Quantitative mapping of individual voxels in the peritumoral region of IDH-wildtype glioblastoma to distinguish between tumor infiltration and edema

Artificial Intelligence Uncertainty Quantification in Radiotherapy Applications - A Scoping Review

Background/purpose

The use of artificial intelligence (AI) in radiotherapy (RT) is expanding rapidly. However, there exists a notable lack of clinician trust in AI models, underscoring the need for effective uncertainty quantification (UQ) methods. The purpose of this study was to scope existing literature related to UQ in RT, identify areas of improvement, and determine future directions.

Methods

We followed the PRISMA-ScR scoping review reporting guidelines. We utilized the population (human cancer patients), concept (utilization of AI UQ), context (radiotherapy applications) framework to structure our search and screening process. We conducted a systematic search spanning seven databases, supplemented by manual curation, up to January 2024. Our search yielded a total of 8980 articles for initial review. Manuscript screening and data extraction was performed in Covidence. Data extraction categories included general study characteristics, RT characteristics, AI characteristics, and UQ characteristics.

Results

We identified 56 articles published from 2015-2024. 10 domains of RT applications were represented; most studies evaluated auto-contouring (50%), followed by image-synthesis (13%), and multiple applications simultaneously (11%). 12 disease sites were represented, with head and neck cancer being the most common disease site independent of application space (32%). Imaging data was used in 91% of studies, while only 13% incorporated RT dose information. Most studies focused on failure detection as the main application of UQ (60%), with Monte Carlo dropout being the most commonly implemented UQ method (32%) followed by ensembling (16%). 55% of studies did not share code or datasets.

Conclusion

Our review revealed a lack of diversity in UQ for RT applications beyond auto-contouring. Moreover, there was a clear need to study additional UQ methods, such as conformal prediction. Our results may incentivize the development of guidelines for reporting and implementation of UQ in RT.

Evolving concepts in margin strategies and adaptive radiotherapy for glioblastoma: A new future is on the horizon

Chemoradiotherapy is the standard treatment after maximal safe resection for glioblastoma (GBM). Despite advances in molecular profiling, surgical techniques, and neuro-imaging, there have been no major breakthroughs in radiotherapy (RT) volumes in decades. Although the majority of recurrences occur within the original gross tumor volume (GTV), treatment of a clinical target volume (CTV) ranging from 1.5 to 3.0 cm beyond the GTV remains the standard of care. Over the past 15 years, the incorporation of standard and functional MRI sequences into the treatment workflow has become a routine practice with increasing adoption of MR simulators, and new integrated MR-Linac technologies allowing for daily pre-, intra- and post-treatment MR imaging. There is now unprecedented ability to understand the tumor dynamics and biology of GBM during RT, and safe CTV margin reduction is being investigated with the goal of improving the therapeutic ratio. The purpose of this review is to discuss margin strategies and the potential for adaptive RT for GBM, with a focus on the challenges and opportunities associated with both online and offline adaptive workflows. Lastly, opportunities to biologically guide adaptive RT using non-invasive imaging biomarkers and the potential to define appropriate volumes for dose modification will be discussed.

Exploring the association of glioma tumor residuals from incongruent [18F]FET PET/MR imaging with tumor proliferation using a multiparametric MRI radiomics nomogram

PURPOSE

The study aimed to using multiparametric MRI radiomics to predict glioma tumor residuals (TRFET over MR) derived from incongruent [18F]fluoroethyl-L-tyrosine ([18F]FET) PET/MR imaging.

METHODS

One hundred ten patients with gliomas who underwent [18F]FET PET/MR scanning were retrospectively analyzed. The TRFET over MR was identified by the discrepancy-PET that the extent of resection (EOR) based on MRI subtracted the biological tumor volume on PET images. The MRI parameters and radiomics features were extracted based on EOR and selected by the least absolute shrinkage and selection operator to construct radiomics score (Rad-score). The correlation network analysis of all features was analyzed by Spearman's correlation tests. The methods for evaluating the clinical usefulness consisted of the receiver operating characteristic curve, the calibration curve, and decision curve analysis.

