Focused active learning for histopathological image classification Schmidt, Arne Morales Álvarez, Pablo Cooper, L.A, Newberg, L.A. Enquobahrie, A Molina Soriano, Rafael Katsaggelos, Aggelos Active Learning Cancer Classification Histological Images Bayesian Deep Learning Active Learning (AL) has the potential to solve a major problem of digital pathology: the efficient acquisition of labeled data for machine learning algorithms. However, existing AL methods often struggle in realistic settings with artifacts, ambiguities, and class imbalances, as commonly seen in the medical field. The lack of precise uncertainty estimations leads to the acquisition of images with a low informative value. To address these challenges, we propose Focused Active Learning (FocAL), which combines a Bayesian Neural Network with Out-of-Distribution detection to estimate different uncertainties for the acquisition function. Specifically, the weighted epistemic uncertainty accounts for the class imbalance, aleatoric uncertainty for ambiguous images, and an OoD score for artifacts. We perform extensive experiments to validate our method on MNIST and the real-world Panda dataset for the classification of prostate cancer. The results confirm that other AL methods are ’distracted’ by ambiguities and artifacts which harm the performance. FocAL effectively focuses on the most informative images, avoiding ambiguities and artifacts during acquisition. For both experiments, FocAL outperforms existing AL approaches, reaching a Cohen’s kappa of 0.764 with only 0.69% of the labeled Panda data. 2025-01-15T08:06:37Z 2025-01-15T08:06:37Z 2024 journal article Schmidt, A., Morales-Álvarez, P., Cooper, L.A., Newberg, L.A., Enquobahrie, A., Molina, R. , Katsaggelos, A.K. , Focused active learning for histopathological image classification, Medical Image Analysis, volumen 95, 2024 https://hdl.handle.net/10481/99172 10.1016/J.MEDIA.2024.103162 eng http://creativecommons.org/licenses/by-nc-nd/4.0/ open access Attribution-NonCommercial-NoDerivatives 4.0 Internacional Elsevier