Quantitative susceptibility mapping in multiple sclerosis: A systematic review and meta-analysis

BACKGROUND

Quantitative susceptibility mapping (QSM) is a quantitative measure based on magnetic resonance imaging sensitive to iron and myelin content. This makes QSM a promising non-invasive tool for multiple sclerosis (MS) in research and clinical practice.

OBJECTIVE

We performed a systematic review and meta-analysis on the use of QSM in MS.

METHODS

Our review was prospectively registered on PROSPERO (CRD42022309563). We searched five databases for studies published between inception and 30th April 2023. We identified 83 English peer-reviewed studies that applied QSM images on MS cohorts. Fifty-five included studies had at least one of the following outcome measures: deep grey matter QSM values in MS, either compared to healthy controls (HC) (k = 13) or correlated with the score on the Expanded Disability Status Scale (EDSS) (k = 7), QSM lesion characteristics (k = 22) and their clinical correlates (k = 17), longitudinal correlates (k = 11), histological correlates (k = 7), or correlates with other imaging techniques (k = 12). Two meta-analyses on deep grey matter (DGM) susceptibility data were performed, while the remaining findings could only be analyzed descriptively.

RESULTS

After outlier removal, meta-analyses demonstrated a significant increase in the basal ganglia susceptibility (QSM values) in MS compared to HC, caudate (k = 9, standardized mean difference (SDM) = 0.54, 95 % CI = 0.39-0.70, I2 = 46 %), putamen (k = 9, SDM = 0.38, 95 % CI = 0.19-0.57, I2 = 59 %), and globus pallidus (k = 9, SDM = 0.48, 95 % CI = 0.28-0.67, I2 = 60 %), whereas thalamic QSM values exhibited a significant reduction (k = 12, SDM = -0.39, 95 % CI = -0.66--0.12, I2 = 84 %); these susceptibility differences in MS were independent of age. Further, putamen QSM values positively correlated with EDSS (k = 4, r = 0.36, 95 % CI = 0.16-0.53, I2 = 0 %). Regarding rim lesions, four out of seven studies, representing 73 % of all patients, reported rim lesions to be associated with more severe disability. Moreover, lesion development from initial detection to the inactive stage is paralleled by increasing, plateauing (after about two years), and gradually decreasing QSM values, respectively. Only one longitudinal study provided clinical outcome measures and found no association. Histological data suggest iron content to be the primary source of QSM values in DGM and at the edges of rim lesions; further, when also considering data from myelin water imaging, the decrease of myelin is likely to drive the increase of QSM values within WM lesions.

CONCLUSIONS

We could provide meta-analytic evidence for DGM susceptibility changes in MS compared to HC; basal ganglia susceptibility is increased and, in the putamen, associated with disability, while thalamic susceptibility is decreased. Beyond these findings, further investigations are necessary to establish the role of QSM in MS for research or even clinical routine.

Single brain metastases - prognostic factors and impact of residual tumor burden on overall survival

Background

Brain metastases (BM) are a common and challenging issue, with their incidence on the rise due to advancements in systemic therapies and increased patient survival. Most patients present with single BM, some of them without any further extracranial metastasis (i.e., solitary BM). The significance of postoperative intracranial tumor volume in the treatment of singular and solitary BM is still debated.

Objective

This study aimed to determine the impact of resection and postoperative tumor burden on overall survival (OS) in patients with single BM.

Methods

Patients with surgically treated single BM between 04/2007-01/2020 were retrospectively included. Residual tumor burden (RTB) was determined by manual segmentation of early postoperative brain MRI (72 h). Survival analyses were performed using Kaplan-Meier estimates for univariate analysis and Cox regression proportional hazards model for multivariate analysis, using preoperative Karnofsky performance status scale (KPSS), age, sex, RTB, incomplete resection and singular/solitary BM as covariates.

Results

340 patients were included, median age 64 years (54-71). 119 patients (35%) had solitary BM, 221 (65%) singular BM. Complete resection (RTB=0) was achieved in 73%, median preoperative tumor burden was 11.2 cm3 (5-25), and RTB 0 cm3 (0-0.2). Median OS of patients with singular BM was 13 months (4-33) vs 20 months (5-92) for solitary BM; p=0.062. Multivariate analysis revealed singular BM as independent risk factor for poorer OS: HR 1.840 (1.202-2.817), p=0.005. Complete vs. incomplete resection showed no significant OS difference (13 vs. 13 months, p=0.737). When focusing on solitary BM, complete resection led to a longer OS than incomplete resection (21 vs. 8 months), without statistical significance(p=0.250). Achieving RTB=0 resulted in higher OS for patients with solitary BM compared to singular BM (21 vs. 12 months, p=0.027). Patients who received postoperative radiotherapy (RT) had significantly longer OS compared to those without it (14 vs. 4 months, p<0.001), with favorable OS in those receiving stereotactic radiosurgery (SRS) (15 months (3-42), p<0.001) or hypofractionated stereotactic radiotherapy (HSRT).

Conclusion

When complete intracranial tumor resection RTB=0 is achieved, patients with solitary BM have a favorable outcome compared to singular BM. Singular BM was confirmed as independent risk factor. There is a strong presumption that complete resection leads to an improved oncological prognosis. Patients with solitary BM tend to benefit with a favorable outcome following complete resection. Hence, surgical resection should be considered as a treatment option for patients presenting with either no or minimal extracranial disease. Furthermore, the highly favorable impact of postoperative RT on OS was demonstrated and confirmed, especially with SRS or HSRT.

Intensity scaling of conventional brain magnetic resonance images avoiding cerebral reference regions: A systematic review

BACKGROUND

Conventional brain magnetic resonance imaging (MRI) produces image intensities that have an arbitrary scale, hampering quantification. Intensity scaling aims to overcome this shortfall. As neurodegenerative and inflammatory disorders may affect all brain compartments, reference regions within the brain may be misleading. Here we summarize approaches for intensity scaling of conventional T1-weighted (w) and T2w brain MRI avoiding reference regions within the brain.

METHODS

Literature was searched in the databases of Scopus, PubMed, and Web of Science. We included only studies that avoided reference regions within the brain for intensity scaling and provided validating evidence, which we divided into four categories: 1) comparative variance reduction, 2) comparative correlation with clinical parameters, 3) relation to quantitative imaging, or 4) relation to histology.

RESULTS

Of the 3825 studies screened, 24 fulfilled the inclusion criteria. Three studies used scaled T1w images, 2 scaled T2w images, and 21 T1w/T2w-ratio calculation (with double counts). A robust reduction in variance was reported. Twenty studies investigated the relation of scaled intensities to different types of quantitative imaging. Statistically significant correlations with clinical or demographic data were reported in 8 studies. Four studies reporting the relation to histology gave no clear picture of the main signal driver of conventional T1w and T2w MRI sequences.

CONCLUSIONS

T1w/T2w-ratio calculation was applied most often. Variance reduction and correlations with other measures suggest a biologically meaningful signal harmonization. However, there are open methodological questions and uncertainty on its biological underpinning. Validation evidence on other scaling methods is even sparser.

Noninvasive- and invasive mapping reveals similar language network centralities - A function-based connectome analysis

BACKGROUND

Former comparisons between direct cortical stimulation (DCS) and navigated transcranial magnetic stimulation (nTMS) only focused on cortical mapping. While both can be combined with diffusion tensor imaging, their differences in the visualization of subcortical and even network levels remain unclear. Network centrality is an essential parameter in network analysis to measure the importance of nodes identified by mapping. Those include Degree centrality, Eigenvector centrality, Closeness centrality, Betweenness centrality, and PageRank centrality. While DCS and nTMS have repeatedly been compared on the cortical level, the underlying network identified by both has not been investigated yet.

METHOD

27 patients with brain lesions necessitating preoperative nTMS and intraoperative DCS language mapping during awake craniotomy were enrolled. Function-based connectome analysis was performed based on the cortical nodes obtained through the two mapping methods, and language-related network centralities were compared.

RESULTS

Compared with DCS language mapping, the positive predictive value of cortical nTMS language mapping is 74.1%, with good consistency of tractography for the arcuate fascicle and superior longitudinal fascicle. Moreover, network centralities did not differ between the two mapping methods. However, ventral stream tracts can be better traced based on nTMS mappings, demonstrating its strengths in acquiring language-related networks. In addition, it showed lower centralities than other brain areas, with decentralization as an indicator of language function loss.

CONCLUSION

This study deepens the understanding of language-related functional anatomy and proves that non-invasive mapping-based network analysis is comparable to the language network identified via invasive cortical mapping.

LST-AI: a Deep Learning Ensemble for Accurate MS Lesion Segmentation

Automated segmentation of brain white matter lesions is crucial for both clinical assessment and scientific research in multiple sclerosis (MS). Over a decade ago, we introduced an engineered lesion segmentation tool, LST. While recent lesion segmentation approaches have leveraged artificial intelligence (AI), they often remain proprietary and difficult to adopt. As an open-source tool, we present LST-AI, an advanced deep learning-based extension of LST that consists of an ensemble of three 3D-UNets. LST-AI explicitly addresses the imbalance between white matter (WM) lesions and non-lesioned WM. It employs a composite loss function incorporating binary cross-entropy and Tversky loss to improve segmentation of the highly heterogeneous MS lesions. We train the network ensemble on 491 MS pairs of T1w and FLAIR images, collected in-house from a 3T MRI scanner, and expert neuroradiologists manually segmented the utilized lesion maps for training. LST-AI additionally includes a lesion location annotation tool, labeling lesion location according to the 2017 McDonald criteria (periventricular, infratentorial, juxtacortical, subcortical). We conduct evaluations on 103 test cases consisting of publicly available data using the Anima segmentation validation tools and compare LST-AI with several publicly available lesion segmentation models. Our empirical analysis shows that LST-AI achieves superior performance compared to existing methods. Its Dice and F1 scores exceeded 0.62, outperforming LST, SAMSEG (Sequence Adaptive Multimodal SEGmentation), and the popular nnUNet framework, which all scored below 0.56. Notably, LST-AI demonstrated exceptional performance on the MSSEG-1 challenge dataset, an international WM lesion segmentation challenge, with a Dice score of 0.65 and an F1 score of 0.63-surpassing all other competing models at the time of the challenge. With increasing lesion volume, the lesion detection rate rapidly increased with a detection rate of >75% for lesions with a volume between 10mm3 and 100mm3. Given its higher segmentation performance, we recommend that research groups currently using LST transition to LST-AI. To facilitate broad adoption, we are releasing LST-AI as an open-source model, available as a command-line tool, dockerized container, or Python script, enabling diverse applications across multiple platforms.