RESULTS

The Rad-score of the patients with the TRFET over MR was significantly higher than those with the non TRFET over MR (p < 0.001). The Rad-score was significantly correlated with the discrepancy-PET (r = 0.72, p < 0.001), Ki-67 level (r = 0.76, p < 0.001), and epidermal growth factor receptor (EGFR) of gliomas (r = 0.75, p < 0.001), respectively. Moreover, there was a difference of the correlation network analysis between the TRPET over MR group and non TRFET over MR group. The nomogram combing Rad-score and clinical features had the greatest performance in predicting TRFET over MR (AUC = 0.90/0.87, training/testing). There was a significant difference in prognosis (median OS, 17 m vs. 43 m) between patients with TRFET over MR and non TRFET over MR based on nomogram prediction (p < 0.001).

CONCLUSION

The nomogram based on MRI radiomics would predict gliomas tumor residuals caused by the absence of 18F-PET PET examination and adjust EOR to improve prognosis.

Current Knowledge about the Peritumoral Microenvironment in Glioblastoma

Glioblastoma is a deadly disease, with a mean overall survival of less than 2 years from diagnosis. Recurrence after gross total surgical resection and adjuvant chemo-radiotherapy almost invariably occurs within the so-called peritumoral brain zone (PBZ). The aim of this narrative review is to summarize the most relevant findings about the biological characteristics of the PBZ currently available in the medical literature. The PBZ presents several peculiar biological characteristics. The cellular landscape of this area is different from that of healthy brain tissue and is characterized by a mixture of cell types, including tumor cells (seen in about 30% of cases), angiogenesis-related endothelial cells, reactive astrocytes, glioma-associated microglia/macrophages (GAMs) with anti-inflammatory polarization, tumor-infiltrating lymphocytes (TILs) with an "exhausted" phenotype, and glioma-associated stromal cells (GASCs). From a genomic and transcriptomic point of view, compared with the tumor core and healthy brain tissue, the PBZ presents a "half-way" pattern with upregulation of genes related to angiogenesis, the extracellular matrix, and cellular senescence and with stemness features and downregulation in tumor suppressor genes. This review illustrates that the PBZ is a transition zone with a pre-malignant microenvironment that constitutes the base for GBM progression/recurrence. Understanding of the PBZ could be relevant to developing more effective treatments to prevent GBM development and recurrence.

Multimodality MRI Radiomics Based on Machine Learning for Identifying True Tumor Recurrence and Treatment-Related Effects in Patients with Postoperative Glioma

INTRODUCTION

Conventional magnetic resonance imaging (MRI) features have difficulty distinguishing glioma true tumor recurrence (TuR) from treatment-related effects (TrE). We aimed to develop a machine-learning model based on multimodality MRI radiomics to help improve the efficiency of identifying glioma TuR.

METHODS

A total of 131 patients were enrolled and randomly divided into the training set (n = 91) and the test set (n = 40). Radiomic features were extracted from the postoperative enhancement (PoE) region and edema (ED) region from four routine MRI sequences. After analyses of Spearman's rank correlation coefficient, and least absolute shrinkage and selection operator, the key radiomic features were selected to construct support vector machine (SVM) and k-nearest neighbor (KNN) models. Decision curve analysis (DCA) and receiver operating characteristic (ROC) curves were used to analyze the performance.

RESULTS

The PoE model had a significantly higher area under curve (AUC) than the ED model (p < 0.05). Among the models constructed with a single sequence, the model using PoE regional features from CE-T1WI was superior to other models, with an AUC of 0.905 for SVM and 0.899 for KNN. In multimodality models, the PoE model outperformed the ED model with an AUC of 0.931 for SVM and 0.896 for KNN. The multimodality model, which combined routine sequences and the whole regional features, showed a slightly better performance with an AUC of 0.965 for SVM and 0.955 for KNN. Decision curve analysis showed the good clinical utility of multimodal radiomics models.

