Histopathology-validated machine learning radiographic biomarker for noninvasive discrimination between true progression and pseudo-progression in glioblastoma

Noninvasive Autopsy-Validated Tumor Probability Maps Identify Glioma Invasion Beyond Contrast Enhancement

BACKGROUND AND OBJECTIVES

This study identified a clinically significant subset of patients with glioma with tumor outside of contrast enhancement present at autopsy and subsequently developed a method for detecting nonenhancing tumor using radio-pathomic mapping. We tested the hypothesis that autopsy-based radio-pathomic tumor probability maps would be able to noninvasively identify areas of infiltrative tumor beyond traditional imaging signatures.

METHODS

A total of 159 tissue samples from 65 subjects were aligned to MRI acquired nearest to death for this retrospective study. Demographic and survival characteristics for patients with and without tumor beyond the contrast-enhancing margin were computed. An ensemble algorithm was used to predict pixelwise tumor presence from pathological annotations using segmented cellularity (Cell), extracellular fluid, and cytoplasm density as input (6 train/3 test subjects). A second level of ensemble algorithms was used to predict voxelwise Cell, extracellular fluid, and cytoplasm on the full data set (43 train/22 test subjects) using 5-by-5 voxel tiles from T1, T1 + C, fluid-attenuated inversion recovery, and apparent diffusion coefficient as input. The models were then combined to generate noninvasive whole brain maps of tumor probability.

RESULTS

Tumor outside of contrast was identified in 41.5% of patients, who showed worse survival outcomes (hazard ratio = 3.90, P < .001). Tumor probability maps reliably tracked nonenhancing tumor on a range of local and external unseen data, identifying tumor outside of contrast in 69% of presurgical cases that also showed reduced survival outcomes (hazard ratio = 1.67, P = .027).

CONCLUSION

This study developed a multistage model for mapping gliomas using autopsy tissue samples as ground truth, which was able to identify regions of tumor beyond traditional imaging signatures.

Artificial intelligence for response prediction and personalisation in radiation oncology

Artificial intelligence (AI) systems may personalise radiotherapy by assessing complex and multifaceted patient data and predicting tumour and normal tissue responses to radiotherapy. Here we describe three distinct generations of AI systems, namely personalised radiotherapy based on pretreatment data, response-driven radiotherapy and dynamically optimised radiotherapy. Finally, we discuss the main challenges in clinical translation of AI systems for radiotherapy personalisation.

CFINet: Cross-Modality MRI Feature Interaction Network for Pseudoprogression Prediction of Glioblastoma

Pseudoprogression (PSP) is a related reaction of glioblastoma treatment, and misdiagnosis can lead to unnecessary intervention. Magnetic resonance imaging (MRI) provides cross-modality images for PSP prediction studies. However, how to effectively use the complementary information between the cross-modality MRI to improve PSP prediction is still a challenging task. To address this challenge, we propose a cross-modality feature interaction network for PSP prediction. Firstly, we propose a triple-branch multi-scale module to extract low-order feature representations and a skip-connection multi-scale module to extract high-order feature representations. Then, a cross-modality interaction module based on attention mechanism is designed to make the complementary information between cross-modality MRI fully interact. Finally, the high-order cross-modality interaction information is fed into a multi-layer perceptron to achieve the PSP prediction task. We evaluate the proposed network on a private dataset with 52 subjects from Hunan Cancer Hospital and validate it on a private dataset with 30 subjects from Xiangya Hospital. The accuracy of our proposed network on the datasets is 0.954 and 0.929, respectively, which is better than most typical convolutional neural network and interaction methods.

Deep learning-based deformable image registration with bilateral pyramid to align pre-operative and follow-up magnetic resonance imaging (MRI) scans

Background

The evaluation of brain tumor recurrence after surgery is based on the comparison between tumor regions on pre-operative and follow-up magnetic resonance imaging (MRI) scans in clinical practice. Accurate alignment of MRI scans is important in this evaluation process. However, existing methods often fail to yield accurate alignment due to substantial appearance and shape changes of tumor regions. The study aimed to improve this misalignment situation through multimodal information and compensation for shape changes.

Methods

In this work, a deep learning-based deformation registration method using bilateral pyramid to create multi-scale image features was developed. Moreover, morphology operations were employed to build correspondence between the surgical resection on the follow-up and pre-operative MRI scans.

Results

Compared with baseline methods, the proposed method achieved the lowest mean absolute error of 1.82 mm on the public BraTS-Reg 2022 dataset.

Conclusions

The results suggest that the proposed method is potentially useful for evaluating tumor recurrence after surgery. We effectively verified its ability to extract and integrate the information of the second modality, and also revealed the micro representation of tumor recurrence. This study can assist doctors in registering multiple sequence images of patients, observing lesions and surrounding areas, analyzing and processing them, and guiding doctors in their treatment plans.

Uses of artificial intelligence in glioma: A systematic review

Glioma is the most prevalent type of primary brain tumor in adults. The use of artificial intelligence (AI) in glioma is increasing and has exhibited promising results. The present study performed a systematic review of the applications of AI in glioma as regards diagnosis, grading, prediction of genotype, progression and treatment response using different databases. The aim of the present study was to demonstrate the trends (main directions) of the recent applications of AI within the field of glioma, and to highlight emerging challenges in integrating AI within clinical practice. A search in four databases (Scopus, PubMed, Wiley and Google Scholar) yielded a total of 42 articles specifically using AI in glioma and glioblastoma. The articles were retrieved and reviewed, and the data were summarized and analyzed. The majority of the articles were from the USA (n=18) followed by China (n=11). The number of articles increased by year reaching the maximum number in 2022. The majority of the articles studied glioma as opposed to glioblastoma. In terms of grading, the majority of the articles were about both low-grade glioma (LGG) and high-grade glioma (HGG) (n=23), followed by HGG/glioblastoma (n=13). Additionally, three articles were about LGG only; two articles did not specify the grade. It was found that one article had the highest sample size among the other studies, reaching 897 samples. Despite the limitations and challenges that face AI, the use of AI in glioma has increased in recent years with promising results, with a variety of applications ranging from diagnosis, grading, prognosis prediction, and reaching to treatment and post-operative care.

Augmented surgical decision-making for glioblastoma: integrating AI tools into education and practice

Surgical decision-making for glioblastoma poses significant challenges due to its complexity and variability. This study investigates the potential of artificial intelligence (AI) tools in improving "decision-making processes" for glioblastoma surgery. A systematic review of literature identified 10 relevant studies, primarily focused on predicting resectability and surgery-related neurological outcomes. AI tools, especially rooted in radiomics and connectomics, exhibited promise in predicting resection extent through precise tumor segmentation and tumor-network relationships. However, they demonstrated limited effectiveness in predicting postoperative neurological due to dynamic and less quantifiable nature of patient-related factors. Recognizing these challenges, including limited datasets and the interpretability requirement in medical applications, underscores the need for standardization, algorithm optimization, and addressing variability in model performance and then further validation in clinical settings. While AI holds potential, it currently does not possess the capacity to emulate the nuanced decision-making process utilized by experienced neurosurgeons in the comprehensive approach to glioblastoma surgery.

Post-treatment imaging of gliomas: challenging the existing dogmas

Gliomas are the commonest malignant central nervous system tumours in adults and imaging is the cornerstone of diagnosis, treatment, and post-treatment follow-up of these patients. With the ever-evolving treatment strategies post-treatment imaging and interpretation in glioma remains challenging, more so with the advent of anti-angiogenic drugs and immunotherapy, which can significantly alter the appearance in this setting, thus making interpretation of routine imaging findings such as contrast enhancement, oedema, and mass effect difficult to interpret. This review details the various methods of management of glioma including the upcoming novel therapies and their impact on imaging findings, with a comprehensive description of the imaging findings in conventional and advanced imaging techniques. A systematic appraisal for the existing and emerging techniques of imaging in these settings and their clinical application including various response assessment guidelines and artificial intelligence based response assessment will also be discussed.

Incidence and outcome of pseudoprogression after radiation therapy in glioblastoma patients: A cohort study

Background

Differentiating post-radiation MRI changes from progressive disease (PD) in glioblastoma (GBM) patients represents a major challenge. The clinical problem is two-sided; avoid termination of effective therapy in case of pseudoprogression (PsP) and continuation of ineffective therapy in case of PD. We retrospectively assessed the incidence, management, and prognostic impact of PsP and analyzed factors associated with PsP in a GBM patient cohort.