The Brain Tumor Segmentation (BraTS) Challenge 2023: Focus on Pediatrics (CBTN-CONNECT-DIPGR-ASNR-MICCAI BraTS-PEDs)

Pediatric tumors of the central nervous system are the most common cause of cancer-related death in children. The five-year survival rate for high-grade gliomas in children is less than 20\%. Due to their rarity, the diagnosis of these entities is often delayed, their treatment is mainly based on historic treatment concepts, and clinical trials require multi-institutional collaborations. The MICCAI Brain Tumor Segmentation (BraTS) Challenge is a landmark community benchmark event with a successful history of 12 years of resource creation for the segmentation and analysis of adult glioma. Here we present the CBTN-CONNECT-DIPGR-ASNR-MICCAI BraTS-PEDs 2023 challenge, which represents the first BraTS challenge focused on pediatric brain tumors with data acquired across multiple international consortia dedicated to pediatric neuro-oncology and clinical trials. The BraTS-PEDs 2023 challenge focuses on benchmarking the development of volumentric segmentation algorithms for pediatric brain glioma through standardized quantitative performance evaluation metrics utilized across the BraTS 2023 cluster of challenges. Models gaining knowledge from the BraTS-PEDs multi-parametric structural MRI (mpMRI) training data will be evaluated on separate validation and unseen test mpMRI dataof high-grade pediatric glioma. The CBTN-CONNECT-DIPGR-ASNR-MICCAI BraTS-PEDs 2023 challenge brings together clinicians and AI/imaging scientists to lead to faster development of automated segmentation techniques that could benefit clinical trials, and ultimately the care of children with brain tumors.

A Learnable Prior Improves Inverse Tumor Growth Modeling

Biophysical modeling, particularly involving partial differential equations (PDEs), offers significant potential for tailoring disease treatment protocols to individual patients. However, the inverse problem-solving aspect of these models presents a substantial challenge, either due to the high computational requirements of model-based approaches or the limited robustness of deep learning (DL) methods. We propose a novel framework that leverages the unique strengths of both approaches in a synergistic manner. Our method incorporates a DL ensemble for initial parameter estimation, facilitating efficient downstream evolutionary sampling initialized with this DL-based prior. We showcase the effectiveness of integrating a rapid deep-learning algorithm with a high-precision evolution strategy in estimating brain tumor cell concentrations from magnetic resonance images. The DL-Prior plays a pivotal role, significantly constraining the effective sampling-parameter space. This reduction results in a fivefold convergence acceleration and a Dice-score of 95.

Deep Learning to Differentiate Benign and Malignant Vertebral Fractures at Multidetector CT

Background Differentiating between benign and malignant vertebral fractures poses diagnostic challenges. Purpose To investigate the reliability of CT-based deep learning models to differentiate between benign and malignant vertebral fractures. Materials and Methods CT scans acquired in patients with benign or malignant vertebral fractures from June 2005 to December 2022 at two university hospitals were retrospectively identified based on a composite reference standard that included histopathologic and radiologic information. An internal test set was randomly selected, and an external test set was obtained from an additional hospital. Models used a three-dimensional U-Net encoder-classifier architecture and applied data augmentation during training. Performance was evaluated using the area under the receiver operating characteristic curve (AUC) and compared with that of two residents and one fellowship-trained radiologist using the DeLong test. Results The training set included 381 patients (mean age, 69.9 years ± 11.4 [SD]; 193 male) with 1307 vertebrae (378 benign fractures, 447 malignant fractures, 482 malignant lesions). Internal and external test sets included 86 (mean age, 66.9 years ± 12; 45 male) and 65 (mean age, 68.8 years ± 12.5; 39 female) patients, respectively. The better-performing model of two training approaches achieved AUCs of 0.85 (95% CI: 0.77, 0.92) in the internal and 0.75 (95% CI: 0.64, 0.85) in the external test sets. Including an uncertainty category further improved performance to AUCs of 0.91 (95% CI: 0.83, 0.97) in the internal test set and 0.76 (95% CI: 0.64, 0.88) in the external test set. The AUC values of residents were lower than that of the best-performing model in the internal test set (AUC, 0.69 [95% CI: 0.59, 0.78] and 0.71 [95% CI: 0.61, 0.80]) and external test set (AUC, 0.70 [95% CI: 0.58, 0.80] and 0.71 [95% CI: 0.60, 0.82]), with significant differences only for the internal test set (P < .001). The AUCs of the fellowship-trained radiologist were similar to those of the best-performing model (internal test set, 0.86 [95% CI: 0.78, 0.93; P = .39]; external test set, 0.71 [95% CI: 0.60, 0.82; P = .46]). Conclusion Developed models showed a high discriminatory power to differentiate between benign and malignant vertebral fractures, surpassing or matching the performance of radiology residents and matching that of a fellowship-trained radiologist. © RSNA, 2024 See also the editorial by Booz and D'Angelo in this issue.

(Predictable) performance bias in unsupervised anomaly detection

BACKGROUND

With the ever-increasing amount of medical imaging data, the demand for algorithms to assist clinicians has amplified. Unsupervised anomaly detection (UAD) models promise to aid in the crucial first step of disease detection. While previous studies have thoroughly explored fairness in supervised models in healthcare, for UAD, this has so far been unexplored.

METHODS

In this study, we evaluated how dataset composition regarding subgroups manifests in disparate performance of UAD models along multiple protected variables on three large-scale publicly available chest X-ray datasets. Our experiments were validated using two state-of-the-art UAD models for medical images. Finally, we introduced subgroup-AUROC (sAUROC), which aids in quantifying fairness in machine learning.

FINDINGS

Our experiments revealed empirical "fairness laws" (similar to "scaling laws" for Transformers) for training-dataset composition: Linear relationships between anomaly detection performance within a subpopulation and its representation in the training data. Our study further revealed performance disparities, even in the case of balanced training data, and compound effects that exacerbate the drop in performance for subjects associated with multiple adversely affected groups.

INTERPRETATION

Our study quantified the disparate performance of UAD models against certain demographic subgroups. Importantly, we showed that this unfairness cannot be mitigated by balanced representation alone. Instead, the representation of some subgroups seems harder to learn by UAD models than that of others. The empirical "fairness laws" discovered in our study make disparate performance in UAD models easier to estimate and aid in determining the most desirable dataset composition.

FUNDING

European Research Council Deep4MI.

Enhancing predictability of IDH mutation status in glioma patients at initial diagnosis: a comparative analysis of radiomics from MRI, [18F]FET PET, and TSPO PET

PURPOSE

According to the World Health Organization classification for tumors of the central nervous system, mutation status of the isocitrate dehydrogenase (IDH) genes has become a major diagnostic discriminator for gliomas. Therefore, imaging-based prediction of IDH mutation status is of high interest for individual patient management. We compared and evaluated the diagnostic value of radiomics derived from dual positron emission tomography (PET) and magnetic resonance imaging (MRI) data to predict the IDH mutation status non-invasively.

METHODS

Eighty-seven glioma patients at initial diagnosis who underwent PET targeting the translocator protein (TSPO) using [18F]GE-180, dynamic amino acid PET using [18F]FET, and T1-/T2-weighted MRI scans were examined. In addition to calculating tumor-to-background ratio (TBR) images for all modalities, parametric images quantifying dynamic [18F]FET PET information were generated. Radiomic features were extracted from TBR and parametric images. The area under the receiver operating characteristic curve (AUC) was employed to assess the performance of logistic regression (LR) classifiers. To report robust estimates, nested cross-validation with five folds and 50 repeats was applied.

RESULTS

TBRGE-180 features extracted from TSPO-positive volumes had the highest predictive power among TBR images (AUC 0.88, with age as co-factor 0.94). Dynamic [18F]FET PET reached a similarly high performance (0.94, with age 0.96). The highest LR coefficients in multimodal analyses included TBRGE-180 features, parameters from kinetic and early static [18F]FET PET images, age, and the features from TBRT2 images such as the kurtosis (0.97).

CONCLUSION

The findings suggest that incorporating TBRGE-180 features along with kinetic information from dynamic [18F]FET PET, kurtosis from TBRT2, and age can yield very high predictability of IDH mutation status, thus potentially improving early patient management.

Personalized Predictions of Glioblastoma Infiltration: Mathematical Models, Physics-Informed Neural Networks and Multimodal Scans

Predicting the infiltration of Glioblastoma (GBM) from medical MRI scans is crucial for understanding tumor growth dynamics and designing personalized radiotherapy treatment plans.Mathematical models of GBM growth can complement the data in the prediction of spatial distributions of tumor cells. However, this requires estimating patient-specific parameters of the model from clinical data, which is a challenging inverse problem due to limited temporal data and the limited time between imaging and diagnosis. This work proposes a method that uses Physics-Informed Neural Networks (PINNs) to estimate patient-specific parameters of a reaction-diffusion PDE model of GBM growth from a single 3D structural MRI snapshot. PINNs embed both the data and the PDE into a loss function, thus integrating theory and data. Key innovations include the identification and estimation of characteristic non-dimensional parameters, a pre-training step that utilizes the non-dimensional parameters and a fine-tuning step to determine the patient specific parameters. Additionally, the diffuse domain method is employed to handle the complex brain geometry within the PINN framework. Our method is validated both on synthetic and patient datasets, and shows promise for real-time parametric inference in the clinical setting for personalized GBM treatment.

Amino acid PET vs. RANO MRI for prediction of overall survival in patients with recurrent high grade glioma under bevacizumab therapy

PURPOSE

To summarize evidence on the comparative value of amino acid (AA) PET and conventional MRI for prediction of overall survival (OS) in patients with recurrent high grade glioma (rHGG) under bevacizumab therapy.

METHODS

Medical databases were screened for studies with individual data on OS, follow-up MRI, and PET findings in the same patient. MRI images were assessed according to the RANO criteria. A receiver operating characteristic curve analysis was used to predict OS at 9 months.

RESULTS

Five studies with a total of 72 patients were included. Median OS was significantly lower in the PET-positive than in the PET-negative group. PET findings predicted OS with a pooled sensitivity and specificity of 76% and 71%, respectively. Corresponding values for MRI were 32% and 82%. Area under the curve and sensitivity were significantly higher for PET than for MRI.

CONCLUSION

For monitoring of patients with rHGG under bevacizumab therapy, AA-PET should be preferred over RANO MRI.

Navigating Post-Operative Outcomes: A Comprehensive Reframing of an Original Graded Prognostic Assessment in Patients with Brain Metastases

BACKGROUND

Graded Prognostic Assessment (GPA) has been proposed for various brain metastases (BMs) tailored to the primary histology and molecular profiles. However, it does not consider whether patients have been operated on or not and does not include surgical outcomes as prognostic factors. The residual tumor burden (RTB) is a strong predictor of overall survival. We validated the GPA score and introduced "volumetric GPA" in the largest cohort of operated patients and further explored the role of RTB as an additional prognostic factor.

METHODS

A total of 630 patients with BMs between 2007 and 2020 were included. The four GPA components were analyzed. The validity of the original score was assessed using Cox regression, and a modified index incorporating RTB was developed by comparing the accuracy, sensitivity, specificity, F1-score, and AUC parameters.

