Abstract
(1) Background: The segmentation of cell nuclei is an essential task in a wide range of biomedical studies and clinical practices. The full automation of this process remains a challenge due to intra- and internuclear variations across a wide range of tissue morphologies, differences in staining protocols and imaging procedures. (2) Methods: A deep learning model with metric embeddings such as contrastive loss and triplet loss with semi-hard negative mining is proposed in order to accurately segment cell nuclei in a diverse set of microscopy images. The effectiveness of the proposed model was tested on a large-scale multi-tissue collection of microscopy image sets. (3) Results: The use of deep metric learning increased the overall segmentation prediction by 3.12% in the average value of Dice similarity coefficients as compared to no metric learning. In particular, the largest gain was observed for segmenting cell nuclei in H&E -stained images when deep learning network and triplet loss with semi-hard negative mining were considered for the task. (4) Conclusion: We conclude that deep metric learning gives an additional boost to the overall learning process and consequently improves the segmentation performance. Notably, the improvement ranges approximately between 0.13% and 22.31% for different types of images in the terms of Dice coefficients when compared to no metric deep learning.
Highlights
The ongoing digitisation in pathology allows for computer-aided diagnosis in a wide spectrum of applications
The developed model must be able to generalise across a wide range of tissue morphologies due to intra- and internuclear variations, where the overlap of cells is a common phenomenon
Adjustments in the learning strategy were made in order to use the metric embeddings, by which either contrastive loss or triplet loss with semi-hard negative mining can be selected
Summary
The ongoing digitisation in pathology allows for computer-aided diagnosis in a wide spectrum of applications. Automation can provide reproducible measurements and standardisation for follow-up evaluations and comparative studies used, for example, in personalised medicine. Quantitative information such as cell size, shape and spatial distribution are generally used by pathologists for cancer diagnosis [3]. Detecting nuclei enables the computer-aided assessment of immune cell infiltrates, which has a clear advantage due to its prognostic potential and use in immunotherapy trials [4,5]. A robust and generalised technique that accurately segments nuclei in a diverse range of images could be integrated into the computer-aided assessment technology used by pathologists
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.
