Automatic multi-modal MR tissue classification for the assessment of response to bevacizumab in patients with glioblastoma

Automatic Brain Tissue and Lesion Segmentation and Multi-Parametric Mapping of Contrast-Enhancing Gliomas without the Injection of Contrast Agents: A Preliminary Study

This study aimed to develop a rapid, 1 mm3 isotropic resolution, whole-brain MRI technique for automatic lesion segmentation and multi-parametric mapping without using contrast by continuously applying balanced steady-state free precession with inversion pulses throughout incomplete inversion recovery in a single 6 min scan. Modified k-means clustering was performed for automatic brain tissue and lesion segmentation using distinct signal evolutions that contained mixed T1/T2/magnetization transfer properties. Multi-compartment modeling was used to derive quantitative multi-parametric maps for tissue characterization. Fourteen patients with contrast-enhancing gliomas were scanned with this sequence prior to the injection of a contrast agent, and their segmented lesions were compared to conventionally defined manual segmentations of T2-hyperintense and contrast-enhancing lesions. Simultaneous T1, T2, and macromolecular proton fraction maps were generated and compared to conventional 2D T1 and T2 mapping and myelination water fraction mapping acquired with MAGiC. The lesion volumes defined with the new method were comparable to the manual segmentations (r = 0.70, p < 0.01; t-test p > 0.05). The T1, T2, and macromolecular proton fraction mapping values of the whole brain were comparable to the reference values and could distinguish different brain tissues and lesion types (p < 0.05), including infiltrating tumor regions within the T2-lesion. Highly efficient, whole-brain, multi-contrast imaging facilitated automatic lesion segmentation and quantitative multi-parametric mapping without contrast, highlighting its potential value in the clinic when gadolinium is contraindicated.

Computer especially AI-assisted drug virtual screening and design in traditional Chinese medicine

BACKGROUND

Traditional Chinese medicine (TCM), as a significant part of the global pharmaceutical science, the abundant molecular compounds it contains is a valuable potential source of designing and screening new drugs. However, due to the un-estimated quantity of the natural molecular compounds and diversity of the related problems drug discovery such as precise screening of molecular compounds or the evaluation of efficacy, physicochemical properties and pharmacokinetics, it is arduous for researchers to design or screen applicable compounds through old methods. With the rapid development of computer technology recently, especially artificial intelligence (AI), its innovation in the field of virtual screening contributes to an increasing efficiency and accuracy in the process of discovering new drugs.

PURPOSE

This study systematically reviewed the application of computational approaches and artificial intelligence in drug virtual filtering and devising of TCM and presented the potential perspective of computer-aided TCM development.

STUDY DESIGN

We made a systematic review following the Preferred Reporting Items for Systematic Reviews and Meta-Analyses (PRISMA) guidelines. Then screening the most typical articles for our research.

METHODS

The systematic review was performed by following the PRISMA guidelines. The databases PubMed, EMBASE, Web of Science, CNKI were used to search for publications that focused on computer-aided drug virtual screening and design in TCM.

RESULT

Totally, 42 corresponding articles were included in literature reviewing. Aforementioned studies were of great significance to the treatment and cost control of many challenging diseases such as COVID-19, diabetes, Alzheimer's Disease (AD), etc. Computational approaches and AI were widely used in virtual screening in the process of TCM advancing, which include structure-based virtual screening (SBVS) and ligand-based virtual screening (LBVS). Besides, computational technologies were also extensively applied in absorption, distribution, metabolism, excretion and toxicity (ADMET) prediction of candidate drugs and new drug design in crucial course of drug discovery.

CONCLUSIONS

The applications of computer and AI play an important role in the drug virtual screening and design in the field of TCM, with huge application prospects.

Trends in DNN Model Based Classification and Segmentation of Brain Tumor Detection

Background:

Due to the complexities of scrutinizing and diagnosing brain tumors from MR images, brain tumor analysis has become one of the most indispensable concerns. Characterization of a brain tumor before any treatment, such as radiotherapy, requires decisive treatment planning and accurate implementation. As a result, early detection of brain tumors is imperative for better clinical outcomes and subsequent patient survival.