RESULTS

GPA categories showed an association with survival: age (p < 0.001, hazard ratio (HR) 2.9, 95% confidence interval (CI) 2.5-3.3), Karnofsky performance status (KPS) (p < 0.001, HR 1.3, 95% CI 1.2-1.5), number of BMs (p = 0.019, HR 1.4, 95% CI 1.1-1.8), and the presence of extracranial manifestation (p < 0.001, HR 3, 95% CI 1.6-2.5). The median survival for GPA 0-1 was 4 months; for GPA 1.5-2, it was 12 months; for GPA 2.5-3, it was 21 months; and for GPA 3.5-4, it was 38 months (p < 0.001). RTB was identified as an independent prognostic factor. A cut-off of 2 cm3 was used for further analysis, which showed a median survival of 6 months (95% CI 4-8) vs. 13 months (95% CI 11-14, p < 0.001) for patients with RTB > 2 cm3 and <2 cm3, respectively. RTB was added as an additional component for a modified volumetric GPA score. The survival rates with the modified GPA score were: GPA 0-1: 4 months, GPA 1.5-2: 7 months, GPA 2.5-3: 18 months, and GPA 3.5-4: 34 months. Both scores showed good stratification, with the new score showed a trend towards better discrimination in patients with more favorable prognoses.

CONCLUSION

The prognostic value of the original GPA was confirmed in our cohort of patients who underwent surgery for BM. The RTB was identified as a parameter of high prognostic significance and was incorporated into an updated "volumetric GPA". This score provides a novel tool for prognosis and clinical decision making in patients undergoing surgery. This method may be useful for stratification and patient selection for further treatment and in future clinical trials.

Impact of function-guided glioma treatment on oncological outcome in the elderly

Introduction

Many patients with high-grade gliomas (HGG) are of older age.

Research question

We hypothesize that pre- and intraoperative mapping and monitoring preserve functional status in elderly patients while gross total resection (GTR) is the aim, resulting in overall survival (OS) rates comparable to the general population with HGG.

Material and methods

We subdivided a prospective cohort of 168 patients above 65 years with eloquent high-grade gliomas into four groups ([years/cases] 1: 65-69/58; 2: 70-74/47; 3: 75-79/43; 4: >79/20). All patients underwent preoperative noninvasive mapping, which was also used for decision-making, intraoperative neuromonitoring in 138 cases, direct cortical and/or subcortical motor mapping in 66 and 50 cases, and awake language mapping in 11 cases.

Results

GTR and subtotal resection (STR) could be achieved in 65% and 28%, respectively. Stereotactic biopsy was performed in 8% of cases. Postoperatively, we found transient and permanent functional deficits in 13% and 11% of cases. Postoperative Karnofsky Performance Scale (KPS) did not differ between subgroups. Patients with long-term follow-up (51%) had a progression-free survival of 5.5 (1-47) months and an overall survival of 10.5 (0-86) months.

Discussion and conclusion

The interdisciplinary glioma treatment in the elderly is less age-dependent but must be adjusted to the functional status. Function-guided surgical resections could be performed as usual, with maximal tumor resection being the primary goal. However, less network capacity in the elderly to compensate for deficits might cause higher rates of permanent deficits in this group of patients with more fast-growing malignant gliomas.

Where is VALDO? VAscular Lesions Detection and segmentatiOn challenge at MICCAI 2021

Imaging markers of cerebral small vessel disease provide valuable information on brain health, but their manual assessment is time-consuming and hampered by substantial intra- and interrater variability. Automated rating may benefit biomedical research, as well as clinical assessment, but diagnostic reliability of existing algorithms is unknown. Here, we present the results of the VAscular Lesions DetectiOn and Segmentation (Where is VALDO?) challenge that was run as a satellite event at the international conference on Medical Image Computing and Computer Aided Intervention (MICCAI) 2021. This challenge aimed to promote the development of methods for automated detection and segmentation of small and sparse imaging markers of cerebral small vessel disease, namely enlarged perivascular spaces (EPVS) (Task 1), cerebral microbleeds (Task 2) and lacunes of presumed vascular origin (Task 3) while leveraging weak and noisy labels. Overall, 12 teams participated in the challenge proposing solutions for one or more tasks (4 for Task 1-EPVS, 9 for Task 2-Microbleeds and 6 for Task 3-Lacunes). Multi-cohort data was used in both training and evaluation. Results showed a large variability in performance both across teams and across tasks, with promising results notably for Task 1-EPVS and Task 2-Microbleeds and not practically useful results yet for Task 3-Lacunes. It also highlighted the performance inconsistency across cases that may deter use at an individual level, while still proving useful at a population level.

Toward image-based personalization of glioblastoma therapy: A clinical and biological validation study of a novel, deep learning-driven tumor growth model

Background

The diffuse growth pattern of glioblastoma is one of the main challenges for accurate treatment. Computational tumor growth modeling has emerged as a promising tool to guide personalized therapy. Here, we performed clinical and biological validation of a novel growth model, aiming to close the gap between the experimental state and clinical implementation.

Methods

One hundred and twenty-four patients from The Cancer Genome Archive (TCGA) and 397 patients from the UCSF Glioma Dataset were assessed for significant correlations between clinical data, genetic pathway activation maps (generated with PARADIGM; TCGA only), and infiltration (Dw) as well as proliferation (ρ) parameters stemming from a Fisher-Kolmogorov growth model. To further evaluate clinical potential, we performed the same growth modeling on preoperative magnetic resonance imaging data from 30 patients of our institution and compared model-derived tumor volume and recurrence coverage with standard radiotherapy plans.

Results

The parameter ratio Dw/ρ (P < .05 in TCGA) as well as the simulated tumor volume (P < .05 in TCGA/UCSF) were significantly inversely correlated with overall survival. Interestingly, we found a significant correlation between 11 proliferation pathways and the estimated proliferation parameter. Depending on the cutoff value for tumor cell density, we observed a significant improvement in recurrence coverage without significantly increased radiation volume utilizing model-derived target volumes instead of standard radiation plans.

Conclusions

Identifying a significant correlation between computed growth parameters and clinical and biological data, we highlight the potential of tumor growth modeling for individualized therapy of glioblastoma. This might improve the accuracy of radiation planning in the near future.

Cortical Thin Patch Fraction Reflects Disease Burden in MS: The Mosaic Approach

BACKGROUND AND PURPOSE

GM pathology plays an essential role in MS disability progression, emphasizing the importance of neuroradiologic biomarkers to capture the heterogeneity of cortical disease burden. This study aimed to assess the validity of a patch-wise, individual interpretation of cortical thickness data to identify GM pathology, the "mosaic approach," which was previously suggested as a biomarker for assessing and localizing atrophy.

MATERIALS AND METHODS

We investigated the mosaic approach in a cohort of 501 patients with MS with respect to 89 internal and 651 external controls. The resulting metric of the mosaic approach is the so-called thin patch fraction, which is an estimate of overall cortical disease burden per patient. We evaluated the mosaic approach with respect to the following: 1) discrimination between patients with MS and controls, 2) classification between different MS phenotypes, and 3) association with established biomarkers reflecting MS disease burden, using general linear modeling.

RESULTS

The thin patch fraction varied significantly between patients with MS and healthy controls and discriminated among MS phenotypes. Furthermore, the thin patch fraction was associated with disease burden, including the Expanded Disability Status Scale, cognitive and fatigue scores, and lesion volume.

CONCLUSIONS

This study demonstrates the validity of the mosaic approach as a neuroradiologic biomarker in MS. The output of the mosaic approach, namely the thin patch fraction, is a candidate biomarker for assessing and localizing cortical GM pathology. The mosaic approach can furthermore enhance the development of a personalized cortical MS biomarker, given that the thin patch fraction provides a feature on which artificial intelligence methods can be trained. Most important, we showed the validity of the mosaic approach when referencing data with respect to external control MR imaging repositories.

A Genetic Risk Variant for Multiple Sclerosis Severity is Associated with Brain Atrophy

The minor allele of the genetic variant rs10191329 in the DYSF-ZNF638 locus is associated with unfavorable long-term clinical outcomes in multiple sclerosis patients. We investigated if rs10191329 is associated with brain atrophy measured by magnetic resonance imaging in a discovery cohort of 748 and a replication cohort of 360 people with relapsing multiple sclerosis. We observed an association with 28% more brain atrophy per rs10191329*A allele. Our results encourage stratification for rs10191329 in clinical trials. Unraveling the underlying mechanisms may enhance our understanding of pathophysiology and identify treatment targets. ANN NEUROL 2023;94:1080-1085.

Benefits of a mosaic approach for assessing cortical atrophy in individual multiple sclerosis patients

OBJECTIVE

Cortical gray matter (GM) atrophy plays a central role in multiple sclerosis (MS) pathology. However, it is not commonly assessed in clinical routine partly because a number of methodological problems hamper the development of a robust biomarker to quantify GM atrophy. In previous work, we have demonstrated the clinical utility of the "mosaic approach" (MAP) to assess individual GM atrophy in the motor neuron disease spectrum and frontotemporal dementia. In this study, we investigated the clinical utility of MAP in MS, comparing this novel biomarker to existing methods for computing GM atrophy in single patients. We contrasted the strategies based on correlations with established biomarkers reflecting MS disease burden.

METHODS

We analyzed T1-weighted MPRAGE magnetic resonance imaging data from 465 relapsing-remitting MS patients and 89 healthy controls. We inspected how variations of existing strategies to estimate individual GM atrophy ("standard approaches") as well as variations of MAP (i.e., different parcellation schemes) impact downstream analysis results, both on a group and an individual level. We interpreted individual cortical disease burden as single metric reflecting the fraction of significantly atrophic data points with respect to the control group. In addition, we evaluated the correlations to lesion volume (LV) and Expanded Disability Status Scale (EDSS).

RESULTS

We found that the MAP method yielded highest correlations with both LV and EDSS as compared to all other strategies. Although the parcellation resolution played a minor role in terms of absolute correlations with clinical variables, higher resolutions provided more clearly defined statistical brain maps which may facilitate clinical interpretability.

CONCLUSION

This study provides evidence that MAP yields high potential for a clinically relevant biomarker in MS, outperforming existing methods to compute cortical disease burden in single patients. Of note, MAP outputs brain maps illustrating individual cortical disease burden which can be directly interpreted in daily clinical routine.

Denoising diffusion-based MRI to CT image translation enables automated spinal segmentation

BACKGROUND

Automated segmentation of spinal magnetic resonance imaging (MRI) plays a vital role both scientifically and clinically. However, accurately delineating posterior spine structures is challenging.

METHODS

This retrospective study, approved by the ethical committee, involved translating T1-weighted and T2-weighted images into computed tomography (CT) images in a total of 263 pairs of CT/MR series. Landmark-based registration was performed to align image pairs. We compared two-dimensional (2D) paired - Pix2Pix, denoising diffusion implicit models (DDIM) image mode, DDIM noise mode - and unpaired (SynDiff, contrastive unpaired translation) image-to-image translation using "peak signal-to-noise ratio" as quality measure. A publicly available segmentation network segmented the synthesized CT datasets, and Dice similarity coefficients (DSC) were evaluated on in-house test sets and the "MRSpineSeg Challenge" volumes. The 2D findings were extended to three-dimensional (3D) Pix2Pix and DDIM.

RESULTS

2D paired methods and SynDiff exhibited similar translation performance and DCS on paired data. DDIM image mode achieved the highest image quality. SynDiff, Pix2Pix, and DDIM image mode demonstrated similar DSC (0.77). For craniocaudal axis rotations, at least two landmarks per vertebra were required for registration. The 3D translation outperformed the 2D approach, resulting in improved DSC (0.80) and anatomically accurate segmentations with higher spatial resolution than that of the original MRI series.

