Novel Radiomic Features Based on Joint Intensity Matrices for Predicting Glioblastoma Patient Survival Time

Radiomics and visual analysis for predicting success of transplantation of heterotopic glioblastoma in mice with MRI

BACKGROUND

Quantifying tumor growth and treatment response noninvasively poses a challenge to all experimental tumor models. The aim of our study was, to assess the value of quantitative and visual examination and radiomic feature analysis of high-resolution MR images of heterotopic glioblastoma xenografts in mice to determine tumor cell proliferation (TCP).

METHODS

Human glioblastoma cells were injected subcutaneously into both flanks of immunodeficient mice and followed up on a 3 T MR scanner. Volumes and signal intensities were calculated. Visual assessment of the internal tumor structure was based on a scoring system. Radiomic feature analysis was performed using MaZda software. The results were correlated with histopathology and immunochemistry.

RESULTS

21 tumors in 14 animals were analyzed. The volumes of xenografts with high TCP (H-TCP) increased, whereas those with low TCP (L-TCP) or no TCP (N-TCP) continued to decrease over time (p < 0.05). A low intensity rim (rim sign) on unenhanced T1-weighted images provided the highest diagnostic accuracy at visual analysis for assessing H-TCP (p < 0.05). Applying radiomic feature analysis, wavelet transform parameters were best for distinguishing between H-TCP and L-TCP / N-TCP (p < 0.05).

CONCLUSION

Visual and radiomic feature analysis of the internal structure of heterotopically implanted glioblastomas provide reproducible and quantifiable results to predict the success of transplantation.

Survival Outcome Prediction in Glioblastoma: Insights from MRI Radiomics

Background: Extracting multiregional radiomic features from multiparametric MRI for predicting pretreatment survival in isocitrate dehydrogenase (IDH) wild-type glioblastoma (GBM) patients is a promising approach. Methods: MRI data from 49 IDH wild-type glioblastoma patients pre-treatment were utilized. Diffusion and perfusion maps were generated, and tumor subregions segmented. Radiomic features were extracted for each tissue type and map. Feature selection on 1862 radiomic features identified 25 significant features. The Cox proportional-hazards model with LASSO regularization was used to perform survival analysis. Internal and external validation used a 38-patient training cohort and an 11-patient validation cohort. Statistical significance was set at p < 0.05. Results: Age and six radiomic features (shape and first and second order) from T1W, diffusion, and perfusion maps contributed to the final model. Findings suggest that a small necrotic subregion, inhomogeneous vascularization in the solid non-enhancing subregion, and edema-related tissue damage in the enhancing and edema subregions are linked to poor survival. The model's C-Index was 0.66 (95% C.I. 0.54-0.80). External validation demonstrated good accuracy (AUC > 0.65) at all time points. Conclusions: Radiomics analysis, utilizing segmented perfusion and diffusion maps, provide predictive indicators of survival in IDH wild-type glioblastoma patients, revealing associations with microstructural and vascular heterogeneity in the tumor.

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.

Imaging phenotypes predict overall survival in glioma more accurate than basic demographic and cell mutation profiles

BACKGROUND

Magnetic resonance imaging (MRI), digital pathology imaging (PATH), demographics, and IDH mutation status predict overall survival (OS) in glioma. Identifying and characterizing predictive features in the different modalities may improve OS prediction accuracy.

PURPOSE

To evaluate the OS prediction accuracy of combinations of prognostic markers in glioma patients.

MATERIALS AND METHODS

Multi-contrast MRI, comprising T1-weighted, T1-weighted post-contrast, T2-weighted, T2 fluid-attenuated-inversion-recovery, and pathology images from glioma patients (n = 160) were retrospectively collected (1983-2008) from TCGA alongside age and sex. Phenotypic profiling of tumors was performed by quantifying the radiographic and histopathologic descriptors extracted from the delineated region-of-interest in MRI and PATH images. A Cox proportional hazard model was trained with the MRI and PATH features, IDH mutation status, and basic demographic variables (age and sex) to predict OS. The performance was evaluated in a split-train-test configuration using the concordance-index, computed between the predicted risk score and observed OS.

RESULTS

The average age of patients was 51.2years (women: n = 77, age-range=18-84years; men: n = 83, age-range=21-80years). The median OS of the participants was 494.5 (range,3-4752), 481 (range,7-4752), and 524.5 days (range,3-2869), respectively, in complete dataset, training, and test datasets. The addition of MRI or PATH features improved prediction of OS when compared to models based on age, sex, and mutation status alone or their combination (p < 0.001). The full multi-omics model integrated MRI, PATH, clinical, and genetic profiles and predicted the OS best (c-index= 0.87).

CONCLUSION

The combination of imaging, genetic, and clinical profiles leads to a more accurate prognosis than the clinical and/or mutation status.

Time-to-event overall survival prediction in glioblastoma multiforme patients using magnetic resonance imaging radiomics

PURPOSE

Glioblastoma Multiforme (GBM) represents the predominant aggressive primary tumor of the brain with short overall survival (OS) time. We aim to assess the potential of radiomic features in predicting the time-to-event OS of patients with GBM using machine learning (ML) algorithms.

MATERIALS AND METHODS

One hundred nineteen patients with GBM, who had T1-weighted contrast-enhanced and T2-FLAIR MRI sequences, along with clinical data and survival time, were enrolled. Image preprocessing methods included 64 bin discretization, Laplacian of Gaussian (LOG) filters with three Sigma values and eight variations of Wavelet Transform. Images were then segmented, followed by the extraction of 1212 radiomic features. Seven feature selection (FS) methods and six time-to-event ML algorithms were utilized. The combination of preprocessing, FS, and ML algorithms (12 × 7 × 6 = 504 models) was evaluated by multivariate analysis.

RESULTS

Our multivariate analysis showed that the best prognostic FS/ML combinations are the Mutual Information (MI)/Cox Boost, MI/Generalized Linear Model Boosting (GLMB) and MI/Generalized Linear Model Network (GLMN), all of which were done via the LOG (Sigma = 1 mm) preprocessing method (C-index = 0.77). The LOG filter with Sigma = 1 mm preprocessing method, MI, GLMB and GLMN achieved significantly higher C-indices than other preprocessing, FS, and ML methods (all p values < 0.05, mean C-indices of 0.65, 0.70, and 0.64, respectively).

CONCLUSION

ML algorithms are capable of predicting the time-to-event OS of patients using MRI-based radiomic and clinical features. MRI-based radiomics analysis in combination with clinical variables might appear promising in assisting clinicians in the survival prediction of patients with GBM. Further research is needed to establish the applicability of radiomics in the management of GBM in the clinic.

An interpretable feature-learned model for overall survival classification of High-Grade Gliomas

PURPOSE

An accurate and well-defined survival prediction of High Grade Gliomas (HGGs) is indispensable because of its high incidence and aggressiveness. Therefore, this paper presents a unified framework for fully automatic overall survival classification and its interpretation.

METHODS AND MATERIALS

Initially, a glioma detection model is utilized to detect the tumorous images. A pre-processing module is designed for extracting 2D slices and creating a survival data array for the classification network. Then, the classification pipeline is integrated with two separate pathways: a modality-specific and a modality-concatenated pathway. The modality-specific pathway runs three separate CNNs for extracting rich predictive features from three sub-regions of HGGs (peritumoral edema, enhancing tumor and necrosis) by using three neuro-imaging modalities. In these pathways, the image vectors of the different modalities are also concatenated to the final fusion layer to overcome the loss of lower-level tumor features. Furthermore, to exploit the intra-modality correlations, a modality-concatenated pathway is also added to the classification pipeline. The experiments are conducted on BraTS 2018 and BraTS 2019 benchmarks, demonstrating that the proposed approach performs competitively in classifying HGG patients into three survival groups, namely, short, mid, and long survivors.

RESULTS

The proposed approach achieves an overall classification accuracy, sensitivity, and specificity of about 0.998, 0.997, and 0.999, respectively, for the BraTS 2018 dataset, and for BraTS 2019, these values correspond to 1.000, 0.999, and 0.999.

CONCLUSIONS

The results indicate that the proposed model achieves the highest values of the evaluation metrics for the overall survival classification of HGG.

Prognostic and predictive impact of abnormal signal volume evolution early after chemoradiotherapy in glioblastoma

INTRODUCTION

This study was designed to explore the feasibility of semiautomatic measurement of abnormal signal volume (ASV) in glioblastoma (GBM) patients, and the predictive value of ASV evolution for the survival prognosis after chemoradiotherapy (CRT).

METHODS

This retrospective trial included 110 consecutive patients with GBM. MRI metrics, including the orthogonal diameter (OD) of the abnormal signal lesions, the pre-radiation enhancement volume (PRRCE), the volume change rate of enhancement (rCE), and fluid attenuated inversion recovery (rFLAIR) before and after CRT were analyzed. Semi-automatic measurements of ASV were done through the Slicer software.

