Tumor detection of the thyroid and salivary glands using hyperspectral imaging and deep learning.

The performance of hyperspectral imaging (HSI) for tumor detection is investigated in ex-vivo specimens from the thyroid (N = 200) and salivary glands (N = 16) from 82 patients. Tissues were imaged with HSI in broadband reflectance and autofluorescence modes. For comparison, the tissues were imaged with two fluorescent dyes. Additionally, HSI was used to synthesize three-band RGB multiplex images to represent the human-eye response and Gaussian RGBs, which are referred to as HSI-synthesized RGB images. Using histological ground truths, deep learning algorithms were developed for tumor detection. For the classification of thyroid tumors, HSI-synthesized RGB images achieved the best performance with an AUC score of 0.90. In salivary glands, HSI had the best performance with 0.92 AUC score. This study demonstrates that HSI could aid surgeons and pathologists in detecting tumors of the thyroid and salivary glands.

[1]  S. Mandel,et al.  2015 American Thyroid Association Management Guidelines for Adult Patients with Thyroid Nodules and Differentiated Thyroid Cancer: The American Thyroid Association Guidelines Task Force on Thyroid Nodules and Differentiated Thyroid Cancer. , 2009, Thyroid : official journal of the American Thyroid Association.

[2]  Henricus J C M Sterenborg,et al.  Hyperspectral imaging for tissue classification, a way toward smart laparoscopic colorectal surgery , 2019, Journal of biomedical optics.

[3]  Abhishek Das,et al.  Grad-CAM: Visual Explanations from Deep Networks via Gradient-Based Localization , 2016, 2017 IEEE International Conference on Computer Vision (ICCV).

[4]  R. Lloyd,et al.  Papillary Thyroid Carcinoma Variants , 2011, Head and neck pathology.

[5]  J. J. Vos.  Colorimetric and photometric properties of a 2° fundamental observer , 1978 .

[6]  Gustavo Marrero Callicó,et al.  Deep Learning-Based Framework for In Vivo Identification of Glioblastoma Tumor using Hyperspectral Images of Human Brain , 2019, Sensors.

[7]  Guang-Zhong Yang,et al.  In-Vivo Hyperspectral Human Brain Image Database for Brain Cancer Detection , 2019, IEEE Access.

[8]  Eva Negri,et al.  Thyroid cancer mortality and incidence: A global overview , 2015, International journal of cancer.

[9]  Xu Wang,et al.  Deformable registration of histological cancer margins to gross hyperspectral images using demons , 2018, Medical Imaging.

[10]  T. Matsuzuka,et al.  The role of frozen section biopsy for parotid gland tumour with benign fine-needle aspiration cytology , 2019, The Journal of Laryngology & Otology.

[11]  Rachel Gaulton,et al.  ESTIMATION OF THE SPECTRAL SENSITIVITY FUNCTIONS OF UN-MODIFIED AND MODIFIED COMMERCIAL OFF-THE-SHELF DIGITAL CAMERAS TO ENABLE THEIR USE AS A MULTISPECTRAL IMAGING SYSTEM FOR UAVS , 2015 .

[12]  Sharmila Anandasabapathy,et al.  Vital-dye enhanced fluorescence imaging of GI mucosa: metaplasia, neoplasia, inflammation. , 2012, Gastrointestinal endoscopy.

[13]  Sebastien Ourselin,et al.  Intraoperative multispectral and hyperspectral label‐free imaging: A systematic review of in vivo clinical studies , 2019, Journal of biophotonics.

[14]  B. Erovic,et al.  Fine‐needle aspiration cytology and intraoperative frozen section in parotid gland tumour surgery: A retrospective multicenter analysis of 417 cases , 2019, Clinical otolaryngology : official journal of ENT-UK ; official journal of Netherlands Society for Oto-Rhino-Laryngology & Cervico-Facial Surgery.

[15]  Brenessa Lindeman,et al.  Is Frozen-Section Analysis During Thyroid Operation Useful in the Era of Molecular Testing? , 2019, Journal of the American College of Surgeons.

