True digital hair removal with real value inpainting for improved dermoscopy based on image fusion

Publikation: Beitrag in Buch/Bericht/Sammelwerk/KonferenzbandAufsatz in KonferenzbandForschungPeer-Review

Forschungs-netzwerk anzeigen

Details

OriginalspracheEnglisch
Titel des SammelwerksPhotonics in Dermatology and Plastic Surgery 2023
Herausgeber/-innenBernard Choi, Haishan Zeng
Herausgeber (Verlag)SPIE
ISBN (elektronisch)9781510658097
PublikationsstatusVeröffentlicht - 14 März 2023
VeranstaltungPhotonics in Dermatology and Plastic Surgery 2023 - San Francisco, USA / Vereinigte Staaten
Dauer: 28 Jan. 20233 Feb. 2023

Publikationsreihe

NameProgress in Biomedical Optics and Imaging - Proceedings of SPIE
Band12352
ISSN (Print)1605-7422

Abstract

We propose a method for digital hair removal from dermoscopic images that involves a new scheme for the acquisition of dermoscopic images to uncover hidden information by employing image fusion of multiple images of lesions. Classical approaches for the removal of hair from dermoscopic images are usually based on interpolation, pattern propagation or machine learning. These replace the hair pixels with calculated data aiming to reduce the impairment of the medical diagnostics. While these approaches are well established, the problem of information loss is not addressed. We show that our approach can lead to improved skin lesion assessment in dermoscopy.

ASJC Scopus Sachgebiete

Ziele für nachhaltige Entwicklung

Zitieren

True digital hair removal with real value inpainting for improved dermoscopy based on image fusion. / Jütte, Lennart; Emmert, Steffen; Roth, Bernhard.
Photonics in Dermatology and Plastic Surgery 2023. Hrsg. / Bernard Choi; Haishan Zeng. SPIE, 2023. 1235202 (Progress in Biomedical Optics and Imaging - Proceedings of SPIE; Band 12352).

Publikation: Beitrag in Buch/Bericht/Sammelwerk/KonferenzbandAufsatz in KonferenzbandForschungPeer-Review

Jütte, L, Emmert, S & Roth, B 2023, True digital hair removal with real value inpainting for improved dermoscopy based on image fusion. in B Choi & H Zeng (Hrsg.), Photonics in Dermatology and Plastic Surgery 2023., 1235202, Progress in Biomedical Optics and Imaging - Proceedings of SPIE, Bd. 12352, SPIE, Photonics in Dermatology and Plastic Surgery 2023, San Francisco, USA / Vereinigte Staaten, 28 Jan. 2023. https://doi.org/10.1117/12.2646227
Jütte, L., Emmert, S., & Roth, B. (2023). True digital hair removal with real value inpainting for improved dermoscopy based on image fusion. In B. Choi, & H. Zeng (Hrsg.), Photonics in Dermatology and Plastic Surgery 2023 Artikel 1235202 (Progress in Biomedical Optics and Imaging - Proceedings of SPIE; Band 12352). SPIE. https://doi.org/10.1117/12.2646227
Jütte L, Emmert S, Roth B. True digital hair removal with real value inpainting for improved dermoscopy based on image fusion. in Choi B, Zeng H, Hrsg., Photonics in Dermatology and Plastic Surgery 2023. SPIE. 2023. 1235202. (Progress in Biomedical Optics and Imaging - Proceedings of SPIE). doi: 10.1117/12.2646227
Jütte, Lennart ; Emmert, Steffen ; Roth, Bernhard. / True digital hair removal with real value inpainting for improved dermoscopy based on image fusion. Photonics in Dermatology and Plastic Surgery 2023. Hrsg. / Bernard Choi ; Haishan Zeng. SPIE, 2023. (Progress in Biomedical Optics and Imaging - Proceedings of SPIE).
Download
@inproceedings{b68ed2faf5594b659815c5c16e0064b3,
title = "True digital hair removal with real value inpainting for improved dermoscopy based on image fusion",
abstract = "We propose a method for digital hair removal from dermoscopic images that involves a new scheme for the acquisition of dermoscopic images to uncover hidden information by employing image fusion of multiple images of lesions. Classical approaches for the removal of hair from dermoscopic images are usually based on interpolation, pattern propagation or machine learning. These replace the hair pixels with calculated data aiming to reduce the impairment of the medical diagnostics. While these approaches are well established, the problem of information loss is not addressed. We show that our approach can lead to improved skin lesion assessment in dermoscopy.",
keywords = "digital hair removal, image fusion, melanoma, skin cancer",
author = "Lennart J{\"u}tte and Steffen Emmert and Bernhard Roth",
note = "Funding Information: This work has been supported by iToBoS (Intelligent Total Body Scanner for Early Detection of Melanoma), project funded by the European Union{\textquoteright}s Horizon 2020 research and innovation programme, under grant agreement No 965221. Also, financial support by the Deutsche Forschungsgemeinschaft (DFG, German Research Foundation) under Germany{\textquoteright}s Excellence Strategy within the Cluster of Excellence PhoenixD (EXC 2122, Project ID 390833453) is acknowledged.; Photonics in Dermatology and Plastic Surgery 2023 ; Conference date: 28-01-2023 Through 03-02-2023",
year = "2023",
month = mar,
day = "14",
doi = "10.1117/12.2646227",
language = "English",
series = "Progress in Biomedical Optics and Imaging - Proceedings of SPIE",
publisher = "SPIE",
editor = "Bernard Choi and Haishan Zeng",
booktitle = "Photonics in Dermatology and Plastic Surgery 2023",
address = "United States",

