Keywords: Nuclei Segmentation, Breast Cancer, Deep Learning, Histopathology, CNNs
TL;DR: We employ Gated-CNNs to improve segmentation of overlapping nuclei in breast cancer H&E histopathology images.
Abstract: Nuclei segmentation using deep learning has been achieving high accuracy using U-Net and variants, but a remaining challenge is distinguishing touching and overlapping cells. In this work, we propose using gated CNN (GCNN) networks to obtain sharper predictions around object boundaries and improve nuclei segmentation performance. The method is evaluated in over 1000 multicentre diverse H&E breast cancer images from three databases and compared to baseline U-Net and R2U-Net.
Paper Type: validation/application paper
Primary Subject Area: Segmentation
Secondary Subject Area: Application: Histopathology
Paper Status: original work, not submitted yet
Source Code Url: N/A
Data Set Url: TNBC, TUPAC, and part of TCGA datasets are already publicly available.
Registration: I acknowledge that publication of this at MIDL and in the proceedings requires at least one of the authors to register and present the work during the conference.
Authorship: I confirm that I am the author of this work and that it has not been submitted to another publication before.