Methods

Consecutive GBM patients diagnosed in the South-Eastern Norway Health Region from 2015 to 2018 who had received RT and follow-up MRI were included. Tumor, patient, and treatment characteristics were analyzed in relationship to re-evaluated MRI examinations at 3 and 6 months post-radiation using Response Assessment in Neuro-Oncology criteria.

Results

A total of 284 patients were included in the study. PsP incidence 3 and 6 months post-radiation was 19.4% and 7.0%, respectively. In adjusted analyses, methylated O6-methylguanine-DNA methyltransferase (MGMT) promoter and the absence of neurological deterioration were associated with PsP at both 3 (p < .001 and p = .029, respectively) and 6 months (p = .045 and p = .034, respectively) post-radiation. For patients retrospectively assessed as PD 3 months post-radiation, there was no survival benefit of treatment change (p = .838).

Conclusions

PsP incidence was similar to previous reports. In addition to the previously described correlation of methylated MGMT promoter with PsP, we also found that absence of neurological deterioration significantly correlated with PsP. Continuation of temozolomide courses did not seem to compromise survival for patients with PD at 3 months post-radiation; therefore, we recommend continuing adjuvant temozolomide courses in case of inconclusive MRI findings.

The application value of deep learning in the background of precision medicine in glioblastoma

Introduction: Glioblastoma is a highly malignant central nervous system tumor, World Health Organization Ⅳ, glioblastoma is the most common primary malignancy, due to its own specificity and complexity, different patients often benefit from the current conventional treatment regimen because of different molecular subtypes, in the context of precision medicine, the application of deep learning to identify the salient features of tumors on brain imaging, prognostic predictive assessment combined with clinical data to maximize the benefits of each patient from the treatment regimen is a non-invasive and feasible regimen. Methods: We conducted a comprehensive review of the existing literature on the role of deep learning in glioblastomas, covering molecular classification and diagnosis, prognosis assessment. Results: Data based on a variety of magnetic resonance imaging sequences, genetic information, and clinical combinations enable noninvasive predictive tumor diagnosis of glioblastoma and assess overall survival and treatment response accuracy. For images, standardized image acquisition and data extraction techniques can be effectively translated into learning models for clinical practice. However, it must be recognized that interventions in the treatment of glioblastoma using deep learning are still in their infancy, and the robustness of the model is challenged, as the current total number of glioblastoma samples is insufficient for large-scale experimental methods, which is directly related to the difficulty of application of the model. Conclusion: Compared to radiomics and shallow machine learning, deep learning can be a more robust, non-invasive, and effective approach, providing more valuable information as clinicians develop personalized medical protocols for glioblastoma patients.

Artificial intelligence in neuroimaging of brain tumors: reality or still promise?

PURPOSE OF REVIEW

To provide an updated overview of artificial intelligence (AI) applications in neuro-oncologic imaging and discuss current barriers to wider clinical adoption.

RECENT FINDINGS

A wide variety of AI applications in neuro-oncologic imaging have been developed and researched, spanning tasks from pretreatment brain tumor classification and segmentation, preoperative planning, radiogenomics, prognostication and survival prediction, posttreatment surveillance, and differentiating between pseudoprogression and true disease progression. While earlier studies were largely based on data from a single institution, more recent studies have demonstrated that the performance of these algorithms are also effective on external data from other institutions. Nevertheless, most of these algorithms have yet to see widespread clinical adoption, given the lack of prospective studies demonstrating their efficacy and the logistical difficulties involved in clinical implementation.

SUMMARY

While there has been significant progress in AI and neuro-oncologic imaging, clinical utility remains to be demonstrated. The next wave of progress in this area will be driven by prospective studies measuring outcomes relevant to clinical practice and go beyond retrospective studies which primarily aim to demonstrate high performance.

Neurosurgical Management of Cerebrospinal Tumors in the Era of Artificial Intelligence : A Scoping Review

Central nervous system tumors are identified as tumors of the brain and spinal cord. The associated morbidity and mortality of cerebrospinal tumors are disproportionately high compared to other malignancies. While minimally invasive techniques have initiated a revolution in neurosurgery, artificial intelligence (AI) is expediting it. Our study aims to analyze AI's role in the neurosurgical management of cerebrospinal tumors. We conducted a scoping review using the Arksey and O'Malley framework. Upon screening, data extraction and analysis were focused on exploring all potential implications of AI, classification of these implications in the management of cerebrospinal tumors. AI has enhanced the precision of diagnosis of these tumors, enables surgeons to excise the tumor margins completely, thereby reducing the risk of recurrence, and helps to make a more accurate prediction of the patient's prognosis than the conventional methods. AI also offers real-time training to neurosurgeons using virtual and 3D simulation, thereby increasing their confidence and skills during procedures. In addition, robotics is integrated into neurosurgery and identified to increase patient outcomes by making surgery less invasive. AI, including machine learning, is rigorously considered for its applications in the neurosurgical management of cerebrospinal tumors. This field requires further research focused on areas clinically essential in improving the outcome that is also economically feasible for clinical use. The authors suggest that data analysts and neurosurgeons collaborate to explore the full potential of AI.

Tracking Therapy Response in Glioblastoma Using 1D Convolutional Neural Networks

BACKGROUND

Glioblastoma (GB) is a malignant brain tumour that is challenging to treat, often relapsing even after aggressive therapy. Evaluating therapy response relies on magnetic resonance imaging (MRI) following the Response Assessment in Neuro-Oncology (RANO) criteria. However, early assessment is hindered by phenomena such as pseudoprogression and pseudoresponse. Magnetic resonance spectroscopy (MRS/MRSI) provides metabolomics information but is underutilised due to a lack of familiarity and standardisation.

METHODS

This study explores the potential of spectroscopic imaging (MRSI) in combination with several machine learning approaches, including one-dimensional convolutional neural networks (1D-CNNs), to improve therapy response assessment. Preclinical GB (GL261-bearing mice) were studied for method optimisation and validation.

RESULTS

The proposed 1D-CNN models successfully identify different regions of tumours sampled by MRSI, i.e., normal brain (N), control/unresponsive tumour (T), and tumour responding to treatment (R). Class activation maps using Grad-CAM enabled the study of the key areas relevant to the models, providing model explainability. The generated colour-coded maps showing the N, T and R regions were highly accurate (according to Dice scores) when compared against ground truth and outperformed our previous method.

CONCLUSIONS

The proposed methodology may provide new and better opportunities for therapy response assessment, potentially providing earlier hints of tumour relapsing stages.

Taming Glioblastoma in "Real Time": Integrating Multimodal Advanced Neuroimaging/AI Tools Towards Creating a Robust and Therapy Agnostic Model for Response Assessment in Neuro-Oncology

The highly aggressive nature of glioblastoma carries a dismal prognosis despite aggressive multimodal therapy. Alternative treatment regimens, such as immunotherapies, are known to intensify the inflammatory response in the treatment field. Follow-up imaging in these scenarios often mimics disease progression on conventional MRI, making accurate evaluation extremely challenging. To this end, revised criteria for assessment of treatment response in high-grade gliomas were successfully proposed by the RANO Working Group to distinguish pseudoprogression from true progression, with intrinsic constraints related to the postcontrast T1-weighted MRI sequence. To address these existing limitations, our group proposes a more objective and quantifiable "treatment agnostic" model, integrating into the RANO criteria advanced multimodal neuroimaging techniques, such as diffusion tensor imaging (DTI), dynamic susceptibility contrast-perfusion weighted imaging (DSC-PWI), dynamic contrast enhanced (DCE)-MRI, MR spectroscopy, and amino acid-based positron emission tomography (PET) imaging tracers, along with artificial intelligence (AI) tools (radiomics, radiogenomics, and radiopathomics) and molecular information to address this complex issue of treatment-related changes versus tumor progression in "real-time", particularly in the early posttreatment window. Our perspective delineates the potential of incorporating multimodal neuroimaging techniques to improve consistency and automation for the assessment of early treatment response in neuro-oncology.