CONCLUSIONS

Multimodality radiomics can identify glioma TuR and TrE, potentially aiding clinical decision-making for individualized treatment. And edematous regions may provide useful information for recognizing recurrence.

RETROSPECTIVELY REGISTERED

2021.04.15, No:2020039.

Classification of brain lesions using a machine learning approach with cross-sectional ADC value dynamics

Diffusion-weighted imaging (DWI) and its numerical expression via apparent diffusion coefficient (ADC) values are commonly utilized in non-invasive assessment of various brain pathologies. Although numerous studies have confirmed that ADC values could be pathognomic for various ring-enhancing lesions (RELs), their true potential is yet to be exploited in full. The article was designed to introduce an image analysis method allowing REL recognition independently of either absolute ADC values or specifically defined regions of interest within the evaluated image. For this purpose, the line of interest (LOI) was marked on each ADC map to cross all of the RELs' compartments. Using a machine learning approach, we analyzed the LOI between two representatives of the RELs, namely, brain abscess and glioblastoma (GBM). The diagnostic ability of the selected parameters as predictors for the machine learning algorithms was assessed using two models, the k-NN model and the SVM model with a Gaussian kernel. With the k-NN machine learning method, 80% of the abscesses and 100% of the GBM were classified correctly at high accuracy. Similar results were obtained via the SVM method. The proposed assessment of the LOI offers a new approach for evaluating ADC maps obtained from different RELs and contributing to the standardization of the ADC map assessment.

Conventional and Advanced Magnetic Resonance Imaging Assessment of Non-Enhancing Peritumoral Area in Brain Tumor

The non-enhancing peritumoral area (NEPA) is defined as the hyperintense region in T2-weighted and fluid-attenuated inversion recovery (FLAIR) images surrounding a brain tumor. The NEPA corresponds to different pathological processes, including vasogenic edema and infiltrative edema. The analysis of the NEPA with conventional and advanced magnetic resonance imaging (MRI) was proposed in the differential diagnosis of solid brain tumors, showing higher accuracy than MRI evaluation of the enhancing part of the tumor. In particular, MRI assessment of the NEPA was demonstrated to be a promising tool for distinguishing high-grade gliomas from primary lymphoma and brain metastases. Additionally, the MRI characteristics of the NEPA were found to correlate with prognosis and treatment response. The purpose of this narrative review was to describe MRI features of the NEPA obtained with conventional and advanced MRI techniques to better understand their potential in identifying the different characteristics of high-grade gliomas, primary lymphoma and brain metastases and in predicting clinical outcome and response to surgery and chemo-irradiation. Diffusion and perfusion techniques, such as diffusion tensor imaging (DTI), diffusional kurtosis imaging (DKI), dynamic susceptibility contrast-enhanced (DSC) perfusion imaging, dynamic contrast-enhanced (DCE) perfusion imaging, arterial spin labeling (ASL), spectroscopy and amide proton transfer (APT), were the advanced MRI procedures we reviewed.

Imaging-Based Patterns of Failure following Re-Irradiation for Recurrent/Progressive High-Grade Glioma

BACKGROUND

Re-irradiation (ReRT) is an effective treatment modality in appropriately selected patients with recurrent/progressive high-grade glioma (HGG). The literature is limited regarding recurrence patterns following ReRT, which was investigated in the current study.

METHODS

Patients with available radiation (RT) contours, dosimetry, and imaging-based evidence of recurrence were included in the retrospective study. All patients were treated with fractionated focal conformal RT. Recurrence was detected on imaging with magnetic resonance imaging (MRI) and/ or amino-acid positron emission tomography (PET), which was co-registered with the RT planning dataset. Failure patterns were classified as central, marginal, and distant if >80%, 20-80%, or <20% of the recurrence volumes were within 95% isodose lines, respectively.

