Share Email Print
cover

Proceedings Paper

Detection of squamous cell carcinoma in digitized histological images from the head and neck using convolutional neural networks
Author(s): Martin Halicek; Maysam Shahedi; James V. Little; Amy Y. Chen; Larry L. Myers; Baran D. Sumer; Baowei Fei
Format Member Price Non-Member Price
PDF $17.00 $21.00

Paper Abstract

Primary management for head and neck squamous cell carcinoma (SCC) involves surgical resection with negative cancer margins. Pathologists guide surgeons during these operations by detecting SCC in histology slides made from the excised tissue. In this study, 192 digitized histological images from 84 head and neck SCC patients were used to train, validate, and test an inception-v4 convolutional neural network. The proposed method performs with an AUC of 0.91 and 0.92 for the validation and testing group. The careful experimental design yields a robust method with potential to help create a tool to increase efficiency and accuracy of pathologists for detecting SCC in histological images.

Paper Details

Date Published: 18 March 2019
PDF: 9 pages
Proc. SPIE 10956, Medical Imaging 2019: Digital Pathology, 109560K (18 March 2019); doi: 10.1117/12.2512570
Show Author Affiliations
Martin Halicek, The Univ. of Texas at Dallas (United States)
Georgia Institute of Technology & Emory Univ. School of Medicine (United States)
Medical College of Georgia, Augusta Univ. (United States)
Maysam Shahedi, The Univ. of Texas at Dallas (United States)
James V. Little, Emory Univ. School of Medicine (United States)
Amy Y. Chen, Emory Univ. School of Medicine (United States)
Larry L. Myers, The Univ. of Texas Southwestern Medical Ctr. (United States)
Baran D. Sumer, The Univ. of Texas Southwestern Medical Ctr. (United States)
Baowei Fei, The Univ. of Texas at Dallas (United States)
Univ. of Texas Southwestern Medical Ctr. (United States)


Published in SPIE Proceedings Vol. 10956:
Medical Imaging 2019: Digital Pathology
John E. Tomaszewski; Aaron D. Ward, Editor(s)

© SPIE. Terms of Use
Back to Top