RESULTS

In logistic regression analysis, age (HR = 2.185, p = 0.012), PRRCE (HR = 0.373, p < 0.001), post CE volume (HR = 4.261, p = 0.001), rCE_1m (HR = 0.519, p = 0.046) were the significant independent predictors of short overall survival (OS) (< 15.43 months). The areas under the receiver operating characteristic curve (AUCs) for predicting short OS with rFLAIR_3m and rCE_1m were 0.646 and 0.771, respectively. The AUCs of Model 1 (clinical), Model 2 (clinical + conventional MRI), Model 3 (volume parameters), Model 4 (volume parameters + conventional MRI), and Model 5 (clinical + conventional MRI + volume parameters) for predicting short OS were 0.690, 0.723, 0.877, 0.879, 0.898, respectively.

CONCLUSION

Semi-automatic measurement of ASV in GBM patients is feasible. The early evolution of ASV after CRT was beneficial in improving the survival evaluation after CRT. The efficacy of rCE_1m was better than that of rFLAIR_3m in this evaluation.

MRI texture-based machine learning models for the evaluation of renal function on different segmentations: a proof-of-concept study

BACKGROUND

To develop and validate an MRI texture-based machine learning model for the noninvasive assessment of renal function.

METHODS

A retrospective study of 174 diabetic patients (training cohort, n = 123; validation cohort, n = 51) who underwent renal MRI scans was included. They were assigned to normal function (n = 71), mild or moderate impairment (n = 69), and severe impairment groups (n = 34) according to renal function. Four methods of kidney segmentation on T2-weighted images (T2WI) were compared, including regions of interest covering all coronal slices (All-K), the largest coronal slices (LC-K), and subregions of the largest coronal slices (TLCO-K and PIZZA-K). The speeded-up robust features (SURF) and support vector machine (SVM) algorithms were used for texture feature extraction and model construction, respectively. Receiver operating characteristic (ROC) curve analysis was used to evaluate the diagnostic performance of models.

RESULTS

The models based on LC-K and All-K achieved the nonsignificantly highest accuracy in the classification of renal function (all p values > 0.05). The optimal model yielded high performance in classifying the normal function, mild or moderate impairment, and severe impairment, with an area under the curve of 0.938 (95% confidence interval [CI] 0.935-0.940), 0.919 (95%CI 0.916-0.922), and 0.959 (95%CI 0.956-0.962) in the training cohorts, respectively, as well as 0.802 (95%CI 0.800-0.807), 0.852 (95%CI 0.846-0.857), and 0.863 (95%CI 0.857-0.887) in the validation cohorts, respectively.

CONCLUSION

We developed and internally validated an MRI-based machine-learning model that can accurately evaluate renal function. Once externally validated, this model has the potential to facilitate the monitoring of patients with impaired renal function.

MR Intensity Normalization Methods Impact Sequence Specific Radiomics Prognostic Model Performance in Primary and Recurrent High-Grade Glioma

PURPOSE

This study investigates the impact of different intensity normalization (IN) methods on the overall survival (OS) radiomics models' performance of MR sequences in primary (pHGG) and recurrent high-grade glioma (rHGG).

METHODS

MR scans acquired before radiotherapy were retrieved from two independent cohorts (rHGG C1: 197, pHGG C2: 141) from multiple scanners (15, 14). The sequences are T1 weighted (w), contrast-enhanced T1w (T1wce), T2w, and T2w-FLAIR. Sequence-specific significant features (SF) associated with OS, extracted from the tumour volume, were derived after applying 15 different IN methods. Survival analyses were conducted using Cox proportional hazard (CPH) and Poisson regression (POI) models. A ranking score was assigned based on the 10-fold cross-validated (CV) concordance index (C-I), mean square error (MSE), and the Akaike information criterion (AICs), to evaluate the methods' performance.

RESULTS

Scatter plots of the 10-CV C-I and MSE against the AIC showed an impact on the survival predictions between the IN methods and MR sequences (C1/C2 C-I range: 0.62-0.71/0.61-0.72, MSE range: 0.20-0.42/0.13-0.22). White stripe showed stable results for T1wce (C1/C2 C-I: 0.71/0.65, MSE: 0.21/0.14). Combat (0.68/0.62, 0.22/0.15) and histogram matching (HM, 0.67/0.64, 0.22/0.15) showed consistent prediction results for T2w models. They were also the top-performing methods for T1w in C2 (Combat: 0.67, 0.13; HM: 0.67, 0.13); however, only HM achieved high predictions in C1 (0.66, 0.22). After eliminating IN impacted SF using Spearman's rank-order correlation coefficient, a mean decrease in the C-I and MSE of 0.05 and 0.03 was observed in all four sequences.

CONCLUSION

The IN method impacted the predictive power of survival models; thus, performance is sequence-dependent.

MRI-derived radiomics to guide post-operative management of glioblastoma: Implication for personalized radiation treatment volume delineation

Background

The glioblastoma's bad prognosis is primarily due to intra-tumor heterogeneity, demonstrated from several studies that collected molecular biology, cytogenetic data and more recently radiomic features for a better prognostic stratification. The GLIFA project (GLIoblastoma Feature Analysis) is a multicentric project planned to investigate the role of radiomic analysis in GB management, to verify if radiomic features in the tissue around the resection cavity may guide the radiation target volume delineation.

Materials and methods

We retrospectively analyze from three centers radiomic features extracted from 90 patients with total or near total resection, who completed the standard adjuvant treatment and for whom we had post-operative images available for features extraction. The Manual segmentation was performed on post gadolinium T1w MRI sequence by 2 radiation oncologists and reviewed by a neuroradiologist, both with at least 10 years of experience. The Regions of interest (ROI) considered for the analysis were: the surgical cavity ± post-surgical residual mass (CTV_cavity); the CTV a margin of 1.5 cm added to CTV_cavity and the volume resulting from subtracting the CTV_cavity from the CTV was defined as CTV_Ring. Radiomic analysis and modeling were conducted in RStudio. Z-score normalization was applied to each radiomic feature. A radiomic model was generated using features extracted from the Ring to perform a binary classification and predict the PFS at 6 months. A 3-fold cross-validation repeated five times was implemented for internal validation of the model.

Results

Two-hundred and seventy ROIs were contoured. The proposed radiomic model was given by the best fitting logistic regression model, and included the following 3 features: F_cm_merged.contrast, F_cm_merged.info.corr.2, F_rlm_merged.rlnu. A good agreement between model predicted probabilities and observed outcome probabilities was obtained (p-value of 0.49 by Hosmer and Lemeshow statistical test). The ROC curve of the model reported an AUC of 0.78 (95% CI: 0.68-0.88).

Conclusion

This is the first hypothesis-generating study which applies a radiomic analysis focusing on healthy tissue ring around the surgical cavity on post-operative MRI. This study provides a preliminary model for a decision support tool for a customization of the radiation target volume in GB patients in order to achieve a margin reduction strategy.

Current Evidence, Limitations and Future Challenges of Survival Prediction for Glioblastoma Based on Advanced Noninvasive Methods: A Narrative Review

Background and Objectives: Survival estimation for patients diagnosed with Glioblastoma (GBM) is an important information to consider in patient management and communication. Despite some known risk factors, survival estimation remains a major challenge. Novel non-invasive technologies such as radiomics and artificial intelligence (AI) have been implemented to increase the accuracy of these predictions. In this article, we reviewed and discussed the most significant available research on survival estimation for GBM through advanced non-invasive methods. Materials and Methods: PubMed database was queried for articles reporting on survival prognosis for GBM through advanced image and data management methods. Articles including in their title or abstract the following terms were initially screened: ((glioma) AND (survival)) AND ((artificial intelligence) OR (radiomics)). Exclusively English full-text articles, reporting on humans, published as of 1 September 2022 were considered. Articles not reporting on overall survival, evaluating the effects of new therapies or including other tumors were excluded. Research with a radiomics-based methodology were evaluated using the radiomics quality score (RQS). Results: 382 articles were identified. After applying the inclusion criteria, 46 articles remained for further analysis. These articles were thoroughly assessed, summarized and discussed. The results of the RQS revealed some of the limitations of current radiomics investigation on this field. Limitations of analyzed studies included data availability, patient selection and heterogeneity of methodologies. Future challenges on this field are increasing data availability, improving the general understanding of how AI handles data and establishing solid correlations between image features and tumor's biology. Conclusions: Radiomics and AI methods of data processing offer a new paradigm of possibilities to tackle the question of survival prognosis in GBM.