Introduction:

Brain tumor segmentation is a crucial task in medical image analysis. Because of tumor heterogeneity and varied intensity patterns, manual segmentation takes a long time, limiting the use of accurate quantitative interventions in clinical practice. Automated computer-based brain tumor image processing has become more valuable with technological advancement. With various imaging and statistical analysis tools, deep learning algorithms offer a viable option to enable health care practitioners to rule out the disease and estimate the growth.

Methods:

This article presents a comprehensive evaluation of conventional machine learning models as well as evolving deep learning techniques for brain tumor segmentation and classification.

Conclusion:

In this manuscript, a hierarchical review has been presented for brain tumor segmentation and detection. It is found that the segmentation methods hold a wide margin of improvement in the context of the implementation of adaptive thresholding and segmentation methods, the feature training and mapping requires redundancy correction, the input data training needs to be more exhaustive and the detection algorithms are required to be robust in terms of handling online input data analysis/tumor detection.

Development and Validation of a Deep Learning Model for Brain Tumor Diagnosis and Classification Using Magnetic Resonance Imaging

IMPORTANCE

Deep learning may be able to use patient magnetic resonance imaging (MRI) data to aid in brain tumor classification and diagnosis.

OBJECTIVE

To develop and clinically validate a deep learning system for automated identification and classification of 18 types of brain tumors from patient MRI data.

DESIGN, SETTING, AND PARTICIPANTS

This diagnostic study was conducted using MRI data collected between 2000 and 2019 from 37 871 patients. A deep learning system for segmentation and classification of 18 types of intracranial tumors based on T1- and T2-weighted images and T2 contrast MRI sequences was developed and tested. The diagnostic accuracy of the system was tested using 1 internal and 3 external independent data sets. The clinical value of the system was assessed by comparing the tumor diagnostic accuracy of neuroradiologists with vs without assistance of the proposed system using a separate internal test data set. Data were analyzed from March 2019 through February 2020.

MAIN OUTCOMES AND MEASURES

Changes in neuroradiologist clinical diagnostic accuracy in brain MRI scans with vs without the deep learning system were evaluated.

RESULTS

A deep learning system was trained among 37 871 patients (mean [SD] age, 41.6 [11.4] years; 18 519 women [48.9%]). It achieved a mean area under the receiver operating characteristic curve of 0.92 (95% CI, 0.84-0.99) on 1339 patients from 4 centers' data sets in diagnosis and classification of 18 types of tumors. Higher outcomes were found compared with neuroradiologists for accuracy and sensitivity and similar outcomes for specificity (for 300 patients in the Tiantan Hospital test data set: accuracy, 73.3% [95% CI, 67.7%-77.7%] vs 60.9% [95% CI, 46.8%-75.1%]; sensitivity, 88.9% [95% CI, 85.3%-92.4%] vs 53.4% [95% CI, 41.8%-64.9%]; and specificity, 96.3% [95% CI, 94.2%-98.4%] vs 97.9%; [95% CI, 97.3%-98.5%]). With the assistance of the deep learning system, the mean accuracy of neuroradiologists among 1166 patients increased by 12.0 percentage points, from 63.5% (95% CI, 60.7%-66.2%) without assistance to 75.5% (95% CI, 73.0%-77.9%) with assistance.

CONCLUSIONS AND RELEVANCE

These findings suggest that deep learning system-based automated diagnosis may be associated with improved classification and diagnosis of intracranial tumors from MRI data among neuroradiologists.

Performance optimisation of deep learning models using majority voting algorithm for brain tumour classification

BACKGROUND

Although biopsy is the gold standard for tumour grading, being invasive, this procedure also proves fatal to the brain. Thus, non-invasive methods for brain tumour grading are urgently needed. Here, a magnetic resonance imaging (MRI)-based non-invasive brain tumour grading method has been proposed using deep learning (DL) and machine learning (ML) techniques.

METHOD

Four clinically applicable datasets were designed. The four datasets were trained and tested on five DL-based models (convolutional neural networks), AlexNet, VGG16, ResNet18, GoogleNet, and ResNet50, and five ML-based models, Support Vector Machine, K-Nearest Neighbours, Naïve Bayes, Decision Tree, and Linear Discrimination using five-fold cross-validation. A majority voting (MajVot)-based ensemble algorithm has been proposed to optimise the overall classification performance of five DL and five ML-based models.

