TY - JOUR
T1 - Tissue Classification of Breast Cancer by Hyperspectral Unmixing
AU - Jong, Lynn-Jade S.
AU - Post, Anouk L.
AU - Veluponnar, Dinusha
AU - Geldof, Freija
AU - Sterenborg, Henricus J. C. M.
AU - Ruers, Theo J. M.
AU - Dashtbozorg, Behdad
N1 - Funding Information: The authors thank M.T.F.D. Vrancken Peeters, F. van Duijnhoven, and all other surgeons and nurses from the department of Surgery. The authors also thank the NKI-AVL core Facility Molecular Pathology & Biobanking (CFMPB) for supplying NKI-AVL biobank material, and J. Sanders and M. Guimaraes as well as the pathologist assistants from the department of Pathology for their assistance in investigating the specimens. Research at the Netherlands Cancer Institute is supported by institutional grants of the Dutch Cancer Society and of the Dutch Ministry of Health, Welfare and Sport. Funding Information: This research was funded by the Dutch Cancer Society, grant number 10747. Publisher Copyright: © 2023 by the authors.
PY - 2023/5/1
Y1 - 2023/5/1
N2 - (1) Background: Assessing the resection margins during breast-conserving surgery is an important clinical need to minimize the risk of recurrent breast cancer. However, currently there is no technique that can provide real-time feedback to aid surgeons in the margin assessment. Hyperspectral imaging has the potential to overcome this problem. To classify resection margins with this technique, a tissue discrimination model should be developed, which requires a dataset with accurate ground-truth labels. However, establishing such a dataset for resection specimens is difficult. (2) Methods: In this study, we therefore propose a novel approach based on hyperspectral unmixing to determine which pixels within hyperspectral images should be assigned to the ground-truth labels from histopathology. Subsequently, we use this hyperspectral-unmixing-based approach to develop a tissue discrimination model on the presence of tumor tissue within the resection margins of ex vivo breast lumpectomy specimens. (3) Results: In total, 372 measured locations were included on the lumpectomy resection surface of 189 patients. We achieved a sensitivity of 0.94, specificity of 0.85, accuracy of 0.87, Matthew’s correlation coefficient of 0.71, and area under the curve of 0.92. (4) Conclusion: Using this hyperspectral-unmixing-based approach, we demonstrated that the measured locations with hyperspectral imaging on the resection surface of lumpectomy specimens could be classified with excellent performance.
AB - (1) Background: Assessing the resection margins during breast-conserving surgery is an important clinical need to minimize the risk of recurrent breast cancer. However, currently there is no technique that can provide real-time feedback to aid surgeons in the margin assessment. Hyperspectral imaging has the potential to overcome this problem. To classify resection margins with this technique, a tissue discrimination model should be developed, which requires a dataset with accurate ground-truth labels. However, establishing such a dataset for resection specimens is difficult. (2) Methods: In this study, we therefore propose a novel approach based on hyperspectral unmixing to determine which pixels within hyperspectral images should be assigned to the ground-truth labels from histopathology. Subsequently, we use this hyperspectral-unmixing-based approach to develop a tissue discrimination model on the presence of tumor tissue within the resection margins of ex vivo breast lumpectomy specimens. (3) Results: In total, 372 measured locations were included on the lumpectomy resection surface of 189 patients. We achieved a sensitivity of 0.94, specificity of 0.85, accuracy of 0.87, Matthew’s correlation coefficient of 0.71, and area under the curve of 0.92. (4) Conclusion: Using this hyperspectral-unmixing-based approach, we demonstrated that the measured locations with hyperspectral imaging on the resection surface of lumpectomy specimens could be classified with excellent performance.
KW - breast tissue
KW - breast-conserving surgery
KW - hyperspectral imaging
KW - hyperspectral unmixing
KW - resection margin assessment
KW - tissue classification
UR - http://www.scopus.com/inward/record.url?scp=85160690793&partnerID=8YFLogxK
U2 - https://doi.org/10.3390/cancers15102679
DO - https://doi.org/10.3390/cancers15102679
M3 - Article
C2 - 37345015
SN - 2072-6694
VL - 15
JO - Cancers
JF - Cancers
IS - 10
M1 - 2679
ER -