Hyperspectral Superpixel-Wise Glioblastoma Tumor Detection in Histological Samples
<b> </b>The combination of hyperspectral imaging (HSI) and digital pathology may yield more accurate diagnosis. In this work, we propose the use of superpixels in HS images for combining regions of pixels that can be classified according to their spectral information to classify glioblas...
Main Authors: | , , , , , , |
---|---|
Format: | Article |
Language: | English |
Published: |
MDPI AG
2020-06-01
|
Series: | Applied Sciences |
Subjects: | |
Online Access: | https://www.mdpi.com/2076-3417/10/13/4448 |
id |
doaj-234b8b34e85c46cfa5c0619dd436cf6c |
---|---|
record_format |
Article |
spelling |
doaj-234b8b34e85c46cfa5c0619dd436cf6c2020-11-25T03:04:13ZengMDPI AGApplied Sciences2076-34172020-06-01104448444810.3390/app10134448Hyperspectral Superpixel-Wise Glioblastoma Tumor Detection in Histological SamplesSamuel Ortega0Himar Fabelo1Martin Halicek2Rafael Camacho3María de la Luz Plaza4Gustavo M. Callicó5Baowei Fei6Institute for Applied Microelectronics (IUMA), University of Las Palmas de Gran Canaria (ULPGC), 35017 Las Palmas de Gran Canaria, SpainInstitute for Applied Microelectronics (IUMA), University of Las Palmas de Gran Canaria (ULPGC), 35017 Las Palmas de Gran Canaria, SpainQuantitative Bioimaging Laboratory, Department of Bioengineering, The University of Texas at Dallas, Richardson, TX 75080, USADepartment of Pathological Anatomy, University Hospital Doctor Negrin of Gran Canaria, Barranco de la Ballena s/n, 35010 Las Palmas de Gran Canaria, SpainDepartment of Pathological Anatomy, University Hospital Doctor Negrin of Gran Canaria, Barranco de la Ballena s/n, 35010 Las Palmas de Gran Canaria, SpainInstitute for Applied Microelectronics (IUMA), University of Las Palmas de Gran Canaria (ULPGC), 35017 Las Palmas de Gran Canaria, SpainQuantitative Bioimaging Laboratory, Department of Bioengineering, The University of Texas at Dallas, Richardson, TX 75080, USA<b> </b>The combination of hyperspectral imaging (HSI) and digital pathology may yield more accurate diagnosis. In this work, we propose the use of superpixels in HS images for combining regions of pixels that can be classified according to their spectral information to classify glioblastoma (GB) brain tumors in histologic slides. The superpixels are generated by a modified simple linear iterative clustering (SLIC) method to accommodate HS images. This work employs a dataset of H&E (Hematoxylin and Eosin) stained histology slides from 13 patients with GB and over 426,000 superpixels. A linear support vector machine (SVM) classifier was performed on independent training, validation, and testing datasets. The results of this investigation show that the proposed method can detect GB brain tumors from non-tumor samples with average sensitivity and specificity of 87% and 81%, respectively. The overall accuracy of this method is 83%. The study demonstrates that hyperspectral digital pathology can be useful for detecting GB brain tumors by exploiting spectral information alone on a superpixel level.https://www.mdpi.com/2076-3417/10/13/4448hyperspectral imagingoptics diagnosisdigital pathologysuperpixelmachine learningtissue diagnostics |
collection |
DOAJ |
language |
English |
format |
Article |
sources |
DOAJ |
author |
Samuel Ortega Himar Fabelo Martin Halicek Rafael Camacho María de la Luz Plaza Gustavo M. Callicó Baowei Fei |
spellingShingle |
Samuel Ortega Himar Fabelo Martin Halicek Rafael Camacho María de la Luz Plaza Gustavo M. Callicó Baowei Fei Hyperspectral Superpixel-Wise Glioblastoma Tumor Detection in Histological Samples Applied Sciences hyperspectral imaging optics diagnosis digital pathology superpixel machine learning tissue diagnostics |
author_facet |
Samuel Ortega Himar Fabelo Martin Halicek Rafael Camacho María de la Luz Plaza Gustavo M. Callicó Baowei Fei |
author_sort |
Samuel Ortega |
title |
Hyperspectral Superpixel-Wise Glioblastoma Tumor Detection in Histological Samples |
title_short |
Hyperspectral Superpixel-Wise Glioblastoma Tumor Detection in Histological Samples |
title_full |
Hyperspectral Superpixel-Wise Glioblastoma Tumor Detection in Histological Samples |
title_fullStr |
Hyperspectral Superpixel-Wise Glioblastoma Tumor Detection in Histological Samples |
title_full_unstemmed |
Hyperspectral Superpixel-Wise Glioblastoma Tumor Detection in Histological Samples |
title_sort |
hyperspectral superpixel-wise glioblastoma tumor detection in histological samples |
publisher |
MDPI AG |
series |
Applied Sciences |
issn |
2076-3417 |
publishDate |
2020-06-01 |
description |
<b> </b>The combination of hyperspectral imaging (HSI) and digital pathology may yield more accurate diagnosis. In this work, we propose the use of superpixels in HS images for combining regions of pixels that can be classified according to their spectral information to classify glioblastoma (GB) brain tumors in histologic slides. The superpixels are generated by a modified simple linear iterative clustering (SLIC) method to accommodate HS images. This work employs a dataset of H&E (Hematoxylin and Eosin) stained histology slides from 13 patients with GB and over 426,000 superpixels. A linear support vector machine (SVM) classifier was performed on independent training, validation, and testing datasets. The results of this investigation show that the proposed method can detect GB brain tumors from non-tumor samples with average sensitivity and specificity of 87% and 81%, respectively. The overall accuracy of this method is 83%. The study demonstrates that hyperspectral digital pathology can be useful for detecting GB brain tumors by exploiting spectral information alone on a superpixel level. |
topic |
hyperspectral imaging optics diagnosis digital pathology superpixel machine learning tissue diagnostics |
url |
https://www.mdpi.com/2076-3417/10/13/4448 |
work_keys_str_mv |
AT samuelortega hyperspectralsuperpixelwiseglioblastomatumordetectioninhistologicalsamples AT himarfabelo hyperspectralsuperpixelwiseglioblastomatumordetectioninhistologicalsamples AT martinhalicek hyperspectralsuperpixelwiseglioblastomatumordetectioninhistologicalsamples AT rafaelcamacho hyperspectralsuperpixelwiseglioblastomatumordetectioninhistologicalsamples AT mariadelaluzplaza hyperspectralsuperpixelwiseglioblastomatumordetectioninhistologicalsamples AT gustavomcallico hyperspectralsuperpixelwiseglioblastomatumordetectioninhistologicalsamples AT baoweifei hyperspectralsuperpixelwiseglioblastomatumordetectioninhistologicalsamples |
_version_ |
1724682202021625856 |