By employing machine learning techniques, we were able to demonstrate that imaging patterns are highly predictive of patient survival. Additionally, we found that GB subtypes have distinctive imaging phenotypes. These results reveal that when imaging markers related to infiltration, cell density, microvascularity, and blood-brain barrier compromise are integrated via advanced pattern analysis methods, they form very accurate predictive biomarkers. These predictive markers used solely preoperative images, hence they can significantly augment diagnosis and treatment of GB patients.

Evaluating various algorithms for the inter-subject registration of brain magnetic resonance images (MRI) is a necessary topic receiving growing attention. Existing studies evaluated image registration algorithms in specific tasks or using specific databases (e.g., only for skull-stripped images, only for single-site images, etc.). Consequently, the choice of registration algorithms seems task- and usage/parameter-dependent. Nevertheless, recent large-scale, often multi-institutional imaging-related studies create the need and raise the question whether some registration algorithms can 1) generally apply to various tasks/databases posing various challenges; 2) perform consistently well, and while doing so, 3) require minimal or ideally no parameter tuning. In seeking answers to this question, we evaluated 12 general-purpose registration algorithms, for their generality, accuracy and robustness. We fixed their parameters at values suggested by algorithm developers as reported in the literature. We tested them in 7 databases/tasks, which present one or more of 4 commonly-encountered challenges: 1) inter-subject anatomical variability in skull-stripped images; 2) intensity homogeneity, noise and large structural differences in raw images; 3) imaging protocol and field-of-view (FOV) differences in multi-site data; and 4) missing correspondences in pathology-bearing images. Totally 7,562 registrations were performed. Registration accuracies were measured by (multi-)expert-annotated landmarks or regions of interest (ROIs). To ensure reproducibility, we used public software tools, public databases (whenever possible), and we fully disclose the parameter settings. We show evaluation results, and discuss the performances in light of algorithms’ similarity metrics, transformation models and optimization strategies. We also discuss future directions for the algorithm development and evaluations.

BackgroundAutopsy series commonly report a high percentage of coincident pathologies in demented patients, including patients with a clinical diagnosis of dementia of the Alzheimer type (DAT). However many clinical and biomarker studies report cases with a single neurodegenerative disease. We examined multimodal biomarker correlates of the consecutive series of the first 22 Alzheimer’s Disease Neuroimaging Initiative autopsies. Clinical data, neuropsychological measures, cerebrospinal fluid Aβ, total and phosphorylated tau and α-synuclein and MRI and FDG-PET scans.ResultsClinical diagnosis was either probable DAT or Alzheimer’s disease (AD)-type mild cognitive impairment (MCI) at last evaluation prior to death. All patients had a pathological diagnosis of AD, but only four had pure AD. A coincident pathological diagnosis of dementia with Lewy bodies (DLB), medial temporal lobe pathology (TDP-43 proteinopathy, argyrophilic grain disease and hippocampal sclerosis), referred to collectively here as MTL, and vascular pathology were present in 45.5%, 40.0% and 22.7% of these patients, respectively. Hallucinations were a strong predictor of coincident DLB (100% specificity) and a more severe dysexecutive profile was also a useful predictor of coincident DLB (80.0% sensitivity and 83.3% specificity). Occipital FDG-PET hypometabolism accurately classified coincident DLB (80% sensitivity and 100% specificity). Subjects with coincident MTL showed lower hippocampal volume.ConclusionsBiomarkers can be used to independently predict coincident AD and DLB pathology, a common finding in amnestic MCI and DAT patients. Cohorts with comprehensive neuropathological assessments and multimodal biomarkers are needed to characterize independent predictors for the different neuropathological substrates of cognitive impairment.