in the non-persistent DME group than in the persistent DME group (p < 0.001). OCT-omics scores were also positively correlated with the rate of decline in central subfield thickness after treatment (Pearson's R = 0.44, p < 0.001).

CONCLUSION

The developed OCT-omics model accurately assesses anti-VEGF treatment response in DME patients. The model's robust performance and clinical implications highlight its utility as a non-invasive tool for personalized treatment prediction and retinal pathology assessment.

The effect Of vascular related CeRNA genes and corresponding imaging biomarkers on survival in lower grade glioma

BACKGROUND & AIMS

To investigate the differential expression of vascular related ceRNA regulatory genes in LGG with different mutations of IDH1 and MGMT, and to verify imaging gene markers that can be closely associated with vascular related ceRNA regulatory genes.

METHOD

Five hundred fifteen patients with LGG were collected from TCGA database. CeRNA network analysis, GO analysis and Cox risk regression were used to find vascular ceRNA regulatory genes and their genetic markers related to survival. The preoperative MRI image data and postoperative tumor tissues of 14 patients with WHO grade III glioma were collected for full transcriptome analysis. The correlation between image characteristics of LGG and survival related vascular ceRNA regulatory genes was compared using nonparametric U test and Pearson correlation coefficient analysis.

RESULTS

Vascular related genes ranked first in the functional enrichment analysis of differentially expressed genes in LGG. EPHA2, ETS1, YAP1 and MEIS1 could significantly affect the survival of patients in each group of LGG. The volume of enhanced region was negatively correlated with IDH1 (r = -0.622, P = 0.009) mutation and TMEM100 (r = -0.535, P = 0.024), and positively correlated with MEIS1 (r = 0.551, P = 0.021), rCBFmax value was negatively correlated with TMEM100 (r = -0.492, P = 0.037).

CONCLUSIONS

Under different IDH1 mutations, lncRNA-dominated vascular-related ceRNA regulatory genes were the first differentially expressed subset of each group, and could be used as an effective risk factor affecting the survival of LGG. The image characteristics of LGG was an ideal image gene marker. It was a reliable imaging biological marker which can truly reflect the pathophysiological characteristics of glioma.

Radiomic profiling for insular diffuse glioma stratification with distinct biologic pathway activities

Current literature emphasizes surgical complexities and customized resection for managing insular gliomas; however, radiogenomic investigations into prognostic radiomic traits remain limited. We aimed to develop and validate a radiomic model using multiparametric magnetic resonance imaging (MRI) for prognostic prediction and to reveal the underlying biological mechanisms. Radiomic features from preoperative MRI were utilized to develop and validate a radiomic risk signature (RRS) for insular gliomas, validated through paired MRI and RNA-seq data (N = 39), to identify core pathways underlying the RRS and individual prognostic radiomic features. An 18-feature-based RRS was established for overall survival (OS) prediction. Gene set enrichment analysis (GSEA) and weighted gene coexpression network analysis (WGCNA) were used to identify intersectional pathways. In total, 364 patients with insular gliomas (training set, N = 295; validation set, N = 69) were enrolled. RRS was significantly associated with insular glioma OS (log-rank p = 0.00058; HR = 3.595, 95% CI:1.636-7.898) in the validation set. The radiomic-pathological-clinical model (R-P-CM) displayed enhanced reliability and accuracy in prognostic prediction. The radiogenomic analysis revealed 322 intersectional pathways through GSEA and WGCNA fusion; 13 prognostic radiomic features were significantly correlated with these intersectional pathways. The RRS demonstrated independent predictive value for insular glioma prognosis compared with established clinical and pathological profiles. The biological basis for prognostic radiomic indicators includes immune, proliferative, migratory, metabolic, and cellular biological function-related pathways.

