Deep Consensus Network

• Verfasst von: Wollmann, Thomas [VerfasserIn]
• Verfasst von: Rohr, Karl [VerfasserIn]
• Titel: Deep Consensus Network
• Titelzusatz: aggregating predictions to improve object detection in microscopy images
• Verf.angabe: Thomas Wollmann, Karl Rohr
• E-Jahr: 2021
• Jahr: 24 February 2021
• Umfang: 14 S.
• Teil: volume:70
• Teil: year:2021
• Teil: elocationid:102019
• Teil: pages:1-14
• Teil: extent:14
• Fussnoten: Gesehen am 02.06.2021
• Titel Quelle: Enthalten in: Medical image analysis
• Ort Quelle: Amsterdam [u.a.] : Elsevier Science, 1996
• Jahr Quelle: 2021
• Band/Heft Quelle: 70(2021), Artikel-ID 102019, Seite 1-14
• ISSN Quelle: 1361-8423
• DOI: doi:10.1016/j.media.2021.102019
• Datenträger: Online-Ressource
• Sprache: eng
• Sach-SW: Deep Learning
• Sach-SW: Detection
• Sach-SW: Microscopy
• Sach-SW: Voting
• K10plus-PPN: 1759390852

Abstract

Detection of cells and particles in microscopy images is a common and challenging task. In recent years, detection approaches in computer vision achieved remarkable improvements by leveraging deep learning. Microscopy images pose challenges like small and clustered objects, low signal to noise, and complex shape and appearance, for which current approaches still struggle. We introduce Deep Consensus Network, a new deep neural network for object detection in microscopy images based on object centroids. Our network is trainable end-to-end and comprises a Feature Pyramid Network-based feature extractor, a Centroid Proposal Network, and a layer for ensembling detection hypotheses over all image scales and anchors. We suggest an anchor regularization scheme that favours prior anchors over regressed locations. We also propose a novel loss function based on Normalized Mutual Information to cope with strong class imbalance, which we derive within a Bayesian framework. In addition, we introduce an improved algorithm for Non-Maximum Suppression which significantly reduces the algorithmic complexity. Experiments on synthetic data are performed to provide insights into the properties of the proposed loss function and its robustness. We also applied our method to challenging data from the TUPAC16 mitosis detection challenge and the Particle Tracking Challenge, and achieved results competitive or better than state-of-the-art.