Differential cell counts using center-point networks achieves human-level accuracy and efficiency over segmentation

Abstract Differential cell counts is a challenging task when applying computer vision algorithms to pathology. Existing approaches to train cell recognition require high availability of multi-class segmentation and/or bounding box annotations and suffer in performance when objects are tightly cluste...

Description complète

Enregistré dans:
Détails bibliographiques
Auteurs principaux: Sarada M. W. Lee, Andrew Shaw, Jodie L. Simpson, David Uminsky, Luke W. Garratt
Format: article
Langue:EN
Publié: Nature Portfolio 2021
Sujets:
R
Q
Accès en ligne:https://doaj.org/article/bc5ecf7f2ac74511b28084801ee0ef06
Tags: Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
Description
Résumé:Abstract Differential cell counts is a challenging task when applying computer vision algorithms to pathology. Existing approaches to train cell recognition require high availability of multi-class segmentation and/or bounding box annotations and suffer in performance when objects are tightly clustered. We present differential count network (“DCNet”), an annotation efficient modality that utilises keypoint detection to locate in brightfield images the centre points of cells (not nuclei) and their cell class. The single centre point annotation for DCNet lowered burden for experts to generate ground truth data by 77.1% compared to bounding box labeling. Yet centre point annotation still enabled high accuracy when training DCNet on a multi-class algorithm on whole cell features, matching human experts in all 5 object classes in average precision and outperforming humans in consistency. The efficacy and efficiency of the DCNet end-to-end system represents a significant progress toward an open source, fully computationally approach to differential cell count based diagnosis that can be adapted to any pathology need.