Texture Analysis of the Apparent Diffusion Coefficient Focused on Contrast-Enhancing Lesions in Predicting Survival for Bevacizumab-Treated Patients with Recurrent Glioblastoma

PURPOSE

Glioblastoma often recurs after treatment. Bevacizumab increases progression-free survival in some patients with recurrent glioblastoma. Identifying pretreatment predictors of survival can help clinical decision making. Magnetic resonance texture analysis (MRTA) quantifies macroscopic tissue heterogeneity indirectly linked to microscopic tissue properties. We investigated the usefulness of MRTA in predicting survival in patients with recurrent glioblastoma treated with bevacizumab.

METHODS

We evaluated retrospective longitudinal data from 33 patients (20 men; mean age 56 ± 13 years) who received bevacizumab on the first recurrence of glioblastoma. Volumes of contrast-enhancing lesions segmented on postcontrast T1-weighted sequences were co-registered on apparent diffusion coefficient maps to extract 107 radiomic features. To assess the performance of textural parameters in predicting progression-free survival and overall survival, we used receiver operating characteristic curves, univariate and multivariate regression analysis, and Kaplan-Meier plots.

RESULTS

Longer progression-free survival (>6 months) and overall survival (>1 year) were associated with lower values of major axis length (MAL), a lower maximum 2D diameter row (m2Ddr), and higher skewness values. Longer progression-free survival was also associated with higher kurtosis, and longer overall survival with higher elongation values. The model combining MAL, m2Ddr, and skewness best predicted progression-free survival at 6 months (AUC 0.886, 100% sensitivity, 77.8% specificity, 50% PPV, 100% NPV), and the model combining m2Ddr, elongation, and skewness best predicted overall survival (AUC 0.895, 83.3% sensitivity, 85.2% specificity, 55.6% PPV, 95.8% NPV).

CONCLUSIONS

Our preliminary analyses suggest that in patients with recurrent glioblastoma pretreatment, MRTA helps to predict survival after bevacizumab treatment.

Assessment of treatment response to dendritic cell vaccine in patients with glioblastoma using a multiparametric MRI-based prediction model

PURPOSE

Autologous tumor lysate-loaded dendritic cell vaccine (DCVax-L) is a promising treatment modality for glioblastomas. The purpose of this study was to investigate the potential utility of multiparametric MRI-based prediction model in evaluating treatment response in glioblastoma patients treated with DCVax-L.

METHODS

Seventeen glioblastoma patients treated with standard-of-care therapy + DCVax-L were included. When tumor progression (TP) was suspected and repeat surgery was being contemplated, we sought to ascertain the number of cases correctly classified as TP + mixed response or pseudoprogression (PsP) from multiparametric MRI-based prediction model using histopathology/mRANO criteria as ground truth. Multiparametric MRI model consisted of predictive probabilities (PP) of tumor progression computed from diffusion and perfusion MRI-derived parameters. A comparison of overall survival (OS) was performed between patients treated with standard-of-care therapy + DCVax-L and standard-of-care therapy alone (external controls). Additionally, Kaplan-Meier analyses were performed to compare OS between two groups of patients using PsP, Ki-67, and MGMT promoter methylation status as stratification variables.

RESULTS

Multiparametric MRI model correctly predicted TP + mixed response in 72.7% of cases (8/11) and PsP in 83.3% (5/6) with an overall concordance rate of 76.5% with final diagnosis as determined by histopathology/mRANO criteria. There was a significant concordant correlation coefficient between PP values and histopathology/mRANO criteria (r = 0.54; p = 0.026). DCVax-L-treated patients had significantly prolonged OS than those treated with standard-of-care therapy (22.38 ± 12.8 vs. 13.8 ± 9.5 months, p = 0.040). Additionally, glioblastomas with PsP, MGMT promoter methylation status, and Ki-67 values below median had longer OS than their counterparts.

CONCLUSION

Multiparametric MRI-based prediction model can assess treatment response to DCVax-L in patients with glioblastoma.

Validation of multiparametric MRI based prediction model in identification of pseudoprogression in glioblastomas

BACKGROUND

Accurate differentiation of pseudoprogression (PsP) from tumor progression (TP) in glioblastomas (GBMs) is essential for appropriate clinical management and prognostication of these patients. In the present study, we sought to validate the findings of our previously developed multiparametric MRI model in a new cohort of GBM patients treated with standard therapy in identifying PsP cases.

METHODS

Fifty-six GBM patients demonstrating enhancing lesions within 6 months after completion of concurrent chemo-radiotherapy (CCRT) underwent anatomical imaging, diffusion and perfusion MRI on a 3 T magnet. Subsequently, patients were classified as TP + mixed tumor (n = 37) and PsP (n = 19). When tumor specimens were available from repeat surgery, histopathologic findings were used to identify TP + mixed tumor (> 25% malignant features; n = 34) or PsP (< 25% malignant features; n = 16). In case of non-availability of tumor specimens, ≥ 2 consecutive conventional MRIs using mRANO criteria were used to determine TP + mixed tumor (n = 3) or PsP (n = 3). The multiparametric MRI-based prediction model consisted of predictive probabilities (PP) of tumor progression computed from diffusion and perfusion MRI derived parameters from contrast enhancing regions. In the next step, PP values were used to characterize each lesion as PsP or TP+ mixed tumor. The lesions were considered as PsP if the PP value was < 50% and TP+ mixed tumor if the PP value was ≥ 50%. Pearson test was used to determine the concordance correlation coefficient between PP values and histopathology/mRANO criteria. The area under ROC curve (AUC) was used as a quantitative measure for assessing the discriminatory accuracy of the prediction model in identifying PsP and TP+ mixed tumor.

RESULTS

Multiparametric MRI model correctly predicted PsP in 95% (18/19) and TP+ mixed tumor in 57% of cases (21/37) with an overall concordance rate of 70% (39/56) with final diagnosis as determined by histopathology/mRANO criteria. There was a significant concordant correlation coefficient between PP values and histopathology/mRANO criteria (r = 0.56; p < 0.001). The ROC analyses revealed an accuracy of 75.7% in distinguishing PsP from TP+ mixed tumor. Leave-one-out cross-validation test revealed that 73.2% of cases were correctly classified as PsP and TP + mixed tumor.

CONCLUSIONS

Our multiparametric MRI based prediction model may be helpful in identifying PsP in GBM patients.

Assessment and prediction of glioblastoma therapy response: challenges and opportunities

Glioblastoma is the most aggressive type of primary adult brain tumour. The median survival of patients with glioblastoma remains approximately 15 months, and the 5-year survival rate is <10%. Current treatment options are limited, and the standard of care has remained relatively constant since 2011. Over the last decade, a range of different treatment regimens have been investigated with very limited success. Tumour recurrence is almost inevitable with the current treatment strategies, as glioblastoma tumours are highly heterogeneous and invasive. Additionally, another challenging issue facing patients with glioblastoma is how to distinguish between tumour progression and treatment effects, especially when relying on routine diagnostic imaging techniques in the clinic. The specificity of routine imaging for identifying tumour progression early or in a timely manner is poor due to the appearance similarity of post-treatment effects. Here, we concisely describe the current status and challenges in the assessment and early prediction of therapy response and the early detection of tumour progression or recurrence. We also summarize and discuss studies of advanced approaches such as quantitative imaging, liquid biomarker discovery and machine intelligence that hold exceptional potential to aid in the therapy monitoring of this malignancy and early prediction of therapy response, which may decisively transform the conventional detection methods in the era of precision medicine.

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.

Radiomic Analysis to Predict Histopathologically Confirmed Pseudoprogression in Glioblastoma Patients

Purpose

Pseudoprogression mimicking recurrent glioblastoma remains a diagnostic challenge that may adversely confound or delay appropriate treatment or clinical trial enrollment. We sought to build a radiomic classifier to predict pseudoprogression in patients with primary isocitrate dehydrogenase wild type glioblastoma.

Methods and Materials

We retrospectively examined a training cohort of 74 patients with isocitrate dehydrogenase wild type glioblastomas with brain magnetic resonance imaging including dynamic contrast enhanced T1 perfusion before resection of an enhancing lesion indeterminate for recurrent tumor or pseudoprogression. A recursive feature elimination random forest classifier was built using nested cross-validation without and with O⁶-methylguanine-DNA methyltransferase status to predict pseudoprogression.

