5 papers
A Unifying Framework of Concept-based Explainable AI with Completeness Guarantees
Vojtěch Kůr, Adam Kukučka, Tomáš Brázdil +1
Concept-based explanations describe neural network predictions through human-understandable properties of inputs called concepts. The field encompasses approaches that differ in ho…
Weakly Supervised Multicenter Nancy Index Scoring in Ulcerative Colitis Using Foundation Models
Adam Kukučka, Ondřej Fabián, Vít Musil +1
Histologic assessment of ulcerative colitis (UC) activity is an important endpoint in clinical trials and routine care, but manual grading with indices such as the Nancy histologic…
Beyond Occlusion: In Search for Near Real-Time Explainability of CNN-Based Prostate Cancer Classification
Martin Krebs, Jan Obdržálek, Vít Musil +1
Deep neural networks are starting to show their worth in critical applications such as assisted cancer diagnosis. However, for their outputs to get accepted in practice, the result…
LLEXICORP: End-user Explainability of Convolutional Neural Networks
Vojtěch Kůr, Adam Bajger, Adam Kukučka +3
Convolutional neural networks (CNNs) underpin many modern computer vision systems. With applications ranging from common to critical areas, a need to explain and understand the mod…
Explaining Digital Pathology Models via Clustering Activations
Adam Bajger, Jan Obdržálek, Vojtěch Kůr +4
We present a clustering-based explainability technique for digital pathology models based on convolutional neural networks. Unlike commonly used methods based on saliency maps, suc…