Radiomic and Volumetric Measurements as Clinical Trial Endpoints—A Comprehensive Review

Simple Summary

The extraction of quantitative data from standard-of-care imaging modalities offers opportunities to improve the relevance and salience of imaging biomarkers used in drug development. This review aims to identify the challenges and opportunities for discovering new imaging-based biomarkers based on radiomic and volumetric assessment in the single-site solid tumor sites: breast cancer, rectal cancer, lung cancer and glioblastoma. Developing approaches to harmonize three essential areas: segmentation, validation and data sharing may expedite regulatory approval and adoption of novel cancer imaging biomarkers.

Abstract

Clinical trials for oncology drug development have long relied on surrogate outcome biomarkers that assess changes in tumor burden to accelerate drug registration (i.e., Response Evaluation Criteria in Solid Tumors version 1.1 (RECIST v1.1) criteria). Drug-induced reduction in tumor size represents an imperfect surrogate marker for drug activity and yet a radiologically determined objective response rate is a widely used endpoint for Phase 2 trials. With the addition of therapies targeting complex biological systems such as immune system and DNA damage repair pathways, incorporation of integrative response and outcome biomarkers may add more predictive value. We performed a review of the relevant literature in four representative tumor types (breast cancer, rectal cancer, lung cancer and glioblastoma) to assess the preparedness of volumetric and radiomics metrics as clinical trial endpoints. We identified three key areas—segmentation, validation and data sharing strategies—where concerted efforts are required to enable progress of volumetric- and radiomics-based clinical trial endpoints for wider clinical implementation.

Establishment and validation of a radiological-radiomics model for predicting high-grade patterns of lung adenocarcinoma less than or equal to 3 cm

Objective

We aimed to develop a Radiological-Radiomics (R-R) based model for predicting the high-grade pattern (HGP) of lung adenocarcinoma and evaluate its predictive performance.

Methods

The clinical, pathological, and imaging data of 374 patients pathologically confirmed with lung adenocarcinoma (374 lesions in total) were retrospectively analyzed. The 374 lesions were assigned to HGP (n = 81) and non-high-grade pattern (n-HGP, n = 293) groups depending on the presence or absence of high-grade components in pathological findings. The least absolute shrinkage and selection operator (LASSO) method was utilized to screen features on the United Imaging artificial intelligence scientific research platform, and logistic regression models for predicting HGP were constructed, namely, Radiological model, Radiomics model, and R-R model. Also, receiver operating curve (ROC) curves were plotted on the platform, generating corresponding area under the curve (AUC), sensitivity, specificity, and accuracy. Using the platform, nomograms for R-R models were also provided, and calibration curves and decision curves were drawn to evaluate the performance and clinical utility of the model. The statistical differences in the performance of the models were compared by the DeLong test.

Results

The R-R model for HGP prediction achieved an AUC value of 0.923 (95% CI: 0.891-0.948), a sensitivity of 87.0%, a specificity of 83.4%, and an accuracy of 84.2% in the training set. In the validation set, this model exhibited an AUC value of 0.920 (95% CI: 0.887-0.945), a sensitivity of 87.5%, a specificity of 83.3%, and an accuracy of 84.2%. The DeLong test demonstrated optimal performance of the R-R model among the three models, and decision curves validated the clinical utility of the R-R model.

Conclusion

In this study, we developed a fusion model using radiomic features combined with radiological features to predict the high-grade pattern of lung adenocarcinoma, and this model shows excellent diagnostic performance. The R-R model can provide certain guidance for clinical diagnosis and surgical treatment plans, contributing to improving the prognosis of patients.

TSDLPP: A Novel Two-Stage Deep Learning Framework For Prognosis Prediction Based on Whole Slide Histopathological Images

Recently, digital pathology image-based prognosis prediction has become a hot topic in healthcare research to make early decisions on therapy and improve the treatment quality of patients. Therefore, there has been a recent surge of interest in designing deep learning method solving the problem of prognosis prediction with digital pathology images. However, whole slide histopathological images (WSIs) based prognosis prediction is still a challenge due to the large size of pathological images, the heterogeneity of tumors and the high cost of region of interests (ROIs) labeling. In this study, we design a novel two-stage deep learning framework for prognosis prediction (TSDLPP) based on WSIs. Our proposed framework consists of two-stage paradigms: 1) training tissue decomposition network (TDNet) to divide WSIs into cancerous and non-cancerous regions, 2) integrating general prognosis-related densely connected CNN (GPR-DCCNN) and morphology-specific prognosis-related densely connected CNNs (MSPR-DCCNNs) to extract different level features of pathological images. In the end, we apply TSDLPP to the prognosis prediction of breast cancer using The Cancer Genome Atlas (TCGA) datasets. Experiment results demonstrate that TSDLPP obtains superior performance of prognosis prediction compared with the existing state-of-arts methods.

Artificial Intelligence for Survival Prediction in Brain Tumors on Neuroimaging

Survival prediction of patients affected by brain tumors provides essential information to guide surgical planning, adjuvant treatment selection, and patient counseling. Current reliance on clinical factors, such as Karnofsky Performance Status Scale, and simplistic radiological characteristics are, however, inadequate for survival prediction in tumors such as glioma that demonstrate molecular and clinical heterogeneity with variable survival outcomes. Advances in the domain of artificial intelligence have afforded powerful tools to capture a large number of hidden high-dimensional imaging features that reflect abundant information about tumor structure and physiology. Here, we provide an overview of current literature that apply computational analysis tools such as radiomics and machine learning methods to the pipeline of image preprocessing, tumor segmentation, feature extraction, and construction of classifiers to establish survival prediction models based on neuroimaging. We also discuss challenges relating to the development and evaluation of such models and explore ethical issues surrounding the future use of machine learning predictions.

Robustness of radiomic features in magnetic resonance imaging for patients with glioblastoma: multi-center study

Background and purpose

Radiomics offers great potential in improving diagnosis and treatment for patients with glioblastoma multiforme. However, in order to implement radiomics in clinical routine, the features used for prognostic modelling need to be stable. This comprises significant challenge in multi-center studies. The aim of this study was to evaluate the impact of different image normalization methods on MRI features robustness in multi-center study.

Methods

Radiomics stability was checked on magnetic resonance images of eleven patients. The images were acquired in two different hospitals using contrast-enhanced T1 sequences. The images were normalized using one of five investigated approaches including grey-level discretization, histogram matching and z-score. Then, radiomic features were extracted and features stability was evaluated using intra-class correlation coefficients. In the second part of the study, improvement in the prognostic performance of features was tested on 60 patients derived from publicly available dataset.

Results

Depending on the normalization scheme, the percentage of stable features varied from 3.4% to 8%. The histogram matching based on the tumor region showed the highest amount of the stable features (113/1404); while normalization using fixed bin size resulted in 48 stable features. The histogram matching also led to better prognostic value (median c-index increase of 0.065) comparing to non-normalized images.

Conclusions

MRI normalization plays an important role in radiomics. Appropriate normalization helps to select robust features, which can be used for prognostic modelling in multicenter studies. In our study, histogram matching based on tumor region improved both stability of radiomic features and their prognostic value.

Machine Learning for Prediction of Recurrence in Parasagittal and Parafalcine Meningiomas: Combined Clinical and MRI Texture Features

A subset of parasagittal and parafalcine (PSPF) meningiomas may show early progression/recurrence (P/R) after surgery. This study applied machine learning using combined clinical and texture features to predict P/R in PSPF meningiomas. A total of 57 consecutive patients with pathologically confirmed (WHO grade I) PSPF meningiomas treated in our institution between January 2007 to January 2019 were included. All included patients had complete preoperative magnetic resonance imaging (MRI) and more than one year MRI follow-up after surgery. Preoperative contrast-enhanced T1WI, T2WI, T1WI, and T2 fluid-attenuated inversion recovery (FLAIR) were analyzed retrospectively. The most significant 12 clinical features (extracted by LightGBM) and 73 texture features (extracted by SVM) were combined in random forest to predict P/R, and personalized radiomic scores were calculated. Thirteen patients (13/57, 22.8%) had P/R after surgery. The radiomic score was a high-risk factor for P/R with hazard ratio of 15.73 (p < 0.05) in multivariate hazards analysis. In receiver operating characteristic (ROC) analysis, an AUC of 0.91 with cut-off value of 0.269 was observed in radiomic scores for predicting P/R. Subtotal resection, low apparent diffusion coefficient (ADC) values, and high radiomic scores were associated with shorter progression-free survival (p < 0.05). Among different data input, machine learning using combined clinical and texture features showed the best predictive performance, with an accuracy of 91%, precision of 85%, and AUC of 0.88. Machine learning using combined clinical and texture features may have the potential to predict recurrence in PSPF meningiomas.

