Publications by authors named "B Bischl"
Background: Distributed statistical analyses provide a promising approach for privacy protection when analyzing data distributed over several databases. Instead of directly operating on data, the analyst receives anonymous summary statistics, which are combined into an aggregated result. Further, in discrimination model (prognosis, diagnosis, etc.
View Article and Find Full Text PDFCancer cells and pathogens can evade T cell receptors (TCRs) via mutations in immunogenic epitopes. TCR cross-reactivity (i.e.
View Article and Find Full Text PDFArticle Synopsis
- The success of deep learning in computational biology relies on specific architecture design, but there's no agreed-upon optimal approach, often borrowing from computer vision, which may ignore genomic features.
- GenomeNet-Architect is introduced as a framework that automatically optimizes neural network architectures specifically for genome sequence data, enhancing the design and hyperparameter tuning.
- In a viral classification task, GenomeNet-Architect improved accuracy by reducing misclassification rates by 19%, providing 67% faster processing, and achieving similar model performance with 83% fewer parameters compared to existing leading methods.
Bayesian uncertainty estimation for detection of long-tailed and unseen conditions in medical images.
J Med Imaging (Bellingham)
September 2023
Purpose: Deep supervised learning provides an effective approach for developing robust models for various computer-aided diagnosis tasks. However, there is often an underlying assumption that the frequencies of the samples between the different classes of the training dataset are either similar or balanced. In real-world medical data, the samples of positive classes often occur too infrequently to satisfy this assumption.
View Article and Find Full Text PDF