Imaging meningioma biology: Machine learning predicts integrated risk score in WHO grade 2/3 meningioma.

Background: Meningiomas are the most common primary brain tumors. While most are benign (WHO grade 1) and have a favorable prognosis, up to one-fourth are classified as higher-grade, falling into WHO grade 2 or 3 categories. Recently, an integrated risk score (IRS) pertaining to tumor biology was developed and its prognostic relevance was validated in a large, multicenter study. We hypothesized imaging data to be reflective of the IRS. Thus, we assessed the potential of a machine learning classifier for its noninvasive prediction using preoperative magnetic resonance imaging (MRI). Methods: In total, 160 WHO grade 2 and 3 meningioma patients from 2 university centers were included in this study. All patients underwent surgery with histopathological workup including methylation analysis. Preoperative MRI scans were automatically segmented, and radiomic parameters were extracted. Using a random forest classifier, 3 machine learning classifiers (1 multiclass classifier for IRS and 2 binary classifiers for low-risk and high-risk prediction, respectively) were developed in a training set (120 patients) and independently tested in a hold-out test set (40 patients). Results: Multiclass IRS classification had a test set area under the curve (AUC) of 0.7, mostly driven by the difficulties in clearly separating medium-risk from high-risk patients. Consequently, a classifier predicting low-risk IRS versus medium-/high-risk showed a very high test accuracy of 90% (AUC 0.88). In particular, "sphericity" was associated with low-risk IRS classification. Conclusion: The IRS, in particular molecular low-risk, can be predicted from imaging data with high accuracy, making this important prognostic classification accessible by imaging.

Radiomics workflow definition & challenges - German priority program 2177 consensus statement on clinically applied radiomics.

OBJECTIVES: Achieving a consensus on a definition for different aspects of radiomics workflows to support their translation into clinical usage. Furthermore, to assess the perspective of experts on important challenges for a successful clinical workflow implementation. MATERIALS AND METHODS: The consensus was achieved by a multi-stage process. Stage 1 comprised a definition screening, a retrospective analysis with semantic mapping of terms found in 22 workflow definitions, and the compilation of an initial baseline definition. Stages 2 and 3 consisted of a Delphi process with over 45 experts hailing from sites participating in the German Research Foundation (DFG) Priority Program 2177. Stage 2 aimed to achieve a broad consensus for a definition proposal, while stage 3 identified the importance of translational challenges. RESULTS: Workflow definitions from 22 publications (published 2012-2020) were analyzed. Sixty-nine definition terms were extracted, mapped, and semantic ambiguities (e.g., homonymous and synonymous terms) were identified and resolved. The consensus definition was developed via a Delphi process. The final definition comprising seven phases and 37 aspects reached a high overall consensus (> 89% of experts "agree" or "strongly agree"). Two aspects reached no strong consensus. In addition, the Delphi process identified and characterized from the participating experts' perspective the ten most important challenges in radiomics workflows. CONCLUSION: To overcome semantic inconsistencies between existing definitions and offer a well-defined, broad, referenceable terminology, a consensus workflow definition for radiomics-based setups and a terms mapping to existing literature was compiled. Moreover, the most relevant challenges towards clinical application were characterized. CRITICAL RELEVANCE STATEMENT: Lack of standardization represents one major obstacle to successful clinical translation of radiomics. Here, we report a consensus workflow definition on different aspects of radiomics studies and highlight important challenges to advance the clinical adoption of radiomics. KEY POINTS: Published radiomics workflow terminologies are inconsistent, hindering standardization and translation. A consensus radiomics workflow definition proposal with high agreement was developed. Publicly available result resources for further exploitation by the scientific community.

Resolving spatial response heterogeneity in glioblastoma.

PURPOSE: Spatial intratumoral heterogeneity poses a significant challenge for accurate response assessment in glioblastoma. Multimodal imaging coupled with advanced image analysis has the potential to unravel this response heterogeneity. METHODS: Based on automated tumor segmentation and longitudinal registration with follow-up imaging, we categorized contrast-enhancing voxels of 61 patients with suspected recurrence of glioblastoma into either true tumor progression (TP) or pseudoprogression (PsP). To allow the unbiased analysis of semantically related image regions, adjacent voxels with similar values of cerebral blood volume (CBV), FET-PET, and contrast-enhanced T1w were automatically grouped into supervoxels. We then extracted first-order statistics as well as texture features from each supervoxel. With these features, a Random Forest classifier was trained and validated employing a 10-fold cross-validation scheme. For model evaluation, the area under the receiver operating curve, as well as classification performance metrics were calculated. RESULTS: Our image analysis pipeline enabled reliable spatial assessment of tumor response. The predictive model reached an accuracy of 80.0% and a macro-weighted AUC of 0.875, which takes class imbalance into account, in the hold-out samples from cross-validation on supervoxel level. Analysis of feature importances confirmed the significant role of FET-PET-derived features. Accordingly, TP- and PsP-labeled supervoxels differed significantly in their 10th and 90th percentile, as well as the median of tumor-to-background normalized FET-PET. However, CBV- and T1c-related features also relevantly contributed to the model's performance. CONCLUSION: Disentangling the intratumoral heterogeneity in glioblastoma holds immense promise for advancing precise local response evaluation and thereby also informing more personalized and localized treatment strategies in the future.

