Hyperspectral Imaging for the Detection of Glioblastoma Tumor Cells in H&E Slides Using Convolutional Neural Networks

Abstract

Hyperspectral imaging (HSI) technology has demonstrated potential to provide useful information about the chemical composition of tissue and its morphological features in a single image modality. Deep learning (DL) techniques have demonstrated the ability of automatic feature extraction from data for a successful classification. In this study, we exploit HSI and DL for the automatic differentiation of glioblastoma (GB) and non-tumor tissue on hematoxylin and eosin (H&E) stained histological slides of human brain tissue. GB detection is a challenging application, showing high heterogeneity in the cellular morphology across different patients. We employed an HSI microscope, with a spectral range from 400 to 1000 nm, to collect 517 HS cubes from 13 GB patients using 20× magnification. Using a convolutional neural network (CNN), we were able to automatically detect GB within the pathological slides, achieving average sensitivity and specificity values of 88% and 77%, respectively, representing an improvement of 7% and 8% respectively, as compared to the results obtained using RGB (red, green, and blue) images. This study demonstrates that the combination of hyperspectral microscopic imaging and deep learning is a promising tool for future computational pathologies.

Surgical Guidance for Removal of Cholesteatoma Using a Multispectral 3D-Endoscope

“…Multispectral tissue differentiation has become intensively studied and analyzed using machine learning methods as these can catch high-dimensional tissue behavior [ 55 , 56 , 57 ]. In this study, knowledge about the spectral behavior of cholesteatoma and bone, as well as only a few spectral bands are used.…”

Information Extraction Techniques in Hyperspectral Imaging Biomedical Applications

“…In a pilot study to aid brain surgeons with label-free HSI, Fabelo et al compared both 2D-CNN and 1D-DNN, considering spectral-only and spectral-spatial classification using DL [69]. In HSI digital histology, Ortega et al detected glioblastoma brain cancer in digital slides using a patch-based 2D-CNN approach [70]. Additionally, Halicek et al has employed very deep 2D-CNNs for classification, specifically the widely-used Inception v4 model (Figure 4) implemented in a sliding patch-based approach for head and neck squamous cancer [71] and thyroid and salivary gland cancers [72].…”

Sensors, Signal and Image Processing in Biomedicine and Assisted Living

“…A CNN-based approach is proposed for hyperspectral analysis of histopathological images, aiming to the detection of glioblastoma tumor cells [ 14 ]. The main goal of that work is to differentiate between high-grade gliomas (glioblastoma) and non-tumor tissue.…”

“…This special issue gathers a broad range of novel contributions on sensors, systems, and signal/image processing methods for biomedicine and assisted living. These include methods for heart, sleep and vital sign measurement [ 1 , 2 , 3 , 4 , 5 ]; human motion-related signal analysis in the context of rehabilitation and tremor assessment [ 6 , 7 , 8 ]; assistive systems for color deficient and visually challenged individuals, as well as for wheelchair control by people with motor disabilities [ 9 , 10 , 11 , 12 ]; and, image and video-based diagnostic systems [ 13 , 14 , 15 , 16 ].…”