Deep learning for glioblastoma segmentation using preoperative magnetic resonance imaging identifies volumetric features associated with survival

Decoding Glioblastoma Heterogeneity: Neuroimaging Meets Machine Learning

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

Nomogram prediction of molecular characteristics in WHO grade 3-4 diffuse gliomas based on fractal analysis and VASARI features

Effective prediction of molecular features is crucial for the prognostic assessment of glioma patients. This study aims to develop a nomogram model using fractal analysis and Visually AcceSAble Rembrandt Images (VASARI) features to predict the molecular characteristics of WHO Grade 3-4 diffuse gliomas. Retrospective analysis of clinical data and VASARI features of patients with WHO grade 3-4 diffuse gliomas confirmed by pathology between January 2020 and December 2023 at our institution. Preoperative T1-weighted contrast-enhanced and T2-weighted images were used to delineate the tumor and surrounding edema regions on 3D-Slicer. Fractal dimension (FD) and lacunarity of both the tumor and surrounding edema were extracted using ImageJ software. Univariate and multivariate logistic regression analyses were performed to identify independent predictive factors for the Ki_67 proliferation index (PI), p53, and telomerase reverse transcriptase promoter (TERTp) mutations. Based on these findings, a nomogram prediction model was constructed. Model performance was comprehensively assessed using the receiver operating characteristic curve (ROC), calibration curve (CRC), and decision curve analysis (DCA). Sex, Proportion Enhancing, and Pial invasion were identified as independent predictive factors for the Ki_67 PI. FD of the tumor (FD(T)) was an independent predictor for p53 expression. FD(T), Enhancement Quality, and Definition of the enhancing margin were independent predictors for TERTp mutations. The areas under the ROC for each nomogram model were 0.791, 0.739, and 0.601, respectively. Sensitivities were 68.75%, 78.12%, and 51.43%, and specificities were 81.03%, 64.86%, and 71.00%, respectively. CRC showed a high degree of concordance between predicted probabilities and actual observed values, while DCA demonstrated favorable net benefits for all models. VASARI features and fractal analysis effectively predict the Ki_67 PI, p53, and TERTp mutations in WHO grade 3-4 diffuse gliomas. Furthermore, combining these two approaches enhances the predictive performance for TERTp mutations.

Enhancement of the nontumor component in newly diagnosed glioblastoma as a more accurate predictor of local recurrence location: a multicenter study

Background

Although the spatial heterogeneity of glioblastoma (GBM) can be clearly mapped by the habitats generated by magnetic resonance imaging (MRI), the means to accurately predicting the spatial location of local recurrence (SLLR) remains a significant challenge. The aim of this study was to identify the different degrees enhancement of GBM, including the nontumor component and tumor component, and determine their relationship with SLLR.

Methods

A retrospective analysis was performed from three tertiary medical centers, totaling 728 patients with 109 radiation-induced temporal lobe necrosis (TLN) of nasopharyngeal carcinoma (NPC) and 619 with GBM. The spatial location of nontumor component enhancement (SLNTE) and the spatial location of tumor component enhancement (SLTE) for the preoperative images of patients with GBM were identified using TLN as the nontumor component reference by clustering analysis, and then their relationship with the SLLR was analyzed. Decision tree models of 10-fold cross-validation based on SLNTE and SLTE built to predict the SLLR. The area under the curve (AUC) was used to evaluate the predictive efficacy of these models.

Results

The SLNTE had a stronger spatial relationship with SLLR than did SLTE (χ2=4.77; P=0.029). In data set 3, both the SLNTE and SLTE were associated with the SLLR (rSLNTE=0.70, P<0.001; rSLTE=0.34, P=0.005). In data set 4, the SLLR was correlated with SLNTE but not with SLTE (rSLNTE=0.59, P=0.029; rSLTE=0.20, P=0.50). In data sets 3 and 4, the SLNTE-based decision tree models predicted the SLLR with 81% and 79% accuracy, respectively, and the AUC values were greater than 0.80 and 0.75, respectively. Meanwhile, the SLTE-based decision tree models predicted the SLLR with 72% and 50% accuracy, respectively, with AUC values of 0.70 and 0.60, respectively.

Conclusions

Radiation-induced TLN of NPC is a highly effective reference indicator for detecting nontumor components. The tumor periphery adjacent to the nontumor component enhancement of GBM may be associated with a higher risk of local recurrence, which may provide a more accurate imaging basis for performing supertotal resection.

