Broadband hyperspectral imaging for breast tumor detection using spectral and spatial information.
Esther KhoBehdad DashtbozorgLisanne L de BoerKoen K Van de VijverHenricus J C M SterenborgTheo J M RuersPublished in: Biomedical optics express (2019)
Complete tumor removal during breast-conserving surgery remains challenging due to the lack of optimal intraoperative margin assessment techniques. Here, we use hyperspectral imaging for tumor detection in fresh breast tissue. We evaluated different wavelength ranges and two classification algorithms; a pixel-wise classification algorithm and a convolutional neural network that combines spectral and spatial information. The highest classification performance was obtained using the full wavelength range (450-1650 nm). Adding spatial information mainly improved the differentiation of tissue classes within the malignant and healthy classes. High sensitivity and specificity were accomplished, which offers potential for hyperspectral imaging as a margin assessment technique to improve surgical outcome.
Keyphrases
- deep learning
- machine learning
- convolutional neural network
- high resolution
- optical coherence tomography
- health information
- minimally invasive
- magnetic resonance
- healthcare
- magnetic resonance imaging
- mass spectrometry
- computed tomography
- risk assessment
- photodynamic therapy
- lymph node
- loop mediated isothermal amplification
- coronary artery disease
- atrial fibrillation
- climate change
- rectal cancer
- clinical evaluation
- locally advanced