Ensembles of Convolutional Neural Networks for Survival Time Estimation of High-Grade Glioma Patients from Multimodal MRI

Glioma is the most common type of primary malignant brain tumor. Accurate survival time prediction for glioma patients may positively impact treatment planning. In this paper, we develop an automatic survival time prediction tool for glioblastoma patients along with an effective solution to the limited availability of annotated medical imaging datasets. Ensembles of snapshots of three dimensional (3D) deep convolutional neural networks (CNN) are applied to Magnetic Resonance Image (MRI) data to predict survival time of high-grade glioma patients. Additionally, multi-sequence MRI images were used to enhance survival prediction performance. A novel way to leverage the potential of ensembles to overcome the limitation of labeled medical image availability is shown. This new classification method separates glioblastoma patients into long- and short-term survivors. The BraTS (Brain Tumor Image Segmentation) 2019 training dataset was used in this work. Each patient case consisted of three MRI sequences (T1CE, T2, and FLAIR). Our training set contained 163 cases while the test set included 46 cases. The best known prediction accuracy of 74% for this type of problem was achieved on the unseen test set.

Overall Survival Prognostic Modelling of Non-small Cell Lung Cancer Patients Using Positron Emission Tomography/Computed Tomography Harmonised Radiomics Features: The Quest for the Optimal Machine Learning Algorithm

AIMS

Despite the promising results achieved by radiomics prognostic models for various clinical applications, multiple challenges still need to be addressed. The two main limitations of radiomics prognostic models include information limitation owing to single imaging modalities and the selection of optimum machine learning and feature selection methods for the considered modality and clinical outcome. In this work, we applied several feature selection and machine learning methods to single-modality positron emission tomography (PET) and computed tomography (CT) and multimodality PET/CT fusion to identify the best combinations for different radiomics modalities towards overall survival prediction in non-small cell lung cancer patients.

MATERIALS AND METHODS

A PET/CT dataset from The Cancer Imaging Archive, including subjects from two independent institutions (87 and 95 patients), was used in this study. Each cohort was used once as training and once as a test, followed by averaging of the results. ComBat harmonisation was used to address the centre effect. In our proposed radiomics framework, apart from single-modality PET and CT models, multimodality radiomics models were developed using multilevel (feature and image levels) fusion. Two different methods were considered for the feature-level strategy, including concatenating PET and CT features into a single feature set and alternatively averaging them. For image-level fusion, we used three different fusion methods, namely wavelet fusion, guided filtering-based fusion and latent low-rank representation fusion. In the proposed prognostic modelling framework, combinations of four feature selection and seven machine learning methods were applied to all radiomics modalities (two single and five multimodalities), machine learning hyper-parameters were optimised and finally the models were evaluated in the test cohort with 1000 repetitions via bootstrapping. Feature selection and machine learning methods were selected as popular techniques in the literature, supported by open source software in the public domain and their ability to cope with continuous time-to-event survival data. Multifactor ANOVA was used to carry out variability analysis and the proportion of total variance explained by radiomics modality, feature selection and machine learning methods was calculated by a bias-corrected effect size estimate known as ω².

RESULTS

Optimum feature selection and machine learning methods differed owing to the applied radiomics modality. However, minimum depth (MD) as feature selection and Lasso and Elastic-Net regularized generalized linear model (glmnet) as machine learning method had the highest average results. Results from the ANOVA test indicated that the variability that each factor (radiomics modality, feature selection and machine learning methods) introduces to the performance of models is case specific, i.e. variances differ regarding different radiomics modalities and fusion strategies. Overall, the greatest proportion of variance was explained by machine learning, except for models in feature-level fusion strategy.

CONCLUSION

The identification of optimal feature selection and machine learning methods is a crucial step in developing sound and accurate radiomics risk models. Furthermore, optimum methods are case specific, differing due to the radiomics modality and fusion strategy used.

Can Autism Be Diagnosed with Artificial Intelligence? A Narrative Review

Radiomics with deep learning models have become popular in computer-aided diagnosis and have outperformed human experts on many clinical tasks. Specifically, radiomic models based on artificial intelligence (AI) are using medical data (i.e., images, molecular data, clinical variables, etc.) for predicting clinical tasks such as autism spectrum disorder (ASD). In this review, we summarized and discussed the radiomic techniques used for ASD analysis. Currently, the limited radiomic work of ASD is related to the variation of morphological features of brain thickness that is different from texture analysis. These techniques are based on imaging shape features that can be used with predictive models for predicting ASD. This review explores the progress of ASD-based radiomics with a brief description of ASD and the current non-invasive technique used to classify between ASD and healthy control (HC) subjects. With AI, new radiomic models using the deep learning techniques will be also described. To consider the texture analysis with deep CNNs, more investigations are suggested to be integrated with additional validation steps on various MRI sites.

A Radiomics Model for Predicting Early Recurrence in Grade II Gliomas Based on Preoperative Multiparametric Magnetic Resonance Imaging

Objective

This study aimed to develop a radiomics model to predict early recurrence (<1 year) in grade II glioma after the first resection.

Methods

The pathological, clinical, and magnetic resonance imaging (MRI) data of patients diagnosed with grade II glioma who underwent surgery and had a recurrence between 2017 and 2020 in our hospital were retrospectively analyzed. After a rigorous selection, 64 patients were eligible and enrolled in the study. Twenty-two cases had a pathologically confirmed recurrent glioma. The cases were randomly assigned using a ratio of 7:3 to either the training set or validation set. T1-weighted image (T1WI), T2-weighted image (T2WI), and contrast-enhanced T1-weighted image (T1CE) were acquired. The minimum-redundancy-maximum-relevancy (mRMR) method alone or in combination with univariate logistic analysis were used to identify the most optimal predictive feature from the three image sequences. Multivariate logistic regression analysis was then used to develop a predictive model using the screened features. The performance of each model in both training and validation datasets was assessed using a receiver operating characteristic (ROC) curve, calibration curve, and decision curve analysis (DCA).

Results

A total of 396 radiomics features were initially extracted from each image sequence. After running the mRMR and univariate logistic analysis, nine predictive features were identified and used to build the multiparametric radiomics model. The model had a higher AUC when compared with the univariate models in both training and validation data sets with an AUC of 0.966 (95% confidence interval: 0.949–0.99) and 0.930 (95% confidence interval: 0.905–0.973), respectively. The calibration curves indicated a good agreement between the predictable and the actual probability of developing recurrence. The DCA demonstrated that the predictive value of the model improved when combining the three MRI sequences.

Conclusion

Our multiparametric radiomics model could be used as an efficient and accurate tool for predicting the recurrence of grade II glioma.

Differentiation Between Glioblastoma Multiforme and Metastasis From the Lungs and Other Sites Using Combined Clinical/Routine MRI Radiomics

Background

Differentiation between cerebral glioblastoma multiforme (GBM) and solitary brain metastasis (MET) is important. The existing radiomic differentiation method ignores the clinical and routine magnetic resonance imaging (MRI) features.

Purpose

To differentiate between GBM and MET and between METs from the lungs (MET-lung) and other sites (MET-other) through clinical and routine MRI, and radiomics analyses.

Methods and Materials

A total of 350 patients were collected from two institutions, including 182 patients with GBM and 168 patients with MET, which were all proven by pathology. The ROI of the tumor was obtained on axial postcontrast MRI which was performed before operation. Seven radiomic feature selection methods and four classification algorithms constituted 28 classifiers in two classification strategies, with the best classifier serving as the final radiomics model. The clinical and combination models were constructed using the nomograms developed. The performance of the nomograms was evaluated in terms of calibration, discrimination, and clinical usefulness. Student’s t-test or the chi-square test was used to assess the differences in the clinical and radiological characteristics between the training and internal validation cohorts. Receiver operating characteristic curve analysis was performed to assess the performance of developed models with the area under the curve (AUC).

Results

The classifier fisher_decision tree (fisher_DT) showed the best performance (AUC: 0.696, 95% CI:0.608-0.783) for distinguishing between GBM and MET in internal validation cohorts; the classifier reliefF_random forest (reliefF_RF) showed the best performance (AUC: 0.759, 95% CI: 0.613-0.904) for distinguishing between MET-lung and MET-other in internal validation cohorts. The combination models incorporating the radiomics signature and clinical-radiological characteristics were superior to the clinical-radiological models in the two classification strategies (AUC: 0.764 for differentiation between GBM in internal validation cohorts and MET and 0.759 or differentiation between MET-lung and MET-other in internal validation cohorts). The nomograms showed satisfactory performance and calibration and were considered clinically useful, as revealed in the decision curve analysis.

Data Conclusion

The combination of radiomic and non-radiomic features is helpful for the differentiation among GBM, MET-lung, and MET-other.

Radiomics and radiogenomics in gliomas: a contemporary update

The natural history and treatment landscape of primary brain tumours are complicated by the varied tumour behaviour of primary or secondary gliomas (high-grade transformation of low-grade lesions), as well as the dilemmas with identification of radiation necrosis, tumour progression, and pseudoprogression on MRI. Radiomics and radiogenomics promise to offer precise diagnosis, predict prognosis, and assess tumour response to modern chemotherapy/immunotherapy and radiation therapy. This is achieved by a triumvirate of morphological, textural, and functional signatures, derived from a high-throughput extraction of quantitative voxel-level MR image metrics. However, the lack of standardisation of acquisition parameters and inconsistent methodology between working groups have made validations unreliable, hence multi-centre studies involving heterogenous study populations are warranted. We elucidate novel radiomic and radiogenomic workflow concepts and state-of-the-art descriptors in sub-visual MR image processing, with relevant literature on applications of such machine learning techniques in glioma management.