RESULTS

Thirty-seven patients were included in the current analysis. A total of 92% of patients had undergone surgery before ReRT, and 84% received chemotherapy. The median time to recurrence was 9 months. Central, marginal, and distant failures were seen in 27 (73%), 4 (11%), and 6 (16%) patients, respectively. None of the patient-, disease-, or treatment-related factors were significantly different across different recurrence patterns.

CONCLUSION

Failures are seen predominantly within the high-dose region following ReRT in recurrent/ progressive HGG.

Predicting Regions of Local Recurrence in Glioblastomas Using Voxel-Based Radiomic Features of Multiparametric Postoperative MRI

The globally accepted surgical strategy in glioblastomas is removing the enhancing tumor. However, the peritumoral region harbors infiltration areas responsible for future tumor recurrence. This study aimed to evaluate a predictive model that identifies areas of future recurrence using a voxel-based radiomics analysis of magnetic resonance imaging (MRI) data. This multi-institutional study included a retrospective analysis of patients diagnosed with glioblastoma who underwent surgery with complete resection of the enhancing tumor. Fifty-five patients met the selection criteria. The study sample was split into training (N = 40) and testing (N = 15) datasets. Follow-up MRI was used for ground truth definition, and postoperative structural multiparametric MRI was used to extract voxel-based radiomic features. Deformable coregistration was used to register the MRI sequences for each patient, followed by segmentation of the peritumoral region in the postoperative scan and the enhancing tumor in the follow-up scan. Peritumoral voxels overlapping with enhancing tumor voxels were labeled as recurrence, while non-overlapping voxels were labeled as nonrecurrence. Voxel-based radiomic features were extracted from the peritumoral region. Four machine learning-based classifiers were trained for recurrence prediction. A region-based evaluation approach was used for model evaluation. The Categorical Boosting (CatBoost) classifier obtained the best performance on the testing dataset with an average area under the curve (AUC) of 0.81 ± 0.09 and an accuracy of 0.84 ± 0.06, using region-based evaluation. There was a clear visual correspondence between predicted and actual recurrence regions. We have developed a method that accurately predicts the region of future tumor recurrence in MRI scans of glioblastoma patients. This could enable the adaptation of surgical and radiotherapy treatment to these areas to potentially prolong the survival of these patients.

Artificial intelligence-based locoregional markers of brain peritumoral microenvironment

In malignant primary brain tumors, cancer cells infiltrate into the peritumoral brain structures which results in inevitable recurrence. Quantitative assessment of infiltrative heterogeneity in the peritumoral region, the area where biopsy or resection can be hazardous, is important for clinical decision making. Here, we derive a novel set of Artificial intelligence (AI)-based markers capturing the heterogeneity of tumor infiltration, by characterizing free water movement restriction in the peritumoral region using Diffusion Tensor Imaging (DTI)-based free water volume fraction maps. We leverage the differences in the peritumoral region of metastasis and glioblastomas, the former consisting of vasogenic versus the latter containing infiltrative edema, to extract a voxel-wise deep learning-based peritumoral microenvironment index (PMI). Descriptive characteristics of locoregional hubs of uniformly high PMI values are then extracted as AI-based markers to capture distinct aspects of infiltrative heterogeneity. The proposed markers are utilized to stratify patients' survival and IDH1 mutation status on a population of 275 adult-type diffuse gliomas (CNS WHO grade 4). Our results show significant differences in the proposed markers between patients with different overall survival and IDH1 mutation status (t test, Wilcoxon rank sum test, linear regression; p < 0.01). Clustering of patients using the proposed markers reveals distinct survival groups (logrank; p < 10-5, Cox hazard ratio = 1.82; p < 0.005). Our findings provide a panel of markers as surrogates of infiltration that might capture novel insight about underlying biology of peritumoral microstructural heterogeneity, providing potential biomarkers of prognosis pertaining to survival and molecular stratification, with applicability in clinical decision making.

