Automated tumor assessment of squamous cell carcinoma on tongue cancer patients with hyperspectral imaging

Francesca Manni, Fons van der Sommen, Sveta Zinger, Esther Kho, Susan Brouwer de Koning, Theo Ruers, Caifeng Shan, Jean Schleipen, Peter de With

Research output: Chapter in Book/Report/Conference proceedingConference contributionAcademicpeer-review

2 Citations (Scopus)

Abstract

Head and neck cancer (HNC) includes cancers in the oral/nasal cavity, pharynx, larynx, etc., and it is the sixth most common cancer worldwide. The principal treatment is surgical removal where a complete tumor resection is crucial to reduce the recurrence and mortality rate. Intraoperative tumor imaging enables surgeons to objectively visualize the malignant lesion to maximize the tumor removal with healthy safe margins. Hyperspectral imaging (HSI) is an emerging imaging modality for cancer detection, which can augment surgical tumor inspection, currently limited to subjective visual inspection. In this paper, we aim to investigate HSI for automated cancer detection during image-guided surgery, because it can provide quantitative information about light interaction with biological tissues and exploit the potential for malignant tissue discrimination. The proposed solution forms a novel framework for automated tongue-cancer detection, explicitly exploiting HSI, which particularly uses the spectral variations in specific bands describing the cancerous tissue properties. The method follows a machine-learning based classification, employing linear support vector machine (SVM), and offers a superior sensitivity and a significant decrease in computation time. The model evaluation is on 7 ex-vivo specimens of squamous cell carcinoma of the tongue, with known histology. The HSI combined with the proposed classification reaches a sensitivity of 94%, specificity of 68% and area under the curve (AUC) of 92%. This feasibility study paves the way for introducing HSI as a non-invasive imaging aid for cancer detection and increase of the effectiveness of surgical oncology.
LanguageEnglish
Title of host publicationMedical Imaging 2019
Subtitle of host publicationImage-Guided Procedures, Robotic Interventions, and Modeling
Place of PublicationBellingham
PublisherSPIE
Number of pages7
DOIs
StatePublished - 8 Mar 2019
EventSPIE Medical Imaging 2019 - San Diego, United States
Duration: 16 Feb 201921 Feb 2019
http://spie.org/MI/entireprogram/2019-2-20?print=2&SSO=1

Publication series

NameProceedings of SPIE
Volume10951

Conference

ConferenceSPIE Medical Imaging 2019
CountryUnited States
CitySan Diego
Period16/02/1921/02/19
Internet address

Fingerprint

Tongue Neoplasms
Squamous Cell Carcinoma
Neoplasms
Computer-Assisted Surgery
Nasal Cavity
Mouth Neoplasms
Feasibility Studies
Head and Neck Neoplasms
Larynx
Pharynx
Tongue
Area Under Curve
Mouth
Histology
Light
Recurrence
Sensitivity and Specificity
Mortality

Keywords

  • hyperspectral imaging
  • tongue cancer
  • intraoperative tumor detection
  • image-guided surgery
  • cancer detection

Cite this

Manni, F., van der Sommen, F., Zinger, S., Kho, E., Brouwer de Koning, S., Ruers, T., ... de With, P. (2019). Automated tumor assessment of squamous cell carcinoma on tongue cancer patients with hyperspectral imaging. In Medical Imaging 2019: Image-Guided Procedures, Robotic Interventions, and Modeling [109512K] (Proceedings of SPIE; Vol. 10951). Bellingham: SPIE. DOI: 10.1117/12.2512238
Manni, Francesca ; van der Sommen, Fons ; Zinger, Sveta ; Kho, Esther ; Brouwer de Koning, Susan ; Ruers, Theo ; Shan, Caifeng ; Schleipen, Jean ; de With, Peter. / Automated tumor assessment of squamous cell carcinoma on tongue cancer patients with hyperspectral imaging. Medical Imaging 2019: Image-Guided Procedures, Robotic Interventions, and Modeling. Bellingham : SPIE, 2019. (Proceedings of SPIE).
@inproceedings{db9a2f7b01c74598bb7d9dd412ef9293,
title = "Automated tumor assessment of squamous cell carcinoma on tongue cancer patients with hyperspectral imaging",
abstract = "Head and neck cancer (HNC) includes cancers in the oral/nasal cavity, pharynx, larynx, etc., and it is the sixth most common cancer worldwide. The principal treatment is surgical removal where a complete tumor resection is crucial to reduce the recurrence and mortality rate. Intraoperative tumor imaging enables surgeons to objectively visualize the malignant lesion to maximize the tumor removal with healthy safe margins. Hyperspectral imaging (HSI) is an emerging imaging modality for cancer detection, which can augment surgical tumor inspection, currently limited to subjective visual inspection. In this paper, we aim to investigate HSI for automated cancer detection during image-guided surgery, because it can provide quantitative information about light interaction with biological tissues and exploit the potential for malignant tissue discrimination. The proposed solution forms a novel framework for automated tongue-cancer detection, explicitly exploiting HSI, which particularly uses the spectral variations in specific bands describing the cancerous tissue properties. The method follows a machine-learning based classification, employing linear support vector machine (SVM), and offers a superior sensitivity and a significant decrease in computation time. The model evaluation is on 7 ex-vivo specimens of squamous cell carcinoma of the tongue, with known histology. The HSI combined with the proposed classification reaches a sensitivity of 94{\%}, specificity of 68{\%} and area under the curve (AUC) of 92{\%}. This feasibility study paves the way for introducing HSI as a non-invasive imaging aid for cancer detection and increase of the effectiveness of surgical oncology.",
keywords = "hyperspectral imaging, tongue cancer, intraoperative tumor detection, image-guided surgery, cancer detection",
author = "Francesca Manni and {van der Sommen}, Fons and Sveta Zinger and Esther Kho and {Brouwer de Koning}, Susan and Theo Ruers and Caifeng Shan and Jean Schleipen and {de With}, Peter",
year = "2019",
month = "3",
day = "8",
doi = "10.1117/12.2512238",
language = "English",
series = "Proceedings of SPIE",
publisher = "SPIE",
booktitle = "Medical Imaging 2019",
address = "United States",