Effects of interobserver and interdisciplinary segmentation variabilities on CT-based radiomics for pancreatic cancer

Radiomics is a method to mine large numbers of quantitative imaging features and develop predictive models. It has shown exciting promise for improved cancer decision support from early detection to personalized precision treatment, and therefore offers a desirable new direction for pancreatic cancer where the mortality remains high despite the current care and intense research. For radiomics, interobserver segmentation variability and its effect on radiomic feature stability is a crucial consideration. While investigations have been reported for high-contrast cancer sites such as lung cancer, no studies to date have investigated it on CT-based radiomics for pancreatic cancer. With three radiation oncology observers and three radiology observers independently contouring on the contrast CT of 21 pancreatic cancer patients, we conducted the first interobserver segmentation variability study on CT-based radiomics for pancreatic cancer. Moreover, our novel investigation assessed whether there exists an interdisciplinary difference between the two disciplines. For each patient, a consensus tumor volume was generated using the simultaneous truth and performance level expectation algorithm, using the dice similarity coefficient (DSC) to assess each observer's delineation against the consensus volume. Radiation oncology observers showed a higher average DSC of 0.81 ± 0.06 than the radiology observers at 0.69 ± 0.16 (p = 0.002). On a panel of 1277 radiomic features, the intraclass correlation coefficients (ICC) was calculated for all observers and those of each discipline. Large variations of ICCs were observed for different radiomic features, but ICCs were generally higher for the radiation oncology group than for the radiology group. Applying a threshold of ICC > 0.75 for considering a feature as stable, 448 features (35%) were found stable for the radiation oncology group and 214 features (16%) were stable from the radiology group. Among them, 205 features were found stable for both groups. Our results provide information for interobserver segmentation variability and its effect on CT-based radiomics for pancreatic cancer. An interesting interdisciplinary variability found in this study also introduces new considerations for the deployment of radiomics models.

Future artificial intelligence tools and perspectives in medicine

PURPOSE OF REVIEW

Artificial intelligence has become popular in medical applications, specifically as a clinical support tool for computer-aided diagnosis. These tools are typically employed on medical data (i.e., image, molecular data, clinical variables, etc.) and used the statistical and machine-learning methods to measure the model performance. In this review, we summarized and discussed the most recent radiomic pipeline used for clinical analysis.

RECENT FINDINGS

Currently, limited management of cancers benefits from artificial intelligence, mostly related to a computer-aided diagnosis that avoids a biopsy analysis that presents additional risks and costs. Most artificial intelligence tools are based on imaging features, known as radiomic analysis that can be refined into predictive models in noninvasively acquired imaging data. This review explores the progress of artificial intelligence-based radiomic tools for clinical applications with a brief description of necessary technical steps. Explaining new radiomic approaches based on deep-learning techniques will explain how the new radiomic models (deep radiomic analysis) can benefit from deep convolutional neural networks and be applied on limited data sets.

SUMMARY

To consider the radiomic algorithms, further investigations are recommended to involve deep learning in radiomic models with additional validation steps on various cancer types.

Artificial intelligence in tumor subregion analysis based on medical imaging: A review

Medical imaging is widely used in the diagnosis and treatment of cancer, and artificial intelligence (AI) has achieved tremendous success in medical image analysis. This paper reviews AI-based tumor subregion analysis in medical imaging. We summarize the latest AI-based methods for tumor subregion analysis and their applications. Specifically, we categorize the AI-based methods by training strategy: supervised and unsupervised. A detailed review of each category is presented, highlighting important contributions and achievements. Specific challenges and potential applications of AI in tumor subregion analysis are discussed.

Combining MRI and Histologic Imaging Features for Predicting Overall Survival in Patients with Glioma

Purpose To test the hypothesis that combined features from MR and digital histopathologic images more accurately predict overall survival (OS) in patients with glioma compared with MRI or histopathologic features alone. Materials and Methods Multiparametric MR and histopathologic images in patients with a diagnosis of glioma (high- or low-grade glioma [HGG or LGG]) were obtained from The Cancer Imaging Archive (original images acquired 1983-2008). An extensive set of engineered features such as intensity, histogram, and texture were extracted from delineated tumor regions in MR and histopathologic images. Cox proportional hazard regression and support vector machine classification (SVC) models were applied to (a) MRI features only (MRI_cox/svc), histopathologic features only (HistoPath_cox/svc), and (c) combined MRI and histopathologic features (MRI+HistoPath_cox/svc) and evaluated in a split train-test configuration. Results A total of 171 patients (mean age, 51 years ± 15; 91 men) were included with HGG (n = 75) and LGG (n = 96). Median OS was 467 days (range, 3-4752 days) for all patients, 350 days (range, 15-1561 days) for HGG, and 595 days (range, 3-4752 days) for LGG. The MRI+HistoPath_cox model demonstrated higher concordance index (C-index) compared with MRI_cox and HistoPath_cox models on all patients (C-index, 0.79 vs 0.70 [P = .02; MRI_cox] and 0.67 [P = .01; HistoPath_cox]), patients with HGG (C-index, 0.78 vs 0.68 [P = .03; MRI_cox] and 0.64 [P = .01; HistoPath_cox]), and patients with LGG (C-index, 0.88 vs 0.62 [P = .008; MRI_cox] and 0.62 [P = .006; HistoPath_cox]). In binary classification, the MRI+HistoPath_svc model (area under the receiver operating characteristic curve [AUC], 0.86 [95% CI: 0.80, 0.95]) had higher performance than the MRI_svc model (AUC, 0.68 [95% CI: 0.50, 0.81]; P = .01) and the HistoPath_svc model (AUC, 0.72 [95% CI: 0.60, 0.85]; P = .04). Conclusion The model combining features from MR and histopathologic images had higher accuracy in predicting OS compared with the models with MR or histopathologic images alone. Keywords: Survival Prediction, Gliomas, Digital Pathology Imaging, MR Imaging, Machine Learning Supplemental material is available for this article.

Radiogenomics in brain, breast, and lung cancer: opportunities and challenges

The field of radiogenomics largely focuses on developing imaging surrogates for genomic signatures and integrating imaging, genomic, and molecular data to develop combined personalized biomarkers for characterizing various diseases. Our study aims to highlight the current state-of-the-art and the role of radiogenomics in cancer research, focusing mainly on solid tumors, and is broadly divided into four sections. The first section reviews representative studies that establish the biologic basis of radiomic signatures using gene expression and molecular profiling information. The second section includes studies that aim to non-invasively predict molecular subtypes of tumors using radiomic signatures. The third section reviews studies that evaluate the potential to augment the performance of established prognostic signatures by combining complementary information encoded by radiomic and genomic signatures derived from cancer tumors. The fourth section includes studies that focus on ascertaining the biological significance of radiomic phenotypes. We conclude by discussing current challenges and opportunities in the field, such as the importance of coordination between imaging device manufacturers, regulatory organizations, health care providers, pharmaceutical companies, academic institutions, and physicians for the effective standardization of the results from radiogenomic signatures and for the potential use of these findings to improve precision care for cancer patients.

A Hybrid Feature Selection based Brain Tumor Detection and Segmentation in Multiparametric Magnetic Resonance Imaging

PURPOSE

To develop a novel method based on feature selection, combining convolutional neural network (CNN) and ensemble learning (EL), to achieve high accuracy and efficiency of glioma detection and segmentation using multiparametric MRIs.

METHODS

We proposed an evolutionary feature selection-based hybrid approach for glioma detection and segmentation on 4 MR sequences (T2-FLAIR, T1, T1Gd, and T2). First, we trained a lightweight CNN to detect glioma and mask the suspected region to process large batch of MRI images. Second, we employed a differential evolution algorithm to search a feature space, which composed of 416-dimensions radiomics features extracted from 4 sequences of MRIs and 128-dimensions high-order features extracted by the CNN, to generate an optimal feature combination for pixel classification. Finally, we trained an EL classifier using the optimal feature combination to segment whole tumor (WT) and its subregions including non-enhancing tumor (NET), peritumoral edema (ED), and enhancing tumor (ET) in the suspected region. Experiments were carried out on 300 glioma patients from the BraTS2019 dataset using 5-fold cross-validation, the model was independently validated using the rest 35 patients from the same database.

