Davatzikos, Christos

Pediatric central nervous system tumors are the leading cause of cancer-related deaths in children. The five-year survival rate for high-grade glioma in children is less than 20%. The development of new treatments is dependent upon multi-institutional collaborative clinical trials requiring reproducible and accurate centralized response assessment. We present the results of the BraTS-PEDs 2023 challenge, the first Brain Tumor Segmentation (BraTS) challenge focused on pediatric brain tumors. This challenge utilized data acquired from multiple international consortia dedicated to pediatric neuro-oncology and clinical trials. BraTS-PEDs 2023 aimed to evaluate volumetric segmentation algorithms for pediatric brain gliomas from magnetic resonance imaging using standardized quantitative performance evaluation metrics employed across the BraTS 2023 challenges. The top-performing AI approaches for pediatric tumor analysis included ensembles of nnU-Net and Swin UNETR, Auto3DSeg, or nnU-Net with a self-supervised framework. The BraTS-PEDs 2023 challenge fostered collaboration between clinicians (neuro-oncologists, neuroradiologists) and AI/imaging scientists, promoting faster data sharing and the development of automated volumetric analysis techniques. These advancements could significantly benefit clinical trials and improve the care of children with brain tumors.

We describe the design and results from the BraTS 2023 Intracranial Meningioma Segmentation Challenge. The BraTS Meningioma Challenge differed from prior BraTS Glioma challenges in that it focused on meningiomas, which are typically benign extra-axial tumors with diverse radiologic and anatomical presentation and a propensity for multiplicity. Nine participating teams each developed deep-learning automated segmentation models using image data from the largest multi-institutional systematically expert annotated multilabel multi-sequence meningioma MRI dataset to date, which included 1000 training set cases, 141 validation set cases, and 283 hidden test set cases. Each case included T2, FLAIR, T1, and T1Gd brain MRI sequences with associated tumor compartment labels delineating enhancing tumor, non-enhancing tumor, and surrounding non-enhancing FLAIR hyperintensity. Participant automated segmentation models were evaluated and ranked based on a scoring system evaluating lesion-wise metrics including dice similarity coefficient (DSC) and 95% Hausdorff Distance. The top ranked team had a lesion-wise median dice similarity coefficient (DSC) of 0.976, 0.976, and 0.964 for enhancing tumor, tumor core, and whole tumor, respectively and a corresponding average DSC of 0.899, 0.904, and 0.871, respectively. These results serve as state-of-the-art benchmarks for future pre-operative meningioma automated segmentation algorithms. Additionally, we found that 1286 of 1424 cases (90.3%) had at least 1 compartment voxel abutting the edge of the skull-stripped image edge, which requires further investigation into optimal pre-processing face anonymization steps.

Accurate prediction of progression in subjects at risk of Alzheimer's disease is crucial for enrolling the right subjects in clinical trials. However, a prospective comparison of state-of-the-art algorithms for predicting disease onset and progression is currently lacking. We present the findings of "The Alzheimer's Disease Prediction Of Longitudinal Evolution" (TADPOLE) Challenge, which compared the performance of 92 algorithms from 33 international teams at predicting the future trajectory of 219 individuals at risk of Alzheimer's disease. Challenge participants were required to make a prediction, for each month of a 5-year future time period, of three key outcomes: clinical diagnosis, Alzheimer's Disease Assessment Scale Cognitive Subdomain (ADAS-Cog13), and total volume of the ventricles. The methods used by challenge participants included multivariate linear regression, machine learning methods such as support vector machines and deep neural networks, as well as disease progression models. No single submission was best at predicting all three outcomes. For clinical diagnosis and ventricle volume prediction, the best algorithms strongly outperform simple baselines in predictive ability. However, for ADAS-Cog13 no single submitted prediction method was significantly better than random guesswork. Two ensemble methods based on taking the mean and median over all predictions, obtained top scores on almost all tasks. Better than average performance at diagnosis prediction was generally associated with the additional inclusion of features from cerebrospinal fluid (CSF) samples and diffusion tensor imaging (DTI). On the other hand, better performance at ventricle volume prediction was associated with inclusion of summary statistics, such as the slope or maxima/minima of patient-specific biomarkers. On a limited, cross-sectional subset of the data emulating clinical trials, performance of the best algorithms at predicting clinical diagnosis decreased only slightly (2 percentage points) compared to the full longitudinal dataset. The submission system remains open via the website https://tadpole.grand-challenge.org, while TADPOLE SHARE (https://tadpole-share.github.io/) collates code for submissions. TADPOLE's unique results suggest that current prediction algorithms provide sufficient accuracy to exploit biomarkers related to clinical diagnosis and ventricle volume, for cohort refinement in clinical trials for Alzheimer's disease. However, results call into question the usage of cognitive test scores for patient selection and as a primary endpoint in clinical trials.