VASARI-auto: Equitable, efficient, and economical featurisation of glioma MRI

The VASARI MRI feature set is a quantitative system designed to standardise glioma imaging descriptions. Though effective, deriving VASARI is time-consuming and seldom used clinically. We sought to resolve this problem with software automation and machine learning. Using glioma data from 1172 patients, we developed VASARI-auto, an automated labelling software applied to open-source lesion masks and an openly available tumour segmentation model. Consultant neuroradiologists independently quantified VASARI features in 100 held-out glioblastoma cases. We quantified 1) agreement across neuroradiologists and VASARI-auto, 2) software equity, 3) an economic workforce analysis, and 4) fidelity in predicting survival. Tumour segmentation was compatible with the current state of the art and equally performant regardless of age or sex. A modest inter-rater variability between in-house neuroradiologists was comparable to between neuroradiologists and VASARI-auto, with far higher agreement between VASARI-auto methods. The time for neuroradiologists to derive VASARI was substantially higher than VASARI-auto (mean time per case 317 vs. 3 s). A UK hospital workforce analysis forecast that three years of VASARI featurisation would demand 29,777 consultant neuroradiologist workforce hours and >£1.5 ($1.9) million, reducible to 332 hours of computing time (and £146 of power) with VASARI-auto. The best-performing survival model utilised VASARI-auto features instead of those derived by neuroradiologists. VASARI-auto is a highly efficient and equitable automated labelling system, a favourable economic profile if used as a decision support tool, and non-inferior survival prediction. Future work should iterate upon and integrate such tools to enhance patient care.

Automated volumetry of meningiomas in contrast-enhanced T1-Weighted MRI using deep learning

BACKGROUND

Meningiomas are among the most common intracranial tumors. In these tumors, volumetric assessment is not only important for planning therapeutic intervention but also for follow-up examination.However, a highly accurate automated volumetric method for meningiomas using single-modality magnetic resonance imaging (MRI) has not yet been reported. Here, we aimed to develop a deep learning-based automated volumetry method for meningiomas in MRI and investigate its accuracy and potential clinical applications.

METHODS

For deep learning, we used MRI images of patients with meningioma who were referred to Osaka University Hospital between January 2007 and October 2020. Imaging data of eligible patients were divided into three non-overlapping groups: training, validation, and testing. The model was trained and tested using the leave-oneout cross-validation method. Dice index (DI) and root mean squared percentage error (RMSPE) were measured to evaluate the model accuracy. Result: A total of 178 patients (64.6 ± 12.3 years [standard deviation]; 147 women) were evaluated. Comparison of the deep learning model and manual segmentation revealed a mean DI of 0.923 ± 0.051 for tumor lesions. For total tumor volume, RMSPE was 9.5 ± 1.2%, and Mann-Whitney U test did not show a significant difference between manual and algorithm-based measurement of the tumor volume (p = 0.96).

CONCLUSION

The automatic tumor volumetry algorithm developed in this study provides a potential volume-based imaging biomarker for tumor evaluation in the field of neuroradiological imaging, which will contribute to the optimization and personalization of treatment for central nervous system tumors in the near future.

Marker-controlled watershed algorithm and fuzzy C-means clustering machine learning: automated segmentation of glioblastoma from MRI images in a case series

INTRODUCTION AND IMPORTANCE

Automated segmentation of glioblastoma multiforme (GBM) from MRI images is crucial for accurate diagnosis and treatment planning. This paper presents a new and innovative approach for automating the segmentation of GBM from MRI images using the marker-controlled watershed segmentation (MCWS) algorithm.

CASE PRESENTATION AND METHODS

The technique involves several image processing techniques, including adaptive thresholding, morphological filtering, gradient magnitude calculation, and regional maxima identification. The MCWS algorithm efficiently segments images based on local intensity structures using the watershed transform, and fuzzy c-means (FCM) clustering improves segmentation accuracy. The presented approach achieved improved segmentation accuracy in detecting and segmenting GBM tumours from axial T2-weighted (T2-w) MRI images, as demonstrated by the mean characteristics performance metrics for GBM segmentation (sensitivity: 0.9905, specificity: 0.9483, accuracy: 0.9508, precision: 0.5481, F_measure: 0.7052, and jaccard: 0.9340).