CONCLUSIONS

Two landmarks per vertebra registration enabled paired image-to-image translation from MRI to CT and outperformed all unpaired approaches. The 3D techniques provided anatomically correct segmentations, avoiding underprediction of small structures like the spinous process.

RELEVANCE STATEMENT

This study addresses the unresolved issue of translating spinal MRI to CT, making CT-based tools usable for MRI data. It generates whole spine segmentation, previously unavailable in MRI, a prerequisite for biomechanical modeling and feature extraction for clinical applications.

KEY POINTS

• Unpaired image translation lacks in converting spine MRI to CT effectively. • Paired translation needs registration with two landmarks per vertebra at least. • Paired image-to-image enables segmentation transfer to other domains. • 3D translation enables super resolution from MRI to CT. • 3D translation prevents underprediction of small structures.

Modern preoperative imaging and functional mapping in patients with intracranial glioma

Magnetic resonance imaging (MRI) in therapy-naïve intracranial glioma is paramount for neuro-oncological diagnostics, and it provides images that are helpful for surgery planning and intraoperative guidance during tumor resection, including assessment of the involvement of functionally eloquent brain structures. This study reviews emerging MRI techniques to depict structural information, diffusion characteristics, perfusion alterations, and metabolism changes for advanced neuro-oncological imaging. In addition, it reflects current methods to map brain function close to a tumor, including functional MRI and navigated transcranial magnetic stimulation with derived function-based tractography of subcortical white matter pathways. We conclude that modern preoperative MRI in neuro-oncology offers a multitude of possibilities tailored to clinical needs, and advancements in scanner technology (e. g., parallel imaging for acceleration of acquisitions) make multi-sequence protocols increasingly feasible. Specifically, advanced MRI using a multi-sequence protocol enables noninvasive, image-based tumor grading and phenotyping in patients with glioma. Furthermore, the add-on use of preoperatively acquired MRI data in combination with functional mapping and tractography facilitates risk stratification and helps to avoid perioperative functional decline by providing individual information about the spatial location of functionally eloquent tissue in relation to the tumor mass. KEY POINTS::   · Advanced preoperative MRI allows for image-based tumor grading and phenotyping in glioma.. · Multi-sequence MRI protocols nowadays make it possible to assess various tumor characteristics (incl. perfusion, diffusion, and metabolism).. · Presurgical MRI in glioma is increasingly combined with functional mapping to identify and enclose individual functional areas.. · Advancements in scanner technology (e. g., parallel imaging) facilitate increasing application of dedicated multi-sequence imaging protocols.. CITATION FORMAT: · Sollmann N, Zhang H, Kloth C et al. Modern preoperative imaging and functional mapping in patients with intracranial glioma. Fortschr Röntgenstr 2023; 195: 989 - 1000.

Multiscale quantification of morphological heterogeneity with creation of a predictor of longer survival in glioblastoma

Intratumor heterogeneity is a main cause of the dismal prognosis of glioblastoma (GBM). Yet, there remains a lack of a uniform assessment of the degree of heterogeneity. With a multiscale approach, we addressed the hypothesis that intratumor heterogeneity exists on different levels comprising traditional regional analyses, but also innovative methods including computer-assisted analysis of tumor morphology combined with epigenomic data. With this aim, 157 biopsies of 37 patients with therapy-naive IDH-wildtype GBM were analyzed regarding the intratumor variance of protein expression of glial marker GFAP, microglia marker Iba1 and proliferation marker Mib1. Hematoxylin and eosin stained slides were evaluated for tumor vascularization. For the estimation of pixel intensity and nuclear profiling, automated analysis was used. Additionally, DNA methylation profiling was conducted separately for the single biopsies. Scoring systems were established to integrate several parameters into one score for the four examined modalities of heterogeneity (regional, cellular, pixel-level and epigenomic). As a result, we could show that heterogeneity was detected in all four modalities. Furthermore, for the regional, cellular and epigenomic level, we confirmed the results of earlier studies stating that a higher degree of heterogeneity is associated with poorer overall survival. To integrate all modalities into one score, we designed a predictor of longer survival, which showed a highly significant separation regarding the OS. In conclusion, multiscale intratumor heterogeneity exists in glioblastoma and its degree has an impact on overall survival. In future studies, the implementation of a broadly feasible heterogeneity index should be considered.

Identifying core MRI sequences for reliable automatic brain metastasis segmentation

BACKGROUND

Many automatic approaches to brain tumor segmentation employ multiple magnetic resonance imaging (MRI) sequences. The goal of this project was to compare different combinations of input sequences to determine which MRI sequences are needed for effective automated brain metastasis (BM) segmentation.

METHODS

We analyzed preoperative imaging (T1-weighted sequence ± contrast-enhancement (T1/T1-CE), T2-weighted sequence (T2), and T2 fluid-attenuated inversion recovery (T2-FLAIR) sequence) from 339 patients with BMs from seven centers. A baseline 3D U-Net with all four sequences and six U-Nets with plausible sequence combinations (T1-CE, T1, T2-FLAIR, T1-CE + T2-FLAIR, T1-CE + T1 + T2-FLAIR, T1-CE + T1) were trained on 239 patients from two centers and subsequently tested on an external cohort of 100 patients from five centers.

RESULTS

The model based on T1-CE alone achieved the best segmentation performance for BM segmentation with a median Dice similarity coefficient (DSC) of 0.96. Models trained without T1-CE performed worse (T1-only: DSC = 0.70 and T2-FLAIR-only: DSC = 0.73). For edema segmentation, models that included both T1-CE and T2-FLAIR performed best (DSC = 0.93), while the remaining four models without simultaneous inclusion of these both sequences reached a median DSC of 0.81-0.89.

CONCLUSIONS

A T1-CE-only protocol suffices for the segmentation of BMs. The combination of T1-CE and T2-FLAIR is important for edema segmentation. Missing either T1-CE or T2-FLAIR decreases performance. These findings may improve imaging routines by omitting unnecessary sequences, thus allowing for faster procedures in daily clinical practice while enabling optimal neural network-based target definitions.

Cytoreduction of Residual Tumor Burden Is Decisive for Prolonged Survival in Patients with Recurrent Brain Metastases-Retrospective Analysis of 219 Patients

BACKGROUND

Despite advances in treatment for brain metastases (BMs), the prognosis for recurrent BMs remains poor and requires further research to advance clinical management and improve patient outcomes. In particular, data addressing the impact of tumor volume and surgical resection with regard to survival remain scarce.

METHODS

Adult patients with recurrent BMs between December 2007 and December 2022 were analyzed. A distinction was made between operated and non-operated patients, and the residual tumor burden (RTB) was determined by using (postoperative) MRI. Survival analysis was performed and RTB cutoff values were calculated using maximally selected log-rank statistics. In addition, further analyses on systemic tumor progression and (postoperative) tumor therapy were conducted.

RESULTS

In total, 219 patients were included in the analysis. Median age was 60 years (IQR 52-69). Median preoperative tumor burden was 2.4 cm3 (IQR 0.8-8.3), and postoperative tumor burden was 0.5 cm3 (IQR 0.0-2.9). A total of 95 patients (43.4%) underwent surgery, and complete cytoreduction was achieved in 55 (25.1%) patients. Median overall survival was 6 months (IQR 2-10). Cutoff RTB in all patients was 0.12 cm3, showing a significant difference (p = 0.00029) in overall survival (OS). Multivariate analysis showed preoperative KPSS (HR 0.983, 95% CI, 0.967-0.997, p = 0.015), postoperative tumor burden (HR 1.03, 95% CI 1.008-1.053, p = 0.007), and complete vs. incomplete resection (HR 0.629, 95% CI 0.420-0.941, p = 0.024) as significant. Longer survival was significantly associated with surgery for recurrent BMs (p = 0.00097), and additional analysis demonstrated the significant effect of complete resection on survival (p = 0.0027). In the subgroup of patients with systemic progression, a cutoff RTB of 0.97 cm3 (p = 0.00068) was found; patients who had received surgery also showed prolonged OS (p = 0.036). Single systemic therapy (p = 0.048) and the combination of radiotherapy and systemic therapy had a significant influence on survival (p = 0.036).

CONCLUSIONS

RTB is a strong prognostic factor for survival in patients with recurrent BMs. Operated patients with recurrent BMs showed longer survival independent of systemic progression. Maximal cytoreduction should be targeted to achieve better long-term outcomes.

MRI-detected intraosseous bone marrow edema recedes after effective therapy of periodontitis

OBJECTIVES

T2 STIR MRI sequences can detect preclinical changes associated with periodontal inflammation, i.e. intraosseous edema in the tooth-supporting bone. In this study, we assessed whether MRI can be used for monitoring periodontal disease.

MATERIAL AND METHODS

In a prospective cohort study, we examined 35 patients with periodontitis between 10/2018 and 04/2019 by using 3D isotropic T2-weighted short tau inversion recovery (STIR) and Fast Field Echo T1-weighted Black bone sequences. All patients received standardized clinical exams before and three months after non-surgical periodontal therapy. Bone marrow edema extent was quantified in the STIR sequence at 922 sites before and after treatment. Results were compared with standard clinical findings. Non-parametric statistical analysis was performed.

RESULTS

Non-surgical periodontal treatment caused significant improvement in mean probing depth (p < 0.001) and frequency of bleeding on probing (p < 0.001). The mean depth of osseous edema per site was reduced from a median [IQR] of 2 [1, 3] mm at baseline to 1 [0, 3] mm, (p < 0.001). Periodontal treatment reduced the frequency of sites with edema from 35 to 24% (p < 0.01).

CONCLUSION

The decrease of periodontal bone marrow edema, as observed with T2 STIR MR imaging, is indicative of successful periodontal healing.

CLINICAL RELEVANCE STATEMENT

T2 STIR hyperintense bone marrow edema in the periodontal bone decreases after treatment and can therefore be used to evaluate treatment success. Furthermore, MRI reveals new options to depict hidden aspects of periodontitis.

KEY POINTS

• T2 STIR hyperintense periodontal intraosseous edema was prospectively investigated in 35 patients with periodontitis before and after treatment and compared to clinical outcomes. • The frequency of affected sites was reduced from 35 to 24% (p < 0.001), and mean edema depth was reduced from a median [IQR] of 2 [1, 3] mm at baseline to 1 [0, 3] mm 3 months after treatment. (p < 0.001). • T2 STIR sequences can be used to monitor the posttreatment course of periodontitis.

Improving tractography in brainstem cavernoma patients by distortion correction

Introduction

The resection of brainstem cerebral cavernous malformations (CCM) harbors the risk of damaging the corticospinal tract (CST) and other major tracts. Hence, visualization of eloquent fiber tracts supports pre- and intraoperative planning. However, diffusion tensor imaging fiber tracking at brainstem level suffers from distortion due to field inhomogeneities and eddy currents by steep diffusion gradients.

Research question

This study aims to analyze the effect of distortion correction for CST tractography in brainstem CCM patients.

