RESUMO
Listeriosis has more than a 50% mortality when the central nervous system is involved, necessitating rapid diagnosis and treatment. We present four patients with brain abscesses in the setting of diagnosed neurolisteriosis, all of which demonstrated an odd presentation of multiple small, contiguous tubular lesions with rim enhancement on magnetic resonance imaging. Our review of published cases of neurolisteriosis suggests that this may be a useful pattern to identify neurolisteriosis abscesses, allowing earlier detection and therapy.
RESUMO
Deep learning models have demonstrated great potential in medical imaging but are limited by the expensive, large volume of annotations required. To address this, we compared different active learning strategies by training models on subsets of the most informative images using real-world clinical datasets for brain tumor segmentation and proposing a framework that minimizes the data needed while maintaining performance. Then, 638 multi-institutional brain tumor magnetic resonance imaging scans were used to train three-dimensional U-net models and compare active learning strategies. Uncertainty estimation techniques including Bayesian estimation with dropout, bootstrapping, and margins sampling were compared to random query. Strategies to avoid annotating similar images were also considered. We determined the minimum data necessary to achieve performance equivalent to the model trained on the full dataset (α = 0.05). Bayesian approximation with dropout at training and testing showed results equivalent to that of the full data model (target) with around 30% of the training data needed by random query to achieve target performance (p = 0.018). Annotation redundancy restriction techniques can reduce the training data needed by random query to achieve target performance by 20%. We investigated various active learning strategies to minimize the annotation burden for three-dimensional brain tumor segmentation. Dropout uncertainty estimation achieved target performance with the least annotated data.