RESULTS

The average accuracy improvement of four datasets using the DL-based MajVot algorithm against AlexNet, VGG16, ResNet18, GoogleNet, and ResNet50 models was 2.02%, 1.11%, 1.04%, 2.67%, and 1.65%, respectively. Further, a 10.12% improvement was seen in the average accuracy of four datasets using the DL method against ML. Furthermore, the proposed DL-based MajVot algorithm was validated on synthetic face data and improved the male versus female face image classification accuracy by 2.88%, 0.71%, 1.90%, 2.24%, and 0.35% against AlexNet, VGG16, ResNet18, GoogleNet, and ResNet50, respectively.

CONCLUSION

The proposed MajVot algorithm achieved promising results for brain tumour classification and is able to utilise the combined potential of multiple models.

Automatic brain lesion segmentation on standard magnetic resonance images: a scoping review

OBJECTIVES

Medical image analysis practices face challenges that can potentially be addressed with algorithm-based segmentation tools. In this study, we map the field of automatic MR brain lesion segmentation to understand the clinical applicability of prevalent methods and study designs, as well as challenges and limitations in the field.

DESIGN

Scoping review.

SETTING

Three databases (PubMed, IEEE Xplore and Scopus) were searched with tailored queries. Studies were included based on predefined criteria. Emerging themes during consecutive title, abstract, methods and whole-text screening were identified. The full-text analysis focused on materials, preprocessing, performance evaluation and comparison.

RESULTS

Out of 2990 unique articles identified through the search, 441 articles met the eligibility criteria, with an estimated growth rate of 10% per year. We present a general overview and trends in the field with regard to publication sources, segmentation principles used and types of lesions. Algorithms are predominantly evaluated by measuring the agreement of segmentation results with a trusted reference. Few articles describe measures of clinical validity.

CONCLUSIONS

The observed reporting practices leave room for improvement with a view to studying replication, method comparison and clinical applicability. To promote this improvement, we propose a list of recommendations for future studies in the field.

Multi-parametric MR Imaging Biomarkers Associated to Clinical Outcomes in Gliomas: A Systematic Review

PURPOSE

To systematically review evidence regarding the association of multiparametric biomarkers with clinical outcomes and their capacity to explain relevant subcompartments of gliomas.

MATERIALS AND METHODS

Scopus database was searched for original journal papers from January 1st, 2007 to February 20th, 2017 according to PRISMA. Four hundred forty-nine abstracts of papers were reviewed and scored independently by two out of six authors. Based on those papers we analyzed associations between biomarkers, subcompartments within the tumor lesion, and clinical outcomes. From all the articles analyzed, the twenty-seven papers with the highest scores were highlighted to represent the evidence about MR imaging biomarkers associated with clinical outcomes. Similarly, eighteen studies defining subcompartments within the tumor region were also highlighted to represent the evidence of MR imaging biomarkers. Their reports were critically appraised according to the QUADAS-2 criteria.

RESULTS

It has been demonstrated that multi-parametric biomarkers are prepared for surrogating diagnosis, grading, segmentation, overall survival, progression-free survival, recurrence, molecular profiling and response to treatment in gliomas. Quantifications and radiomics features obtained from morphological exams (T1, T2, FLAIR, T1c), PWI (including DSC and DCE), diffusion (DWI, DTI) and chemical shift imaging (CSI) are the preferred MR biomarkers associated to clinical outcomes. Subcompartments relative to the peritumoral region, invasion, infiltration, proliferation, mass effect and pseudo flush, relapse compartments, gross tumor volumes, and highrisk regions have been defined to characterize the heterogeneity. For the majority of pairwise cooccurrences, we found no evidence to assert that observed co-occurrences were significantly different from their expected co-occurrences (Binomial test with False Discovery Rate correction, α=0.05). The co-occurrence among terms in the studied papers was found to be driven by their individual prevalence and trends in the literature.