Material and methods

25 patients who underwent resection of brainstem CCM were enrolled, 24 suffered from hemorrhage. We performed an anatomically based tractography of the CST with a mean minimal fractional anisotropy of 0.22 ± 0.04 before and after cranial distortion correction (CDC). Accuracy was measured by anatomical plausibility and aberrant fibers.

Results

CDC led to a more precise CST tractography, further approximating its assumed anatomical localization in all cases. CDC resulted in a significantly more ventral location of the CST of 1.5 ± 0.6 mm (6.1 ± 2.7 mm before CDC vs. 4.6 ± 2.1 mm after CDC; p < .0001) as measured by the distance to the basilar artery and of 1.7 ± 0.6 mm (8.9 ± 2.7 mm vs. 7.2 ± 2.1 mm; p < .0001) in relation to the clivus. Aberrant fibers were reduced by CDC in 44% of cases. We found a mean difference in CST volume of 0.6 ± 0.8 ccm. We could not detect motor deficits after resection of irregular fibers.

Discussion and conclusion

CDC effectively corrects tractography for distortion at brainstem level, especially in patients suffering from brainstem CCM, further approximating its actual anatomical localization.

What MRI Sequences are Necessary for Automated Neural Network-Based Metastasis Segmentation - An Ablation Study

PURPOSE/OBJECTIVE(S)

Brain metastasis (BM) delineation is a time-consuming process in both daily clinical practice and research. Automated BM segmentation algorithms can be used to assist in this task. Most approaches to brain tumor segmentation, such as algorithms trained on the BraTS challenge, use four magnetic resonance imaging (MRI) sequences as input, making them susceptible to missing or corrupted sequences and increase the number of sequences necessary for MRI RT planning. The goal of this project is to compare neural networks with different combinations of input sequences for the segmentation of the contrast-enhancing metastasis and the surrounding FLAIR hyperintense edema. All models were tested in a multicenter international external test cohort. This allows us to determine which MRI sequences are needed for effective automated segmentations.

MATERIALS/METHODS

In total, we had T1-weighted sequences without (T1) and with contrast enhancement (T1-CE), T2-weighted sequences (T2), and T2 fluid-attenuated inversion recovery (FLAIR) sequences from 339 patients with at least one brain metastasis from seven centers available. Preprocessing yielded co-registered, skull-stripped sequences with an isotropic resolution of 1 millimeter. The contrast-enhancing metastasis as well as the surrounding FLAIR hyperintense edema were manually segmented to create reference labels. A baseline 3D U-Net with all four sequences as well as six additional U-Nets with different clinically plausible combinations (T1-CE; T1; FLAIR; T1-CE+FLAIR; T1-CE+T1+FLAIR; T1-CE+T1) of input sequences were trained on a cohort of 239 patients from two centers and subsequently tested on an external cohort of 100 patients from the remaining five centers.

RESULTS

All models that included T1-CE in their selected sequences showed similar performance for metastasis segmentation with a median Dice similarity coefficient (DSC) of 0.93-0.96. T1-CE alone likewise achieved a performance of 0.96 (IQR 0.93-0.97). The model trained with only FLAIR performed worse (DSC = 0.73, IQR 0.54-0.84). For edema segmentation, models that included both T1-CE and FLAIR performed best (median DSC = 0.93), while the remaining four models without simultaneous inclusion of these two sequences (T1-CE; T1; FLAIR; T1-CE+T1) reached a median DSC of 0.81-0.89.

CONCLUSION

Automatic segmentation of brain metastases with less than four input sequences is feasible with minimal or no loss of quality. A T1-CE-only protocol suffices for metastasis segmentation. In contrast, for edema segmentation, the combination of T1-CE and FLAIR seems to be important. Missing either T1-CE or FLAIR decreases performance. These findings may improve future imaging routines by omitting unnecessary sequences, thus speeding up procedures in daily clinical practice while allowing for optimal neural network-based target definitions.

Hypofractionated Stereotactic Radiotherapy vs. Single Fraction Stereotactic Radiosurgery to the Resection Cavity of Brain Metastases after Surgical Resection (SATURNUS trial): A Prospective, Randomized Phase III Trial

PURPOSE/OBJECTIVE(S)

The brain is a common site for metastases. Resection of large or symptomatic metastases is followed by stereotactic radiotherapy to prevent local recurrence. The optimal fractionation scheme is subject of ongoing research. Supported by emerging retrospective data, we hypothesize that hypofractionated stereotactic radiotherapy (HFSRT) is superior to single-fraction stereotactic radiosurgery (SRS) in terms of local control (LC). We designed the SATURNUS trial to prospectively demonstrate the superiority of HFSRT over SRS after resection of brain metastases in terms of LC.

MATERIALS/METHODS

The SATURNUS trial is a prospective, randomized phase III trial, currently recruiting patients at a single institution. Patients are 1:1 allocated to HFSRT or SRS using permuted block randomization. Affiliation to the treatment arm is solely blinded to the neuroradiologist assessing therapy response. HFSRT will be delivered with 6 - 7 x 5 Gy and SRS with 1 x 12-20 Gy, prescribed to the surrounding isodose, depending on cavity size and proximity to structures at risk. For SRS, doses do not exceed the maximum doses according to RTOG 90-05. Case number calculation was based on own institutional data on HFSRT (mean LC rate of 88% at 12 months) and data from large phase III trials on SRS (pooled mean LC rate of 66% at 12 months). Using a Chi-squared test of equal proportions (odds ratio = 1), setting test significance level (α) to 0.05, and allocating an equal number of patients to both treatment arms, 114 patients are needed to detect the superiority of HFSRT in terms of LC at 12 months (primary endpoint) with a power of at least 80%. Estimating a dropout rate of 10%, the case number was set to 126. The trial was registered with clinicaltrials.gov (NCT05160818). The first patient was enrolled in May 2021 and recruitment is ongoing. Patients with up to three resected brain metastases are considered for study participation. Further eligibility criteria are histologically confirmed solid tumor disease, resection cavity diameter ≤ 4 cm, consent to perform adjuvant radiotherapy by an interdisciplinary tumor board, completed wound healing, resection within the last six weeks at the time of study inclusion, age ≥ 18 years, KPS ≥ 60%, adequate contraceptive measures for fertile women / men and written informed consent. Patients are followed up clinically and with MRI at 6 weeks and 3, 6, 9 and 12 months after treatment. LC is assessed according to RANO-BM. Toxicity (CTCAE v4.03) is assessed as a secondary endpoint. The rather broad dose corridors allowed within the trial do justice to clinical reality, however, may represent a limitation of the trial. They are therefore addressed with a predefined subgroup analysis, as will be cavity size, among others. Participation of further study centers is desired. To the best of our knowledge, the SATURNUS trial is the only randomized phase III trial adequately powered to detect the superiority of HFSRT over SRS with regard to LC for resected brain metastases.

RESULTS

To be determined.

CONCLUSION

To be determined.

Clinical, radiological and pathological features of temporomesial tumors in the adult. A single center experience from 15 years

Introduction

The mesial temporal lobe plays a distinct role in epileptogenesis, and tumors in this part of the brain potentially have specific clinical and radiological features. Differentiating high-grade from lower-grade tumors or non-neoplastic lesions can be challenging, preventing the decision for early resection that can be critical in high-grade tumors.

Methods

A brain tumor database was analyzed retrospectively to identify patients with temporomesial tumors. We determined clinical features (age, sex, symptoms leading to clinical presentation) as well as neuroradiological (tumor location and the presence of contrast enhancement on initial magnetic resonance imaging (MRI)) and neuropathological findings.

Results

We identified 324 temporal tumors. 39 involved the mesial temporal lobe. 77% of temporomesial tumors occured in males, and 77% presented with seizures, regardless of tumor type or grade. In patients 50 years or older, 90% were male and 80% had glioblastoma (GBM); there was no GBM in patients younger than 50 years. 50% of GBMs lacked contrast enhancement. Male sex was significantly associated with GBM. In both contrast-enhancing and non-enhancing tumors, age of 50 years or older was also significantly associated with GBM.

Conclusion

In middle-aged and older patients with a mesial temporal lobe tumor, GBM is the most likely diagnosis even when there is no MRI contrast enhancement. Prolonged diagnostic workup or surveillance strategies should be avoided and early resection may be justified in these patients.

Epigenetic neural glioblastoma enhances synaptic integration and predicts therapeutic vulnerability

Neural-tumor interactions drive glioma growth as evidenced in preclinical models, but clinical validation is nascent. We present an epigenetically defined neural signature of glioblastoma that independently affects patients' survival. We use reference signatures of neural cells to deconvolve tumor DNA and classify samples into low- or high-neural tumors. High-neural glioblastomas exhibit hypomethylated CpG sites and upregulation of genes associated with synaptic integration. Single-cell transcriptomic analysis reveals high abundance of stem cell-like malignant cells classified as oligodendrocyte precursor and neural precursor cell-like in high-neural glioblastoma. High-neural glioblastoma cells engender neuron-to-glioma synapse formation in vitro and in vivo and show an unfavorable survival after xenografting. In patients, a high-neural signature associates with decreased survival as well as increased functional connectivity and can be detected via DNA analytes and brain-derived neurotrophic factor in plasma. Our study presents an epigenetically defined malignant neural signature in high-grade gliomas that is prognostically relevant.

Synthetic T2-weighted fat sat based on a generative adversarial network shows potential for scan time reduction in spine imaging in a multicenter test dataset

OBJECTIVES

T2-weighted (w) fat sat (fs) sequences, which are important in spine MRI, require a significant amount of scan time. Generative adversarial networks (GANs) can generate synthetic T2-w fs images. We evaluated the potential of synthetic T2-w fs images by comparing them to their true counterpart regarding image and fat saturation quality, and diagnostic agreement in a heterogenous, multicenter dataset.

METHODS

A GAN was used to synthesize T2-w fs from T1- and non-fs T2-w. The training dataset comprised scans of 73 patients from two scanners, and the test dataset, scans of 101 patients from 38 multicenter scanners. Apparent signal- and contrast-to-noise ratios (aSNR/aCNR) were measured in true and synthetic T2-w fs. Two neuroradiologists graded image (5-point scale) and fat saturation quality (3-point scale). To evaluate whether the T2-w fs images are indistinguishable, a Turing test was performed by eleven neuroradiologists. Six pathologies were graded on the synthetic protocol (with synthetic T2-w fs) and the original protocol (with true T2-w fs) by the two neuroradiologists.

RESULTS

aSNR and aCNR were not significantly different between the synthetic and true T2-w fs images. Subjective image quality was graded higher for synthetic T2-w fs (p = 0.023). In the Turing test, synthetic and true T2-w fs could not be distinguished from each other. The intermethod agreement between synthetic and original protocol ranged from substantial to almost perfect agreement for the evaluated pathologies.

DISCUSSION

The synthetic T2-w fs might replace a physical T2-w fs. Our approach validated on a challenging, multicenter dataset is highly generalizable and allows for shorter scan protocols.

KEY POINTS

• Generative adversarial networks can be used to generate synthetic T2-weighted fat sat images from T1- and non-fat sat T2-weighted images of the spine. • The synthetic T2-weighted fat sat images might replace a physically acquired T2-weighted fat sat showing a better image quality and excellent diagnostic agreement with the true T2-weighted fat images. • The present approach validated on a challenging, multicenter dataset is highly generalizable and allows for significantly shorter scan protocols.