Results

A classifier constructed with cross-validation on the training cohort achieved an area under the receiver operating curve of 81% for predicting pseudoprogression. This was further improved to 89% with the addition of O⁶-methylguanine-DNA methyltransferase status into the classifier.

Conclusions

Our results suggest that radiomic analysis of contrast T1-weighted images and magnetic resonance imaging perfusion images can assist the prompt diagnosis of pseudoprogression. Validation on external and independent data sets is necessary to verify these advanced analyses, which can be performed on routinely acquired clinical images and may help inform clinical treatment decisions.

Radiomics analysis of amide proton transfer-weighted and structural MR images for treatment response assessment in malignant gliomas

The purpose of this study was to evaluate the value of amide proton transfer-weighted (APTw) MRI radiomic features for the differentiation of tumor recurrence from treatment effect in malignant gliomas. Eighty-six patients who had suspected tumor recurrence after completion of chemoradiation or radiotherapy, and who had APTw-MRI data acquired at 3 T, were retrospectively analyzed. Using a fluid-attenuated inversion recovery (FLAIR) image-based mask, radiomics analysis was applied to the processed APTw and structural MR images. A chi-square automatic interaction detector decision tree was used for classification analysis. Models with and without APTw features were built using the same strategy. Tenfold cross-validation was applied to obtain the overall classification performance of each model. Sixty patients were confirmed as having tumor recurrence, and the remainder were confirmed as having treatment effect, at median time points of 190 and 171 days after therapy, respectively. There were 525 radiomic features extracted from each of the processed APTw and structural MR images. Based on these, the APTw-based model yielded the highest accuracy (86.0%) for the differentiation of tumor recurrence from treatment effect, compared with 74.4%, 76.7%, 83.7%, and 76.7% for T1 w, T2 w, FLAIR, and Gd-T1 w, respectively. Model classification accuracy was 82.6% when using the combined structural MR images (T1 w, T2 w, FLAIR, Gd-T1 w), and increased to 89.5% when using these structural plus APTw images. The corresponding sensitivity and specificity were 85.0% and 76.9% for the combination of structural MR images, and 85.0% and 100% after adding APTw image features. Adding APTw-based radiomic features increased MRI accuracy in the assessment of the treatment response in post-treatment malignant gliomas.

Cost Matrix of Molecular Pathology in Glioma-Towards AI-Driven Rational Molecular Testing and Precision Care for the Future

Gliomas are the most common and aggressive primary brain tumors. Gliomas carry a poor prognosis because of the tumor's resistance to radiation and chemotherapy leading to nearly universal recurrence. Recent advances in large-scale genomic research have allowed for the development of more targeted therapies to treat glioma. While precision medicine can target specific molecular features in glioma, targeted therapies are often not feasible due to the lack of actionable markers and the high cost of molecular testing. This review summarizes the clinically relevant molecular features in glioma and the current cost of care for glioma patients, focusing on the molecular markers and meaningful clinical features that are linked to clinical outcomes and have a realistic possibility of being measured, which is a promising direction for precision medicine using artificial intelligence approaches.

The federated tumor segmentation (FeTS) tool: an open-source solution to further solid tumor research

Objective.De-centralized data analysis becomes an increasingly preferred option in the healthcare domain, as it alleviates the need for sharing primary patient data across collaborating institutions. This highlights the need for consistent harmonized data curation, pre-processing, and identification of regions of interest based on uniform criteria.Approach.Towards this end, this manuscript describes theFederatedTumorSegmentation (FeTS) tool, in terms of software architecture and functionality.Main results.The primary aim of the FeTS tool is to facilitate this harmonized processing and the generation of gold standard reference labels for tumor sub-compartments on brain magnetic resonance imaging, and further enable federated training of a tumor sub-compartment delineation model across numerous sites distributed across the globe, without the need to share patient data.Significance.Building upon existing open-source tools such as the Insight Toolkit and Qt, the FeTS tool is designed to enable training deep learning models targeting tumor delineation in either centralized or federated settings. The target audience of the FeTS tool is primarily the computational researcher interested in developing federated learning models, and interested in joining a global federation towards this effort. The tool is open sourced athttps://github.com/FETS-AI/Front-End.

Deep Learning Assessment for Mining Important Medical Image Features of Various Modalities

Deep learning (DL) is a well-established pipeline for feature extraction in medical and nonmedical imaging tasks, such as object detection, segmentation, and classification. However, DL faces the issue of explainability, which prohibits reliable utilisation in everyday clinical practice. This study evaluates DL methods for their efficiency in revealing and suggesting potential image biomarkers. Eleven biomedical image datasets of various modalities are utilised, including SPECT, CT, photographs, microscopy, and X-ray. Seven state-of-the-art CNNs are employed and tuned to perform image classification in tasks. The main conclusion of the research is that DL reveals potential biomarkers in several cases, especially when the models are trained from scratch in domains where low-level features such as shapes and edges are not enough to make decisions. Furthermore, in some cases, device acquisition variations slightly affect the performance of DL models.

Artificial intelligence in the radiomic analysis of glioblastomas: A review, taxonomy, and perspective

Radiological imaging techniques, including magnetic resonance imaging (MRI) and positron emission tomography (PET), are the standard-of-care non-invasive diagnostic approaches widely applied in neuro-oncology. Unfortunately, accurate interpretation of radiological imaging data is constantly challenged by the indistinguishable radiological image features shared by different pathological changes associated with tumor progression and/or various therapeutic interventions. In recent years, machine learning (ML)-based artificial intelligence (AI) technology has been widely applied in medical image processing and bioinformatics due to its advantages in implicit image feature extraction and integrative data analysis. Despite its recent rapid development, ML technology still faces many hurdles for its broader applications in neuro-oncological radiomic analysis, such as lack of large accessible standardized real patient radiomic brain tumor data of all kinds and reliable predictions on tumor response upon various treatments. Therefore, understanding ML-based AI technologies is critically important to help us address the skyrocketing demands of neuro-oncology clinical deployments. Here, we provide an overview on the latest advancements in ML techniques for brain tumor radiomic analysis, emphasizing proprietary and public dataset preparation and state-of-the-art ML models for brain tumor diagnosis, classifications (e.g., primary and secondary tumors), discriminations between treatment effects (pseudoprogression, radiation necrosis) and true progression, survival prediction, inflammation, and identification of brain tumor biomarkers. We also compare the key features of ML models in the realm of neuroradiology with ML models employed in other medical imaging fields and discuss open research challenges and directions for future work in this nascent precision medicine area.

The University of Pennsylvania glioblastoma (UPenn-GBM) cohort: advanced MRI, clinical, genomics, & radiomics

Glioblastoma is the most common aggressive adult brain tumor. Numerous studies have reported results from either private institutional data or publicly available datasets. However, current public datasets are limited in terms of: a) number of subjects, b) lack of consistent acquisition protocol, c) data quality, or d) accompanying clinical, demographic, and molecular information. Toward alleviating these limitations, we contribute the "University of Pennsylvania Glioblastoma Imaging, Genomics, and Radiomics" (UPenn-GBM) dataset, which describes the currently largest publicly available comprehensive collection of 630 patients diagnosed with de novo glioblastoma. The UPenn-GBM dataset includes (a) advanced multi-parametric magnetic resonance imaging scans acquired during routine clinical practice, at the University of Pennsylvania Health System, (b) accompanying clinical, demographic, and molecular information, (d) perfusion and diffusion derivative volumes, (e) computationally-derived and manually-revised expert annotations of tumor sub-regions, as well as (f) quantitative imaging (also known as radiomic) features corresponding to each of these regions. This collection describes our contribution towards repeatable, reproducible, and comparative quantitative studies leading to new predictive, prognostic, and diagnostic assessments.

