Machine learning of dissection photographs and surface scanning for quantitative 3D neuropathology.

We present open-source tools for three-dimensional (3D) analysis of photographs of dissected slices of human brains, which are routinely acquired in brain banks but seldom used for quantitative analysis. Our tools can: (1) 3D reconstruct a volume from the photographs and, optionally, a surface scan; and (2) produce a high-resolution 3D segmentation into 11 brain regions per hemisphere (22 in total), independently of the slice thickness. Our tools can be used as a substitute for ex vivo magnetic resonance imaging (MRI), which requires access to an MRI scanner, ex vivo scanning expertise, and considerable financial resources. We tested our tools on synthetic and real data from two NIH Alzheimer's Disease Research Centers. The results show that our methodology yields accurate 3D reconstructions, segmentations, and volumetric measurements that are highly correlated to those from MRI. Our method also detects expected differences between post mortem confirmed Alzheimer's disease cases and controls. The tools are available in our widespread neuroimaging suite 'FreeSurfer' (https://surfer.nmr.mgh.harvard.edu/fswiki/PhotoTools).

Every year, thousands of human brains are donated to science. These brains are used to study normal aging, as well as neurological diseases like Alzheimer's or Parkinson's. Donated brains usually go to 'brain banks', institutions where the brains are dissected to extract tissues relevant to different diseases. During this process, it is routine to take photographs of brain slices for archiving purposes. Often, studies of dead brains rely on qualitative observations, such as 'the hippocampus displays some atrophy', rather than concrete 'numerical' measurements. This is because the gold standard to take three-dimensional measurements of the brain is magnetic resonance imaging (MRI), which is an expensive technique that requires high expertise ­ especially with dead brains. The lack of quantitative data means it is not always straightforward to study certain conditions. To bridge this gap, Gazula et al. have developed an openly available software that can build three-dimensional reconstructions of dead brains based on photographs of brain slices. The software can also use machine learning methods to automatically extract different brain regions from the three-dimensional reconstructions and measure their size. These data can be used to take precise quantitative measurements that can be used to better describe how different conditions lead to changes in the brain, such as atrophy (reduced volume of one or more brain regions). The researchers assessed the accuracy of the method in two ways. First, they digitally sliced MRI-scanned brains and used the software to compute the sizes of different structures based on these synthetic data, comparing the results to the known sizes. Second, they used brains for which both MRI data and dissection photographs existed and compared the measurements taken by the software to the measurements obtained with MRI images. Gazula et al. show that, as long as the photographs satisfy some basic conditions, they can provide good estimates of the sizes of many brain structures. The tools developed by Gazula et al. are publicly available as part of FreeSurfer, a widespread neuroimaging software that can be used by any researcher working at a brain bank. This will allow brain banks to obtain accurate measurements of dead brains, allowing them to cheaply perform quantitative studies of brain structures, which could lead to new findings relating to neurodegenerative diseases.

Machine learning of dissection photographs and surface scanning for quantitative 3D neuropathology.

We present open-source tools for 3D analysis of photographs of dissected slices of human brains, which are routinely acquired in brain banks but seldom used for quantitative analysis. Our tools can: (i) 3D reconstruct a volume from the photographs and, optionally, a surface scan; and (ii) produce a high-resolution 3D segmentation into 11 brain regions per hemisphere (22 in total), independently of the slice thickness. Our tools can be used as a substitute for ex vivo magnetic resonance imaging (MRI), which requires access to an MRI scanner, ex vivo scanning expertise, and considerable financial resources. We tested our tools on synthetic and real data from two NIH Alzheimer's Disease Research Centers. The results show that our methodology yields accurate 3D reconstructions, segmentations, and volumetric measurements that are highly correlated to those from MRI. Our method also detects expected differences between post mortem confirmed Alzheimer's disease cases and controls. The tools are available in our widespread neuroimaging suite "FreeSurfer" ( https://surfer.nmr.mgh.harvard.edu/fswiki/PhotoTools ).

Deep active learning for suggestive segmentation of biomedical image stacks via optimisation of Dice scores and traced boundary length.