[16]  Baowei Fei,et al.  In-Vivo and Ex-Vivo Tissue Analysis through Hyperspectral Imaging Techniques: Revealing the Invisible Features of Cancer , 2019, Cancers.

[17]  T Neumuth,et al.  Determination of the transection margin during colorectal resection with hyperspectral imaging (HSI) , 2019, International Journal of Colorectal Disease.

[18]  Egidijus Auksorius,et al.  Fast subsurface fingerprint imaging with full-field optical coherence tomography system equipped with a silicon camera , 2017, Journal of biomedical optics.

[19]  James V. Little,et al.  Detection of Head and Neck Cancer in Surgical Specimens Using Quantitative Hyperspectral Imaging , 2017, Clinical Cancer Research.

[20]  Thomas Neumuth,et al.  Hyperspectral based discrimination of thyroid and parathyroid during surgery , 2018, Current Directions in Biomedical Engineering.

[21]  Rebecca Richards-Kortum,et al.  Vital-dye-enhanced multimodal imaging of neoplastic progression in a mouse model of oral carcinogenesis , 2013, Journal of biomedical optics.

[22]  Samuel Ortega,et al.  Hyperspectral imaging for head and neck cancer detection: specular glare and variance of the tumor margin in surgical specimens , 2019, Journal of medical imaging.

[23]  Xu Wang,et al.  Tumor margin classification of head and neck cancer using hyperspectral imaging and convolutional neural networks , 2018, Medical Imaging.

[24]  Baowei Fei,et al.  Head and Neck Cancer Detection in Digitized Whole-Slide Histology Using Convolutional Neural Networks , 2019, Scientific Reports.

[25]  M. Sobrinho-Simões,et al.  Follicular thyroid carcinoma , 2011, Modern Pathology.

[26]  Herb Chen,et al.  Current understanding and management of medullary thyroid cancer. , 2013, The oncologist.

[27]  K. Chatura.  Polymorphous low grade adenocarcinoma , 2015, Journal of oral and maxillofacial pathology : JOMFP.

[28]  James V. Little,et al.  Label-free reflectance hyperspectral imaging for tumor margin assessment: a pilot study on surgical specimens of cancer patients , 2017, Journal of biomedical optics.

[29]  D. Howlett,et al.  Establishing an accurate diagnosis of a parotid lump: evaluation of the current biopsy methods - fine needle aspiration cytology, ultrasound-guided core biopsy, and intraoperative frozen section. , 2015, The British journal of oral & maxillofacial surgery.

[30]  Anna Hilsmann,et al.  Intraoperative hyperspectral determination of human tissue properties , 2018, Journal of biomedical optics.

[31]  V. Dombale,et al.  Histopathological study of salivary gland tumors , 2017, Journal of oral and maxillofacial pathology : JOMFP.

[32]  Carmen Lopez,et al.  Hyperspectral imaging fluorescence excitation scanning for colon cancer detection , 2016, Journal of biomedical optics.

[33]  C. Land,et al.  Incidence of Carcinoma of the Major Salivary Glands According to the WHO Classification, 1992 to 2006: A Population-Based Study in the United States , 2009, Cancer Epidemiology, Biomarkers & Prevention.

[34]  Xu Wang,et al.  Optical biopsy of head and neck cancer using hyperspectral imaging and convolutional neural networks , 2019, Journal of biomedical optics.

[35]  Martin T. Halicek,et al.  Hyperspectral Imaging of Head and Neck Squamous Cell Carcinoma for Cancer Margin Detection in Surgical Specimens from 102 Patients Using Deep Learning , 2019, Cancers.

[36]  Douglas B. Evans,et al.  Analysis of an institutional protocol for thyroid lobectomy: Utility of routine intraoperative frozen section and expedited (overnight) pathology. , 2016, Surgery.

[37]  Guolan Lu,et al.  Medical hyperspectral imaging: a review , 2014, Journal of biomedical optics.

[38]  J. Chan,et al.  Review of Salivary Gland Neoplasms , 2012, ISRN otolaryngology.

[39]  Guolan Lu,et al.  Deep convolutional neural networks for classifying head and neck cancer using hyperspectral imaging , 2017, Journal of biomedical optics.