RESULTS

The approach achieved a detection accuracy of 98.8% using four MRIs. The Dice coefficients (and standard deviations) were 0.852±0.057, 0.844±0.046, and 0.799±0.053 for segmentation of WT (NET+ET+ED), tumor core (NET+ET), and ET, respectively. The sensitivities and specificities were 0.873±0.074, 0.863±0.072, and 0.852±0.082; the specificities were 0.994±0.005, 0.994±0.005, and 0.995±0.004 for the WT, tumor core and ET, respectively. The performances and calculation times were compared with the state-of-the-art approaches, our approach yielded a better overall performance with average processing time of 139.5 sec per set of four sequence MRIs.

CONCLUSIONS

We demonstrated a robust and computational cost-effective hybrid segmentation approach for glioma and its subregions on multi-sequence MR images. The proposed approach can be used for automated target delineation for glioma patients.

Glioblastoma multiforme prognosis: MRI missing modality generation, segmentation and radiogenomic survival prediction

The accurate prognosis of glioblastoma multiforme (GBM) plays an essential role in planning correlated surgeries and treatments. The conventional models of survival prediction rely on radiomic features using magnetic resonance imaging (MRI). In this paper, we propose a radiogenomic overall survival (OS) prediction approach by incorporating gene expression data with radiomic features such as shape, geometry, and clinical information. We exploit TCGA (The Cancer Genomic Atlas) dataset and synthesize the missing MRI modalities using a fully convolutional network (FCN) in a conditional generative adversarial network (cGAN). Meanwhile, the same FCN architecture enables the tumor segmentation from the available and the synthesized MRI modalities. The proposed FCN architecture comprises octave convolution (OctConv) and a novel decoder, with skip connections in spatial and channel squeeze & excitation (skip-scSE) block. The OctConv can process low and high-frequency features individually and improve model efficiency by reducing channel-wise redundancy. Skip-scSE applies spatial and channel-wise excitation to signify the essential features and reduces the sparsity in deeper layers learning parameters using skip connections. The proposed approaches are evaluated by comparative experiments with state-of-the-art models in synthesis, segmentation, and overall survival (OS) prediction. We observe that adding missing MRI modality improves the segmentation prediction, and expression levels of gene markers have a high contribution in the GBM prognosis prediction, and fused radiogenomic features boost the OS estimation.

Diagnosis and Management of Glioblastoma: A Comprehensive Perspective

Glioblastoma is the most common malignant brain tumor in adults. The current management relies on surgical resection and adjuvant radiotherapy and chemotherapy. Despite advances in our understanding of glioblastoma onset, we are still faced with an increased incidence, an altered quality of life and a poor prognosis, its relapse and a median overall survival of 15 months. For the past few years, the understanding of glioblastoma physiopathology has experienced an exponential acceleration and yielded significant insights and new treatments perspectives. In this review, through an original R-based literature analysis, we summarize the clinical presentation, current standards of care and outcomes in patients diagnosed with glioblastoma. We also present the recent advances and perspectives regarding pathophysiological bases as well as new therapeutic approaches such as cancer vaccination and personalized treatments.

Survival prediction in glioblastoma on post-contrast magnetic resonance imaging using filtration based first-order texture analysis: Comparison of multiple machine learning models

OBJECTIVE

Magnetic resonance texture analysis (MRTA) is a relatively new technique that can be a valuable addition to clinical and imaging parameters in predicting prognosis. In the present study, we investigated the efficacy of MRTA for glioblastoma survival using T1 contrast-enhanced (CE) images for texture analysis.

METHODS

We evaluated the diagnostic performance of multiple machine learning models based on first-order histogram statistical parameters derived from T1-weighted CE images in the survival stratification of glioblastoma multiforme (GBM). Retrospective evaluation of 85 patients with GBM was performed. Thirty-six first-order texture parameters at six spatial scale filters (SSF) were extracted on the T1 CE axial images for the whole tumor using commercially available research software. Several machine learning classification models (in four broad categories: linear, penalized linear, non-linear, and ensemble classifiers) were evaluated to assess the survival prediction performance using optimal features. Principal component analysis was used prior to fitting the linear classifiers in order to reduce the dimensionality of the feature inputs. Fivefold cross-validation was used to partition the data iteratively into training and testing sets. The area under the receiver operating characteristic curve (AUC) was used to assess the diagnostic performance.

RESULTS

The neural network model was the highest performing model with the highest observed AUC (0.811) and cross-validated AUC (0.71). The most important variable was the age at diagnosis, with mean and mean of positive pixels (MPP) for SSF = 0 being the second and third most important, followed by skewness for SSF = 0 and SSF = 4.

CONCLUSIONS

First-order texture features, when combined with age at presentation, show good accuracy in predicting GBM survival.

Magnetic Resonance Imaging Based Radiomic Models of Prostate Cancer: A Narrative Review

Simple Summary

The increasing interest in implementing artificial intelligence in radiomic models has occurred alongside advancement in the tools used for computer-aided diagnosis. Such tools typically apply both statistical and machine learning methodologies to assess the various modalities used in medical image analysis. Specific to prostate cancer, the radiomics pipeline has multiple facets that are amenable to improvement. This review discusses the steps of a magnetic resonance imaging based radiomics pipeline. Present successes, existing opportunities for refinement, and the most pertinent pending steps leading to clinical validation are highlighted.

Abstract

The management of prostate cancer (PCa) is dependent on biomarkers of biological aggression. This includes an invasive biopsy to facilitate a histopathological assessment of the tumor’s grade. This review explores the technical processes of applying magnetic resonance imaging based radiomic models to the evaluation of PCa. By exploring how a deep radiomics approach further optimizes the prediction of a PCa’s grade group, it will be clear how this integration of artificial intelligence mitigates existing major technological challenges faced by a traditional radiomic model: image acquisition, small data sets, image processing, labeling/segmentation, informative features, predicting molecular features and incorporating predictive models. Other potential impacts of artificial intelligence on the personalized treatment of PCa will also be discussed. The role of deep radiomics analysis-a deep texture analysis, which extracts features from convolutional neural networks layers, will be highlighted. Existing clinical work and upcoming clinical trials will be reviewed, directing investigators to pertinent future directions in the field. For future progress to result in clinical translation, the field will likely require multi-institutional collaboration in producing prospectively populated and expertly labeled imaging libraries.

Heterogeneous parameters based on 18F-FET PET imaging can non-invasively predict tumor grade and isocitrate dehydrogenase gene 1 mutation in untreated gliomas

Background

The present study aimed to explore the efficacy of easily obtained intratumoral heterogeneous parameters, other than regular semi-quantitative parameters, based on static O-(2-[18F]fluoroethyl)-l-tyrosine (¹⁸F-FET) positron emission tomography (PET) imaging in glioma grade and isocitrate dehydrogenase (IDH) gene 1 mutation prediction.

Methods

Fifty-eight adult patients with untreated glioma (grades II-IV) who underwent preoperative ¹⁸F-FET PET/computed tomography (CT) imaging were enrolled in the present study. Eight semi-automatically obtained static PET imaging parameters after lesion delineation were chosen for analysis. These were: maximal tumor-to-background ratio (TBRmax), peak tumor-to-background ratio (TBRpeak), mean tumor-to-background ratio (TBRmean), coefficient of variation (COV), heterogeneity index (HI), the standard deviation of lesion standardized uptake value (SUVsd), metabolic tumor volume (MTV), and total lesion tracer standardized uptake (TLU). Pathological and immunohistochemical results were used as a reference. The receiver-operating characteristic analysis was used to investigate the predictive efficacy of these parameters in glioma grade and IDH1 mutation status.

Results

TLU [area under the curve (AUC): 0.841, P<0.0001], TBRpeak (AUC: 0.832, P<0.0001), and HI (AUC: 0.826, P<0.0001) had the top 3 single-parameter predictive performance between grade II or III and grade IV glioma patients. Combinations of TBRmax, SUVsd, and TBRmean (AUC: 0.850, P<0.0001); HI, SUVsd, and MTV (AUC: 0.848, P<0.0001); and HI, SUVsd, and TLU (AUC: 0.848, P<0.0001) had the top 3 multiple-parameter predictive performance. SUVsd (AUC: 0.710, P=0.0028), TLU (AUC: 0.698, P=0.0074), and HI (AUC: 0.676, P=0.0159) had the top 3 single-parameter predictive performance in the IDH1 genotype. Combinations of TBRmax, SUVsd, and TBRmean (AUC: 0.821, P<0.0001); SUVsd and TBRmean (AUC: 0.804, P<0.0001); and SUVsd, HI, and TBRmean (AUC: 0.799, P<0.0001) had the top 3 multiple-parameter predictive performance.

Conclusions

These easily obtained and highly repetitive heterogeneous parameters based on static ¹⁸F-FET PET/CT imaging can non-invasively predict glioma grade and IDH1 mutation, crucial in treatment planning, and prognostic evaluation.