Metabolic and physiologic magnetic resonance imaging in distinguishing true progression from pseudoprogression in patients with glioblastoma

Pseudoprogression (PsP) refers to treatment-related clinico-radiologic changes mimicking true progression (TP) that occurs in patients with glioblastoma (GBM), predominantly within the first 6 months after the completion of surgery and concurrent chemoradiation therapy (CCRT) with temozolomide. Accurate differentiation of TP from PsP is essential for making informed decisions on appropriate therapeutic intervention as well as for prognostication of these patients. Conventional neuroimaging findings are often equivocal in distinguishing between TP and PsP and present a considerable diagnostic dilemma to oncologists and radiologists. These challenges have emphasized the need for developing alternative imaging techniques that may aid in the accurate diagnosis of TP and PsP. In this review, we encapsulate the current state of knowledge in the clinical applications of commonly used metabolic and physiologic magnetic resonance (MR) imaging techniques such as diffusion and perfusion imaging and proton spectroscopy in distinguishing TP from PsP. We also showcase the potential of promising imaging techniques, such as amide proton transfer and amino acid-based positron emission tomography, in providing useful information about the treatment response. Additionally, we highlight the role of "radiomics", which is an emerging field of radiology that has the potential to change the way in which advanced MR techniques are utilized in assessing treatment response in GBM patients. Finally, we present our institutional experiences and discuss future perspectives on the role of multiparametric MR imaging in identifying PsP in GBM patients treated with "standard-of-care" CCRT as well as novel/targeted therapies.

Machine learning imaging applications in the differentiation of true tumour progression from treatment‐related effects in brain tumours: A systematic review and meta‐analysis

Introduction

Chemotherapy and radiotherapy can produce treatment‐related effects, which may mimic tumour progression. Advances in Artificial Intelligence (AI) offer the potential to provide a more consistent approach of diagnosis with improved accuracy. The aim of this study was to determine the efficacy of machine learning models to differentiate treatment‐related effects (TRE), consisting of pseudoprogression (PsP) and radiation necrosis (RN), and true tumour progression (TTP).

Methods

The systematic review was conducted in accordance with PRISMA‐DTA guidelines. Searches were performed on PubMed, Scopus, Embase, Medline (Ovid) and ProQuest databases. Quality was assessed according to the PROBAST and CLAIM criteria. There were 25 original full‐text journal articles eligible for inclusion.

Results

For gliomas: PsP versus TTP (16 studies, highest AUC = 0.98), RN versus TTP (4 studies, highest AUC = 0.9988) and TRE versus TTP (3 studies, highest AUC = 0.94). For metastasis: RN vs. TTP (2 studies, highest AUC = 0.81). A meta‐analysis was performed on 9 studies in the gliomas PsP versus TTP group using STATA. The meta‐analysis reported a high sensitivity of 95.2% (95%CI: 86.6–98.4%) and specificity of 82.4% (95%CI: 67.0–91.6%).

Conclusion

TRE can be distinguished from TTP with good performance using machine learning‐based imaging models. There remain issues with the quality of articles and the integration of models into clinical practice. Future studies should focus on the external validation of models and utilize standardized criteria such as CLAIM to allow for consistency in reporting.

Advanced MRI Protocols to Discriminate Glioma From Treatment Effects: State of the Art and Future Directions

In the follow-up treatment of high-grade gliomas (HGGs), differentiating true tumor progression from treatment-related effects, such as pseudoprogression and radiation necrosis, presents an ongoing clinical challenge. Conventional MRI with and without intravenous contrast serves as the clinical benchmark for the posttreatment surveillance imaging of HGG. However, many advanced imaging techniques have shown promise in helping better delineate the findings in indeterminate scenarios, as posttreatment effects can often mimic true tumor progression on conventional imaging. These challenges are further confounded by the histologic admixture that can commonly occur between tumor growth and treatment-related effects within the posttreatment bed. This review discusses the current practices in the surveillance imaging of HGG and the role of advanced imaging techniques, including perfusion MRI and metabolic MRI.

MRI-based contrast clearance analysis shows high differentiation accuracy between radiation-induced reactions and progressive disease after cranial radiotherapy

Background

Pseudoprogression (PsP) or radiation necrosis (RN) may frequently occur after cranial radiotherapy and show a similar imaging pattern compared with progressive disease (PD). We aimed to evaluate the diagnostic accuracy of magnetic resonance imaging-based contrast clearance analysis (CCA) in this clinical setting.

Patients and methods

Patients with equivocal imaging findings after cranial radiotherapy were consecutively included into this monocentric prospective study. CCA was carried out by software-based automated subtraction of imaging features in late versus early T1-weighted sequences after contrast agent application. Two experienced neuroradiologists evaluated CCA with respect to PsP/RN and PD being blinded for histological findings. The radiological assessment was compared with the histopathological results, and its accuracy was calculated statistically.

Results

A total of 33 patients were included; 16 (48.5%) were treated because of a primary brain tumor (BT), and 17 (51.1%) because of a secondary BT. In one patient, CCA was technically infeasible. The accuracy of CCA in predicting the histological result was 0.84 [95% confidence interval (CI) 0.67-0.95; one-sided P = 0.051; n = 32]. Sensitivity and specificity of CCA were 0.93 (95% CI 0.66-1.00) and 0.78 (95% CI 0.52-0.94), respectively. The accuracy in patients with secondary BTs was 0.94 (95% CI 0.71-1.00) and nonsignificantly higher compared with patients with primary BT with an accuracy of 0.73 (95% CI 0.45-0.92), P = 0.16.

Conclusions

In this study, CCA was a highly accurate, easy, and helpful method for distinguishing PsP or RN from PD after cranial radiotherapy, especially in patients with secondary tumors after radiosurgical treatment.

•

CCA is accurate in distinguishing treatment reactions from true PD.

•

CCA was more accurate for irradiated metastases than primary BTs.

•

CCA is not feasible for lesions with no contrast media uptake.

A deep hybrid learning pipeline for accurate diagnosis of ovarian cancer based on nuclear morphology

Nuclear morphological features are potent determining factors for clinical diagnostic approaches adopted by pathologists to analyze the malignant potential of cancer cells. Considering the structural alteration of the nucleus in cancer cells, various groups have developed machine learning techniques based on variation in nuclear morphometric information like nuclear shape, size, nucleus-cytoplasm ratio and various non-parametric methods like deep learning have also been tested for analyzing immunohistochemistry images of tissue samples for diagnosing various cancers. We aim to correlate the morphometric features of the nucleus along with the distribution of nuclear lamin proteins with classical machine learning to differentiate between normal and ovarian cancer tissues. It has already been elucidated that in ovarian cancer, the extent of alteration in nuclear shape and morphology can modulate genetic changes and thus can be utilized to predict the outcome of low to a high form of serous carcinoma. In this work, we have performed exhaustive imaging of ovarian cancer versus normal tissue and developed a dual pipeline architecture that combines the matrices of morphometric parameters with deep learning techniques of auto feature extraction from pre-processed images. This novel Deep Hybrid Learning model, though derived from classical machine learning algorithms and standard CNN, showed a training and validation AUC score of 0.99 whereas the test AUC score turned out to be 1.00. The improved feature engineering enabled us to differentiate between cancerous and non-cancerous samples successfully from this pilot study.

Imaging Biomarkers of Glioblastoma Treatment Response: A Systematic Review and Meta-Analysis of Recent Machine Learning Studies

OBJECTIVE

Monitoring biomarkers using machine learning (ML) may determine glioblastoma treatment response. We systematically reviewed quality and performance accuracy of recently published studies.

METHODS

Following Preferred Reporting Items for Systematic Reviews and Meta-Analysis: Diagnostic Test Accuracy, we extracted articles from MEDLINE, EMBASE and Cochrane Register between 09/2018-01/2021. Included study participants were adults with glioblastoma having undergone standard treatment (maximal resection, radiotherapy with concomitant and adjuvant temozolomide), and follow-up imaging to determine treatment response status (specifically, distinguishing progression/recurrence from progression/recurrence mimics, the target condition). Using Quality Assessment of Diagnostic Accuracy Studies Two/Checklist for Artificial Intelligence in Medical Imaging, we assessed bias risk and applicability concerns. We determined test set performance accuracy (sensitivity, specificity, precision, F1-score, balanced accuracy). We used a bivariate random-effect model to determine pooled sensitivity, specificity, area-under the receiver operator characteristic curve (ROC-AUC). Pooled measures of balanced accuracy, positive/negative likelihood ratios (PLR/NLR) and diagnostic odds ratio (DOR) were calculated. PROSPERO registered (CRD42021261965).

RESULTS

Eighteen studies were included (1335/384 patients for training/testing respectively). Small patient numbers, high bias risk, applicability concerns (particularly confounding in reference standard and patient selection) and low level of evidence, allow limited conclusions from studies. Ten studies (10/18, 56%) included in meta-analysis gave 0.769 (0.649-0.858) sensitivity [pooled (95% CI)]; 0.648 (0.749-0.532) specificity; 0.706 (0.623-0.779) balanced accuracy; 2.220 (1.560-3.140) PLR; 0.366 (0.213-0.572) NLR; 6.670 (2.800-13.500) DOR; 0.765 ROC-AUC.