Manual segmentation of stacks of 2D biomedical images (e.g., histology) is a time-consuming task which can be sped up with semi-automated techniques. In this article, we present a suggestive deep active learning framework that seeks to minimise the annotation effort required to achieve a certain level of accuracy when labelling such a stack. The framework suggests, at every iteration, a specific region of interest (ROI) in one of the images for manual delineation. Using a deep segmentation neural network and a mixed cross-entropy loss function, we propose a principled strategy to estimate class probabilities for the whole stack, conditioned on heterogeneous partial segmentations of the 2D images, as well as on weak supervision in the form of image indices that bound each ROI. Using the estimated probabilities, we propose a novel active learning criterion based on predictions for the estimated segmentation performance and delineation effort, measured with average Dice scores and total delineated boundary length, respectively, rather than common surrogates such as entropy. The query strategy suggests the ROI that is expected to maximise the ratio between performance and effort, while considering the adjacency of structures that may have already been labelled - which decrease the length of the boundary to trace. We provide quantitative results on synthetically deformed MRI scans and real histological data, showing that our framework can reduce labelling effort by up to 60-70% without compromising accuracy.

Risk Factors for Dental Caries Experience in Children and Adolescents with Cerebral Palsy-A Scoping Review.

Cerebral palsy is a developmental motor disorder which has far-reaching impacts on oral health. This scoping review examined the extent of research undertaken regarding the risk factors affecting dental caries experience in children and adolescents with cerebral palsy. Data were obtained from the electronic databases Web of Science and PubMed, using 10 search strings, for studies published between 1983 and 2018. Eligible studies were required to have investigated caries in children under 18 with cerebral palsy, as well as be written in English. 30 papers published were identified for inclusion in the review. These included 23 cross-sectional, 6 case-control, and 1 longitudinal study. Studies were categorized into six domains of risk factors: socioeconomic status (SE); cerebral palsy subtype (CPS); demographics (D); condition of oral cavity (OC); dental habits (DH); nutrition and diet (ND). This review was conducted and reported in accordance with Preferred Reporting Items for Systematic reviews and Meta-Analyses Extension for Scoping Reviews (PRISMA-ScR) guidelines. The most significant risk factors were caregiver-related education levels, oral health literacy, and sugar intake; this underlines the important role of special education and dental awareness in reducing dental caries incidence in CP children. Other factors showed divergent findings, highlighting the need for standardization and culturally specific studies in future literature.

Predictors of motor outcome after childhood arterial ischemic stroke.

AIM: To identify clinical and radiological predictors of long-term motor outcome after childhood-onset arterial ischemic stroke (AIS) in the middle cerebral artery (MCA) territory. METHOD: Medical records of 69 children (36 females, 33 males; median age at index AIS 3y 3mo, range: 1mo-16y) who presented to Great Ormond Street Hospital with first AIS in the MCA territory were reviewed retrospectively. Cases were categorized using the Childhood AIS Standardized Classification and Diagnostic Evaluation (CASCADE). Magnetic resonance imaging (MRI) and angiography were evaluated. An Alberta Stroke Program Early Computed Tomography Score (ASPECTS) was calculated on MRI. The Recurrence and Recovery Questionnaire assessed motor outcome and was dichotomized into good/poor. RESULTS: Eventual motor outcome was good in 49 children and poor in 20. There were no acute radiological predictors of eventual motor outcome. At follow-up, CASCADE 3A (i.e. moyamoya) and Wallerian degeneration were significantly associated with poor motor outcome. In the multivariate analysis, younger age and CASCADE 3A predicted poor motor outcome. INTERPRETATION: In the context of recommendations regarding unproven and potentially high-risk hyperacute therapies for childhood AIS, prediction of outcome could usefully contribute to risk/benefit analysis. Unfortunately, paradigms used in adults, such as ASPECTS, are not useful in children in the acute/early subacute phase of AIS. What this paper adds Adult paradigms, such as the Alberta Stroke Program Early Computed Tomography Score system, are not useful for predicting outcome in children. Younger children tend to have a poorer long-term prognosis than older children. Moyamoya is associated with poor prognosis.