Computational limits to the legibility of the imaged human brain.

Our knowledge of the organisation of the human brain at the population-level is yet to translate into power to predict functional differences at the individual-level, limiting clinical applications and casting doubt on the generalisability of inferred mechanisms. It remains unknown whether the difficulty arises from the absence of individuating biological patterns within the brain, or from limited power to access them with the models and compute at our disposal. Here we comprehensively investigate the resolvability of such patterns with data and compute at unprecedented scale. Across 23 810 unique participants from UK Biobank, we systematically evaluate the predictability of 25 individual biological characteristics, from all available combinations of structural and functional neuroimaging data. Over 4526 GPU*hours of computation, we train, optimize, and evaluate out-of-sample 700 individual predictive models, including fully-connected feed-forward neural networks of demographic, psychological, serological, chronic disease, and functional connectivity characteristics, and both uni- and multi-modal 3D convolutional neural network models of macro- and micro-structural brain imaging. We find a marked discrepancy between the high predictability of sex (balanced accuracy 99.7%), age (mean absolute error 2.048 years, R2 0.859), and weight (mean absolute error 2.609Kg, R2 0.625), for which we set new state-of-the-art performance, and the surprisingly low predictability of other characteristics. Neither structural nor functional imaging predicted an individual's psychology better than the coincidence of common chronic disease (p < 0.05). Serology predicted chronic disease (p < 0.05) and was best predicted by it (p < 0.001), followed by structural neuroimaging (p < 0.05). Our findings suggest either more informative imaging or more powerful models will be needed to decipher individual level characteristics from the human brain. We make our models and code openly available.

Brain tumour genetic network signatures of survival.

Tumour heterogeneity is increasingly recognized as a major obstacle to therapeutic success across neuro-oncology. Gliomas are characterized by distinct combinations of genetic and epigenetic alterations, resulting in complex interactions across multiple molecular pathways. Predicting disease evolution and prescribing individually optimal treatment requires statistical models complex enough to capture the intricate (epi)genetic structure underpinning oncogenesis. Here, we formalize this task as the inference of distinct patterns of connectivity within hierarchical latent representations of genetic networks. Evaluating multi-institutional clinical, genetic and outcome data from 4023 glioma patients over 14 years, across 12 countries, we employ Bayesian generative stochastic block modelling to reveal a hierarchical network structure of tumour genetics spanning molecularly confirmed glioblastoma, IDH-wildtype; oligodendroglioma, IDH-mutant and 1p/19q codeleted; and astrocytoma, IDH-mutant. Our findings illuminate the complex dependence between features across the genetic landscape of brain tumours and show that generative network models reveal distinct signatures of survival with better prognostic fidelity than current gold standard diagnostic categories.

VASARI-auto: Equitable, efficient, and economical featurisation of glioma MRI.

The VASARI MRI feature set is a quantitative system designed to standardise glioma imaging descriptions. Though effective, deriving VASARI is time-consuming and seldom used clinically. We sought to resolve this problem with software automation and machine learning. Using glioma data from 1172 patients, we developed VASARI-auto, an automated labelling software applied to open-source lesion masks and an openly available tumour segmentation model. Consultant neuroradiologists independently quantified VASARI features in 100 held-out glioblastoma cases. We quantified 1) agreement across neuroradiologists and VASARI-auto, 2) software equity, 3) an economic workforce analysis, and 4) fidelity in predicting survival. Tumour segmentation was compatible with the current state of the art and equally performant regardless of age or sex. A modest inter-rater variability between in-house neuroradiologists was comparable to between neuroradiologists and VASARI-auto, with far higher agreement between VASARI-auto methods. The time for neuroradiologists to derive VASARI was substantially higher than VASARI-auto (mean time per case 317 vs. 3 s). A UK hospital workforce analysis forecast that three years of VASARI featurisation would demand 29,777 consultant neuroradiologist workforce hours and >£1.5 ($1.9) million, reducible to 332 hours of computing time (and £146 of power) with VASARI-auto. The best-performing survival model utilised VASARI-auto features instead of those derived by neuroradiologists. VASARI-auto is a highly efficient and equitable automated labelling system, a favourable economic profile if used as a decision support tool, and non-inferior survival prediction. Future work should iterate upon and integrate such tools to enhance patient care.

Brain tumour segmentation with incomplete imaging data.

Progress in neuro-oncology is increasingly recognized to be obstructed by the marked heterogeneity-genetic, pathological, and clinical-of brain tumours. If the treatment susceptibilities and outcomes of individual patients differ widely, determined by the interactions of many multimodal characteristics, then large-scale, fully-inclusive, richly phenotyped data-including imaging-will be needed to predict them at the individual level. Such data can realistically be acquired only in the routine clinical stream, where its quality is inevitably degraded by the constraints of real-world clinical care. Although contemporary machine learning could theoretically provide a solution to this task, especially in the domain of imaging, its ability to cope with realistic, incomplete, low-quality data is yet to be determined. In the largest and most comprehensive study of its kind, applying state-of-the-art brain tumour segmentation models to large scale, multi-site MRI data of 1251 individuals, here we quantify the comparative fidelity of automated segmentation models drawn from MR data replicating the various levels of completeness observed in real life. We demonstrate that models trained on incomplete data can segment lesions very well, often equivalently to those trained on the full completement of images, exhibiting Dice coefficients of 0.907 (single sequence) to 0.945 (complete set) for whole tumours and 0.701 (single sequence) to 0.891 (complete set) for component tissue types. This finding opens the door both to the application of segmentation models to large-scale historical data, for the purpose of building treatment and outcome predictive models, and their application to real-world clinical care. We further ascertain that segmentation models can accurately detect enhancing tumour in the absence of contrast-enhancing imaging, quantifying the burden of enhancing tumour with an R 2 > 0.97, varying negligibly with lesion morphology. Such models can quantify enhancing tumour without the administration of intravenous contrast, inviting a revision of the notion of tumour enhancement if the same information can be extracted without contrast-enhanced imaging. Our analysis includes validation on a heterogeneous, real-world 50 patient sample of brain tumour imaging acquired over the last 15 years at our tertiary centre, demonstrating maintained accuracy even on non-isotropic MRI acquisitions, or even on complex post-operative imaging with tumour recurrence. This work substantially extends the translational opportunity for quantitative analysis to clinical situations where the full complement of sequences is not available and potentially enables the characterization of contrast-enhanced regions where contrast administration is infeasible or undesirable.