Year-end Sale % OFF 
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.
Highlights
Differential cell counts is a challenging task when applying computer vision algorithms to pathology
Cytopathology is a common technique to visualise cells through a glass slide preparation, created by cytocentrifugation of a cell suspension followed by treatment with histological stains
The deep learning field working on cell orientated computer vision has largely taken a dichotomous approach, seeking to identify the cells in an image from the surrounding non-cell features
Summary
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. The analysis of prepared cytocentrifugation slides remains surprisingly reliant upon labor-intensive assessment by trained humans This presents a number of methodological variations including human error, the area observed and the number of cells counted[2,3]. Keypoint detection (CenterNet) has shown to be a simpler and yet often more accurate approach than bounding box or segmentation, even in complex image tasks such as real-time inference from video streaming[18]
Sign-in/Register to view highlights & summary Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