}

Manni, F, van der Sommen, F, Zinger, S, Kho, E, Brouwer de Koning, S, Ruers, T, Shan, C, Schleipen, J & de With, P 2019, Automated tumor assessment of squamous cell carcinoma on tongue cancer patients with hyperspectral imaging. in Medical Imaging 2019: Image-Guided Procedures, Robotic Interventions, and Modeling., 109512K, Proceedings of SPIE, vol. 10951, SPIE, Bellingham, SPIE Medical Imaging 2019, San Diego, United States, 16/02/19. DOI: 10.1117/12.2512238

Automated tumor assessment of squamous cell carcinoma on tongue cancer patients with hyperspectral imaging. / Manni, Francesca; van der Sommen, Fons; Zinger, Sveta; Kho, Esther; Brouwer de Koning, Susan; Ruers, Theo; Shan, Caifeng; Schleipen, Jean; de With, Peter.

Medical Imaging 2019: Image-Guided Procedures, Robotic Interventions, and Modeling. Bellingham : SPIE, 2019. 109512K (Proceedings of SPIE; Vol. 10951).

Research output: Chapter in Book/Report/Conference proceedingConference contributionAcademicpeer-review

TY - GEN

T1 - Automated tumor assessment of squamous cell carcinoma on tongue cancer patients with hyperspectral imaging

AU - Manni,Francesca

AU - van der Sommen,Fons

AU - Zinger,Sveta

AU - Kho,Esther

AU - Brouwer de Koning,Susan

AU - Ruers,Theo

AU - Shan,Caifeng

AU - Schleipen,Jean

AU - de With,Peter

PY - 2019/3/8

Y1 - 2019/3/8

N2 - Head and neck cancer (HNC) includes cancers in the oral/nasal cavity, pharynx, larynx, etc., and it is the sixth most common cancer worldwide. The principal treatment is surgical removal where a complete tumor resection is crucial to reduce the recurrence and mortality rate. Intraoperative tumor imaging enables surgeons to objectively visualize the malignant lesion to maximize the tumor removal with healthy safe margins. Hyperspectral imaging (HSI) is an emerging imaging modality for cancer detection, which can augment surgical tumor inspection, currently limited to subjective visual inspection. In this paper, we aim to investigate HSI for automated cancer detection during image-guided surgery, because it can provide quantitative information about light interaction with biological tissues and exploit the potential for malignant tissue discrimination. The proposed solution forms a novel framework for automated tongue-cancer detection, explicitly exploiting HSI, which particularly uses the spectral variations in specific bands describing the cancerous tissue properties. The method follows a machine-learning based classification, employing linear support vector machine (SVM), and offers a superior sensitivity and a significant decrease in computation time. The model evaluation is on 7 ex-vivo specimens of squamous cell carcinoma of the tongue, with known histology. The HSI combined with the proposed classification reaches a sensitivity of 94%, specificity of 68% and area under the curve (AUC) of 92%. This feasibility study paves the way for introducing HSI as a non-invasive imaging aid for cancer detection and increase of the effectiveness of surgical oncology.

AB - Head and neck cancer (HNC) includes cancers in the oral/nasal cavity, pharynx, larynx, etc., and it is the sixth most common cancer worldwide. The principal treatment is surgical removal where a complete tumor resection is crucial to reduce the recurrence and mortality rate. Intraoperative tumor imaging enables surgeons to objectively visualize the malignant lesion to maximize the tumor removal with healthy safe margins. Hyperspectral imaging (HSI) is an emerging imaging modality for cancer detection, which can augment surgical tumor inspection, currently limited to subjective visual inspection. In this paper, we aim to investigate HSI for automated cancer detection during image-guided surgery, because it can provide quantitative information about light interaction with biological tissues and exploit the potential for malignant tissue discrimination. The proposed solution forms a novel framework for automated tongue-cancer detection, explicitly exploiting HSI, which particularly uses the spectral variations in specific bands describing the cancerous tissue properties. The method follows a machine-learning based classification, employing linear support vector machine (SVM), and offers a superior sensitivity and a significant decrease in computation time. The model evaluation is on 7 ex-vivo specimens of squamous cell carcinoma of the tongue, with known histology. The HSI combined with the proposed classification reaches a sensitivity of 94%, specificity of 68% and area under the curve (AUC) of 92%. This feasibility study paves the way for introducing HSI as a non-invasive imaging aid for cancer detection and increase of the effectiveness of surgical oncology.

KW - hyperspectral imaging

KW - tongue cancer

KW - intraoperative tumor detection

KW - image-guided surgery

KW - cancer detection

U2 - 10.1117/12.2512238

DO - 10.1117/12.2512238

M3 - Conference contribution

T3 - Proceedings of SPIE

BT - Medical Imaging 2019

PB - SPIE

CY - Bellingham

ER -

Manni F, van der Sommen F, Zinger S, Kho E, Brouwer de Koning S, Ruers T et al. Automated tumor assessment of squamous cell carcinoma on tongue cancer patients with hyperspectral imaging. In Medical Imaging 2019: Image-Guided Procedures, Robotic Interventions, and Modeling. Bellingham: SPIE. 2019. 109512K. (Proceedings of SPIE). Available from, DOI: 10.1117/12.2512238