CONCLUSION

Combinations of MR imaging biomarkers from morphological, PWI, DWI and CSI exams have demonstrated their capability to predict clinical outcomes in different management moments of gliomas. Whereas morphologic-derived compartments have been mostly studied during the last ten years, new multi-parametric MRI approaches have also been proposed to discover specific subcompartments of the tumors. MR biomarkers from those subcompartments show the local behavior within the heterogeneous tumor and may quantify the prognosis and response to treatment of gliomas.

Differentiation between vasogenic edema and infiltrative tumor in patients with high-grade gliomas using texture patch-based analysis

BACKGROUND

High-grade gliomas (HGGs) induce both vasogenic edema and extensive infiltration of tumor cells, both of which present with similar appearance on conventional MRI. Using current radiological criteria, differentiation between these tumoral and nontumoral areas within the nonenhancing lesion area remains challenging.

PURPOSE

To use radiomics patch-based analysis, based on conventional MRI, for the classification of the nonenhancing lesion area in patients with HGG into tumoral and nontumoral components.

STUDY TYPE

Prospective.

SUBJECTS

In all, 179 MRI scans were obtained from 102 patients: 67 patients with HGG and 35 patients with brain metastases. A subgroup of 15 patients with HGG were scanned before and following administration of bevacizumab.

FIELD STRENGTH/SEQUENCE

Pre and postcontrast agent T1 -weighted-imaging (WI), T2 WI, FLAIR, diffusion-tensor-imaging (DTI), and dynamic-contrast-enhanced (DCE)-MRI at 3T.

ASSESSMENT

A total of 225 histograms and gray-level-co-occurrence matrix-based features were extracted from the nonenhancing lesion area. Tumoral volumes of interest (VOIs) were defined at the peritumoral area in patients with HGG; nontumoral VOIs were defined in patients with brain metastasis. Twenty machine-learning algorithms including support-vector-machine (SVM), k-nearest neighbor, decision-trees, and ensemble classifiers were tested. The best classifier was trained on the entire labeled data, and was used to classify the entire data.

STATISTICAL TESTS

Dimensional reduction was performed on the 225 features using principal component analysis. Classification results were evaluated based on the sensitivity, specificity, and accuracy of each of the 20 classifiers, first based on a training and testing dataset (80% of the labeled data) in a 5-fold manner, and next by applying the best classifier to the validation data (the remaining 20% of the labeled data). Results were additionally evaluated by assessing differences in dynamic-contrast-enhanced plasma-volume (vp ) and volume-transfer-constant (ktrans ) values between the two components using Mann-Whitney U-test/t-test.

RESULTS

The best classification into tumoral and nontumoral lesion components was obtained using a linear SVM classifier, with average accuracy of 87%, sensitivity 86%, and specificity of 89% (for the training and testing data). Significantly higher vp and ktrans values (P < 0.0001) were detected in the tumoral compared to the nontumoral component. Preliminary classification results in a subgroup of patients treated with bevacizumab demonstrated a reduction mainly in the nontumoral component following administration of bevacizumab, enabling early assessment of disease progression in some patients.

DATA CONCLUSION

A radiomics patch-based analysis enables classification of the nonenhancing lesion area in patients with HGG. Preliminary results were promising and the proposed method has the potential to assist in clinical decision-making and to improve therapy response assessment in patients with HGG.

LEVEL OF EVIDENCE

1 Technical Efficacy Stage 4 J. Magn. Reson. Imaging 2018.

Imaging the DNA Alkylator Melphalan by CEST MRI: An Advanced Approach to Theranostics

