Jan Obdržálek

Martin Krebs, Jan Obdržálek, Vít Musil et al.

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 results they provide should be explainable in a way easily understood by pathologists. A well-known and widely used explanation technique is occlusion, which, however, can take a long time to compute, thus slowing the development and interaction with pathologists. In this work, we set out to find a faster replacement for occlusion in a successful system for detecting prostate cancer. Since there is no established framework for comparing the performance of various explanation methods, we first identified suitable comparison criteria and selected corresponding metrics. Based on the results, we were able to choose a different explanation method, which cut the previously required explanation time at least by a factor of 10, without any negative impact on the quality of outputs. This speedup enables rapid iteration in model development and debugging and brings us closer to adopting AI-assisted prostate cancer detection in clinical settings. We propose that our approach to finding the replacement for occlusion can be used to evaluate candidate methods in other related applications.

Adam Bajger, Jan Obdržálek, Vojtěch Kůr et al.

We present a clustering-based explainability technique for digital pathology models based on convolutional neural networks. Unlike commonly used methods based on saliency maps, such as occlusion, GradCAM, or relevance propagation, which highlight regions that contribute the most to the prediction for a single slide, our method shows the global behaviour of the model under consideration, while also providing more fine-grained information. The result clusters can be visualised not only to understand the model, but also to increase confidence in its operation, leading to faster adoption in clinical practice. We also evaluate the performance of our technique on an existing model for detecting prostate cancer, demonstrating its usefulness.

Jan Obdržálek, Jiří Slabý, Marek Trtík

STANSE is a free (available under the GPLv2 license) modular framework for finding bugs in C programs using static analysis. Its two main design goals are 1) ability to process large software projects like the Linux kernel and 2) extensibility with new bug-finding techniques with a minimal effort. Currently there are four bug-finding algorithms implemented within STANSE: AutomatonChecker checks properties described in an automata-based formalism, ThreadChecker detects deadlocks among multiple threads, LockChecker finds locking errors based on statistics, and ReachabilityChecker looks for unreachable code. STANSE has been tested on the Linux kernel, where it has found dozens of previously undiscovered bugs.