CLINICAL DISCUSSION

The results of this study underline the importance of reliable and accurate image segmentation for effective diagnosis and treatment planning of GBM tumours.

CONCLUSION

The MCWS technique provides an effective and efficient approach for the segmentation of challenging medical images.

Convolutional Neural Networks for Glioma Segmentation and Prognosis: A Systematic Review

Deep learning (DL) is poised to redefine the way medical images are processed and analyzed. Convolutional neural networks (CNNs), a specific type of DL architecture, are exceptional for high-throughput processing, allowing for the effective extraction of relevant diagnostic patterns from large volumes of complex visual data. This technology has garnered substantial interest in the field of neuro-oncology as a promising tool to enhance medical imaging throughput and analysis. A multitude of methods harnessing MRI-based CNNs have been proposed for brain tumor segmentation, classification, and prognosis prediction. They are often applied to gliomas, the most common primary brain cancer, to classify subtypes with the goal of guiding therapy decisions. Additionally, the difficulty of repeating brain biopsies to evaluate treatment response in the setting of often confusing imaging findings provides a unique niche for CNNs to help distinguish the treatment response to gliomas. For example, glioblastoma, the most aggressive type of brain cancer, can grow due to poor treatment response, can appear to grow acutely due to treatment-related inflammation as the tumor dies (pseudo-progression), or falsely appear to be regrowing after treatment as a result of brain damage from radiation (radiation necrosis). CNNs are being applied to separate this diagnostic dilemma. This review provides a detailed synthesis of recent DL methods and applications for intratumor segmentation, glioma classification, and prognosis prediction. Furthermore, this review discusses the future direction of MRI-based CNN in the field of neuro-oncology and challenges in model interpretability, data availability, and computation efficiency.

Assessment of Ki-67 expression levels in IDH-wildtype glioblastoma using logistic regression modelling of VASARI features

To investigate the value of using VASARI signs preoperatively to assess Ki-67 proliferation index levels in patients with IDH-wildtype glioblastoma (GB).Pathological and imaging data of 154 patients with GB confirmed by surgical pathology were retrospectively analysed, and the level of Ki-67 proliferative index was assessed in tumour tissue samples from patients using immunohistochemistry (IHC) staining. Patients were divided into a high and low Ki-67 proliferation index expression group. Two radiologists analysed MRI images of patients with IDH-wildtype GB using the VASARI features system. VASARI parameters between the two groups were statistically analysed to identify characteristic parameters with significant differences and their predictive performance was determined using ROC curves.Among the obtained clinical and VASARI features of IDH-wildtype GB patients, the distribution of Maximum diameter, Proportion of necrosis and Hemorrhage was significantly different between the two groups (all p < 0.05). Multivariate logistic regression analysis showed that Maximum diameter and Hemorrhage were independent risk factors distinguishing the group with high and low expression of Ki-67 proliferative index. ROC curve analysis showed that the logistic regression model achieved an AUC value of 0.730 (95% CI: 0.639, 0.822), sensitivity of 0.628 and specificity of 0.756.Logistic regression modelling of preoperative VASARI features can be used as a reliable tool for predicting the level of Ki-67 proliferative index in IDH-wildtype GB patients, which can help in preoperative development of treatment and follow-up strategies for 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.

Interpreting deep learning models for glioma survival classification using visualization and textual explanations

BACKGROUND

Saliency-based algorithms are able to explain the relationship between input image pixels and deep-learning model predictions. However, it may be difficult to assess the clinical value of the most important image features and the model predictions derived from the raw saliency map. This study proposes to enhance the interpretability of saliency-based deep learning model for survival classification of patients with gliomas, by extracting domain knowledge-based information from the raw saliency maps.

MATERIALS AND METHODS

Our study includes presurgical T1-weighted (pre- and post-contrast), T2-weighted and T2-FLAIR MRIs of 147 glioma patients from the BraTs 2020 challenge dataset aligned to the SRI 24 anatomical atlas. Each image exam includes a segmentation mask and the information of overall survival (OS) from time of diagnosis (in days). This dataset was divided into training ([Formula: see text]) and validation ([Formula: see text]) datasets. The extent of surgical resection for all patients was gross total resection. We categorized the data into 42 short (mean [Formula: see text] days), 30 medium ([Formula: see text] days), and 46 long ([Formula: see text] days) survivors. A 3D convolutional neural network (CNN) trained on brain tumour MRI volumes classified all patients based on expected prognosis of either short-term, medium-term, or long-term survival. We extend the popular 2D Gradient-weighted Class Activation Mapping (Grad-CAM), for the generation of saliency map, to 3D and combined it with the anatomical atlas, to extract brain regions, brain volume and probability map that reveal domain knowledge-based information.