A prognostic neural epigenetic signature in high-grade glioma.

Neural-tumor interactions drive glioma growth as evidenced in preclinical models, but clinical validation is limited. We present an epigenetically defined neural signature of glioblastoma that independently predicts 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 a high abundance of malignant stemcell-like cells in high-neural glioblastoma, primarily of the neural lineage. These cells are further classified as neural-progenitor-cell-like, astrocyte-like and oligodendrocyte-progenitor-like, alongside oligodendrocytes and excitatory neurons. In line with these findings, 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 is associated with decreased overall and progression-free survival. High-neural tumors also exhibit increased functional connectivity in magnetencephalography and resting-state magnet resonance imaging and can be detected via DNA analytes and brain-derived neurotrophic factor in patients' plasma. The prognostic importance of the neural signature was further validated in patients diagnosed with diffuse midline glioma. Our study presents an epigenetically defined malignant neural signature in high-grade gliomas that is prognostically relevant. High-neural gliomas likely require a maximized surgical resection approach for improved outcomes.

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 U-Nets. 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 T1-weighted and FLAIR images, collected in-house from a 3T MRI scanner, and expert neuroradiologists manually segmented the utilized lesion maps for training. LST-AI also includes a lesion location annotation tool, labeling lesions as periventricular, infratentorial, and juxtacortical according to the 2017 McDonald criteria, and, additionally, as 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 10 mm3 and 100 mm3. 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.

Toward a systematic grading for the selection of patients to undergo awake surgery: identifying suitable predictor variables.

Background: Awake craniotomy is the standard of care for treating language eloquent gliomas. However, depending on preoperative functionality, it is not feasible in each patient and selection criteria are highly heterogeneous. Thus, this study aimed to identify broadly applicable predictor variables allowing for a more systematic and objective patient selection. Methods: We performed post-hoc analyses of preoperative language status, patient and tumor characteristics including language eloquence of 96 glioma patients treated in a single neurosurgical center between 05/2018 and 01/2021. Multinomial logistic regression and stepwise variable selection were applied to identify significant predictors of awake surgery feasibility. Results: Stepwise backward selection confirmed that a higher number of paraphasias, lower age, and high language eloquence level were suitable indicators for an awake surgery in our cohort. Subsequent descriptive and ROC-analyses indicated a cut-off at ≤54 years and a language eloquence level of at least 6 for awake surgeries, which require further validation. A high language eloquence, lower age, preexisting semantic and phonological aphasic symptoms have shown to be suitable predictors. Conclusion: The combination of these factors may act as a basis for a systematic and standardized grading of patients' suitability for an awake craniotomy which is easily integrable into the preoperative workflow across neurosurgical centers.

Radiomics-based prediction of local control in patients with brain metastases following postoperative stereotactic radiotherapy.

BACKGROUND: Surgical resection is the standard of care for patients with large or symptomatic brain metastases (BMs). Despite improved local control after adjuvant stereotactic radiotherapy, the risk of local failure (LF) persists. Therefore, we aimed to develop and externally validate a pre-therapeutic radiomics-based prediction tool to identify patients at high LF risk. METHODS: Data were collected from A Multicenter Analysis of Stereotactic Radiotherapy to the Resection Cavity of Brain Metastases (AURORA) retrospective study (training cohort: 253 patients from two centers; external test cohort: 99 patients from five centers). Radiomic features were extracted from the contrast-enhancing BM (T1-CE MRI sequence) and the surrounding edema (FLAIR sequence). Different combinations of radiomic and clinical features were compared. The final models were trained on the entire training cohort with the best parameter set previously determined by internal 5-fold cross-validation and tested on the external test set. RESULTS: The best performance in the external test was achieved by an elastic net regression model trained with a combination of radiomic and clinical features with a concordance index (CI) of 0.77, outperforming any clinical model (best CI: 0.70). The model effectively stratified patients by LF risk in a Kaplan-Meier analysis (p < 0.001) and demonstrated an incremental net clinical benefit. At 24 months, we found LF in 9% and 74% of the low and high-risk groups, respectively. CONCLUSIONS: A combination of clinical and radiomic features predicted freedom from LF better than any clinical feature set alone. Patients at high risk for LF may benefit from stricter follow-up routines or intensified therapy.

