Discriminating healthy from tumor tissue in breast lumpectomy specimens using deep learning-based hyperspectral imaging

Lynn Jade S. Jong; Naomi de Kruif; Freija Geldof; Dinusha Veluponnar; Joyce Sanders; Marie Jeanne T.F.D. Vrancken Peeters; Frederieke van Duijnhoven; Henricus J.C.M. Sterenborg; Behdad Dashtbozorg; Theo J.M. Ruers

doi:10.1364/BOE.455208

Discriminating healthy from tumor tissue in breast lumpectomy specimens using deep learning-based hyperspectral imaging

Lynn Jade S. Jong, Naomi de Kruif, Freija Geldof, Dinusha Veluponnar, Joyce Sanders, Marie Jeanne T.F.D. Vrancken Peeters, Frederieke van Duijnhoven, Henricus J.C.M. Sterenborg, Behdad Dashtbozorg^*, Theo J.M. Ruers

^*Corresponding author for this work

Research output: Contribution to journal › Article › Academic › peer-review

12 Citations (Scopus)

97 Downloads (Pure)

Abstract

Achieving an adequate resection margin during breast-conserving surgery remains challenging due to the lack of intraoperative feedback. Here, we evaluated the use of hyperspectral imaging to discriminate healthy tissue from tumor tissue in lumpectomy specimens. We first used a dataset obtained on tissue slices to develop and evaluate three convolutional neural networks. Second, we fine-tuned the networks with lumpectomy data to predict the tissue percentages of the lumpectomy resection surface. A MCC of 0.92 was achieved on the tissue slices and an RMSE of 9% on the lumpectomy resection surface. This shows the potential of hyperspectral imaging to classify the resection margins of lumpectomy specimens.

Original language	English
Pages (from-to)	2581-2604
Number of pages	24
Journal	Biomedical optics express
Volume	13
Issue number	5
DOIs	https://doi.org/10.1364/BOE.455208
Publication status	Published - 1 May 2022

UN SDGs

This output contributes to the following UN Sustainable Development Goals (SDGs)

Access to Document

10.1364/BOE.455208Licence: CC BY

ArticleFinal published version, 5.85 MBLicence: CC BY

Cite this

Jong, L. J. S., de Kruif, N., Geldof, F., Veluponnar, D., Sanders, J., Vrancken Peeters, M. J. T. F. D., van Duijnhoven, F., Sterenborg, H. J. C. M., Dashtbozorg, B., & Ruers, T. J. M. (2022). Discriminating healthy from tumor tissue in breast lumpectomy specimens using deep learning-based hyperspectral imaging. Biomedical optics express, 13(5), 2581-2604. https://doi.org/10.1364/BOE.455208

@article{1cd61e91eddd4bfa9ced85710bc350c1,

title = "Discriminating healthy from tumor tissue in breast lumpectomy specimens using deep learning-based hyperspectral imaging",

abstract = "Achieving an adequate resection margin during breast-conserving surgery remains challenging due to the lack of intraoperative feedback. Here, we evaluated the use of hyperspectral imaging to discriminate healthy tissue from tumor tissue in lumpectomy specimens. We first used a dataset obtained on tissue slices to develop and evaluate three convolutional neural networks. Second, we fine-tuned the networks with lumpectomy data to predict the tissue percentages of the lumpectomy resection surface. A MCC of 0.92 was achieved on the tissue slices and an RMSE of 9% on the lumpectomy resection surface. This shows the potential of hyperspectral imaging to classify the resection margins of lumpectomy specimens.",

author = "Jong, {Lynn Jade S.} and {de Kruif}, Naomi and Freija Geldof and Dinusha Veluponnar and Joyce Sanders and {Vrancken Peeters}, {Marie Jeanne T.F.D.} and {van Duijnhoven}, Frederieke and Sterenborg, {Henricus J.C.M.} and Behdad Dashtbozorg and Ruers, {Theo J.M.}",