Hypofractionated stereotactic radiotherapy (HFSRT) versus single fraction stereotactic radiosurgery (SRS) to the resection cavity of brain metastases after surgical resection (SATURNUS): study protocol for a randomized phase III trial

BACKGROUND

The brain is a common site for cancer metastases. In case of large and/or symptomatic brain metastases, neurosurgical resection is performed. Adjuvant radiotherapy is a standard procedure to minimize the risk of local recurrence and is increasingly performed as local stereotactic radiotherapy to the resection cavity. Both hypofractionated stereotactic radiotherapy (HFSRT) and single fraction stereotactic radiosurgery (SRS) can be applied in this case. Although adjuvant stereotactic radiotherapy to the resection cavity is widely used in clinical routine and recommended in international guidelines, the optimal fractionation scheme still remains unclear. The SATURNUS trial prospectively compares adjuvant HFSRT with SRS and seeks to detect the superiority of HFSRT over SRS in terms of local tumor control.

METHODS

In this single center two-armed randomized phase III trial, adjuvant radiotherapy to the resection cavity of brain metastases with HFSRT (6 - 7 × 5 Gy prescribed to the surrounding isodose) is compared to SRS (1 × 12-20 Gy prescribed to the surrounding isodose). Patients are randomized 1:1 into the two different treatment arms. The primary endpoint of the trial is local control at the resected site at 12 months. The trial is based on the hypothesis that HFSRT is superior to SRS in terms of local tumor control.

DISCUSSION

Although adjuvant stereotactic radiotherapy after resection of brain metastases is considered standard of care treatment, there is a need for further prospective research to determine the optimal fractionation scheme. To the best of our knowledge, the SATURNUS study is the only randomized phase III study comparing different regimes of postoperative stereotactic radiotherapy to the resection cavity adequately powered to detect the superiority of HFSRT regarding local control.

TRIAL REGISTRATION

The study was retrospectively registered with ClinicalTrials.gov, number NCT05160818, on December 16, 2021. The trial registry record is available on  https://clinicaltrials.gov/study/NCT05160818 . The presented protocol refers to version V1.3 from March 21, 2021.

AI-based detection of contrast-enhancing MRI lesions in patients with multiple sclerosis

BACKGROUND

Contrast-enhancing (CE) lesions are an important finding on brain magnetic resonance imaging (MRI) in patients with multiple sclerosis (MS) but can be missed easily. Automated solutions for reliable CE lesion detection are emerging; however, independent validation of artificial intelligence (AI) tools in the clinical routine is still rare.

METHODS

A three-dimensional convolutional neural network for CE lesion segmentation was trained externally on 1488 datasets of 934 MS patients from 81 scanners using concatenated information from FLAIR and T1-weighted post-contrast imaging. This externally trained model was tested on an independent dataset comprising 504 T1-weighted post-contrast and FLAIR image datasets of MS patients from clinical routine. Two neuroradiologists (R1, R2) labeled CE lesions for gold standard definition in the clinical test dataset. The algorithmic output was evaluated on both patient- and lesion-level.

RESULTS

On a patient-level, recall, specificity, precision, and accuracy of the AI tool to predict patients with CE lesions were 0.75, 0.99, 0.91, and 0.96. The agreement between the AI tool and both readers was within the range of inter-rater agreement (Cohen's kappa; AI vs. R1: 0.69; AI vs. R2: 0.76; R1 vs. R2: 0.76). On a lesion-level, false negative lesions were predominately found in infratentorial location, significantly smaller, and at lower contrast than true positive lesions (p < 0.05).

CONCLUSIONS

AI-based identification of CE lesions on brain MRI is feasible, approaching human reader performance in independent clinical data and might be of help as a second reader in the neuroradiological assessment of active inflammation in MS patients.

CRITICAL RELEVANCE STATEMENT

Al-based detection of contrast-enhancing multiple sclerosis lesions approaches human reader performance, but careful visual inspection is still needed, especially for infratentorial, small and low-contrast lesions.

The Impact of ioMRI on Glioblastoma Resection and Clinical Outcomes in a State-of-the-Art Neuro-Oncological Setup

Intraoperative magnetic resonance imaging (ioMRI) aims to improve gross total resection (GTR) in glioblastoma (GBM) patients. Despite some older randomized data on safety and feasibility, ioMRI's actual impact in a modern neurosurgical setting utilizing a larger armamentarium of techniques has not been sufficiently investigated to date. We therefore aimed to analyze its effects on residual tumor, patient outcome, and progression-free survival (PFS) in GBM patients in a modern high-volume center. Patients undergoing ioMRI for resection of supratentorial GBM were enrolled between March 2018 and June 2020. ioMRI was performed in all cases at the end of resection when surgeons expected complete macroscopic tumor removal. Extent of resection (EOR) was performed by volumetric analysis, with GTR defined as an EOR ≥ 95%, respectively. Progression-free survival (PFS) was analyzed through univariate and multivariate Cox proportional regression analyses. In total, we enrolled 172 patients. Mean EOR increased from 93.9% to 98.3% (p < 0.0001) due to ioMRI, equaling an increase in GTR rates from 78.5% to 93.0% (p = 0.0002). Residual tumor volume decreased from 1.3 ± 4.2 cm³ to 0.6 ± 2.5 cm³ (p = 0.0037). Logistic regression revealed recurrent GBM as a risk factor leading to subtotal resection (STR) (odds ratio (OR) = 3.047, 95% confidence interval (CI) 1.165-7.974, p = 0.023). Additional resection after ioMRI led to equally long PFS compared to patients with complete tumor removal before ioMRI (hazard ratio (HR) = 0.898, 95%-CI 0.543-1.483, p = 0.67). ioMRI considerably reduces residual tumor volume and helps to achieve comparable PFS, even in patients with unexpected residual tumor after initial resection before ioMRI.

The Brain Tumor Segmentation (BraTS) Challenge 2023: Brain MR Image Synthesis for Tumor Segmentation (BraSyn)

Automated brain tumor segmentation methods have become well-established and reached performance levels offering clear clinical utility. These methods typically rely on four input magnetic resonance imaging (MRI) modalities: T1-weighted images with and without contrast enhancement, T2-weighted images, and FLAIR images. However, some sequences are often missing in clinical practice due to time constraints or image artifacts, such as patient motion. Consequently, the ability to substitute missing modalities and gain segmentation performance is highly desirable and necessary for the broader adoption of these algorithms in the clinical routine. In this work, we present the establishment of the Brain MR Image Synthesis Benchmark (BraSyn) in conjunction with the Medical Image Computing and Computer-Assisted Intervention (MICCAI) 2023. The primary objective of this challenge is to evaluate image synthesis methods that can realistically generate missing MRI modalities when multiple available images are provided. The ultimate aim is to facilitate automated brain tumor segmentation pipelines. The image dataset used in the benchmark is diverse and multi-modal, created through collaboration with various hospitals and research institutions.

The Brain Tumor Segmentation (BraTS-METS) Challenge 2023: Brain Metastasis Segmentation on Pre-treatment MRI

Clinical monitoring of metastatic disease to the brain can be a laborious and timeconsuming process, especially in cases involving multiple metastases when the assessment is performed manually. The Response Assessment in Neuro-Oncology Brain Metastases (RANO-BM) guideline, which utilizes the unidimensional longest diameter, is commonly used in clinical and research settings to evaluate response to therapy in patients with brain metastases. However, accurate volumetric assessment of the lesion and surrounding peri-lesional edema holds significant importance in clinical decision-making and can greatly enhance outcome prediction. The unique challenge in performing segmentations of brain metastases lies in their common occurrence as small lesions. Detection and segmentation of lesions that are smaller than 10 mm in size has not demonstrated high accuracy in prior publications. The brain metastases challenge sets itself apart from previously conducted MICCAI challenges on glioma segmentation due to the significant variability in lesion size. Unlike gliomas, which tend to be larger on presentation scans, brain metastases exhibit a wide range of sizes and tend to include small lesions. We hope that the BraTS-METS dataset and challenge will advance the field of automated brain metastasis detection and segmentation.

The Brain Tumor Segmentation (BraTS) Challenge 2023: Glioma Segmentation in Sub-Saharan Africa Patient Population (BraTS-Africa)

Gliomas are the most common type of primary brain tumors. Although gliomas are relatively rare, they are among the deadliest types of cancer, with a survival rate of less than 2 years after diagnosis. Gliomas are challenging to diagnose, hard to treat and inherently resistant to conventional therapy. Years of extensive research to improve diagnosis and treatment of gliomas have decreased mortality rates across the Global North, while chances of survival among individuals in low- and middle-income countries (LMICs) remain unchanged and are significantly worse in Sub-Saharan Africa (SSA) populations. Long-term survival with glioma is associated with the identification of appropriate pathological features on brain MRI and confirmation by histopathology. Since 2012, the Brain Tumor Segmentation (BraTS) Challenge have evaluated state-of-the-art machine learning methods to detect, characterize, and classify gliomas. However, it is unclear if the state-of-the-art methods can be widely implemented in SSA given the extensive use of lower-quality MRI technology, which produces poor image contrast and resolution and more importantly, the propensity for late presentation of disease at advanced stages as well as the unique characteristics of gliomas in SSA (i.e., suspected higher rates of gliomatosis cerebri). Thus, the BraTS-Africa Challenge provides a unique opportunity to include brain MRI glioma cases from SSA in global efforts through the BraTS Challenge to develop and evaluate computer-aided-diagnostic (CAD) methods for the detection and characterization of glioma in resource-limited settings, where the potential for CAD tools to transform healthcare are more likely.

The ASNR-MICCAI Brain Tumor Segmentation (BraTS) Challenge 2023: Intracranial Meningioma

Meningiomas are the most common primary intracranial tumor in adults and can be associated with significant morbidity and mortality. Radiologists, neurosurgeons, neuro-oncologists, and radiation oncologists rely on multiparametric MRI (mpMRI) for diagnosis, treatment planning, and longitudinal treatment monitoring; yet automated, objective, and quantitative tools for non-invasive assessment of meningiomas on mpMRI are lacking. The BraTS meningioma 2023 challenge will provide a community standard and benchmark for state-of-the-art automated intracranial meningioma segmentation models based on the largest expert annotated multilabel meningioma mpMRI dataset to date. Challenge competitors will develop automated segmentation models to predict three distinct meningioma sub-regions on MRI including enhancing tumor, non-enhancing tumor core, and surrounding nonenhancing T2/FLAIR hyperintensity. Models will be evaluated on separate validation and held-out test datasets using standardized metrics utilized across the BraTS 2023 series of challenges including the Dice similarity coefficient and Hausdorff distance. The models developed during the course of this challenge will aid in incorporation of automated meningioma MRI segmentation into clinical practice, which will ultimately improve care of patients with meningioma.

