Your browser doesn't support javascript.
loading
Focused active learning for histopathological image classification.
Schmidt, Arne; Morales-Álvarez, Pablo; Cooper, Lee Ad; Newberg, Lee A; Enquobahrie, Andinet; Molina, Rafael; Katsaggelos, Aggelos K.
Afiliación
  • Schmidt A; Department of Computer Science and Artificial Intelligence, University of Granada, Granada, 18010, Spain. Electronic address: arne@decsai.ugr.es.
  • Morales-Álvarez P; Department of Statistics and Operation Research, University of Granada, Granada, 18010, Spain. Electronic address: pablomorales@decsai.ugr.es.
  • Cooper LA; Department of Pathology, Northwestern University, Chicago, IL, 60611, USA. Electronic address: lee.cooper@northwestern.edu.
  • Newberg LA; Kitware Inc., Carrboro, NC, 27510, USA. Electronic address: lee.newberg@kitware.com.
  • Enquobahrie A; Kitware Inc., Carrboro, NC, 27510, USA. Electronic address: andinet.enqu@kitware.com.
  • Molina R; Department of Computer Science and Artificial Intelligence, University of Granada, Granada, 18010, Spain. Electronic address: rms@decsai.ugr.es.
  • Katsaggelos AK; Department of Electrical Computer Engineering, Northwestern University, Evanston, IL, 60208, USA. Electronic address: a-katsaggelos@northwestern.edu.
Med Image Anal ; 95: 103162, 2024 Jul.
Article en En | MEDLINE | ID: mdl-38593644
ABSTRACT
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.
Asunto(s)
Palabras clave

Texto completo: 1 Colección: 01-internacional Base de datos: MEDLINE Asunto principal: Neoplasias de la Próstata Límite: Humans / Male Idioma: En Revista: Med Image Anal Asunto de la revista: DIAGNOSTICO POR IMAGEM Año: 2024 Tipo del documento: Article Pais de publicación: Países Bajos

Texto completo: 1 Colección: 01-internacional Base de datos: MEDLINE Asunto principal: Neoplasias de la Próstata Límite: Humans / Male Idioma: En Revista: Med Image Anal Asunto de la revista: DIAGNOSTICO POR IMAGEM Año: 2024 Tipo del documento: Article Pais de publicación: Países Bajos