8 papers
Deep Learning-Based Fixation Type Prediction for Quality Assurance in Digital Pathology
Oskar Thaeter, Tanja Niedermair, Jan E. G. Albin +3
Accurate annotation of fixation type is a critical step in slide preparation for pathology laboratories. However, this manual process is prone to errors, impacting downstream analy…
Efficient Special Stain Classification
Oskar Thaeter, Christian Grashei, Anette Haas +3
Stains are essential in histopathology to visualize specific tissue characteristics, with Haematoxylin and Eosin (H&E) serving as the clinical standard. However, pathologists frequ…
Rethinking Tokenization for Clinical Time Series: When Less is More
Rafi Al Attrach, Rajna Fani, David Restrepo +2
Tokenization strategies shape how models process electronic health records, yet fair comparisons of their effectiveness remain limited. We present a systematic evaluation of tokeni…
Coefficient of Variation Masking: A Volatility-Aware Strategy for EHR Foundation Models
Rajna Fani, Rafi Al Attrach, David Restrepo +3
Masked autoencoders (MAEs) are increasingly applied to electronic health records (EHR) for learning general-purpose representations that support diverse clinical tasks. However, ex…
Pathryoshka: Compressing Pathology Foundation Models via Multi-Teacher Knowledge Distillation with Nested Embeddings
Christian Grashei, Christian Brechenmacher, Rao Muhammad Umer +5
Pathology foundation models (FMs) have driven significant progress in computational pathology. However, these high-performing models can easily exceed a billion parameters and prod…
HASD: Hierarchical Adaption for pathology Slide-level Domain-shift
Jingsong Liu, Han Li, Chen Yang +6
Domain shift is a critical problem for pathology AI as pathology data is heavily influenced by center-specific conditions. Current pathology domain adaptation methods focus on imag…