Artificial intelligence-based MRI radiomics and radiogenomics in glioma

The specific genetic subtypes that gliomas exhibit result in variable clinical courses and the need to involve multidisciplinary teams of neurologists, epileptologists, neurooncologists and neurosurgeons. Currently, the diagnosis of gliomas pivots mainly around the preliminary radiological findings and the subsequent definitive surgical diagnosis (via surgical sampling). Radiomics and radiogenomics present a potential to precisely diagnose and predict survival and treatment responses, via morphological, textural, and functional features derived from MRI data, as well as genomic data. In spite of their advantages, it is still lacking standardized processes of feature extraction and analysis methodology among different research groups, which have made external validations infeasible. Radiomics and radiogenomics can be used to better understand the genomic basis of gliomas, such as tumor spatial heterogeneity, treatment response, molecular classifications and tumor microenvironment immune infiltration. These novel techniques have also been used to predict histological features, grade or even overall survival in gliomas. In this review, workflows of radiomics and radiogenomics are elucidated, with recent research on machine learning or artificial intelligence in glioma.

Multiparametric MRI-based radiomics nomogram for predicting malignant transformation of sinonasal inverted papilloma

AIM

To investigate the feasibility of a radiomics nomogram model for predicting malignant transformation in sinonasal inverted papilloma (IP) based on radiomic signature and clinical risk factors.

MATERIALS AND METHODS

This single institutional retrospective review included a total of 143 patients with IP and 75 patients with IP with malignant transformation to squamous cell carcinoma (IP-SCC). All patients underwent surgical pathology and had preoperative magnetic resonance imaging (MRI) and computed tomography (CT) sinus studies between June 2014 and February 2022. Radiomics features were extracted from contrast-enhanced T1-weighted images (CE-T1WI), T2-weighted images (T2WI), and apparent diffusion coefficient (ADC) maps. The least absolute shrinkage and selection operator (LASSO) were performed to select the features extracted from the sequences mentioned above. Independent clinical risk factors were identified by multivariate logistic regression analysis. Radiomics nomogram was constructed by incorporating independent clinical risk factors and radiomics signature. Based on discrimination and calibration, the diagnostic performance of the nomogram was evaluated.

RESULTS

Twelve radiomics features were selected to develop the radiomics model with an area under the curve (AUC) of 0.987 and 0.989, respectively. Epistaxis (p=0.011), T2 equal signal (p=0.003), extranasal invasion (p<0.001), and loss of convoluted cerebriform pattern (p=0.002) were identified as independent clinical predictors. The radiomics nomogram model showed excellent calibration and discrimination (AUC: 0.993, 95% confidence interval [CI]: 0.985-1.00 and 0.990, 95% CI: 0.974-1.00) in the training and validation sets, respectively.

CONCLUSION

The nomogram that the combined radiomics signature and clinical risk factors showed a satisfactory ability to predict IP-SCC.

A multi-cohort study of the hippocampal radiomics model and its associated biological changes in Alzheimer's Disease

There have been no previous reports of hippocampal radiomics features associated with biological functions in Alzheimer's Disease (AD). This study aims to develop and validate a hippocampal radiomics model from structural magnetic resonance imaging (MRI) data for identifying patients with AD, and to explore the mechanism underlying the developed radiomics model using peripheral blood gene expression. In this retrospective multi-study, a radiomics model was developed based on the radiomics discovery group (n = 420) and validated in other cohorts. The biological functions underlying the model were identified in the radiogenomic analysis group using paired MRI and peripheral blood transcriptome analyses (n = 266). Mediation analysis and external validation were applied to further validate the key module and hub genes. A 12 radiomics features-based prediction model was constructed and this model showed highly robust predictive power for identifying AD patients in the validation and other three cohorts. Using radiogenomics mapping, myeloid leukocyte and neutrophil activation were enriched, and six hub genes were identified from the key module, which showed the highest correlation with the radiomics model. The correlation between hub genes and cognitive ability was confirmed using the external validation set of the AddneuroMed dataset. Mediation analysis revealed that the hippocampal radiomics model mediated the association between blood gene expression and cognitive ability. The hippocampal radiomics model can accurately identify patients with AD, while the predictive radiomics model may be driven by neutrophil-related biological pathways.