CONCLUSION

ML models using MRI features to distinguish between progression and mimics appear to demonstrate good diagnostic performance. However, study quality and design require improvement.

Pseudoprogression in Glioblastoma: Role of Metabolic and Functional MRI-Systematic Review

Background: Glioblastoma is the most frequent malignant primitive brain tumor in adults. The treatment includes surgery, radiotherapy, and chemotherapy. During follow-up, combined chemoradiotherapy can induce treatment-related changes mimicking tumor progression on medical imaging, such as pseudoprogression (PsP). Differentiating PsP from true progression (TP) remains a challenge for radiologists and oncologists, who need to promptly start a second-line treatment in the case of TP. Advanced magnetic resonance imaging (MRI) techniques such as diffusion-weighted imaging, perfusion MRI, and proton magnetic resonance spectroscopic imaging are more efficient than conventional MRI in differentiating PsP from TP. None of these techniques are fully effective, but current advances in computer science and the advent of artificial intelligence are opening up new possibilities in the imaging field with radiomics (i.e., extraction of a large number of quantitative MRI features describing tumor density, texture, and geometry). These features are used to build predictive models for diagnosis, prognosis, and therapeutic response. Method: Out of 7350 records for MR spectroscopy, GBM, glioma, recurrence, diffusion, perfusion, pseudoprogression, radiomics, and advanced imaging, we screened 574 papers. A total of 228 were eligible, and we analyzed 72 of them, in order to establish the role of each imaging modality and the usefulness and limitations of radiomics analysis.

Deep learning identified glioblastoma subtypes based on internal genomic expression ranks

Background

Glioblastoma (GBM) can be divided into subtypes according to their genomic features, including Proneural (PN), Neural (NE), Classical (CL) and Mesenchymal (ME). However, it is a difficult task to unify various genomic expression profiles which were standardized with various procedures from different studies and to manually classify a given GBM sample into a subtype.

Methods

An algorithm was developed to unify the genomic profiles of GBM samples into a standardized normal distribution (SND), based on their internal expression ranks. Deep neural networks (DNN) and convolutional DNN (CDNN) models were trained on original and SND data. In addition, expanded SND data by combining various The Cancer Genome Atlas (TCGA) datasets were used to improve the robustness and generalization capacity of the CDNN models.

Results

The SND data kept unimodal distribution similar to their original data, and also kept the internal expression ranks of all genes for each sample. CDNN models trained on the SND data showed significantly higher accuracy compared to DNN and CDNN models trained on primary expression data. Interestingly, the CDNN models classified the NE subtype with the lowest accuracy in the GBM datasets, expanded datasets and in IDH wide type GBMs, consistent with the recent studies that NE subtype should be excluded. Furthermore, the CDNN models also recognized independent GBM datasets, even with small set of genomic expressions.

Conclusions

The GBM expression profiles can be transformed into unified SND data, which can be used to train CDNN models with high accuracy and generalization capacity. These models suggested NE subtype may be not compatible with the 4 subtypes classification system.

Radiomics and radiogenomics in pediatric neuro-oncology: A review

The current era of advanced computing has allowed for the development and implementation of the field of radiomics. In pediatric neuro-oncology, radiomics has been applied in determination of tumor histology, identification of disseminated disease, prognostication, and molecular classification of tumors (ie, radiogenomics). The field also comes with many challenges, such as limitations in study sample sizes, class imbalance, generalizability of the methods, and data harmonization across imaging centers. The aim of this review paper is twofold: first, to summarize existing literature in radiomics of pediatric neuro-oncology; second, to distill the themes and challenges of the field and discuss future directions in both a clinical and technical context.

Classification of Infection and Ischemia in Diabetic Foot Ulcers Using VGG Architectures

Diabetic foot ulceration (DFU) is a serious complication of diabetes, and a major challenge for healthcare systems around the world. Further infection and ischemia in DFU can significantly prolong treatment and often result in limb amputation, with more severe cases resulting in terminal illness. Thus, early identification and regular monitoring is necessary to improve care, and reduce the burden on healthcare systems. With that in mind, this study attempts to address the problem of infection and ischemia classification in diabetic food ulcers, in four distinct classes. We have evaluated a series of VGG architectures with different layers, following numerous training strategies, including k-fold cross validation, data pre-processing options, augmentation techniques, and weighted loss calculations. In favor of transparency and reproducibility, we make all the implementations available through the Generally Nuanced Deep Learning Framework (GaNDLF, github.com/CBICA/GaNDLF. Our best model was evaluated during the DFU Challenge 2021, and was ranked 2^nd, 5^th, and 7^th based on the macro-averaged AUC (area under the curve), macro-averaged F1 score, and macro-averaged recall metrics, respectively. Our findings support that current state-of-the-art architectures provide good results for the DFU image classification task, and further experimentation is required to study the effects of pre-processing and augmentation strategies.

Molecular Biology in Treatment Decision Processes-Neuro-Oncology Edition

Computational approaches including machine learning, deep learning, and artificial intelligence are growing in importance in all medical specialties as large data repositories are increasingly being optimised. Radiation oncology as a discipline is at the forefront of large-scale data acquisition and well positioned towards both the production and analysis of large-scale oncologic data with the potential for clinically driven endpoints and advancement of patient outcomes. Neuro-oncology is comprised of malignancies that often carry poor prognosis and significant neurological sequelae. The analysis of radiation therapy mediated treatment and the potential for computationally mediated analyses may lead to more precise therapy by employing large scale data. We analysed the state of the literature pertaining to large scale data, computational analysis, and the advancement of molecular biomarkers in neuro-oncology with emphasis on radiation oncology. We aimed to connect existing and evolving approaches to realistic avenues for clinical implementation focusing on low grade gliomas (LGG), high grade gliomas (HGG), management of the elderly patient with HGG, rare central nervous system tumors, craniospinal irradiation, and re-irradiation to examine how computational analysis and molecular science may synergistically drive advances in personalised radiation therapy (RT) and optimise patient outcomes.

A Comparison of Single- and Multiparametric MRI Models for Differentiation of Recurrent Glioblastoma from Treatment-Related Change

To evaluate single- and multiparametric MRI models to differentiate recurrent glioblastoma (GBM) and treatment-related changes (TRC) in clinical routine imaging. Selective and unselective apparent diffusion coefficient (ADC) and minimum, mean, and maximum cerebral blood volume (CBV) measurements in the lesion were performed. Minimum, mean, and maximum ratios_CBV (CBV_lesion to CBV_{healthy white matter}) were computed. All data were tested for lesion discrimination. A multiparametric model was compiled via multiple logistic regression using data demonstrating significant difference between GBM and TRC and tested for its diagnostic strength in an independent patient cohort. A total of 34 patients (17 patients with recurrent GBM and 17 patients with TRC) were included. ADC measurements showed no significant difference between both entities. All CBV and ratios_CBV measurements were significantly higher in patients with recurrent GBM than TRC. A minimum CBV of 8.5, mean CBV of 116.5, maximum CBV of 327 and ratio_CBV minimum of 0.17, ratio_CBV mean of 2.26 and ratio_CBV maximum of 3.82 were computed as optimal cut-off values. By integrating these parameters in a multiparametric model and testing it in an independent patient cohort, 9 of 10 patients, i.e., 90%, were classified correctly. The multiparametric model further improves radiological discrimination of GBM from TRC in comparison to single-parameter approaches and enables reliable identification of recurrent tumors.