Radiomic analysis of magnetic resonance fingerprinting in adult brain tumors

PURPOSE

This is a radiomics study investigating the ability of texture analysis of MRF maps to improve differentiation between intra-axial adult brain tumors and to predict survival in the glioblastoma cohort.

METHODS

Magnetic resonance fingerprinting (MRF) acquisition was performed on 31 patients across 3 groups: 17 glioblastomas, 6 low-grade gliomas, and 8 metastases. Using regions of interest for the solid tumor and peritumoral white matter on T1 and T2 maps, second-order texture features were calculated from gray-level co-occurrence matrices and gray-level run length matrices. Selected features were compared across the three tumor groups using Wilcoxon rank-sum test. Receiver operating characteristic curve analysis was performed for each feature. Kaplan-Meier method was used for survival analysis with log rank tests.

RESULTS

Low-grade gliomas and glioblastomas had significantly higher run percentage, run entropy, and information measure of correlation 1 on T1 than metastases (p < 0.017). The best separation of all three tumor types was seen utilizing inverse difference normalized and homogeneity values for peritumoral white matter in both T1 and T2 maps (p < 0.017). In solid tumor T2 maps, lower values in entropy and higher values of maximum probability and high-gray run emphasis were associated with longer survival in glioblastoma patients (p < 0.05). Several texture features were associated with longer survival in glioblastoma patients on peritumoral white matter T1 maps (p < 0.05).

CONCLUSION

Texture analysis of MRF-derived maps can improve our ability to differentiate common adult brain tumors by characterizing tumor heterogeneity, and may have a role in predicting outcomes in patients with glioblastoma.

Differentiating glioblastoma multiforme from cerebral lymphoma: application of advanced texture analysis of quantitative apparent diffusion coefficients

PURPOSE

The purpose of this study was to differentiate glioblastoma multiforme from primary central nervous system lymphoma using the customised first and second-order histogram features derived from apparent diffusion coefficients.Methods and materials: A total of 82 patients (57 with glioblastoma multiforme and 25 with primary central nervous system lymphoma) were included in this study. The axial T1 post-contrast and fluid-attenuated inversion recovery magnetic resonance images were used to delineate regions of interest for the tumour and peritumoral oedema. The regions of interest were then co-registered with the apparent diffusion coefficient maps, and the first and second-order histogram features were extracted and compared between glioblastoma multiforme and primary central nervous system lymphoma groups. Receiver operating characteristic curve analysis was performed to calculate a cut-off value and its sensitivity and specificity to differentiate glioblastoma multiforme from primary central nervous system lymphoma.

RESULTS

Based on the tumour regions of interest, apparent diffusion coefficient mean, maximum, median, uniformity and entropy were higher in the glioblastoma multiforme group than the primary central nervous system lymphoma group (P ≤ 0.001). The most sensitive first and second-order histogram feature to differentiate glioblastoma multiforme from primary central nervous system lymphoma was the maximum of 2.026 or less (95% confidence interval (CI) 75.1-99.9%), and the most specific first and second-order histogram feature was smoothness of 1.28 or greater (84.0% CI 70.9-92.8%). Based on the oedema regions of interest, most of the first and second-order histogram features were higher in the glioblastoma multiforme group compared to the primary central nervous system lymphoma group (P ≤ 0.015). The most sensitive first and second-order histogram feature to differentiate glioblastoma multiforme from primary central nervous system lymphoma was the 25th percentile of 0.675 or less (100% CI 83.2-100%) and the most specific first and second-order histogram feature was the median of 1.28 or less (85.9% CI 66.3-95.8%).

CONCLUSIONS

Texture analysis using first and second-order histogram features derived from apparent diffusion coefficient maps may be helpful in differentiating glioblastoma multiforme from primary central nervous system lymphoma.

Diffusion tensor imaging radiomics in lower-grade glioma: improving subtyping of isocitrate dehydrogenase mutation status

PURPOSE

To evaluate whether diffusion tensor imaging (DTI) radiomics with machine learning improves the prediction of isocitrate dehydrogenase (IDH) mutation status of lower-grade gliomas beyond radiomic features from conventional MRI and DTI histogram parameters.

METHODS

A total of 168 patients with pathologically confirmed lower-grade gliomas were retrospectively enrolled. A total of 158 and 253 radiomic features were extracted from DTI (DTI radiomics) and conventional MRI (T1-weighted image with contrast enhancement, T2-weighted image, and FLAIR [conventional radiomics]), respectively. The random forest models for predicting IDH status were trained with variable combinations as follows: (1) DTI radiomics, (2) conventional radiomics, (3) conventional radiomics + DTI radiomics, and (4) conventional radiomics + DTI histogram. The models were validated with nested cross-validation. The predictive performances of those models were compared by using area under the curve (AUC) from receiver operating characteristic analysis, and 95% confidence interval (CI) was calculated.

RESULTS

Adding DTI radiomics to conventional radiomics significantly improved the accuracy of IDH status subtyping (AUC, 0.900 [95% CI, 0.855-0.945], p = 0.006), whereas adding DTI histogram parameters yielded nonsignificant trend toward improvement (0.869 [95% CI, 0.816-0.922], p = 0.150) compared with the model with conventional radiomics alone (0.835 [95% CI, 0.773-0.896]). The performance of the model consisting of both DTI and conventional radiomics was significantly superior than that of model consisting of both DTI histogram parameters and conventional radiomics (0.900 vs 0.869, p = 0.040).

CONCLUSION

DTI radiomics with machine learning can help improve the subtyping of IDH status beyond conventional radiomics and DTI histogram parameters in patients with lower-grade gliomas.

The Diagnostic Value of MRI-Based Texture Analysis in Discrimination of Tumors Located in Posterior Fossa: A Preliminary Study

Objectives

To investigate the diagnostic value of MRI-based texture analysis in discriminating common posterior fossa tumors, including medulloblastoma, brain metastatic tumor, and hemangioblastoma.

Methods

A total number of 185 patients were enrolled in the current study: 63 of them were diagnosed with medulloblastoma, 56 were diagnosed with brain metastatic tumor, and 66 were diagnosed with hemangioblastoma. Texture features were extracted from contrast-enhanced T1-weighted (T1C) images and fluid-attenuation inversion recovery (FLAIR) images within two matrixes. Mann–Whitney U test was conducted to identify whether texture features were significantly different among subtypes of tumors. Logistic regression analysis was performed to assess if they could be taken as independent predictors and to establish the integrated models. Receiver operating characteristic analysis was conducted to evaluate their performances in discrimination.

Results

There were texture features from both T1C images and FLAIR images found to be significantly different among the three types of tumors. The integrated model represented that the promising diagnostic performance of texture analysis depended on a series of features rather than a single feature. Moreover, the predictive model that combined texture features and clinical feature implied feasible performance in prediction with an accuracy of 0.80.

Conclusion

MRI-based texture analysis could potentially be served as a radiological method in discrimination of common tumors located in posterior fossa.

Texture Analysis of T1-Weighted Contrast-Enhanced Magnetic Resonance Imaging Potentially Predicts Outcomes of Patients with Non-Wingless-Type/Non-Sonic Hedgehog Medulloblastoma

OBJECTIVE

To investigate whether tumor texture features derived from preoperative T1-weighted magnetic resonance imaging (MRI) are associated with overall survival (OS) of patients with non-wingless-type (WNT)/non-sonic hedgehog (SHH) medulloblastoma.

METHODS

We retrospectively reviewed 38 patients with non-WNT/non-SHH (encompassing group 3 and group 4) medulloblastoma treated with surgery in our institution from 2013 to 2016. All patients were followed-up for at least 2 years or until death. Primary tumor traditional parameters were evaluated, and texture features were extracted from preoperative T1-weighted MRI, including 4 features from the histogram matrix and 6 textures from the gray-level co-occurrence matrix (GLCM). Texture features were dichotomized into 2 subgroups based on their optimal cutoff values obtained from receiver operating characteristics curve analysis. Two-year OS was compared between the dichotomized subgroups using the Kaplan-Meier analysis and log-rank test. Multivariate Cox regression analysis was performed to determine independent prognostic factors.

RESULTS

The therapy regimen was the only basic characteristic significantly related to 2-year OS (P = 0.015). Two features of the GLCM were shown to be significantly associated with 24-month OS. Multivariate Cox regression analysis revealed that GLCM homogeneity (adjusted hazard ratio, 0.145; P = 0.013) was an independent prognostic predictor for patients.

CONCLUSIONS

Texture analysis on T1-weighted contrast-enhanced MRI potentially serves as a prognostic predictor of survival for patients with non-WNT/non-SHH medulloblastoma.

A Multi-parametric MRI-Based Radiomics Signature and a Practical ML Model for Stratifying Glioblastoma Patients Based on Survival Toward Precision Oncology

Purpose: Predicting patients' survival outcomes is recognized of key importance to clinicians in oncology toward determining an ideal course of treatment and patient management. This study applies radiomics analysis on pre-operative multi-parametric MRI of patients with glioblastoma from multiple institutions to identify a signature and a practical machine learning model for stratifying patients into groups based on overall survival.