Multiparametric Radiogenomic Model to Predict Survival in Patients with Glioblastoma

BACKGROUND

Clinical, histopathological, and imaging variables have been associated with prognosis in patients with glioblastoma (GBM). We aimed to develop a multiparametric radiogenomic model incorporating MRI texture features, demographic data, and histopathological tumor biomarkers to predict prognosis in patients with GBM.

METHODS

In this retrospective study, patients were included if they had confirmed diagnosis of GBM with histopathological biomarkers and pre-operative MRI. Tumor segmentation was performed, and texture features were extracted to develop a predictive radiomic model of survival (<18 months vs. ≥18 months) using multivariate analysis and Least Absolute Shrinkage and Selection Operator (LASSO) regularization to reduce the risk of overfitting. This radiomic model in combination with clinical and histopathological data was inserted into a backward stepwise logistic regression model to assess survival. The diagnostic performance of this model was reported for the training and external validation sets.

RESULTS

A total of 116 patients were included for model development and 40 patients for external testing validation. The diagnostic performance (AUC/sensitivity/specificity) of the radiomic model generated from seven texture features in determination of ≥18 months survival was 0.71/69.0/70.3. Three variables remained as independent predictors of survival, including radiomics (p = 0.004), age (p = 0.039), and MGMT status (p = 0.025). This model yielded diagnostic performance (AUC/sensitivity/specificity) of 0.77/81.0/66.0 (training) and 0.89/100/78.6 (testing) in determination of survival ≥ 18 months.

CONCLUSIONS

Results show that our radiogenomic model generated from radiomic features at baseline MRI, age, and MGMT status can predict survival ≥ 18 months in patients with GBM.

Immune-related lncRNAs signature and radiomics signature predict the prognosis and immune microenvironment of glioblastoma multiforme

BACKGROUND

Glioblastoma multiforme (GBM) is the most common primary malignant brain tumor in adults. This study aimed to construct immune-related long non-coding RNAs (lncRNAs) signature and radiomics signature to probe the prognosis and immune infiltration of GBM patients.

METHODS

We downloaded GBM RNA-seq data and clinical information from The Cancer Genome Atlas (TCGA) project database, and MRI data were obtained from The Cancer Imaging Archive (TCIA). Then, we conducted a cox regression analysis to establish the immune-related lncRNAs signature and radiomics signature. Afterward, we employed a gene set enrichment analysis (GSEA) to explore the biological processes and pathways. Besides, we used CIBERSORT to estimate the abundance of tumor-infiltrating immune cells (TIICs). Furthermore, we investigated the relationship between the immune-related lncRNAs signature, radiomics signature and immune checkpoint genes. Finally, we constructed a multifactors prognostic model and compared it with the clinical prognostic model.

RESULTS

We identified four immune-related lncRNAs and two radiomics features, which show the ability to stratify patients into high-risk and low-risk groups with significantly different survival rates. The risk score curves and Kaplan-Meier curves confirmed that the immune-related lncRNAs signature and radiomics signature were a novel independent prognostic factor in GBM patients. The GSEA suggested that the immune-related lncRNAs signature were involved in L1 cell adhesion molecular (L1CAM) interactions and the radiomics signature were involved signaling by Robo receptors. Besides, the two signatures was associated with the infiltration of immune cells. Furthermore, they were linked with the expression of critical immune genes and could predict immunotherapy's clinical response. Finally, the area under the curve (AUC) (0.890,0.887) and C-index (0.737,0.817) of the multifactors prognostic model were greater than those of the clinical prognostic model in both the training and validation sets, indicated significantly improved discrimination.

CONCLUSIONS

We identified the immune-related lncRNAs signature and tradiomics signature that can predict the outcomes, immune cell infiltration, and immunotherapy response in patients with GBM.

Predicting very early recurrence in intrahepatic cholangiocarcinoma after curative hepatectomy using machine learning radiomics based on CECT: A multi-institutional study

BACKGROUND

Even after curative resection, the prognosis for patients with intrahepatic cholangiocarcinoma (iCCA) remains disappointing due to the extremely high incidence of postoperative recurrence.