A Brief History of Machine Learning in Neurosurgery

The history of machine learning in neurosurgery spans three decades and continues to develop at a rapid pace. The earliest applications of machine learning within neurosurgery were first published in the 1990s as researchers began developing artificial neural networks to analyze structured datasets and supervised tasks. By the turn of the millennium, machine learning had evolved beyond proof-of-concept; algorithms had success detecting tumors in unstructured clinical imaging, and unsupervised learning showed promise for tumor segmentation. Throughout the 2000s, the role of machine learning in neurosurgery was further refined. Well-trained models began to consistently best expert clinicians at brain tumor diagnosis. Additionally, the digitization of the healthcare industry provided ample data for analysis, both structured and unstructured. By the 2010s, the use of machine learning within neurosurgery had exploded. The rapid deployment of an exciting new toolset also led to the growing realization that it may offer marginal benefit at best over conventional logistical regression models for analyzing tabular datasets. Additionally, the widespread adoption of machine learning in neurosurgical clinical practice continues to lag until additional validation can ensure generalizability. Many exciting contemporary applications nonetheless continue to demonstrate the unprecedented potential of machine learning to revolutionize neurosurgery when applied to appropriate clinical challenges.

Applications of Radiomics and Radiogenomics in High-Grade Gliomas in the Era of Precision Medicine

Simple Summary

Radiomics and radiogenomics offer new insight into high-grade glioma biology, as well as into glioma behavior in response to standard therapies. In this article, we provide neuro-oncology, neuropathology, and computational perspectives on the role of radiomics in providing more accurate diagnoses, prognostication, and surveillance of patients with high-grade glioma, and on the potential application of radiomics in clinical practice, with the overarching goal of advancing precision medicine for optimal patient care.

Abstract

Machine learning (ML) integrated with medical imaging has introduced new perspectives in precision diagnostics of high-grade gliomas, through radiomics and radiogenomics. This has raised hopes for characterizing noninvasive and in vivo biomarkers for prediction of patient survival, tumor recurrence, and genomics and therefore encouraging treatments tailored to individualized needs. Characterization of tumor infiltration based on pre-operative multi-parametric magnetic resonance imaging (MP-MRI) scans may allow prediction of the loci of future tumor recurrence and thereby aid in planning the course of treatment for the patients, such as optimizing the extent of resection and the dose and target area of radiation. Imaging signatures of tumor genomics can help in identifying the patients who benefit from certain targeted therapies. Specifying molecular properties of gliomas and prediction of their changes over time and with treatment would allow optimization of treatment. In this article, we provide neuro-oncology, neuropathology, and computational perspectives on the promise of radiomics and radiogenomics for allowing personalized treatments of patients with gliomas and discuss the challenges and limitations of these methods in multi-institutional clinical trials and suggestions to mitigate the issues and the future directions.

Machine Learning in Oncology: What Should Clinicians Know?

The volume and complexity of scientific and clinical data in oncology have grown markedly over recent years, including but not limited to the realms of electronic health data, radiographic and histologic data, and genomics. This growth holds promise for a deeper understanding of malignancy and, accordingly, more personalized and effective oncologic care. Such goals require, however, the development of new methods to fully make use of the wealth of available data. Improvements in computer processing power and algorithm development have positioned machine learning, a branch of artificial intelligence, to play a prominent role in oncology research and practice. This review provides an overview of the basics of machine learning and highlights current progress and challenges in applying this technology to cancer diagnosis, prognosis, and treatment recommendations, including a discussion of current takeaways for clinicians.

Quantification of tumor microenvironment acidity in glioblastoma using principal component analysis of dynamic susceptibility contrast enhanced MR imaging

Glioblastoma (GBM) has high metabolic demands, which can lead to acidification of the tumor microenvironment. We hypothesize that a machine learning model built on temporal principal component analysis (PCA) of dynamic susceptibility contrast-enhanced (DSC) perfusion MRI can be used to estimate tumor acidity in GBM, as estimated by pH-sensitive amine chemical exchange saturation transfer echo-planar imaging (CEST-EPI). We analyzed 78 MRI scans in 32 treatment naïve and post-treatment GBM patients. All patients were imaged with DSC-MRI, and pH-weighting that was quantified from CEST-EPI estimation of the magnetization transfer ratio asymmetry (MTRasym) at 3 ppm. Enhancing tumor (ET), non-enhancing core (NC), and peritumoral T2 hyperintensity (namely, edema, ED) were used to extract principal components (PCs) and to build support vector machines regression (SVR) models to predict MTRasym values using PCs. Our predicted map correlated with MTRasym values with Spearman's r equal to 0.66, 0.47, 0.67, 0.71, in NC, ET, ED, and overall, respectively (p < 0.006). The results of this study demonstrates that PCA analysis of DSC imaging data can provide information about tumor pH in GBM patients, with the strongest association within the peritumoral regions.

Longitudinal structural and perfusion MRI enhanced by machine learning outperforms standalone modalities and radiological expertise in high-grade glioma surveillance

PURPOSE

Surveillance of patients with high-grade glioma (HGG) and identification of disease progression remain a major challenge in neurooncology. This study aimed to develop a support vector machine (SVM) classifier, employing combined longitudinal structural and perfusion MRI studies, to classify between stable disease, pseudoprogression and progressive disease (3-class problem).

METHODS

Study participants were separated into two groups: group I (total cohort: 64 patients) with a single DSC time point and group II (19 patients) with longitudinal DSC time points (2-3). We retrospectively analysed 269 structural MRI and 92 dynamic susceptibility contrast perfusion (DSC) MRI scans. The SVM classifier was trained using all available MRI studies for each group. Classification accuracy was assessed for different feature dataset and time point combinations and compared to radiologists' classifications.

RESULTS

SVM classification based on combined perfusion and structural features outperformed radiologists' classification across all groups. For the identification of progressive disease, use of combined features and longitudinal DSC time points improved classification performance (lowest error rate 1.6%). Optimal performance was observed in group II (multiple time points) with SVM sensitivity/specificity/accuracy of 100/91.67/94.7% (first time point analysis) and 85.71/100/94.7% (longitudinal analysis), compared to 60/78/68% and 70/90/84.2% for the respective radiologist classifications. In group I (single time point), the SVM classifier also outperformed radiologists' classifications with sensitivity/specificity/accuracy of 86.49/75.00/81.53% (SVM) compared to 75.7/68.9/73.84% (radiologists).

CONCLUSION

Our results indicate that utilisation of a machine learning (SVM) classifier based on analysis of longitudinal perfusion time points and combined structural and perfusion features significantly enhances classification outcome (p value= 0.0001).

Radiomic Analysis to Predict Outcome in Recurrent Glioblastoma Based on Multi-Center MR Imaging From the Prospective DIRECTOR Trial

Background

Based on promising results from radiomic approaches to predict O⁶-methylguanine DNA methyltransferase promoter methylation status (MGMT status) and clinical outcome in patients with newly diagnosed glioblastoma, the current study aimed to evaluate radiomics in recurrent glioblastoma patients.

Methods

Pre-treatment MR-imaging data of 69 patients enrolled into the DIRECTOR trial in recurrent glioblastoma served as a training cohort, and 49 independent patients formed an external validation cohort. Contrast-enhancing tumor and peritumoral volumes were segmented on MR images. 180 radiomic features were extracted after application of two MR intensity normalization techniques: fixed number of bins and linear rescaling. Radiomic feature selection was performed via principal component analysis, and multivariable models were trained to predict MGMT status, progression-free survival from first salvage therapy, referred to herein as PFS₂, and overall survival (OS). The prognostic power of models was quantified with concordance index (CI) for survival data and area under receiver operating characteristic curve (AUC) for the MGMT status.

Results

We established and validated a radiomic model to predict MGMT status using linear intensity interpolation and considering features extracted from gadolinium-enhanced T1-weighted MRI (training AUC = 0.670, validation AUC = 0.673). Additionally, models predicting PFS₂ and OS were found for the training cohort but were not confirmed in our validation cohort.

Conclusions

A radiomic model for prediction of MGMT promoter methylation status from tumor texture features in patients with recurrent glioblastoma was successfully established, providing a non-invasive approach to anticipate patient's response to chemotherapy if biopsy cannot be performed. The radiomic approach to predict PFS₂ and OS failed.

Analyzing magnetic resonance imaging data from glioma patients using deep learning

The quantitative analysis of images acquired in the diagnosis and treatment of patients with brain tumors has seen a significant rise in the clinical use of computational tools. The underlying technology to the vast majority of these tools are machine learning methods and, in particular, deep learning algorithms. This review offers clinical background information of key diagnostic biomarkers in the diagnosis of glioma, the most common primary brain tumor. It offers an overview of publicly available resources and datasets for developing new computational tools and image biomarkers, with emphasis on those related to the Multimodal Brain Tumor Segmentation (BraTS) Challenge. We further offer an overview of the state-of-the-art methods in glioma image segmentation, again with an emphasis on publicly available tools and deep learning algorithms that emerged in the context of the BraTS challenge.

