UCL Discovery
UCL home » Library Services » Electronic resources » UCL Discovery

ConCORDe-net: Cell count regularized convolutional neural network for cell detection in multiplex immunohistochemistry images

Hagos, YB; Narayanan, PL; Akarca, AU; Marafioti, T; Yuan, Y; (2019) ConCORDe-net: Cell count regularized convolutional neural network for cell detection in multiplex immunohistochemistry images. In: Medical Image Computing and Computer Assisted Intervention – MICCAI 2019. (pp. pp. 667-675). Springer: Shenzhen, China. Green open access

[img]
Preview
Text
Akarca_Cell Count Regularized Convolutional Neural Network for Cell Detection in mIHC.pdf - Accepted version

Download (5MB) | Preview

Abstract

In digital pathology, cell detection and classification are often prerequisites to quantify cell abundance and explore tissue spatial heterogeneity. However, these tasks are particularly challenging for multiplex immunohistochemistry (mIHC) images due to high levels of variability in staining, expression intensity, and inherent noise as a result of preprocessing artefacts. We proposed a deep learning method to detect and classify cells in mIHC whole-tumor slide images of breast cancer. Inspired by inception-v3, we developed Cell COunt RegularizeD Convolutional neural Network (ConCORDe-Net) which integrates conventional dice overlap and a new cell count loss function for optimizing cell detection, followed by a multi-stage convolutional neural network for cell classification. In total, 20447 cells, belonging to five cell classes were annotated by experts from 175 patches extracted from 6 whole-tumor mIHC images. These patches were randomly split into training, validation and testing sets. Using ConCORDe-Net, we obtained a cell detection F1 score of 0.873, which is the best score compared to three state of the art methods. In particular, ConCORDe-Net excels at detecting closely located and weakly stained cells compared to other methods. Incorporating cell count loss in the objective function regularizes the network to learn weak gradient boundaries and separate weakly stained cells from background artefacts. Moreover, cell classification accuracy of 96.5% was achieved. These results support that incorporating problem specific knowledge such as cell count into deep learning based cell detection architectures improves robustness of the algorithm.

Type: Proceedings paper
Title: ConCORDe-net: Cell count regularized convolutional neural network for cell detection in multiplex immunohistochemistry images
Event: International Conference on Medical Image Computing and Computer-Assisted Intervention (MICCAI 2019)
Open access status: An open access version is available from UCL Discovery
DOI: 10.1007/978-3-030-32239-7_74
Publisher version: https://doi.org/10.1007/978-3-030-32239-7_74
Language: English
Additional information: This version is the author accepted manuscript. For information on re-use, please refer to the publisher’s terms and conditions.
UCL classification: UCL
UCL > Provost and Vice Provost Offices
UCL > Provost and Vice Provost Offices > School of Life and Medical Sciences
UCL > Provost and Vice Provost Offices > School of Life and Medical Sciences > Faculty of Medical Sciences
UCL > Provost and Vice Provost Offices > School of Life and Medical Sciences > Faculty of Medical Sciences > Cancer Institute
UCL > Provost and Vice Provost Offices > School of Life and Medical Sciences > Faculty of Medical Sciences > Cancer Institute > Research Department of Pathology
URI: https://discovery.ucl.ac.uk/id/eprint/10099579
Downloads since deposit
14Downloads
Download activity - last month
Download activity - last 12 months
Downloads by country - last 12 months

Archive Staff Only

View Item View Item