METHODS

A total of 280 iCCA patients following curative hepatectomy from three independent institutions were recruited to establish the retrospective multicenter cohort study. The very early recurrence (VER) of iCCA was defined as the appearance of recurrence within 6 months. The 3D tumor region of interest (ROI) derived from contrast-enhanced CT (CECT) was used for radiomics analysis. The independent clinical predictors for VER were histological stage, AJCC stage, and CA199 levels. We implemented K-means clustering algorithm to investigate novel radiomics-based subtypes of iCCA. Six types of machine learning (ML) algorithms were performed for VER prediction, including logistic, random forest (RF), neural network, bayes, support vector machine (SVM), and eXtreme Gradient Boosting (XGBoost). Additionally, six clinical ML (CML) models and six radiomics-clinical ML (RCML) models were developed to predict VER. Predictive performance was internally validated by 10-fold cross-validation in the training cohort, and further evaluated in the external validation cohort.

RESULTS

Approximately 30 % of patients with iCCA experienced VER with extremely discouraging outcome (Hazard ratio (HR) = 5.77, 95 % Confidence Interval (CI) = 3.73-8.93, P < 0.001). Two distinct iCCA subtypes based on radiomics features were identified, and subtype 2 harbored a higher proportion of VER (47.62 % Vs 25.53 %) and significant shorter survival time than subtype 1. The average AUC values of the CML and RCML models were 0.744 ± 0.018, and 0.900 ± 0.014 in the training cohort, and 0.769 ± 0.065 and 0.929 ± 0.027 in the external validation cohort, respectively.

CONCLUSION

Two radiomics-based iCCA subtypes were identified, and six RCML models were developed to predict VER of iCCA, which can be used as valid tools to guide individualized management in clinical practice.

Imaging-proteomic analysis for prediction of neoadjuvant chemotherapy responses in patients with breast cancer

BACKGROUND

Optimizing patient selection for neoadjuvant chemotherapy in patients with breast cancer remains an unmet clinical need. Quantitative features from medical imaging were reported to be predictive of treatment responses. However, the biologic meaning of these latent features is poorly understood, preventing the clinical use of such noninvasive imaging markers. The study aimed to develop a deep learning signature (DLS) from pretreatment magnetic resonance imaging (MRI) for predicting responses to neoadjuvant chemotherapy in patients with breast cancer and to further investigate the biologic meaning of the DLS by identifying its underlying pathways using paired MRI and proteomic sequencing data.

METHODS

MRI-based DLS was constructed (radiogenomic training dataset, n = 105) and validated (radiogenomic validation dataset, n = 26) for the prediction of pathologic complete response (pCR) to neoadjuvant chemotherapy. Proteomic sequencing revealed biological functions facilitating pCR (n = 139). Their associations with DLS were uncovered by radiogenomic analysis.

RESULTS

The DLS achieved a prediction accuracy of 0.923 with an AUC of 0.958, higher than the performance of the model trained by transfer learning. Cellular membrane formation, endocytosis, insulin-like growth factor binding, protein localization to membranes, and cytoskeleton-dependent trafficking were differentially regulated in patients showing pCR. Oncogenic signaling pathways, features correlated with human phenotypes, and features correlated with general biological processes were significantly correlated with DLS in both training and validation dataset (p.adj < 0.05).

CONCLUSIONS

Our study offers a biologically interpretable DLS for the prediction of pCR to neoadjuvant chemotherapy in patients with breast cancer, which may guide personalized medication.

Biological underpinnings of radiomic magnetic resonance imaging phenotypes for risk stratification in IDH wild-type glioblastoma

BACKGROUND

To develop and validate a conventional MRI-based radiomic model for predicting prognosis in patients with IDH wild-type glioblastoma (GBM) and reveal the biological underpinning of the radiomic phenotypes.