Longitudinal Assessment of Multiple Sclerosis Lesion Load With Synthetic Magnetic Resonance Imaging-A Multicenter Validation Study

INTRODUCTION

Double inversion recovery (DIR) has been validated as a sensitive magnetic resonance imaging (MRI) contrast in multiple sclerosis (MS). Deep learning techniques can use basic input data to generate synthetic DIR (synthDIR) images that are on par with their acquired counterparts. As assessment of longitudinal MRI data is paramount in MS diagnostics, our study's purpose is to evaluate the utility of synthDIR longitudinal subtraction imaging for detection of disease progression in a multicenter data set of MS patients.

METHODS

We implemented a previously established generative adversarial network to synthesize DIR from input T1-weighted and fluid-attenuated inversion recovery (FLAIR) sequences for 214 MRI data sets from 74 patients and 5 different centers. One hundred and forty longitudinal subtraction maps of consecutive scans (follow-up scan-preceding scan) were generated for both acquired FLAIR and synthDIR. Two readers, blinded to the image origin, independently quantified newly formed lesions on the FLAIR and synthDIR subtraction maps, grouped into specific locations as outlined in the McDonald criteria.

RESULTS

Both readers detected significantly more newly formed MS-specific lesions in the longitudinal subtractions of synthDIR compared with acquired FLAIR (R1: 3.27 ± 0.60 vs 2.50 ± 0.69 [ P = 0.0016]; R2: 3.31 ± 0.81 vs 2.53 ± 0.72 [ P < 0.0001]). Relative gains in detectability were most pronounced in juxtacortical lesions (36% relative gain in lesion counts-pooled for both readers). In 5% of the scans, synthDIR subtraction maps helped to identify a disease progression missed on FLAIR subtraction maps.

CONCLUSIONS

Generative adversarial networks can generate high-contrast DIR images that may improve the longitudinal follow-up assessment in MS patients compared with standard sequences. By detecting more newly formed MS lesions and increasing the rates of detected disease activity, our methodology promises to improve clinical decision-making.

Imaging the WHO 2021 Brain Tumor Classification: Fully Automated Analysis of Imaging Features of Newly Diagnosed Gliomas

BACKGROUND

The fifth version of the World Health Organization (WHO) classification of tumors of the central nervous system (CNS) in 2021 brought substantial changes. Driven by the enhanced implementation of molecular characterization, some diagnoses were adapted while others were newly introduced. How these changes are reflected in imaging features remains scarcely investigated.

MATERIALS AND METHODS

We retrospectively analyzed 226 treatment-naive primary brain tumor patients from our institution who received extensive molecular characterization by epigenome-wide methylation microarray and were diagnosed according to the 2021 WHO brain tumor classification. From multimodal preoperative 3T MRI scans, we extracted imaging metrics via a fully automated, AI-based image segmentation and processing pipeline. Subsequently, we examined differences in imaging features between the three main glioma entities (glioblastoma, astrocytoma, and oligodendroglioma) and particularly investigated new entities such as astrocytoma, WHO grade 4.

RESULTS

Our results confirm prior studies that found significantly higher median CBV (p = 0.00003, ANOVA) and lower median ADC in contrast-enhancing areas of glioblastomas, compared to astrocytomas and oligodendrogliomas (p = 0.41333, ANOVA). Interestingly, molecularly defined glioblastoma, which usually does not contain contrast-enhancing areas, also shows significantly higher CBV values in the non-enhancing tumor than common glioblastoma and astrocytoma grade 4 (p = 0.01309, ANOVA).

CONCLUSIONS

This work provides extensive insights into the imaging features of gliomas in light of the new 2021 WHO CNS tumor classification. Advanced imaging shows promise in visualizing tumor biology and improving the diagnosis of brain tumor patients.

Brain metastases in the elderly – Impact of residual tumor volume on overall survival

Background

Due to demographic changes and an increased incidence of cancer with age, the number of patients with brain metastases (BMs) constantly increases, especially among the elderly. Novel systemic therapies, such as immunotherapy, have led to improved survival in recent years, but intracranial tumor progression may occur independently of a systemically effective therapy. Despite the growing number of geriatric patients, they are often overlooked in clinical trials, and there is no consensus on the impact of BM resection on survival.

Objectives

The aim of this study was to analyze the impact of resection and residual tumor volume on clinical outcome and overall survival (OS) in elderly patients suffering from BM.

Methods

Patients ≥ 75 years who had surgery for BM between April 2007 and January 2020 were retrospectively included. Residual tumor burden (RTB) was determined by segmentation of early postoperative brain MRI (72 h). Contrast-enhancing tumor subvolumes were segmented manually. “Postoperative tumor volume” refers to the targeted BMs. Impact of preoperative Karnofsky performance status scale (KPSS), age, sex and RTB on OS was analyzed. Survival analyses were performed using Kaplan-Meier estimates for the univariate analysis and the Cox regression proportional hazards model for the multivariate analysis.

Results

One hundred and one patients were included. Median age at surgery was 78 years (IQR 76-81). Sixty-two patients (61%) had a single BM; 16 patients (16%) had two BMs; 13 patients (13%) had three BMs; and 10 patients (10%) had more than three BMs. Median preoperative tumor burden was 10.3 cm3 (IQR 5–25 cm3), and postoperative tumor burden was 0 cm3 (IQR 0–1.1 cm3). Complete cytoreduction (RTB = 0) was achieved in 52 patients (52%). Complete resection of the targeted metastases was achieved in 78 patients (78%). Median OS was 7 months (IQR 2–11). In univariate analysis, high preoperative KPSS (HR 0.986, 95% CI 0.973–0.998, p = 0.026) and small postoperative tumor burden (HR 1.025, 95% CI 1.002–1.047, p = 0.029) were significantly associated with prolonged OS. Patients with RTB = 0 survived significantly longer than those with residual tumor did (12 [IQR 5–19] vs. 5 [IQR 3–7] months, p = 0.007). Furthermore, prolongation of survival was significantly associated with surgery in patients with favorable KPSS, with an adjusted HR of 0.986 (p = 0.026). However, there were no significances regarding age.

Conclusions

RTB is a strong predictor for prolonged OS, regardless of age or cancer type. Postoperative MRI should confirm the extent of resection, as intraoperative estimates do not warrant a complete resection. It is crucial to aim for maximal cytoreduction to achieve the best long-term outcomes for these patients, despite the fact the patients are advanced in age.

Molecular imaging of gliomas

Molecular characterization has become a key diagnostic tool for the classification and grading of primary brain tumors. Molecular markers, such as isocitrate dehydrogenase (IDH) mutation status, 1p/19q codeletion, methylation of the O(6)-methylguanine-DNA methyltransferase (MGMT) promoter, or CDKN2A/B homozygous deletion discriminate different tumor entities and grades, and play a crucial role for treatment response and prognosis. In recent years, magnetic resonance imaging (MRI), whose main functions has been to detect a tumor, to provide spatial information for neurosurgical and radiotherapy planning, and to monitor treatment response, has shown potential in assessing molecular features of gliomas from image-based biomarkers. As an outstanding example, numerous studies have proven that the T2/FLAIR mismatch sign can identify IDH-mutant, 1p/19q non-codeleted astrocytomas with a specificity of up to 100%. For other purposes, multiparametric MRI, often coupled with machine learning methods, seems to achieve the highest accuracy in predicting molecular markers. Relevant future applications might be anticipating changes in the molecular composition of gliomas and providing useful information about the cellular and genetic heterogeneity of gliomas, especially in the non-resected tumor parts.

Implementation of GAN-Based, Synthetic T2-Weighted Fat Saturated Images in the Routine Radiological Workflow Improves Spinal Pathology Detection

(1) Background and Purpose: In magnetic resonance imaging (MRI) of the spine, T2-weighted (T2-w) fat-saturated (fs) images improve the diagnostic assessment of pathologies. However, in the daily clinical setting, additional T2-w fs images are frequently missing due to time constraints or motion artifacts. Generative adversarial networks (GANs) can generate synthetic T2-w fs images in a clinically feasible time. Therefore, by simulating the radiological workflow with a heterogenous dataset, this study's purpose was to evaluate the diagnostic value of additional synthetic, GAN-based T2-w fs images in the clinical routine. (2) Methods: 174 patients with MRI of the spine were retrospectively identified. A GAN was trained to synthesize T2-w fs images from T1-w, and non-fs T2-w images of 73 patients scanned in our institution. Subsequently, the GAN was used to create synthetic T2-w fs images for the previously unseen 101 patients from multiple institutions. In this test dataset, the additional diagnostic value of synthetic T2-w fs images was assessed in six pathologies by two neuroradiologists. Pathologies were first graded on T1-w and non-fs T2-w images only, then synthetic T2-w fs images were added, and pathologies were graded again. Evaluation of the additional diagnostic value of the synthetic protocol was performed by calculation of Cohen's ĸ and accuracy in comparison to a ground truth (GT) grading based on real T2-w fs images, pre- or follow-up scans, other imaging modalities, and clinical information. (3) Results: The addition of the synthetic T2-w fs to the imaging protocol led to a more precise grading of abnormalities than when grading was based on T1-w and non-fs T2-w images only (mean ĸ GT versus synthetic protocol = 0.65; mean ĸ GT versus T1/T2 = 0.56; p = 0.043). (4) Conclusions: The implementation of synthetic T2-w fs images in the radiological workflow significantly improves the overall assessment of spine pathologies. Thereby, high-quality, synthetic T2-w fs images can be virtually generated by a GAN from heterogeneous, multicenter T1-w and non-fs T2-w contrasts in a clinically feasible time, which underlines the reproducibility and generalizability of our approach.

Reconstruction of the Corticospinal Tract in Patients with Motor-Eloquent High-Grade Gliomas Using Multilevel Fiber Tractography Combined with Functional Motor Cortex Mapping

BACKGROUND AND PURPOSE

Tractography of the corticospinal tract is paramount to presurgical planning and guidance of intraoperative resection in patients with motor-eloquent gliomas. It is well-known that DTI-based tractography as the most frequently used technique has relevant shortcomings, particularly for resolving complex fiber architecture. The purpose of this study was to evaluate multilevel fiber tractography combined with functional motor cortex mapping in comparison with conventional deterministic tractography algorithms.

MATERIALS AND METHODS

Thirty-one patients (mean age, 61.5 [SD, 12.2] years) with motor-eloquent high-grade gliomas underwent MR imaging with DWI (TR/TE = 5000/78 ms, voxel size = 2 × 2 × 2 mm3, 1 volume at b = 0 s/mm2, 32 volumes at b = 1000 s/mm2). DTI, constrained spherical deconvolution, and multilevel fiber tractography-based reconstruction of the corticospinal tract within the tumor-affected hemispheres were performed. The functional motor cortex was enclosed by navigated transcranial magnetic stimulation motor mapping before tumor resection and used for seeding. A range of angular deviation and fractional anisotropy thresholds (for DTI) was tested.

RESULTS

For all investigated thresholds, multilevel fiber tractography achieved the highest mean coverage of the motor maps (eg, angular threshold = 60°; multilevel/constrained spherical deconvolution/DTI, 25% anisotropy threshold = 71.8%, 22.6%, and 11.7%) and the most extensive corticospinal tract reconstructions (eg, angular threshold = 60°; multilevel/constrained spherical deconvolution/DTI, 25% anisotropy threshold = 26,485 mm3, 6308 mm3, and 4270 mm3).

