4 papers
Re-mixing Embeddings for Patient Augmentation in Data Scarce Multiple Instance Learning
Muhammed Furkan Dasdelen, Fatih Ozlugedik, Anastasia Litinetskaya +3
Data scarcity is a major bottleneck in medical Multiple Instance Learning (MIL), especially for rare diseases or expensive modalities. We introduce a statistically grounded patient…
Genetically Aligned Patient Representations Improve Hematological Diagnosis
Muhammed Furkan Dasdelen, Fatih Ozlugedik, Ilaria Looser +3
Multimodal alignment of histopathology encoders with transcriptomic and genomic data has been shown to significantly improve performance in downstream diagnostic tasks. Hematologic…
Transformer-Based Hematological Malignancy Prediction from Peripheral Blood Smears in a Real-World Cohort
Muhammed Furkan Dasdelen, Ivan Kukuljan, Peter Lienemann +6
Peripheral blood smears remain a cornerstone in the diagnosis of hematological neoplasms, offering rapid and valuable insights that inform subsequent diagnostic steps. However, sin…
Redefining spectral unmixing for in-vivo brain tissue analysis from hyperspectral imaging
Martin Hartenberger, Huzeyfe Ayaz, Fatih Ozlugedik +12
In this paper, we propose a methodology for extracting molecular tumor biomarkers from hyperspectral imaging (HSI), an emerging technology for intraoperative tissue assessment. To…