Brain tumors are among the most lethal types of tumors. Therapeutic response variability and failure in patients have been attributed to several factors, including inadequate drug delivery to tumors due to the blood-brain barrier (BBB). Consequently, drug delivery strategies are being developed for the local and targeted delivery of drugs to brain tumors. These drug delivery strategies could benefit from new approaches to monitor the delivery of drugs to tumors. Here, we evaluated the feasibility of imaging 4-[bis(2-chloroethyl)amino]-l-phenylalanine (melphalan), a clinically used DNA alkylating agent, using chemical exchange saturation transfer magnetic resonance imaging (CEST MRI), for theranostic applications. We evaluated the physicochemical parameters that affect melphalan's CEST contrast and demonstrated the feasibility of imaging the unmodified drug by saturating its exchangeable amine protons. Melphalan generated a CEST signal despite its reactivity in an aqueous milieu. The maximum CEST signal was observed at pH 6.2. This CEST contrast trend was then used to monitor therapeutic responses to melphalan in vitro. Upon cell death, the decrease in cellular pH from ∼7.4 to ∼6.4 caused an amplification of the melphalan CEST signal. This is contrary to what has been reported for other CEST contrast agents used for imaging cell death, where a decrease in the cellular pH following cell death results in a decrease in the CEST signal. Ultimately, this method could be used to noninvasively monitor melphalan delivery to brain tumors and also to validate therapeutic responses to melphalan clinically.

Clinical Evaluation of a Fully-automatic Segmentation Method for Longitudinal Brain Tumor Volumetry

Information about the size of a tumor and its temporal evolution is needed for diagnosis as well as treatment of brain tumor patients. The aim of the study was to investigate the potential of a fully-automatic segmentation method, called BraTumIA, for longitudinal brain tumor volumetry by comparing the automatically estimated volumes with ground truth data acquired via manual segmentation. Longitudinal Magnetic Resonance (MR) Imaging data of 14 patients with newly diagnosed glioblastoma encompassing 64 MR acquisitions, ranging from preoperative up to 12 month follow-up images, was analysed. Manual segmentation was performed by two human raters. Strong correlations (R = 0.83–0.96, p < 0.001) were observed between volumetric estimates of BraTumIA and of each of the human raters for the contrast-enhancing (CET) and non-enhancing T₂-hyperintense tumor compartments (NCE-T₂). A quantitative analysis of the inter-rater disagreement showed that the disagreement between BraTumIA and each of the human raters was comparable to the disagreement between the human raters. In summary, BraTumIA generated volumetric trend curves of contrast-enhancing and non-enhancing T₂-hyperintense tumor compartments comparable to estimates of human raters. These findings suggest the potential of automated longitudinal tumor segmentation to substitute manual volumetric follow-up of contrast-enhancing and non-enhancing T₂-hyperintense tumor compartments.

Lessons from anti-vascular endothelial growth factor and anti-vascular endothelial growth factor receptor trials in patients with glioblastoma

Treatment of glioblastoma (GBM), the most common primary malignant brain tumor in adults, remains a significant unmet need in oncology. Historically, cytotoxic treatments provided little durable benefit, and tumors recurred within several months. This has spurred a substantial research effort to establish more effective therapies for both newly diagnosed and recurrent GBM. In this context, antiangiogenic therapy emerged as a promising treatment strategy because GBMs are highly vascular tumors. In particular, GBMs overexpress vascular endothelial growth factor (VEGF), a proangiogenic cytokine. Indeed, many studies have demonstrated promising radiographic response rates, delayed tumor progression, and a relatively safe profile for anti-VEGF agents. However, randomized phase III trials conducted to date have failed to show an overall survival benefit for antiangiogenic agents alone or in combination with chemoradiotherapy. These results indicate that antiangiogenic agents may not be beneficial in unselected populations of patients with GBM. Unfortunately, biomarker development has lagged behind in the process of drug development, and no validated biomarker exists for patient stratification. However, hypothesis-generating data from phase II trials that reveal an association between increased perfusion and/or oxygenation (ie, consequences of vascular normalization) and survival suggest that early imaging biomarkers could help identify the subset of patients who most likely will benefit from anti-VEGF agents. In this article, we discuss the lessons learned from the trials conducted to date and how we could potentially use recent advances in GBM biology and imaging to improve outcomes of patients with GBM who receive antiangiogenic therapy.