CONCLUSIONS

Multilevel fiber tractography may improve the coverage of the motor cortex by corticospinal tract fibers compared with conventional deterministic algorithms. Thus, it could provide a more detailed and complete visualization of corticospinal tract architecture, particularly by visualizing fiber trajectories with acute angles that might be of high relevance in patients with gliomas and distorted anatomy.

A rare case of H3K27-altered diffuse midline glioma with multiple osseous and spinal metastases at the time of diagnosis

BACKGROUND

H3K27-altered diffuse midline gliomas are uncommon central nervous system tumors with extremely poor prognoses.

CASE PRESENTATION

We report the case of a 24-year-old man patient with multiple, inter alia osseous metastases who presented with back pain, hemi-hypoesthesia, and hemi-hyperhidrosis. The patient underwent combined radio-chemotherapy and demonstrated temporary improvement before deteriorating.

CONCLUSIONS

H3K27-altered diffuse midline glioma presents an infrequent but crucial differential diagnosis and should be considered in cases with rapid neurological deterioration and multiple intracranial and intramedullary tumor lesions in children and young adults. Combined radio-chemotherapy delayed the neurological deterioration, but unfortunately, progression occurred three months after the diagnosis.

Structured Reporting in Multiple Sclerosis - Consensus-Based Reporting Templates for Magnetic Resonance Imaging of the Brain and Spinal Cord

As a result of technical developments and greater availability of imaging equipment, the number of neuroradiological examinations is steadily increasing [1]. Due to improved image quality and sensitivity, more details can be detected making reporting more complex and time-intensive. At the same time, reliable algorithms increasingly allow quantitative image analysis that should be integrated in reports in a standardized manner. Moreover, increasing digitalization is resulting in a decrease in the personal exchange between neuroradiologists and referring disciplines, thereby making communication more difficult. The introduction of structured reporting tailored to the specific disease and medical issue [2, 3] and corresponding to at least the second reporting level as defined by the German Radiological Society (https://www.befundung.drg.de/de-DE/2908/strukturierte-befundung/) is therefore desirable to ensure that the quality standards of neuroradiological reports continue to be met.The advantages of structured reporting include a reduced workload for neuroradiologists and an information gain for referring physicians. A complete and standardized list with relevant details for image reporting is provided to neuroradiologists in accordance with the current state of knowledge, thereby ensuring that important points are not forgotten [4]. A time savings and increase in efficiency during reporting were also seen [5]. Further advantages include report clarity and consistency and better comparability in follow-up examinations regardless of the neuroradiologist's particular reporting style. This results in better communication with the referring disciplines and makes clinical decision significantly easier [6, 7]. Although the advantages are significant, any potential disadvantages like the reduction of autonomy in reporting and inadequate coverage of all relevant details and any incidental findings not associated with the main pathology in complex cases or in rare diseases should be taken into consideration [4]. Therefore, studies examining the advantages of structured reporting, promoting the introduction of this system in the clinical routine, and increasing the acceptance among neuroradiologists are still needed.Numerous specific templates for structured reporting, e. g., regarding diseases in cardiology and oncology, are already available on the website www.befundung.drg.de . Multiple sclerosis (MS) is an idiopathic chronic inflammatory and neurodegenerative disease of the central nervous system and is the most common non-trauma-based inflammatory neurological disease in young adults. Therefore, it has significant individual and socioeconomic relevance [8]. Magnetic resonance imaging (MRI) plays an important role in the diagnosis, prognosis evaluation, and follow-up of this disease. MRI is established as the central diagnostic method in the diagnostic criteria. Therefore, specific changes are seen on MRI in almost all patients with a verified MS diagnosis [9]. Reporting of MRI datasets regarding the brain and spinal cord of patients with MS includes examination of the images with respect to the relevant medical issue in order to determine whether the McDonald criteria, which were revised in 2017 [10] and define dissemination in time and space clinically as well as with respect to MRI based on the recommendations of the MAGNIMS groups [11, 12], are fulfilled. A more precise definition of lesion types and locations according to the recommendations of an international expert group [13] is discussed in the supplementary material. Spinal cord signal abnormalities are seen in up to 92 % of MS patients [14-16] and are primarily located in the cervical spine [15]. The recommendations of the MAGNIMS-CMSC-NAIMS working group published in 2021 [11] explicitly recommend the use of structured reporting for MS patients.Therefore, a reporting template for evaluating MRI examinations of the brain and spinal cord of patients with MS was created as part of the BMBF-funded DIFUTURE consortium in consensus with neuroradiological and neurological experts in concordance with the recommendations mentioned above [11] and was made available for broad use (https://github.com/DRGagit/ak_befundung). The goal is to facilitate efficient and comprehensive evaluation of patients with MS in the primary diagnostic workup and follow-up imaging. These reporting templates are consensus-based recommendations and do not make any claim to general validity or completeness. The information technology working group (@GIT) of the German Radiological Society and the German Society for Neuroradiology strive to keep the reporting templates presented here up-to-date with respect to new research data and recommendations of the MAGNIMS-CMSC-NAIMS group [11]. KEY POINTS:: · consensus-based reporting templates. · template for the structured reporting of MRI examinations of patients with multiple sclerosis. · structured reporting might facilitate communication between neuroradiologists and referring disciplines. CITATION FORMAT: · Riederer I, Mühlau M, Wiestler B et al. Structured Reporting in Multiple Sclerosis - Consensus-Based Reporting Templates for Magnetic Resonance Imaging of the Brain and Spinal Cord. Fortschr Röntgenstr 2023; 195: 135 - 138.

The Liver Tumor Segmentation Benchmark (LiTS)

In this work, we report the set-up and results of the Liver Tumor Segmentation Benchmark (LiTS), which was organized in conjunction with the IEEE International Symposium on Biomedical Imaging (ISBI) 2017 and the International Conferences on Medical Image Computing and Computer-Assisted Intervention (MICCAI) 2017 and 2018. The image dataset is diverse and contains primary and secondary tumors with varied sizes and appearances with various lesion-to-background levels (hyper-/hypo-dense), created in collaboration with seven hospitals and research institutions. Seventy-five submitted liver and liver tumor segmentation algorithms were trained on a set of 131 computed tomography (CT) volumes and were tested on 70 unseen test images acquired from different patients. We found that not a single algorithm performed best for both liver and liver tumors in the three events. The best liver segmentation algorithm achieved a Dice score of 0.963, whereas, for tumor segmentation, the best algorithms achieved Dices scores of 0.674 (ISBI 2017), 0.702 (MICCAI 2017), and 0.739 (MICCAI 2018). Retrospectively, we performed additional analysis on liver tumor detection and revealed that not all top-performing segmentation algorithms worked well for tumor detection. The best liver tumor detection method achieved a lesion-wise recall of 0.458 (ISBI 2017), 0.515 (MICCAI 2017), and 0.554 (MICCAI 2018), indicating the need for further research. LiTS remains an active benchmark and resource for research, e.g., contributing the liver-related segmentation tasks in http://medicaldecathlon.com/. In addition, both data and online evaluation are accessible via https://competitions.codalab.org/competitions/17094.

Hemodynamic MRI parameters to predict asymptomatic unilateral carotid artery stenosis with random forest machine learning

BACKGROUND

Internal carotid artery stenosis (ICAS) can cause stroke and cognitive decline. Associated hemodynamic impairments, which are most pronounced within individual watershed areas (iWSA) between vascular territories, can be assessed with hemodynamic-oxygenation-sensitive MRI and may help to detect severely affected patients. We aimed to identify the most sensitive parameters and volumes of interest (VOI) to predict high-grade ICAS with random forest machine learning. We hypothesized an increased predictive ability considering iWSAs and a decreased cognitive performance in correctly classified patients.

MATERIALS AND METHODS

Twenty-four patients with asymptomatic, unilateral, high-grade carotid artery stenosis and 24 age-matched healthy controls underwent MRI comprising pseudo-continuous arterial spin labeling (pCASL), breath-holding functional MRI (BH-fMRI), dynamic susceptibility contrast (DSC), T2 and T2* mapping, MPRAGE and FLAIR. Quantitative maps of eight perfusion, oxygenation and microvascular parameters were obtained. Mean values of respective parameters within and outside of iWSAs split into gray (GM) and white matter (WM) were calculated for both hemispheres and for interhemispheric differences resulting in 96 features. Random forest classifiers were trained on whole GM/WM VOIs, VOIs considering iWSAs and with additional feature selection, respectively.

RESULTS

The most sensitive features in decreasing order were time-to-peak (TTP), cerebral blood flow (CBF) and cerebral vascular reactivity (CVR), all of these inside of iWSAs. Applying iWSAs combined with feature selection yielded significantly higher receiver operating characteristics areas under the curve (AUC) than whole GM/WM VOIs (AUC: 0.84 vs. 0.90, p = 0.039). Correctly predicted patients presented with worse cognitive performances than frequently misclassified patients (Trail-making-test B: 152.5s vs. 94.4s, p = 0.034).

CONCLUSION

Random forest classifiers trained on multiparametric MRI data allow identification of the most relevant parameters and VOIs to predict ICAS, which may improve personalized treatments.

Retrospective cohort study to devise a treatment decision score predicting adverse 24-month radiological activity in early multiple sclerosis

Background

Multiple sclerosis (MS) is a chronic neuroinflammatory disease affecting about 2.8 million people worldwide. Disease course after the most common diagnoses of relapsing-remitting multiple sclerosis (RRMS) and clinically isolated syndrome (CIS) is highly variable and cannot be reliably predicted. This impairs early personalized treatment decisions.

Objectives

The main objective of this study was to algorithmically support clinical decision-making regarding the options of early platform medication or no immediate treatment of patients with early RRMS and CIS.

Design

Retrospective monocentric cohort study within the Data Integration for Future Medicine (DIFUTURE) Consortium.

Methods

Multiple data sources of routine clinical, imaging and laboratory data derived from a large and deeply characterized cohort of patients with MS were integrated to conduct a retrospective study to create and internally validate a treatment decision score [Multiple Sclerosis Treatment Decision Score (MS-TDS)] through model-based random forests (RFs). The MS-TDS predicts the probability of no new or enlarging lesions in cerebral magnetic resonance images (cMRIs) between 6 and 24 months after the first cMRI.

Results

Data from 65 predictors collected for 475 patients between 2008 and 2017 were included. No medication and platform medication were administered to 277 (58.3%) and 198 (41.7%) patients. The MS-TDS predicted individual outcomes with a cross-validated area under the receiver operating characteristics curve (AUROC) of 0.624. The respective RF prediction model provides patient-specific MS-TDS and probabilities of treatment success. The latter may increase by 5-20% for half of the patients if the treatment considered superior by the MS-TDS is used.

Conclusion

Routine clinical data from multiple sources can be successfully integrated to build prediction models to support treatment decision-making. In this study, the resulting MS-TDS estimates individualized treatment success probabilities that can identify patients who benefit from early platform medication. External validation of the MS-TDS is required, and a prospective study is currently being conducted. In addition, the clinical relevance of the MS-TDS needs to be established.