Dynamic Susceptibility Perfusion Imaging for Differentiating Progressive Disease from Pseudoprogression in Diffuse Glioma Molecular Subtypes

Rationale and Objectives: Advanced adjuvant therapy of diffuse gliomas can result in equivocal findings in follow-up imaging. We aimed to assess the additional value of dynamic susceptibility perfusion imaging in the differentiation of progressive disease (PD) from pseudoprogression (PsP) in different molecular glioma subtypes. Materials and Methods: 89 patients with treated diffuse glioma with different molecular subtypes (IDH wild type (Astro-IDH^wt), IDH mutant astrocytomas (Astro-IDH^mut) and oligodendrogliomas), and tumor-suspect lesions on post-treatment follow-up imaging were classified into two outcome groups (PD or PsP) retrospectively by histopathology or clinical follow-up. The relative cerebral blood volume (rCBV) was assessed in the tumor-suspect FLAIR and contrast-enhancing (CE) lesions. We analyzed how a multilevel classification using a molecular subtype, the presence of a CE lesion, and two rCBV histogram parameters performed for PD prediction compared with a decision tree model (DTM) using additional rCBV parameters. Results: The PD rate was 69% in the whole cohort, 86% in Astro-IDH^wt, 52% in Astro-IDH^mut, and 55% in oligodendrogliomas. In the presence of a CE lesion, the PD rate was higher with 82%, 94%, 59%, and 88%, respectively; if there was no CE lesion, however, the PD rate was only 44%, 60%, 40%, and 33%, respectively. The additional use of the rCBV parameters in the DTM yielded a prediction accuracy for PD of 99%, 100%, 93%, and 95%, respectively. Conclusion: Utilizing combined information about the molecular tumor type, the presence or absence of CE lesions and rCBV parameters increases PD prediction accuracy in diffuse glioma.

Multi-institutional noninvasive in vivo characterization of IDH, 1p/19q, and EGFRvIII in glioma using neuro-Cancer Imaging Phenomics Toolkit (neuro-CaPTk)

Background

Gliomas represent a biologically heterogeneous group of primary brain tumors with uncontrolled cellular proliferation and diffuse infiltration that renders them almost incurable, thereby leading to a grim prognosis. Recent comprehensive genomic profiling has greatly elucidated the molecular hallmarks of gliomas, including the mutations in isocitrate dehydrogenase 1 and 2 (IDH1 and IDH2), loss of chromosomes 1p and 19q (1p/19q), and epidermal growth factor receptor variant III (EGFRvIII). Detection of these molecular alterations is based on ex vivo analysis of surgically resected tissue specimen that sometimes is not adequate for testing and/or does not capture the spatial tumor heterogeneity of the neoplasm.

Methods

We developed a method for noninvasive detection of radiogenomic markers of IDH both in lower-grade gliomas (WHO grade II and III tumors) and glioblastoma (WHO grade IV), 1p/19q in IDH-mutant lower-grade gliomas, and EGFRvIII in glioblastoma. Preoperative MRIs of 473 glioma patients from 3 of the studies participating in the ReSPOND consortium (collection I: Hospital of the University of Pennsylvania [HUP: n = 248], collection II: The Cancer Imaging Archive [TCIA; n = 192], and collection III: Ohio Brain Tumor Study [OBTS, n = 33]) were collected. Neuro-Cancer Imaging Phenomics Toolkit (neuro-CaPTk), a modular platform available for cancer imaging analytics and machine learning, was leveraged to extract histogram, shape, anatomical, and texture features from delineated tumor subregions and to integrate these features using support vector machine to generate models predictive of IDH, 1p/19q, and EGFRvIII. The models were validated using 3 configurations: (1) 70-30% training-testing splits or 10-fold cross-validation within individual collections, (2) 70-30% training-testing splits within merged collections, and (3) training on one collection and testing on another.

Results

These models achieved a classification accuracy of 86.74% (HUP), 85.45% (TCIA), and 75.15% (TCIA) in identifying EGFRvIII, IDH, and 1p/19q, respectively, in configuration I. The model, when applied on combined data in configuration II, yielded a classification success rate of 82.50% in predicting IDH mutation (HUP + TCIA + OBTS). The model when trained on TCIA dataset yielded classification accuracy of 84.88% in predicting IDH in HUP dataset.

Conclusions

Using machine learning algorithms, high accuracy was achieved in the prediction of IDH, 1p/19q, and EGFRvIII mutation. Neuro-CaPTk encompasses all the pipelines required to replicate these analyses in multi-institutional settings and could also be used for other radio(geno)mic analyses.

Association of plasma cell-free DNA with survival in patients with IDH wild-type glioblastoma

BACKGROUND

We aimed to determine whether plasma cell-free DNA (cfDNA) concentration is associated with survival in patients with isocitrate dehydrogenase (IDH) wild-type glioblastoma (GBM).

METHODS

Pre-operative and post-chemoradiotherapy blood samples were prospectively collected from patients with newly diagnosed IDH wild-type GBM. Patients underwent surgical resection or biopsy and received adjuvant radiotherapy with concomitant temozolomide. Cell-free DNA (cfDNA) was isolated from plasma and quantified using SYBR Green-based q polymerase chain reaction (qPCR).

RESULTS

Sixty-two patients were enrolled and categorized into high vs. low cfDNA groups relative to the pre-operative median value (25.2 ng/mL, range 5.7-153.0 ng/mL). High pre-operative cfDNA concentration was associated with inferior PFS (median progression-free survival (PFS), 3.4 vs. 7.7 months; log-rank P = .004; hazard ratio [HR], 2.19; 95% CI, 1.26-3.81) and overall survival (OS) (median OS, 8.0 vs. 13.9 months; log-rank P = .01; HR, 2.43; 95% CI, 1.19-4.95). After adjusting for risk factors, including O6-methylguanine-DNA methyltransferase (MGMT) promoter methylation status, pre-operative cfDNA remained independently associated with PFS (HR, 2.70; 95% CI, 1.50-4.83; P = .001) and OS (HR, 2.65; 95% CI, 1.25-5.59; P = .01). Post-hoc analysis of change in cfDNA post-chemoradiotherapy compared to pre-surgery (n = 24) showed increasing cfDNA concentration was associated with worse PFS (median, 2.7 vs. 6.0 months; log-rank P = .003; HR, 4.92; 95% CI, 1.53-15.84) and OS (median, 3.9 vs. 19.4 months; log-rank P < .001; HR, 7.77; 95% CI, 2.17-27.76).

CONCLUSIONS

cfDNA concentration is a promising prognostic biomarker for patients with IDH wild-type GBM. Plasma cfDNA can be obtained noninvasively and may enable more accurate estimates of survival and effective clinical trial stratification.

Introduction to radiomics and radiogenomics in neuro-oncology: implications and challenges

Neuro-oncology largely consists of malignancies of the brain and central nervous system including both primary as well as metastatic tumors. Currently, a significant clinical challenge in neuro-oncology is to tailor therapies for patients based on a priori knowledge of their survival outcome or treatment response to conventional or experimental therapies. Radiomics or the quantitative extraction of subvisual data from conventional radiographic imaging has recently emerged as a powerful data-driven approach to offer insights into clinically relevant questions related to diagnosis, prediction, prognosis, as well as assessing treatment response. Furthermore, radiogenomic approaches provide a mechanism to establish statistical correlations of radiomic features with point mutations and next-generation sequencing data to further leverage the potential of routine MRI scans to serve as "virtual biopsy" maps. In this review, we provide an introduction to radiomic and radiogenomic approaches in neuro-oncology, including a brief description of the workflow involving preprocessing, tumor segmentation, and extraction of "hand-crafted" features from the segmented region of interest, as well as identifying radiogenomic associations that could ultimately lead to the development of reliable prognostic and predictive models in neuro-oncology applications. Lastly, we discuss the promise of radiomics and radiogenomic approaches in personalizing treatment decisions in neuro-oncology, as well as the challenges with clinical adoption, which will rely heavily on their demonstrated resilience to nonstandardization in imaging protocols across sites and scanners, as well as in their ability to demonstrate reproducibility across large multi-institutional cohorts.