RESULTS

For each OS class, a larger tumor volume was associated with a shorter OS. There were 10, 7 and 27 tumor locations in brain regions that uniquely associate with the short-term, medium-term, and long-term survival, respectively. Tumors located in the transverse temporal gyrus, fusiform, and palladium are associated with short, medium and long-term survival, respectively. The visual and textual information displayed during OS prediction highlights tumor location and the contribution of different brain regions to the prediction of OS. This algorithm design feature assists the physician in analyzing and understanding different model prediction stages.

CONCLUSIONS

Domain knowledge-based information extracted from the saliency map can enhance the interpretability of deep learning models. Our findings show that tumors overlapping eloquent brain regions are associated with short patient survival.

Integrative Imaging Informatics for Cancer Research: Workflow Automation for Neuro-Oncology (I3CR-WANO)

PURPOSE

Efforts to use growing volumes of clinical imaging data to generate tumor evaluations continue to require significant manual data wrangling, owing to data heterogeneity. Here, we propose an artificial intelligence-based solution for the aggregation and processing of multisequence neuro-oncology MRI data to extract quantitative tumor measurements.

MATERIALS AND METHODS

Our end-to-end framework (1) classifies MRI sequences using an ensemble classifier, (2) preprocesses the data in a reproducible manner, (3) delineates tumor tissue subtypes using convolutional neural networks, and (4) extracts diverse radiomic features. Moreover, it is robust to missing sequences and adopts an expert-in-the-loop approach in which the segmentation results may be manually refined by radiologists. After the implementation of the framework in Docker containers, it was applied to two retrospective glioma data sets collected from the Washington University School of Medicine (WUSM; n = 384) and The University of Texas MD Anderson Cancer Center (MDA; n = 30), comprising preoperative MRI scans from patients with pathologically confirmed gliomas.

RESULTS

The scan-type classifier yielded an accuracy of >99%, correctly identifying sequences from 380 of 384 and 30 of 30 sessions from the WUSM and MDA data sets, respectively. Segmentation performance was quantified using the Dice Similarity Coefficient between the predicted and expert-refined tumor masks. The mean Dice scores were 0.882 (±0.244) and 0.977 (±0.04) for whole-tumor segmentation for WUSM and MDA, respectively.

CONCLUSION

This streamlined framework automatically curated, processed, and segmented raw MRI data of patients with varying grades of gliomas, enabling the curation of large-scale neuro-oncology data sets and demonstrating high potential for integration as an assistive tool in clinical practice.

Deep learning for rare disease: A scoping review

Although individually rare, collectively more than 7,000 rare diseases affect about 10% of patients. Each of the rare diseases impacts the quality of life for patients and their families, and incurs significant societal costs. The low prevalence of each rare disease causes formidable challenges in accurately diagnosing and caring for these patients and engaging participants in research to advance treatments. Deep learning has advanced many scientific fields and has been applied to many healthcare tasks. This study reviewed the current uses of deep learning to advance rare disease research. Among the 332 reviewed articles, we found that deep learning has been actively used for rare neoplastic diseases (250/332), followed by rare genetic diseases (170/332) and rare neurological diseases (127/332). Convolutional neural networks (307/332) were the most frequently used deep learning architecture, presumably because image data were the most commonly available data type in rare disease research. Diagnosis is the main focus of rare disease research using deep learning (263/332). We summarized the challenges and future research directions for leveraging deep learning to advance rare disease research.

Predicting Survival in Patients with Brain Tumors: Current State-of-the-Art of AI Methods Applied to MRI

