101. Hyperspectral imaging for colon cancer classification in surgical specimens: towards optical biopsy during image-guided surgery
- Author
-
Francesca Manni, Roger Fonolla, Fons van der Sommen, Svetlana Zinger, Caifeng Shan, Esther Kho, Susan Brouwer de Koning, Theo Ruers, Peter H.N. de With, Video Coding & Architectures, Center for Care & Cure Technology Eindhoven, Signal Processing Systems, Biomedical Diagnostics Lab, and EAISI Health
- Subjects
Surgical resection ,medicine.medical_specialty ,image-guided surgery ,Colorectal cancer ,hyperspectral imaging ,Local/diagnostic imaging ,Biopsy ,0211 other engineering and technologies ,02 engineering and technology ,SDG 3 – Goede gezondheid en welzijn ,01 natural sciences ,010309 optics ,Neoplasm Recurrence, Local/diagnostic imaging ,Computer-Assisted ,SDG 3 - Good Health and Well-being ,0103 physical sciences ,3D-2D CNN ,medicine ,Positive Margins ,Humans ,021101 geological & geomatics engineering ,medicine.diagnostic_test ,business.industry ,Colonic Neoplasms/diagnostic imaging ,Hyperspectral imaging ,Optical Biopsy ,medicine.disease ,3. Good health ,Image-guided surgery ,Neoplasm Recurrence ,Surgery, Computer-Assisted ,colon cancer ,Curative treatment ,Colonic Neoplasms ,Surgery ,Radiology ,Neoplasm Recurrence, Local ,business - Abstract
The main curative treatment for localized colon cancer is surgical resection. However when tumor residuals are left positive margins are found during the histological examinations and additional treatment is needed to inhibit recurrence. Hyperspectral imaging (HSI) can offer non-invasive surgical guidance with the potential of optimizing the surgical effectiveness. In this paper we investigate the capability of HSI for automated colon cancer detection in six ex-vivo specimens employing a spectral-spatial patch-based classification approach. The results demonstrate the feasibility in assessing the benign and malignant boundaries of the lesion with a sensitivity of 0.88 and specificity of 0.78. The results are compared with the state-of-the-art deep learning based approaches. The method with a new hybrid CNN outperforms the state-of the-art approaches (0.74 vs. 0.82 AUC). This study paves the way for further investigation towards improving surgical outcomes with HSI.
- Full Text
- View/download PDF