About this item:

41 Views | 42 Downloads

Author Notes:

Further author information: (Send correspondence to Dr. Fei), bfei@emory.edu, website: https://fei-lab.org/

The authors would like to thank the surgical pathology team at Emory University Hospital Midtown including Andrew Balicki, Jacqueline Ernst, Tara Meade, Dana Uesry, and Mark Mainiero, for their help in collecting fresh tissue specimens.

The authors have no relevant financial interests in this article and no potential conflicts of interest to disclose.


Research Funding:

This research is supported in part by NIH grants CA176684, CA156775 and CA204254, Georgia Cancer Coalition Distinguished Clinicians and Scientists Award, and a pilot project fund from the Winship Cancer Institute of Emory University under the award number P30CA138292.


  • Science & Technology
  • Technology
  • Physical Sciences
  • Engineering, Biomedical
  • Optics
  • Engineering
  • Hyperspectral imaging
  • convolutional neural network
  • deep learning
  • cancer margin detection
  • intraoperative imaging
  • head and neck surgery
  • head and neck cancer

Tumor Margin Classification of Head and Neck Cancer Using Hyperspectral Imaging and Convolutional Neural Networks


Proceedings Title:


Conference Name:

Conference on Medical Imaging - Image-Guided Procedures, Robotic Interventions, and Modeling


Conference Place:

Houston, TX


Volume 10576

Publication Date:

Type of Work:

Conference | Post-print: After Peer Review


One of the largest factors affecting disease recurrence after surgical cancer resection is negative surgical margins. Hyperspectral imaging (HSI) is an optical imaging technique with potential to serve as a computer aided diagnostic tool for identifying cancer in gross ex-vivo specimens. We developed a tissue classifier using three distinct convolutional neural network (CNN) architectures on HSI data to investigate the ability to classify the cancer margins from ex-vivo human surgical specimens, collected from 20 patients undergoing surgical cancer resection as a preliminary validation group. A new approach for generating the HSI ground truth using a registered histological cancer margin is applied in order to create a validation dataset. The CNN-based method classifies the tumor-normal margin of squamous cell carcinoma (SCCa) versus normal oral tissue with an area under the curve (AUC) of 0.86 for inter-patient validation, performing with 81% accuracy, 84% sensitivity, and 77% specificity. Thyroid carcinoma cancer-normal margins are classified with an AUC of 0.94 for inter-patient validation, performing with 90% accuracy, 91% sensitivity, and 88% specificity. Our preliminary results on a limited patient dataset demonstrate the predictive ability of HSI-based cancer margin detection, which warrants further investigation with more patient data and additional processing techniques to optimize the proposed deep learning method.

Copyright information:

© 2018 SPIE.

Export to EndNote