Methods: This study included 163 patients' data with glioblastoma, collected by BRATS 2018 Challenge from multiple institutions. In this proposed method, a set of 147 radiomics image features were extracted locally from three tumor sub-regions on standardized pre-operative multi-parametric MR images. LASSO regression was applied for identifying an informative subset of chosen features whereas a Cox model used to obtain the coefficients of those selected features. Then, a radiomics signature model of 9 features was constructed on the discovery set and it performance was evaluated for patients stratification into short- (<10 months), medium- (10–15 months), and long-survivors (>15 months) groups. Eight ML classification models, trained and then cross-validated, were tested to assess a range of survival prediction performance as a function of the choice of features.

Results: The proposed mpMRI radiomics signature model had a statistically significant association with survival (P < 0.001) in the training set, but was not confirmed (P = 0.110) in the validation cohort. Its performance in the validation set had a sensitivity of 0.476 (short-), 0.231 (medium-), and 0.600 (long-survivors), and specificity of 0.667 (short-), 0.732 (medium-), and 0.794 (long-survivors). Among the tested ML classifiers, the ensemble learning model's results showed superior performance in predicting the survival classes, with an overall accuracy of 57.8% and AUC of 0.81 for short-, 0.47 for medium-, and 0.72 for long-survivors using the LASSO selected features combined with clinical factors.

Conclusion: A derived GLCM feature, representing intra-tumoral inhomogeneity, was found to have a high association with survival. Clinical factors, when added to the radiomics image features, boosted the performance of the ML classification model in predicting individual glioblastoma patient's survival prognosis, which can improve prognostic quality a further step toward precision oncology.

Integration of Radiomic and Multi-omic Analyses Predicts Survival of Newly Diagnosed IDH1 Wild-Type Glioblastoma

Predictors of patient outcome derived from gene methylation, mutation, or expression are severely limited in IDH1 wild-type glioblastoma (GBM). Radiomics offers an alternative insight into tumor characteristics which can provide complementary information for predictive models. The study aimed to evaluate whether predictive models which integrate radiomic, gene, and clinical (multi-omic) features together offer an increased capacity to predict patient outcome. A dataset comprising 200 IDH1 wild-type GBM patients, derived from The Cancer Imaging Archive (TCIA) (n = 71) and the McGill University Health Centre (n = 129), was used in this study. Radiomic features (n = 45) were extracted from tumor volumes then correlated to biological variables and clinical outcomes. By performing 10-fold cross-validation (n = 200) and utilizing independent training/testing datasets (n = 100/100), an integrative model was derived from multi-omic features and evaluated for predictive strength. Integrative models using a limited panel of radiomic (sum of squares variance, large zone/low gray emphasis, autocorrelation), clinical (therapy type, age), genetic (CIC, PIK3R1, FUBP1) and protein expression (p53, vimentin) yielded a maximal AUC of 78.24% (p = 2.9 × 10⁻⁵). We posit that multi-omic models using the limited set of ‘omic’ features outlined above can improve capacity to predict the outcome for IDH1 wild-type GBM patients.

18F-FDG-PET-based radiomics features to distinguish primary central nervous system lymphoma from glioblastoma

The differential diagnosis of primary central nervous system lymphoma from glioblastoma multiforme (GBM) is essential due to the difference in treatment strategies. This study retrospectively reviewed 77 patients (24 with lymphoma and 53 with GBM) to identify the stable and distinguishable characteristics of lymphoma and GBM in ¹⁸F-fluorodeocxyglucose (FDG) positron emission tomography (PET) images using a radiomics approach. Three groups of maps, namely, a standardized uptake value (SUV) map, an SUV map calibrated with the normal contralateral cortex (ncc) activity (SUV/ncc map), and an SUV map calibrated with the normal brain mean (nbm) activity (SUV/nbm map), were generated, and a total of 107 radiomics features were extracted from each SUV map. The margins of the ROI were adjusted to assess the stability of the features, and the area under the curve (AUC) of the receiver operating characteristic curve of each feature was compared with the SUVmax to evaluate the distinguishability of the features. Nighty-five radiomics features from the SUV map were significantly different between lymphoma and GBM, 46 features were numeric stable after marginal adjustment, and 31 features displayed better performance than SUVmax. Features extracted from the SUV map demonstrated higher AUCs than features from the further calibrated maps. Tumors with solid metabolic patterns were also separately evaluated and revealed similar results. Thirteen radiomics features that were stable and distinguishable than SUVmax in every circumstance were selected to distinguish lymphoma from glioblastoma, and they suggested that lymphoma has a higher SUV in most interval segments and is more mathematically heterogeneous than GBM. This study suggested that ¹⁸F-FDG-PET-based radiomics is a reliable noninvasive method to distinguish lymphoma and GBM.

•

¹⁸F-FDG-PET is a reliable technique to differentiate primary CNS lymphoma from GBM.

•

Radiomics identify the stable and distinguishable characteristics of lymphoma and GBM.

•

¹⁸F-FDG-PET-based radiomics provide assistance to the preoperative diagnosis.

A 3D tumor spheroid model for the T98G Glioblastoma cell line phenotypic characterization

Major Glioblastoma's hallmarks include proliferation, invasion and heterogeneity. Biological 3D tumor spheroid models can serve as intermediate systems between traditional 2D cell culture and complex in vivo models. Tumor spheroids have been shown to more accurately reproduce the spatial organization and microenvironmental factors of in vivo micro-tumors, such as relevant gradients of nutrients and other molecular agents, while they maintain cell-to-cell and cell-to-matrix interactions. In vitro 3D assays are useful to monitor these properties. Here, we test the suitability of the well-known T98 G Glioblastoma cell line in such a 3D assay. The doubling time and death rate parameters of T98 G are estimated, as well as their spheroidal growth-expansion curves with and without the presence of basement membrane substrate. The T98 G invasive profile is characterized by collective morphology and proliferation-associated invasion. We show that the T98 G secondary GB cell line exhibits both invasive and proliferative capabilities in 3D and thus, can serve as control cell line for the 3D in vitro study of primary GB cell cultures.

Texture Analysis in Cerebral Gliomas: A Review of the Literature

Texture analysis is a continuously evolving, noninvasive radiomics technique to quantify macroscopic tissue heterogeneity indirectly linked to microscopic tissue heterogeneity beyond human visual perception. In recent years, systemic oncologic applications of texture analysis have been increasingly explored. Here we discuss the basic concepts and methodologies of texture analysis, along with a review of various MR imaging texture analysis applications in glioma imaging. We also discuss MR imaging texture analysis limitations and the technical challenges that impede its widespread clinical implementation. With continued advancement in computational processing, MR imaging texture analysis could potentially develop into a valuable clinical tool in routine oncologic imaging.

Radiomics in Glioblastoma: Current Status and Challenges Facing Clinical Implementation

Radiomics analysis has had remarkable progress along with advances in medical imaging, most notability in central nervous system malignancies. Radiomics refers to the extraction of a large number of quantitative features that describe the intensity, texture and geometrical characteristics attributed to the tumor radiographic data. These features have been used to build predictive models for diagnosis, prognosis, and therapeutic response. Such models are being combined with clinical, biological, genetics and proteomic features to enhance reproducibility. Broadly, the four steps necessary for radiomic analysis are: (1) image acquisition, (2) segmentation or labeling, (3) feature extraction, and (4) statistical analysis. Major methodological challenges remain prior to clinical implementation. Essential steps include: adoption of an optimized standard imaging process, establishing a common criterion for performing segmentation, fully automated extraction of radiomic features without redundancy, and robust statistical modeling validated in the prospective setting. This review walks through these steps in detail, as it pertains to high grade gliomas. The impact on precision medicine will be discussed, as well as the challenges facing clinical implementation of radiomic in the current management of glioblastoma.

Evaluation of tumor shape features for overall survival prognosis in glioblastoma multiforme patients

Glioblastoma multiforme (GBM) is a rapidly growing tumor associated with poor prognosis. This study evaluates the effectiveness of thirteen tumor shape features for overall survival (OS) prognosis in GBM patients. Shape features were extracted from the abnormality regions of the GBM tumor visible on the fluid attenuated inversion recovery (FLAIR) and T1-weighted contrast enhanced (T1CE) MR images of GBM patients. Survival analysis was performed using univariate and multivariate (with clinical features) Cox proportional hazards regression analysis. Kaplan-Meier survival curves were plotted and observed for the shape features which were found to be significant from the Cox regression analysis. Three 3D shape features: Bounding ellipsoid volume ratio (BEVR), sphericity and spherical disproportion, computed from both the abnormality regions were found to be significant for OS prognosis in GBM patients.