note = "Funding Information: KWF Kankerbestrijding (10747). The authors thank the NKI-AVL core Facility Molecular Pathology & Biobanking (CFMPB) for supplying NKI-AVL biobank material, all surgeons and nurses from the Department of Surgery and all pathologist and pathologist assistants from the Department of Pathology for their assistance in collecting the specimens. The Quadro P6000 GPU used for this research was donated by the NVIDIA Corporation. Publisher Copyright: {\textcopyright} 2022 Optica Publishing Group under the terms of the Optica Open Access Publishing Agreement",

year = "2022",

month = may,

day = "1",

doi = "10.1364/BOE.455208",

language = "English",

volume = "13",

pages = "2581--2604",

journal = "Biomedical optics express",

issn = "2156-7085",

publisher = "Optica Publishing Group (formerly OSA)",

number = "5",

}

Jong, LJS, de Kruif, N, Geldof, F, Veluponnar, D, Sanders, J, Vrancken Peeters, MJTFD, van Duijnhoven, F, Sterenborg, HJCM, Dashtbozorg, B & Ruers, TJM 2022, 'Discriminating healthy from tumor tissue in breast lumpectomy specimens using deep learning-based hyperspectral imaging', Biomedical optics express, vol. 13, no. 5, pp. 2581-2604. https://doi.org/10.1364/BOE.455208

TY - JOUR

T1 - Discriminating healthy from tumor tissue in breast lumpectomy specimens using deep learning-based hyperspectral imaging

AU - Jong, Lynn Jade S.

AU - de Kruif, Naomi

AU - Geldof, Freija

AU - Veluponnar, Dinusha

AU - Sanders, Joyce

AU - Vrancken Peeters, Marie Jeanne T.F.D.

AU - van Duijnhoven, Frederieke

AU - Sterenborg, Henricus J.C.M.

AU - Dashtbozorg, Behdad

AU - Ruers, Theo J.M.

N1 - Funding Information: KWF Kankerbestrijding (10747). The authors thank the NKI-AVL core Facility Molecular Pathology & Biobanking (CFMPB) for supplying NKI-AVL biobank material, all surgeons and nurses from the Department of Surgery and all pathologist and pathologist assistants from the Department of Pathology for their assistance in collecting the specimens. The Quadro P6000 GPU used for this research was donated by the NVIDIA Corporation. Publisher Copyright: © 2022 Optica Publishing Group under the terms of the Optica Open Access Publishing Agreement

PY - 2022/5/1

Y1 - 2022/5/1

N2 - Achieving an adequate resection margin during breast-conserving surgery remains challenging due to the lack of intraoperative feedback. Here, we evaluated the use of hyperspectral imaging to discriminate healthy tissue from tumor tissue in lumpectomy specimens. We first used a dataset obtained on tissue slices to develop and evaluate three convolutional neural networks. Second, we fine-tuned the networks with lumpectomy data to predict the tissue percentages of the lumpectomy resection surface. A MCC of 0.92 was achieved on the tissue slices and an RMSE of 9% on the lumpectomy resection surface. This shows the potential of hyperspectral imaging to classify the resection margins of lumpectomy specimens.

AB - Achieving an adequate resection margin during breast-conserving surgery remains challenging due to the lack of intraoperative feedback. Here, we evaluated the use of hyperspectral imaging to discriminate healthy tissue from tumor tissue in lumpectomy specimens. We first used a dataset obtained on tissue slices to develop and evaluate three convolutional neural networks. Second, we fine-tuned the networks with lumpectomy data to predict the tissue percentages of the lumpectomy resection surface. A MCC of 0.92 was achieved on the tissue slices and an RMSE of 9% on the lumpectomy resection surface. This shows the potential of hyperspectral imaging to classify the resection margins of lumpectomy specimens.

UR - http://www.scopus.com/inward/record.url?scp=85128651646&partnerID=8YFLogxK

U2 - 10.1364/BOE.455208

DO - 10.1364/BOE.455208

M3 - Article

AN - SCOPUS:85128651646

SN - 2156-7085

VL - 13

SP - 2581

EP - 2604

JO - Biomedical optics express

JF - Biomedical optics express

IS - 5

ER -

Discriminating healthy from tumor tissue in breast lumpectomy specimens using deep learning-based hyperspectral imaging

Abstract

UN SDGs

Access to Document

Other files and links

Fingerprint

Cite this