3 papers
cs.CV2026
Distribution-based deep multiple instance learning for tumor proportion scoring in NSCLC
Krzysztof Pysz, Artur Bartczak, JarosÅaw KwiecieÅ +2
Accurate assessment of tumor proportion score (TPS) in non-small cell lung cancer (NSCLC) is critical for treatment planning and prognosis. Key challenges include the tedious manua…
eess.IV2025
Foundation Model-Driven Classification of Atypical Mitotic Figures with Domain-Aware Training Strategies
Piotr Giedziun, Jan SoÅtysik, Mateusz Górczany +7
We present a solution for the MIDOG 2025 Challenge Track~2, addressing binary classification of normal mitotic figures (NMFs) versus atypical mitotic figures (AMFs). The approach l…
eess.IV2025
RF-DETR for Robust Mitotic Figure Detection: A MIDOG 2025 Track 1 Approach
Piotr Giedziun, Jan SoÅtysik, Mateusz Górczany +7
Mitotic figure detection in histopathology images remains challenging due to significant domain shifts across different scanners, staining protocols, and tissue types. This paper p…