Classification of tumor area using combined DCE and DSC MRI in patients with glioblastoma

This study proposes an automatic method for identification and quantification of different tissue components: the non-enhanced infiltrative tumor, vasogenic edema and enhanced tumor areas, at the subject level, in patients with glioblastoma (GB) based on dynamic contrast enhancement (DCE) and dynamic susceptibility contrast (DSC) MRI. Nineteen MR data sets, obtained from 12 patients with GB, were included. Seven patients were scanned before and 8 weeks following bevacizumab initiation. Segmentation of the tumor area was performed based on the temporal data of DCE and DSC at the group-level using k-means algorithm, and further at the subject-level using support vector machines algorithm. The obtained components were associated to different tissues types based on their temporal characteristics, calculated perfusion and permeability values and MR-spectroscopy. The method enabled the segmentation of the tumor area into the enhancing permeable component; the non-enhancing hypoperfused component, associated with vasogenic edema; and the non-enhancing hyperperfused component, associated with infiltrative tumor. Good agreement was obtained between the group-level, unsupervised and subject-level, supervised classification results, with significant correlation (r = 0.93, p < 0.001) and average symmetric root-mean-square surface distance of 2.5 ± 5.1 mm. Longitudinal changes in the volumes of the three components were assessed alongside therapy. Tumor area segmentation using DCE and DSC can be used to differentiate between vasogenic edema and infiltrative tumors in patients with GB, which is of major clinical importance in therapy response assessment.

Multimodal imaging of gliomas in the context of evolving cellular and molecular therapies

The vast majority of malignant gliomas relapse after surgery and standard radio-chemotherapy. Novel molecular and cellular therapies are thus being developed, targeting specific aspects of tumor growth. While histopathology remains the gold standard for tumor classification, neuroimaging has over the years taken a central role in the diagnosis and treatment follow up of brain tumors. It is used to detect and localize lesions, define the target area for biopsies, plan surgical and radiation interventions and assess tumor progression and treatment outcome. In recent years the application of novel drugs including anti-angiogenic agents that affect the tumor vasculature, has drastically modulated the outcome of brain tumor imaging. To properly evaluate the effects of emerging experimental therapies and successfully support treatment decisions, neuroimaging will have to evolve. Multi-modal imaging systems with existing and new contrast agents, molecular tracers, technological advances and advanced data analysis can all contribute to the establishment of disease relevant biomarkers that will improve disease management and patient care. In this review, we address the challenges of glioma imaging in the context of novel molecular and cellular therapies, and take a prospective look at emerging experimental and pre-clinical imaging techniques that bear the promise of meeting these challenges.

Differentiation between vasogenic-edema versus tumor-infiltrative area in patients with glioblastoma during bevacizumab therapy: a longitudinal MRI study

BACKGROUND

Treatment with bevacizumab is associated with substantial radiologic response in patients with glioblastoma (GB). However, following this initial response, changes in T2-weighted MRI signal may develop, suggesting an infiltrative pattern of tumor progression. The aim of this study was to differentiate between vasogenic-edema versus tumor-infiltrative area in GB patients.

METHODS AND MATERIALS

Fourteen patients with GB were longitudinally scanned, before and during intravenous bevacizumab therapy (5/10mg/kg every 2-weeks). A total of 40 MR scans including conventional, diffusion, dynamic susceptibility contrast, dynamic contrast enhancement imaging, and MR-spectroscopy (MRS) were analyzed. Classification of non-enhancing fluid-attenuation-inversion-recovery (FLAIR) area was performed based on mean diffusivity, cerebral blood volume and flow maps, and further characterized using multiple MRI parameters.

RESULTS

The non-enhancing FLAIR lesion area was classified into: vasogenic-edema, characterized by reduced perfusion and increased FLAIR values; or tumor-infiltrative area, characterized by increased perfusion. Tumor-infiltrative area demonstrated a higher malignant pattern on MRS compared to areas of vasogenic-edema. Substantial reductions of the enhanced T1-weighted (58 ± 10%) and hyperintense FLAIR (53 ± 9%) lesion volumes were detected mainly during the first weeks of therapy, with a shift to an infiltrative pattern of tumor progression thereafter, as detected by an increase in tumor-infiltrative area in the majority of patients, which correlated with progression-free survival (week 8: r=-0.86, p=0.003, week 16: r=-0.99, p=0.001).

CONCLUSION

Characterization of non-enhancing hyperintense FLAIR lesion area in GB patients can provide an MR-based biomarker, indicating a shift to an infiltrative progression pattern, and may improve therapy response assessment in patients following bevacizumab therapy.