Tissue Classification of Breast Cancer by Hyperspectral Unmixing
(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...
| Main Authors: | , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2023-05-01
|
| Series: | Cancers |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2072-6694/15/10/2679 |
| _version_ | 1797600720451534848 |
|---|---|
| author | Lynn-Jade S. Jong Anouk L. Post Dinusha Veluponnar Freija Geldof Henricus J. C. M. Sterenborg Theo J. M. Ruers Behdad Dashtbozorg |
| author_facet | Lynn-Jade S. Jong Anouk L. Post Dinusha Veluponnar Freija Geldof Henricus J. C. M. Sterenborg Theo J. M. Ruers Behdad Dashtbozorg |
| author_sort | Lynn-Jade S. Jong |
| collection | DOAJ |
| description | (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. |
| first_indexed | 2024-03-11T03:52:53Z |
| format | Article |
| id | doaj.art-96f9196b4b1c45cfb5d21e2fbaf08651 |
| institution | Directory Open Access Journal |
| issn | 2072-6694 |
| language | English |
| last_indexed | 2024-03-11T03:52:53Z |
| publishDate | 2023-05-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Cancers |
| spelling | doaj.art-96f9196b4b1c45cfb5d21e2fbaf086512023-11-18T00:47:22ZengMDPI AGCancers2072-66942023-05-011510267910.3390/cancers15102679Tissue Classification of Breast Cancer by Hyperspectral UnmixingLynn-Jade S. Jong0Anouk L. Post1Dinusha Veluponnar2Freija Geldof3Henricus J. C. M. Sterenborg4Theo J. M. Ruers5Behdad Dashtbozorg6Department of Surgery, Netherlands Cancer Institute, Plesmanlaan 121, 1066 CX Amsterdam, The NetherlandsDepartment of Surgery, Netherlands Cancer Institute, Plesmanlaan 121, 1066 CX Amsterdam, The NetherlandsDepartment of Surgery, Netherlands Cancer Institute, Plesmanlaan 121, 1066 CX Amsterdam, The NetherlandsDepartment of Surgery, Netherlands Cancer Institute, Plesmanlaan 121, 1066 CX Amsterdam, The NetherlandsDepartment of Surgery, Netherlands Cancer Institute, Plesmanlaan 121, 1066 CX Amsterdam, The NetherlandsDepartment of Surgery, Netherlands Cancer Institute, Plesmanlaan 121, 1066 CX Amsterdam, The NetherlandsDepartment of Surgery, Netherlands Cancer Institute, Plesmanlaan 121, 1066 CX Amsterdam, The Netherlands(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.https://www.mdpi.com/2072-6694/15/10/2679breast-conserving surgeryhyperspectral imagingresection margin assessmentbreast tissuehyperspectral unmixingtissue classification |
| spellingShingle | Lynn-Jade S. Jong Anouk L. Post Dinusha Veluponnar Freija Geldof Henricus J. C. M. Sterenborg Theo J. M. Ruers Behdad Dashtbozorg Tissue Classification of Breast Cancer by Hyperspectral Unmixing Cancers breast-conserving surgery hyperspectral imaging resection margin assessment breast tissue hyperspectral unmixing tissue classification |
| title | Tissue Classification of Breast Cancer by Hyperspectral Unmixing |
| title_full | Tissue Classification of Breast Cancer by Hyperspectral Unmixing |
| title_fullStr | Tissue Classification of Breast Cancer by Hyperspectral Unmixing |
| title_full_unstemmed | Tissue Classification of Breast Cancer by Hyperspectral Unmixing |
| title_short | Tissue Classification of Breast Cancer by Hyperspectral Unmixing |
| title_sort | tissue classification of breast cancer by hyperspectral unmixing |
| topic | breast-conserving surgery hyperspectral imaging resection margin assessment breast tissue hyperspectral unmixing tissue classification |
| url | https://www.mdpi.com/2072-6694/15/10/2679 |
| work_keys_str_mv | AT lynnjadesjong tissueclassificationofbreastcancerbyhyperspectralunmixing AT anouklpost tissueclassificationofbreastcancerbyhyperspectralunmixing AT dinushaveluponnar tissueclassificationofbreastcancerbyhyperspectralunmixing AT freijageldof tissueclassificationofbreastcancerbyhyperspectralunmixing AT henricusjcmsterenborg tissueclassificationofbreastcancerbyhyperspectralunmixing AT theojmruers tissueclassificationofbreastcancerbyhyperspectralunmixing AT behdaddashtbozorg tissueclassificationofbreastcancerbyhyperspectralunmixing |