Deep Learning Nuclei Detection in Digitized Histology Images by Superpixels

Sudhir Sornapudi; Ronald Joe Stanley; William V Stoecker; Haidar Almubarak; Rodney Long; Sameer Antani; George Thoma; Rosemary Zuna; Shelliane R Frazier

doi:10.4103/jpi.jpi_74_17

Deep Learning Nuclei Detection in Digitized Histology Images by Superpixels

J Pathol Inform. 2018 Mar 5:9:5. doi: 10.4103/jpi.jpi_74_17. eCollection 2018.

Authors

Sudhir Sornapudi¹, Ronald Joe Stanley¹, William V Stoecker², Haidar Almubarak¹, Rodney Long³, Sameer Antani³, George Thoma³, Rosemary Zuna⁴, Shelliane R Frazier⁵

Affiliations

¹ Department of Electrical and Computer Engineering, Missouri University of Science and Technology, Rolla, USA.
² Stoecker and Associates, Rolla MO, USA.
³ DHHS, Lister Hill National Center for Biomedical Communications for National Library of Medicine, National Institutes of Health, Bethesda, MD, USA.
⁴ Department of Pathology, University of Oklahoma Health Sciences Center, Oklahoma City, OK, USA.
⁵ Department of Surgical Pathology, University of Missouri Hospitals and Clinics, Columbia, USA.

Abstract

Background: Advances in image analysis and computational techniques have facilitated automatic detection of critical features in histopathology images. Detection of nuclei is critical for squamous epithelium cervical intraepithelial neoplasia (CIN) classification into normal, CIN1, CIN2, and CIN3 grades.

Methods: In this study, a deep learning (DL)-based nuclei segmentation approach is investigated based on gathering localized information through the generation of superpixels using a simple linear iterative clustering algorithm and training with a convolutional neural network.

Results: The proposed approach was evaluated on a dataset of 133 digitized histology images and achieved an overall nuclei detection (object-based) accuracy of 95.97%, with demonstrated improvement over imaging-based and clustering-based benchmark techniques.

Conclusions: The proposed DL-based nuclei segmentation Method with superpixel analysis has shown improved segmentation results in comparison to state-of-the-art methods.

Keywords: Cervical cancer; cervical intraepithelial neoplasia; convolutional neural network; deep learning; image processing; segmentation; superpixels.