Using quantitative MRI to study the association of isocitrate dehydrogenase (IDH) status with oxygen metabolism and cellular structure changes in glioma

OBJECTIVE

To investigate the characteristics of oxygen metabolism and the cellular structure of glioma using quantitative MRI to predict the isocitrate dehydrogenase 1 (IDH1) status and to further understand the biological characteristics of gliomas.

METHODS

In this retrospective study, 94 patients with gliomas eventually received quantitative MRI measures to study oxygen metabolism. The oxygen metabolism biomarker maps (oxygen extraction fraction [OEF] and cerebral metabolic rate of oxygen [CMRO₂]) and the tissue-cellular-specific (R₂t*) MRI relaxation parameter were evaluated in different regions of glioma.

RESULTS

MRI results showed differences in oxygen metabolism measures in all patients with gliomas of different IDH1 statuses. Compared to patients with IDH1 mutant gliomas, patients with IDH1 wild type gliomas showed increased (P < 0.01) CMRO₂, OEF, cerebral blood volume [CBF], and R₂t* measures in tumor regions, while only OEF, CBF and R₂t* were found to be increased (P < 0.05) in the peritumoral area. OEF achieved the best performance for distinguishing IDH1 wild type and mutant gliomas in the tumor area (AUC = 0.732, P < 0.001). R₂t* values correlated with Ki-67(R = 0.35, P < 0.001) in the tumor area, while no significant correlations between Ki-67 and R₂t* were found in the peritumoral area (R = 0.19, P = 0.072).

CONCLUSION

Quantitative MRI has potential applications in studying the tumor and peritumoral areas of glioma, and it has the ability to predict and reveal the characteristics of oxygen metabolism and cellular structure in different regions of gliomas.

The Promise of Magnetic Resonance Imaging in Radiation Oncology Practice in the Management of Brain, Prostate, and GI Malignancies

Magnetic resonance imaging (MRI) has a key role to play at multiple steps of the radiotherapy (RT) treatment planning and delivery process. Development of high-precision RT techniques such as intensity-modulated RT, stereotactic ablative RT, and particle beam therapy has enabled oncologists to escalate RT dose to the target while restricting doses to organs at risk (OAR). MRI plays a critical role in target volume delineation in various disease sites, thus ensuring that these high-precision techniques can be safely implemented. Accurate identification of gross disease has also enabled selective dose escalation as a means to widen the therapeutic index. Morphological and functional MRI sequences have also facilitated an understanding of temporal changes in target volumes and OAR during a course of RT, allowing for midtreatment volumetric and biological adaptation. The latest advancement in linear accelerator technology has led to the incorporation of an MRI scanner in the treatment unit. MRI-guided RT provides the opportunity for MRI-only workflow along with online adaptation for either target or OAR or both. MRI plays a key role in post-treatment response evaluation and is an important tool for guiding decision making. In this review, we briefly discuss the RT-related applications of MRI in the management of brain, prostate, and GI malignancies.

Predicting survival in patients with glioblastoma using MRI radiomic features extracted from radiation planning volumes

BACKGROUND

Quantitative image analysis using pre-operative magnetic resonance imaging (MRI) has been able to predict survival in patients with glioblastoma (GBM). The study explored the role of postoperative radiation (RT) planning MRI-based radiomics to predict the outcomes, with features extracted from the gross tumor volume (GTV) and clinical target volume (CTV).

METHODS

Patients with IDH-wildtype GBM treated with adjuvant RT having MRI as a part of RT planning process were included in the study. 546 features were extracted from each GTV and CTV. A LASSO Cox model was applied, and internal validation was performed using leave-one-out cross-validation with overall survival as endpoint. Cross-validated time-dependent area under curve (AUC) was constructed to test the efficacy of the radiomics model, and clinical features were used to generate a combined model. Analysis was done for the entire group and in individual surgical groups-gross total excision (GTR), subtotal resection (STR), and biopsy.

