Tissue Classification of Breast Cancer by Hyperspectral Unmixing.

Simple Summary: To minimize the risk of cancer recurrence, it is crucial for surgeons to assess the resection margins (surface) of surgical specimens during breast-conserving surgeries to determine whether the tumor has been removed entirely. However, this is often not easy and also current techniques lack to aid the surgeons. In our study, we used a hyperspectral imaging technique to overcome this challenge. To assess the resection margins with hyperspectral imaging, a classification model should be developed, which requires a dataset with accurate ground-truth labels. Since it is difficult to establish such a dataset, we introduced a novel approach based on hyperspectral unmixing to enable an accurate correlation between hyperspectral measurements and histology ground-truth labels. Subsequently, we developed a classification model for tumor tissue detection on the lumpectomy resection surface of 189 patients. We achieved a sensitivity of 94% and a specificity of 85%, which demonstrated the potential of hyperspectral imaging for breast-conserving surgeries. (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. [ABSTRACT FROM AUTHOR]