A dual stream network for tumor detection in hyperspectral images

P.J.C. Weijtmans; C. Shan; T. Tan; S.G. Brouwer de Koning; T.J.M. Ruers

doi:10.1109/ISBI.2019.8759566

A dual stream network for tumor detection in hyperspectral images

P.J.C. Weijtmans, C. Shan, T. Tan, S.G. Brouwer de Koning, T.J.M. Ruers

Onderzoeksoutput: Hoofdstuk in Boek/Rapport/Congresprocedure › Conferentiebijdrage › Academic › peer review

25 Citaten (Scopus)

Samenvatting

Hyperspectral imaging has become an emerging imaging modality for medical applications. In this work, we propose to combine both the spectral and structural information in the hyperspectral data cube for tumor detection in tongue tissue. A dual stream network is designed, with a spectral and a structural branch. Hyperspectral data (480 to 920 nm) is collected from 7 patients with tongue squamous cell carcinoma. Histopathological analysis provided ground truth labels. The proposed dual stream model outperforms the pure spectral and structural approaches with areas under the ROC-curve of 0.90, 0.87 and 0.85, respectively.

Originele taal-2	Engels
Titel	ISBI 2019 - 2019 IEEE International Symposium on Biomedical Imaging
Plaats van productie	Piscataway
Uitgeverij	IEEE Computer Society
Pagina's	1256-1259
Aantal pagina's	4
ISBN van elektronische versie	9781538636411
DOI's	https://doi.org/10.1109/ISBI.2019.8759566
Status	Gepubliceerd - 1 apr. 2019
Evenement	16th IEEE International Symposium on Biomedical Imaging (ISBI 2019) - Venice, Italië Duur: 8 apr. 2019 → 11 apr. 2019 Congresnummer: 16

Congres

Congres	16th IEEE International Symposium on Biomedical Imaging (ISBI 2019)
Verkorte titel	ISBI 2019
Land/Regio	Italië
Stad	Venice
Periode	8/04/19 → 11/04/19

Toegang tot document

10.1109/ISBI.2019.8759566

Andere bestanden en links

Link to publication in Scopus

Citeer dit

@inproceedings{1033d6ede9514f388a0348f04889397e,

title = "A dual stream network for tumor detection in hyperspectral images",

abstract = "Hyperspectral imaging has become an emerging imaging modality for medical applications. In this work, we propose to combine both the spectral and structural information in the hyperspectral data cube for tumor detection in tongue tissue. A dual stream network is designed, with a spectral and a structural branch. Hyperspectral data (480 to 920 nm) is collected from 7 patients with tongue squamous cell carcinoma. Histopathological analysis provided ground truth labels. The proposed dual stream model outperforms the pure spectral and structural approaches with areas under the ROC-curve of 0.90, 0.87 and 0.85, respectively.",

keywords = "Hyperspectral imaging, Machine learning, Neural networks, Tongue tumor",

author = "P.J.C. Weijtmans and C. Shan and T. Tan and {Brouwer de Koning}, S.G. and T.J.M. Ruers",

year = "2019",

month = apr,

day = "1",

doi = "10.1109/ISBI.2019.8759566",

language = "English",

pages = "1256--1259",

booktitle = "ISBI 2019 - 2019 IEEE International Symposium on Biomedical Imaging",

publisher = "IEEE Computer Society",

address = "United States",

note = "16th IEEE International Symposium on Biomedical Imaging (ISBI 2019), ISBI 2019 ; Conference date: 08-04-2019 Through 11-04-2019",

}

Weijtmans, PJC, Shan, C, Tan, T, Brouwer de Koning, SG & Ruers, TJM 2019, A dual stream network for tumor detection in hyperspectral images. in ISBI 2019 - 2019 IEEE International Symposium on Biomedical Imaging., 8759566, IEEE Computer Society, Piscataway, blz. 1256-1259, 16th IEEE International Symposium on Biomedical Imaging (ISBI 2019), Venice, Italië, 8/04/19. https://doi.org/10.1109/ISBI.2019.8759566

TY - GEN

T1 - A dual stream network for tumor detection in hyperspectral images

AU - Weijtmans, P.J.C.

AU - Shan, C.

AU - Tan, T.

AU - Brouwer de Koning, S.G.

AU - Ruers, T.J.M.

N1 - Conference code: 16

PY - 2019/4/1

Y1 - 2019/4/1

N2 - Hyperspectral imaging has become an emerging imaging modality for medical applications. In this work, we propose to combine both the spectral and structural information in the hyperspectral data cube for tumor detection in tongue tissue. A dual stream network is designed, with a spectral and a structural branch. Hyperspectral data (480 to 920 nm) is collected from 7 patients with tongue squamous cell carcinoma. Histopathological analysis provided ground truth labels. The proposed dual stream model outperforms the pure spectral and structural approaches with areas under the ROC-curve of 0.90, 0.87 and 0.85, respectively.

AB - Hyperspectral imaging has become an emerging imaging modality for medical applications. In this work, we propose to combine both the spectral and structural information in the hyperspectral data cube for tumor detection in tongue tissue. A dual stream network is designed, with a spectral and a structural branch. Hyperspectral data (480 to 920 nm) is collected from 7 patients with tongue squamous cell carcinoma. Histopathological analysis provided ground truth labels. The proposed dual stream model outperforms the pure spectral and structural approaches with areas under the ROC-curve of 0.90, 0.87 and 0.85, respectively.

KW - Hyperspectral imaging

KW - Machine learning

KW - Neural networks

KW - Tongue tumor

UR - http://www.scopus.com/inward/record.url?scp=85072370566&partnerID=8YFLogxK

U2 - 10.1109/ISBI.2019.8759566

DO - 10.1109/ISBI.2019.8759566

M3 - Conference contribution

AN - SCOPUS:85072370566

SP - 1256

EP - 1259

BT - ISBI 2019 - 2019 IEEE International Symposium on Biomedical Imaging

PB - IEEE Computer Society

CY - Piscataway

T2 - 16th IEEE International Symposium on Biomedical Imaging (ISBI 2019)

Y2 - 8 April 2019 through 11 April 2019

ER -

A dual stream network for tumor detection in hyperspectral images

Samenvatting

Congres

Toegang tot document

Andere bestanden en links

Vingerafdruk

Citeer dit