Given growing clinical needs, in recent years Artificial Intelligence (AI) techniques have increasingly been used to define the best approaches for survival assessment and prediction in patients with brain tumors. Advances in computational resources, and the collection of (mainly) public databases, have promoted this rapid development. This narrative review of the current state-of-the-art aimed to survey current applications of AI in predicting survival in patients with brain tumors, with a focus on Magnetic Resonance Imaging (MRI). An extensive search was performed on PubMed and Google Scholar using a Boolean research query based on MeSH terms and restricting the search to the period between 2012 and 2022. Fifty studies were selected, mainly based on Machine Learning (ML), Deep Learning (DL), radiomics-based methods, and methods that exploit traditional imaging techniques for survival assessment. In addition, we focused on two distinct tasks related to survival assessment: the first on the classification of subjects into survival classes (short and long-term or eventually short, mid and long-term) to stratify patients in distinct groups. The second focused on quantification, in days or months, of the individual survival interval. Our survey showed excellent state-of-the-art methods for the first, with accuracy up to ∼98%. The latter task appears to be the most challenging, but state-of-the-art techniques showed promising results, albeit with limitations, with C-Index up to ∼0.91. In conclusion, according to the specific task, the available computational methods perform differently, and the choice of the best one to use is non-univocal and dependent on many aspects. Unequivocally, the use of features derived from quantitative imaging has been shown to be advantageous for AI applications, including survival prediction. This evidence from the literature motivates further research in the field of AI-powered methods for survival prediction in patients with brain tumors, in particular, using the wealth of information provided by quantitative MRI techniques.

Magnetic resonance image-based brain tumour segmentation methods: A systematic review

Background

Image segmentation is an essential step in the analysis and subsequent characterisation of brain tumours through magnetic resonance imaging. In the literature, segmentation methods are empowered by open-access magnetic resonance imaging datasets, such as the brain tumour segmentation dataset. Moreover, with the increased use of artificial intelligence methods in medical imaging, access to larger data repositories has become vital in method development.

Purpose

To determine what automated brain tumour segmentation techniques can medical imaging specialists and clinicians use to identify tumour components, compared to manual segmentation.

Methods

We conducted a systematic review of 572 brain tumour segmentation studies during 2015-2020. We reviewed segmentation techniques using T1-weighted, T2-weighted, gadolinium-enhanced T1-weighted, fluid-attenuated inversion recovery, diffusion-weighted and perfusion-weighted magnetic resonance imaging sequences. Moreover, we assessed physics or mathematics-based methods, deep learning methods, and software-based or semi-automatic methods, as applied to magnetic resonance imaging techniques. Particularly, we synthesised each method as per the utilised magnetic resonance imaging sequences, study population, technical approach (such as deep learning) and performance score measures (such as Dice score).

Statistical tests

We compared median Dice score in segmenting the whole tumour, tumour core and enhanced tumour.

Results

We found that T1-weighted, gadolinium-enhanced T1-weighted, T2-weighted and fluid-attenuated inversion recovery magnetic resonance imaging are used the most in various segmentation algorithms. However, there is limited use of perfusion-weighted and diffusion-weighted magnetic resonance imaging. Moreover, we found that the U-Net deep learning technology is cited the most, and has high accuracy (Dice score 0.9) for magnetic resonance imaging-based brain tumour segmentation.

Conclusion

U-Net is a promising deep learning technology for magnetic resonance imaging-based brain tumour segmentation. The community should be encouraged to contribute open-access datasets so training, testing and validation of deep learning algorithms can be improved, particularly for diffusion- and perfusion-weighted magnetic resonance imaging, where there are limited datasets available.

Effects of Multi-Shell Free Water Correction on Glioma Characterization

Diffusion MRI is a useful tool to investigate the microstructure of brain tumors. However, the presence of fast diffusing isotropic signals originating from non-restricted edematous fluids, within and surrounding tumors, may obscure estimation of the underlying tissue characteristics, complicating the radiological interpretation and quantitative evaluation of diffusion MRI. A multi-shell regularized free water (FW) elimination model was therefore applied to separate free water from tissue-related diffusion components from the diffusion MRI of 26 treatment-naïve glioma patients. We then investigated the diagnostic value of the derived measures of FW maps as well as FW-corrected tensor-derived maps of fractional anisotropy (FA). Presumed necrotic tumor regions display greater mean and variance of FW content than other parts of the tumor. On average, the area under the receiver operating characteristic (ROC) for the classification of necrotic and enhancing tumor volumes increased by 5% in corrected data compared to non-corrected data. FW elimination shifts the FA distribution in non-enhancing tumor parts toward higher values and significantly increases its entropy (p ≤ 0.003), whereas skewness is decreased (p ≤ 0.004). Kurtosis is significantly decreased (p < 0.001) in high-grade tumors. In conclusion, eliminating FW contributions improved quantitative estimations of FA, which helps to disentangle the cancer heterogeneity.