}

Download

TY - GEN

T1 - True digital hair removal with real value inpainting for improved dermoscopy based on image fusion

AU - Jütte, Lennart

AU - Emmert, Steffen

AU - Roth, Bernhard

N1 - Funding Information: This work has been supported by iToBoS (Intelligent Total Body Scanner for Early Detection of Melanoma), project funded by the European Union’s Horizon 2020 research and innovation programme, under grant agreement No 965221. Also, financial support by the Deutsche Forschungsgemeinschaft (DFG, German Research Foundation) under Germany’s Excellence Strategy within the Cluster of Excellence PhoenixD (EXC 2122, Project ID 390833453) is acknowledged.

PY - 2023/3/14

Y1 - 2023/3/14

N2 - We propose a method for digital hair removal from dermoscopic images that involves a new scheme for the acquisition of dermoscopic images to uncover hidden information by employing image fusion of multiple images of lesions. Classical approaches for the removal of hair from dermoscopic images are usually based on interpolation, pattern propagation or machine learning. These replace the hair pixels with calculated data aiming to reduce the impairment of the medical diagnostics. While these approaches are well established, the problem of information loss is not addressed. We show that our approach can lead to improved skin lesion assessment in dermoscopy.

AB - We propose a method for digital hair removal from dermoscopic images that involves a new scheme for the acquisition of dermoscopic images to uncover hidden information by employing image fusion of multiple images of lesions. Classical approaches for the removal of hair from dermoscopic images are usually based on interpolation, pattern propagation or machine learning. These replace the hair pixels with calculated data aiming to reduce the impairment of the medical diagnostics. While these approaches are well established, the problem of information loss is not addressed. We show that our approach can lead to improved skin lesion assessment in dermoscopy.

KW - digital hair removal

KW - image fusion

KW - melanoma

KW - skin cancer

UR - http://www.scopus.com/inward/record.url?scp=85159719955&partnerID=8YFLogxK

U2 - 10.1117/12.2646227

DO - 10.1117/12.2646227

M3 - Conference contribution

AN - SCOPUS:85159719955

T3 - Progress in Biomedical Optics and Imaging - Proceedings of SPIE

BT - Photonics in Dermatology and Plastic Surgery 2023

A2 - Choi, Bernard

A2 - Zeng, Haishan

PB - SPIE

T2 - Photonics in Dermatology and Plastic Surgery 2023

Y2 - 28 January 2023 through 3 February 2023

ER -

Von denselben Autoren