Publications by authors named "J B Kruger"

The application of supervised models to clinical screening tasks is challenging due to the need for annotated data for each considered pathology. Unsupervised Anomaly Detection (UAD) is an alternative approach that aims to identify any anomaly as an outlier from a healthy training distribution. A prevalent strategy for UAD in brain MRI involves using generative models to learn the reconstruction of healthy brain anatomy for a given input image.

View Article and Find Full Text PDF

Background: Single-subject voxel-based morphometry (VBM) is a powerful technique for reader-independent detection of brain atrophy in structural magnetic resonance imaging (MRI) to support the (differential) diagnosis and staging of neurodegenerative diseases in individual patients. However, VBM is sensitive to the MRI scanner platform and details of the acquisition sequence. To mitigate this limitation, we recently proposed and validated a convolutional neural network (CNN)-based VBM which does not rely on a normative reference database.

View Article and Find Full Text PDF

Testing for developmental toxicity is an integral part of chemical regulations. The applied tests are laborious and costly and require a large number of vertebrate test animals. To reduce animal numbers and associated costs, the zebrafish embryo was proposed as an alternative model.

View Article and Find Full Text PDF

Multiple Sclerosis (MS) is a chronic inflammatory disease of the central nervous system. Cuprizone-induced demyelination, wherein mice are fed a diet containing the copper chelator cuprizone, is a well-established model that replicates key features of demyelination and remyelination. However, the dose-response relationship of cuprizone is complex; high concentrations can induce toxicity, whereas low doses may fail to produce reliable demyelination across subjects.

View Article and Find Full Text PDF

Purpose: To report the summary characteristics of operational models associated with Student Led Free Vision Screening Programs (SLFVSP) and to identify opportunities for program optimization.

Methods: An 81-question mixed methods survey was distributed to SLFVSP leaders nationwide and Medical Student Educators within the American University Ophthalmology Professors (AUPO) Association. Survey responses were analyzed using Mann Whitney U and Fisher's Exact tests.

View Article and Find Full Text PDF