RESULTS

235 patients were included in the study with 57, 118, and 60 in the GTR, STR, and biopsy subgroup, respectively. Using the radiomics model, binary risk groups were feasible in the entire cohort (p < 0.01) and biopsy group (p = 0.04), but not in the other two surgical groups individually. The integrated AUC (iAUC) was 0.613 for radiomics-based classification in the biopsy subgroup, which improved to 0.632 with the inclusion of clinical features.

CONCLUSION

Imaging features extracted from the GTV and CTV regions can lead to risk-stratification of GBM undergoing biopsy, while the utility in other individual subgroups needs to be further explored.

MRI radiomics to differentiate between low grade glioma and glioblastoma peritumoral region

BACKGROUND

The peritumoral region (PTR) of glioblastoma (GBM) appears as a T2W-hyperintensity and is composed of microscopic tumor and edema. Infiltrative low grade glioma (LGG) comprises tumor cells that seem similar to GBM PTR on MRI. The work here explored if a radiomics-based approach can distinguish between the two groups (tumor and edema versus tumor alone).

METHODS

Patients with GBM and LGG imaged using a 1.5 T MRI were included in the study. Image data from cases of GBM PTR, and LGG were manually segmented guided by T2W hyperintensity. A set of 91 first-order and texture features were determined from each of T1W-contrast, and T2W-FLAIR, diffusion-weighted imaging sequences. Applying filtration techniques, a total of 3822 features were obtained. Different feature reduction techniques were employed, and a subsequent model was constructed using four machine learning classifiers. Leave-one-out cross-validation was used to assess classifier performance.

RESULTS

The analysis included 42 GBM and 36 LGG. The best performance was obtained using AdaBoost classifier using all the features with a sensitivity, specificity, accuracy, and area of curve (AUC) of 91%, 86%, 89%, and 0.96, respectively. Amongst the feature selection techniques, the recursive feature elimination technique had the best results, with an AUC ranging from 0.87 to 0.92. Evaluation with the F-test resulted in the most consistent feature selection with 3 T1W-contrast texture features chosen in over 90% of instances.

CONCLUSIONS

Quantitative analysis of conventional MRI sequences can effectively demarcate GBM PTR from LGG, which is otherwise indistinguishable on visual estimation.

Reverse Engineering Glioma Radiomics to Conventional Neuroimaging

A novel radiological research field pursuing comprehensive quantitative image, namely “Radiomics,” gained traction along with the advancement of computational technology and artificial intelligence. This novel concept for analyzing medical images brought extensive interest to the neuro-oncology and neuroradiology research community to build a diagnostic workflow to detect clinically relevant genetic alteration of gliomas noninvasively. Although quite a few promising results were published regarding MRI-based diagnosis of isocitrate dehydrogenase (IDH) mutation in gliomas, it has become clear that an ample amount of effort is still needed to render this technology clinically applicable. At the same time, many significant insights were discovered through this research project, some of which could be “reverse engineered” to improve conventional non-radiomic MR image acquisition. In this review article, the authors aim to discuss the recent advancements and encountering issues of radiomics, how we can apply the knowledge provided by radiomics to standard clinical images, and further expected technological advances in the realm of radiomics and glioma.

[Artificial intelligence, radiomics and pathomics to predict response and survival of patients treated with radiations]

Artificial intelligence approaches in medicine are more and more used and are extremely promising due to the growing number of data produced and the variety of data they allow to exploit. Thus, the computational analysis of medical images in particular, radiological (radiomics), or anatomopathological (pathomics), has shown many very interesting results for the prediction of the prognosis and the response of cancer patients. Radiotherapy is a discipline that particularly benefits from these new approaches based on computer science and imaging. This review will present the main principles of an artificial intelligence approach and in particular machine learning, the principles of a radiomic and pathomic approach and the potential of their use for the prediction of the prognosis of patients treated with radiotherapy.