Quantitative Assessment of Tumor Contact with Neurogenic Zones and Its Effects on Survival: Insights beyond Traditional Predictors.

So far, the cellular origin of glioblastoma (GBM) needs to be determined, with prevalent theories suggesting emergence from transformed endogenous stem cells. Adult neurogenesis primarily occurs in two brain regions: the subventricular zone (SVZ) and the subgranular zone (SGZ) of the hippocampal dentate gyrus. Whether the proximity of GBM to these neurogenic niches affects patient outcome remains uncertain. Previous studies often rely on subjective assessments, limiting the reliability of those results. In this study, we assessed the impact of GBM's relationship with the cortex, SVZ and SGZ on clinical variables using fully automated segmentation methods. In 177 glioblastoma patients, we calculated optimal cutpoints of minimal distances to the SVZ and SGZ to distinguish poor from favorable survival. The impact of tumor contact with neurogenic zones on clinical parameters, such as overall survival, multifocality, MGMT promotor methylation, Ki-67 and KPS score was also examined by multivariable regression analysis, chi-square test and Mann-Whitney-U. The analysis confirmed shorter survival in tumors contacting the SVZ with an optimal cutpoint of 14 mm distance to the SVZ, separating poor from more favorable survival. In contrast, tumor contact with the SGZ did not negatively affect survival. We did not find significant correlations with multifocality or MGMT promotor methylation in tumors contacting the SVZ, as previous studies discussed. These findings suggest that the spatial relationship between GBM and neurogenic niches needs to be assessed differently. Objective measurements disprove prior assumptions, warranting further research on this topic.

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.

Virtual reality-empowered deep-learning analysis of brain cells.

Automated detection of specific cells in three-dimensional datasets such as whole-brain light-sheet image stacks is challenging. Here, we present DELiVR, a virtual reality-trained deep-learning pipeline for detecting c-Fos+ cells as markers for neuronal activity in cleared mouse brains. Virtual reality annotation substantially accelerated training data generation, enabling DELiVR to outperform state-of-the-art cell-segmenting approaches. Our pipeline is available in a user-friendly Docker container that runs with a standalone Fiji plugin. DELiVR features a comprehensive toolkit for data visualization and can be customized to other cell types of interest, as we did here for microglia somata, using Fiji for dataset-specific training. We applied DELiVR to investigate cancer-related brain activity, unveiling an activation pattern that distinguishes weight-stable cancer from cancers associated with weight loss. Overall, DELiVR is a robust deep-learning tool that does not require advanced coding skills to analyze whole-brain imaging data in health and disease.

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.

Human-Level Differentiation of Medulloblastoma from Pilocytic Astrocytoma: A Real-World Multicenter Pilot Study.

Medulloblastoma and pilocytic astrocytoma are the two most common pediatric brain tumors with overlapping imaging features. In this proof-of-concept study, we investigated using a deep learning classifier trained on a multicenter data set to differentiate these tumor types. We developed a patch-based 3D-DenseNet classifier, utilizing automated tumor segmentation. Given the heterogeneity of imaging data (and available sequences), we used all individually available preoperative imaging sequences to make the model robust to varying input. We compared the classifier to diagnostic assessments by five readers with varying experience in pediatric brain tumors. Overall, we included 195 preoperative MRIs from children with medulloblastoma (n = 69) or pilocytic astrocytoma (n = 126) across six university hospitals. In the 64-patient test set, the DenseNet classifier achieved a high AUC of 0.986, correctly predicting 62/64 (97%) diagnoses. It misclassified one case of each tumor type. Human reader accuracy ranged from 100% (expert neuroradiologist) to 80% (resident). The classifier performed significantly better than relatively inexperienced readers (p < 0.05) and was on par with pediatric neuro-oncology experts. Our proof-of-concept study demonstrates a deep learning model based on automated tumor segmentation that can reliably preoperatively differentiate between medulloblastoma and pilocytic astrocytoma, even in heterogeneous data.

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.

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.

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.

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.

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.

(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.

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.