METHODS

A total of 801 adult patients (training set, N = 471; internal validation set, N = 239; external validation set, N = 91) diagnosed with IDH wild-type GBM were included. A 20-feature radiomic risk score (Radscore) was built for overall survival (OS) prediction by univariate prognostic analysis and least absolute shrinkage and selection operator (LASSO) Cox regression in the training set. GSEA and WGCNA were applied to identify the intersectional pathways underlying the prognostic radiomic features in a radiogenomic analysis set with paired MRI and RNA-seq data (N = 132). The biological meaning of the conventional MRI sequences was revealed using a Mantel test.

RESULTS

Radscore was demonstrated to be an independent prognostic factor (P < 0.001). Incorporating the Radscore into a clinical model resulted in a radiomic-clinical nomogram predicting survival better than either the Radscore model or the clinical model alone, with better calibration and classification accuracy (a total net reclassification improvement of 0.403, P < 0.001). Three pathway categories (proliferation, DNA damage response, and immune response) were significantly correlated with the prognostic radiomic phenotypes.

CONCLUSION

Our findings indicated that the prognostic radiomic phenotypes derived from conventional MRI are driven by distinct pathways involved in proliferation, DNA damage response, and immunity of IDH wild-type GBM.

Diffusion tensor imaging-based machine learning for IDH wild-type glioblastoma stratification to reveal the biological underpinning of radiomic features

INTRODUCTION

This study addresses the lack of systematic investigation into the prognostic value of hand-crafted radiomic features derived from diffusion tensor imaging (DTI) in isocitrate dehydrogenase (IDH) wild-type glioblastoma (GBM), as well as the limited understanding of the biological interpretation of individual DTI radiomic features and metrics.

AIMS

To develop and validate a DTI-based radiomic model for predicting prognosis in patients with IDH wild-type GBM and reveal the biological underpinning of individual DTI radiomic features and metrics.

RESULTS

The DTI-based radiomic signature was an independent prognostic factor (p < 0.001). Incorporating the radiomic signature into a clinical model resulted in a radiomic-clinical nomogram that predicted survival better than either the radiomic model or clinical model alone, with a better calibration and classification accuracy. Four categories of pathways (synapse, proliferation, DNA damage response, and complex cellular functions) were significantly correlated with the DTI-based radiomic features and DTI metrics.

CONCLUSION

The prognostic radiomic features derived from DTI are driven by distinct pathways involved in synapse, proliferation, DNA damage response, and complex cellular functions of GBM.

A radio-pathologic integrated model for prediction of lymph node metastasis stage in patients with gastric cancer

BACKGROUND

Accurate prediction of lymph node metastasis stage (LNMs) facilitates precision therapy for gastric cancer. We aimed to develop and validate a deep learning-based radio-pathologic model to predict the LNM stage in patients with gastric cancer by integrating CT images and histopathological whole-slide images (WSIs).

METHODS

A total of 252 patients were enrolled and randomly divided into a training set (n = 202) and a testing set (n = 50). Both pretreatment contrast-enhanced abdominal CT and WSI of biopsy specimens were collected for each patient. The deep radiologic and pathologic features were extracted from CT and WSI using ResNet-50 and Vision Transformer (ViT) network, respectively. By fusing both radiologic and pathologic features, a radio-pathologic integrated model was constructed to predict the five LNM stages. For comparison, four single-modality models using CT images or WSIs were also constructed, respectively. All models were trained on the training set and validated on the testing set.

RESULTS

The radio-pathologic integrated mode achieved an overall accuracy of 84.0% and a kappa coefficient of 0.795 on the testing set. The areas under the curves (AUCs) of the integrated model in predicting the five LNM stages were 0.978 (95% Confidence Interval (CI 0.917-1.000), 0.946 (95% CI 0.867-1.000), 0.890 (95% CI 0.718-1.000), 0.971 (95% CI 0.920-1.000), and 0.982 (95% CI 0.911-1.000), respectively. Moreover, the integrated model achieved an AUC of 0.978 (95% CI 0.912-1.000) in predicting the binary status of nodal metastasis.

CONCLUSION

Our study suggests that radio-pathologic integrated model that combined both macroscale radiologic image and microscale pathologic image can better predict lymph node metastasis stage in patients with gastric cancer.