AbstractWe aimed to evaluate the value of ATN biomarker classification system (amyloid beta [A], pathologic tau [T], and neurodegeneration [N]) for predicting conversion from mild cognitive impairment (MCI) to dementia. In a sample of people with MCI (n = 415) we assessed predictive performance of ATN classification using empirical knowledge‐based cut‐offs for each component of ATN and compared it to two data‐driven approaches, logistic regression and RUSBoost machine learning classifiers, which used continuous clinical or biomarker scores. In data‐driven approaches, we identified ATN features that distinguish normals from individuals with dementia and used them to classify persons with MCI into dementia‐like and normal groups. Both data‐driven classification methods performed better than the empirical cut‐offs for ATN biomarkers in predicting conversion to dementia. Classifiers that used clinical features performed as well as classifiers that used ATN biomarkers for prediction of progression to dementia. We discuss that data‐driven modeling approaches can improve our ability to predict disease progression and might have implications in future clinical trials.

AbstractBackgroundThe NIA‐AA Research Framework on Alzheimer’s disease (AD) represents an important advance in the biological characterization of the AD spectrum. While this framework predicts disease progression, definitions of amyloid, tau, and neurodegeneration positivity based on cut‐scores may limit the performance of predictive models.Method252 cognitively normal (CN), 424 amnestic mild cognitive impairment (aMCI) and 128 AD participants were included in this study. aMCI participants at baseline were classified using 2 different methods: 1) Using conventional AT[N] criteria based on proposed cut‐offs in CSF or brain imaging measures: participants were classified on the AD continuum (A+T‐N‐, A+T+N‐, A+T‐N+, A+T+N+) and non‐AD continuum (all other subgroups); and 2) using a machine learning (ML) based method (ensemble linear discriminant model built using CN and AD participants) to classify MCI participants as CN‐like or AD‐like based on continuous CSF biomarkers, regional amyloid PET, FDG‐PET, and volumetric MRI (variables contributing to AT[N] classification; Table 1). Predictive performance of AT[N]‐based classification and ML‐based classification were assessed using clinical outcomes at 0.5, 1, 2, 3, 4, and 5 years of follow‐up.ResultA total of 414 aMCI participants had at least one wave of follow‐up (N of 397, 400, 346, 297, 238, and 93 at 0.5, 1, 2, 3, 4, and 5 years, respectively). The progression rate from aMCI to AD was 5.8% at 6m, 9.5% at 1y, 17.9% at 2y, 19.9% at 3y, 20.2% at 4y, and 15% at 5y of follow‐up. Presence of AD pathology at baseline (AT[N]‐based AD continuum) predicted progression to AD with high sensitivity but modest specificity during follow up (Table 2). ML‐based classification was less sensitive but substantially more specific. ML‐based classification models were significantly more accurate than AT[N]‐based classification at all follow‐up periods (McNemar test, p‐value<0.001 for all).ConclusionA single cut‐point approach used in AT[N] classification lacks accuracy when research questions require high diagnostic or prognostic certainty. A multivariate approach using ML methods can improve accuracy of prediction of disease progression. PPVs were higher at all follow‐up time points for ML‐based classification, indicating that progression to AD occurs at a higher rate in persons identified by ML.