Tags

Type your tag names separated by a space and hit enter

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

Abstract

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.

Authors+Show Affiliations

Georgia Institute of Technology & Emory University, Wallace H. Coulter Department of Biomedical Engineering, Atlanta, GA, USA. Medical College of Georgia, Augusta University, Augusta, GA, USA.Emory University School of Medicine, Department of Pathology and Laboratory Medicine, Atlanta, GA, USA.Emory University School of Medicine, Department of Hematology and Medical Oncology, Atlanta, GA, USA.Emory University School of Medicine, Department of Otolaryngology, Atlanta, GA, USA. Winship Cancer Institute of Emory University, Atlanta, GA, USA.Emory University School of Medicine, Department of Pathology and Laboratory Medicine, Atlanta, GA, USA.Emory University School of Medicine, Department of Otolaryngology, Atlanta, GA, USA. Winship Cancer Institute of Emory University, Atlanta, GA, USA.Georgia Institute of Technology & Emory University, Wallace H. Coulter Department of Biomedical Engineering, Atlanta, GA, USA. Winship Cancer Institute of Emory University, Atlanta, GA, USA. Emory University, Department of Mathematics and Computer Science, Atlanta, GA, USA. Emory University, Department of Radiology and Imaging Sciences, Atlanta, GA, USA.

Pub Type(s)

Journal Article

Language

eng

PubMed ID

30245540

Citation

Halicek, Martin, et al. "Tumor Margin Classification of Head and Neck Cancer Using Hyperspectral Imaging and Convolutional Neural Networks." Proceedings of SPIE--the International Society for Optical Engineering, vol. 10576, 2018.
Halicek M, Little JV, Wang X, et al. Tumor Margin Classification of Head and Neck Cancer Using Hyperspectral Imaging and Convolutional Neural Networks. Proc SPIE Int Soc Opt Eng. 2018;10576.
Halicek, M., Little, J. V., Wang, X., Patel, M., Griffith, C. C., Chen, A. Y., & Fei, B. (2018). Tumor Margin Classification of Head and Neck Cancer Using Hyperspectral Imaging and Convolutional Neural Networks. Proceedings of SPIE--the International Society for Optical Engineering, 10576, doi:10.1117/12.2293167.
Halicek M, et al. Tumor Margin Classification of Head and Neck Cancer Using Hyperspectral Imaging and Convolutional Neural Networks. Proc SPIE Int Soc Opt Eng. 2018;10576 PubMed PMID: 30245540.
* Article titles in AMA citation format should be in sentence-case
TY - JOUR T1 - Tumor Margin Classification of Head and Neck Cancer Using Hyperspectral Imaging and Convolutional Neural Networks. AU - Halicek,Martin, AU - Little,James V, AU - Wang,Xu, AU - Patel,Mihir, AU - Griffith,Christopher C, AU - Chen,Amy Y, AU - Fei,Baowei, Y1 - 2018/03/12/ PY - 2018/9/25/entrez PY - 2018/9/25/pubmed PY - 2018/9/25/medline KW - Hyperspectral imaging KW - cancer margin detection KW - convolutional neural network KW - deep learning KW - head and neck cancer KW - head and neck surgery KW - intraoperative imaging JF - Proceedings of SPIE--the International Society for Optical Engineering JO - Proc SPIE Int Soc Opt Eng VL - 10576 N2 - 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. SN - 0277-786X UR - https://www.unboundmedicine.com/medline/citation/30245540/Tumor_Margin_Classification_of_Head_and_Neck_Cancer_Using_Hyperspectral_Imaging_and_Convolutional_Neural_Networks_ L2 - https://www.ncbi.nlm.nih.gov/pmc/articles/pmid/30245540/ DB - PRIME DP - Unbound Medicine ER -