Background: Tuberous sclerosis complex (TSC) is an autosomal dominant genetic disease affecting multiple body systems with wide variability in presentation. In 2013, Pediatric Neurology published articles outlining updated diagnostic criteria and recommendations for surveillance and management of disease manifestations. Advances in knowledge and approvals of new therapies necessitated a revision of those criteria and recommendations. Methods: Chairs and working group cochairs from the 2012 International TSC Consensus Group were invited to meet face-to-face over two days at the 2018 World TSC Conference on July 25 and 26 in Dallas, TX, USA. Before the meeting, working group cochairs worked with group members via e-mail and telephone to (1) review TSC literature since the 2013 publication, (2) confirm or amend prior recommendations, and (3) provide new recommendations as required. Results: Only two changes were made to clinical diagnostic criteria reported in 2013: "multiple cortical tubers and/or radial migration lines" replaced the more general term "cortical dysplasias," and sclerotic bone lesions were reinstated as a minor criterion. Genetic diagnostic criteria were reaffirmed, including highlighting recent findings that some individuals with TSC are genetically mosaic for variants in TSC1 or TSC2. Changes to surveillance and management criteria largely reflected increased emphasis on early screening for electroencephalographic abnormalities, enhanced surveillance and management of TSCassociated neuropsychiatric disorders, and new medication approvals. Conclusions: Updated TSC diagnostic criteria and surveillance and management recommendations presented here should provide an improved framework for optimal care of those living with TSC and their families.

No abstract

Identifying nuclei is often a critical first step in analyzing microscopy images of cells and classical image processing algorithms are most commonly used for this task. Recent developments in deep learning can yield superior accuracy, but typical evaluation metrics for nucleus segmentation do not satisfactorily capture error modes that are relevant in cellular images. We present an evaluation framework to measure accuracy, types of errors, and computational efficiency; and use it to compare deep learning strategies and classical approaches. We publicly release a set of 23,165 manually annotated nuclei and source code to reproduce experiments and run the proposed evaluation methodology. Our evaluation framework shows that deep learning improves accuracy and can reduce the number of biologically relevant errors by half. © 2019 The Authors. Cytometry Part A published by Wiley Periodicals, Inc. on behalf of International Society for Advancement of Cytometry.

Patients with obstructive hydrocephalus and a history of either hemorrhage or infection may be good candidates for ETV, with safety and success rates comparable with those in more general series of patients. Patients who have sustained both hemorrhage and infection are poor candidates for ETV, except in selected cases and as a treatment of last resort. In patients who have previously undergone shunt placement posthemorrhage, ETV is highly successful. It is also highly successful in patients with primary aqueductal stenosis, even in those with a history of hemorrhage or CSF infection.

Identifying nuclei is often a critical first step in analyzing microscopy images of cells, and classical image processing algorithms are most commonly used for this task. Recent developments in deep learning can yield superior accuracy, but typical evaluation metrics for nucleus segmentation do not satisfactorily capture error modes that are relevant in cellular images. Besides, large image data sets with ground truth for evaluation have been limiting. We present an evaluation framework to measure accuracy, types of errors, and computational efficiency; and use it to compare two deep learning strategies (U-Net and DeepCell) alongside a classical approach implemented in CellProfiler. We publicly release a set of 23,165 manually annotated nuclei and source code to reproduce experiments. Our results show that U-Net outperforms both pixel-wise classification networks and classical algorithms. Also, our evaluation framework shows that deep learning improves accuracy and reduces the number of biologically relevant errors by half.

Mammalian target of rapamycin inhibitors have been shown to be an effective treatment of various aspects of tuberous sclerosis complex, including subependymal giant cell astrocytomas. Both mammalian target of rapamycin inhibitors and surgery have a role in the treatment of subependymal giant cell astrocytomas. Various subependymal giant cell astrocytoma-related conditions favor a certain treatment.

BACKGROUND AND PURPOSE:There are few articles characterizing cerebellar lesions in patients with TSC and no published series documenting longitudinal evaluation of these lesions, to our knowledge. Recent suggestion of a correlation between autism and cerebellar lesions in patients with TSC heightens the importance of understanding these lesions. Our purpose was to characterize cerebellar lesions in a cohort of young patients with TSC with specific interest in assessing longitudinal changes.

The TRAMs present a novel model-independent approach providing efficient separation between tumor/nontumor tissues by adding a short MRI scan >1 h post contrast injection. The methodology uses robust acquisition sequences, providing high resolution and easy to interpret maps with minimal sensitivity to susceptibility artifacts. The presented results provide histological validation of the TRAMs and demonstrate their potential contribution to the management of brain tumor patients.