.png){kind=icon}
Return
Focused active learning for histopathological image classification *
.png){kind=icon}
OA
AI
DOI：10.1016/j.media.2024.103162.png)
.png){kind=icon}
Original request for help.png){kind=icon}
Share.png){kind=icon}
Save
Abstract
En 中文
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.
Keywords:
Active
learning Cancer classification
Histopathological images
Bayesian deep learning
Journal
IF:
11.8
Papers:
3.9K
Citations:
2.4W
Organization
Cited Papers
The Devil is in the Details: Whole Slide Image Acquisition and Processing for Artifacts Detection, Color Variation, and Data Augmentation: A Review.png)
IEEE ACCESSOAAI
IEEE ACCESSIF3.6
OAAIShareSaveArtificial intelligence for diagnosis and Gleason grading of prostate cancer: the PANDA challengeNATURE MEDICINE
OAAI
NATURE MEDICINEIF50
OAAIShareSaveClinical-grade computational pathology using weakly supervised deep learning on whole slide imagesNATURE MEDICINEOAAI
NATURE MEDICINEIF50
OAAIShareSaveShareSaveInteractive Classification of Whole-Slide Imaging Data for Cancer ResearchersCANCER RESEARCHOAAI
CANCER RESEARCHIF16.6
OAAIShareSaveEfficient Cancer Classification by Coupling Semi Supervised and Multiple Instance LearningIEEE ACCESSOAAI
IEEE ACCESSIF3.6
OAAIShareSave
View more