Hyperspectral imaging for cancer detection and classification

被引：0

作者：

Nathan, M. ^{[1
]}

Kabatznik, A. S. ^{[1
]}

Mahmood, A. ^{[1
]}

机构：

[1] Univ Witwatersrand, Sch Elect & Informat Engn, Johannesburg, South Africa

来源：

2018 3RD BIENNIAL SOUTH AFRICAN BIOMEDICAL ENGINEERING CONFERENCE (SAIBMEC) | 2018年

关键词：

Hyperspectral Imaging; Principal Component Analysis; Artificial Neural Network; Support Vector Machine;

D O I：

暂无

中图分类号：

R318 [生物医学工程];

学科分类号：

0831 ;

摘要：

The design and implementation of a classification system for hyperspectral images of cancer cell cultures is discussed. The ability to distinguish between different types of cancers is of particular importance in this study. This possibility allows for metastasised tumours to be identified, in the near infrared regions of 920 nm - 2514 nm and thus the origin of a tumour. Using Principal Component Analysis (PCA) to find the features for Artificial Neural Networks (ANNs) and Support Vector Machines (SVMs), different cancer types could be distinguished with an overall accuracy of 87.4 % using an ANN solution whereas the SVM accuracy ranged from 73 % - 88.9 % due to the One-Vs-One (OVO) multiclass technique implemented.

引用

页数：4

共 16 条

[1]

American Cancer Society, 2016, UND ADV CANC MET CAN

[2]

[Anonymous], 2017, CANC FACT SHEET

[3]

[Anonymous], 2017, MATLAB NEURAL NETWOR

[4]

[Anonymous], MET CANC

[5]

Clark J. W., 2015, HARRISONS PRINCIPLES

[6]

Donald M., 2003, HOLLAND FREI CANC ME

[7]

Fei B., 2012, INT C BIOM ENG INF A

[8]

Heerboth S., CLIN TRANSLATIONAL M, V4, P6

[9] A comparison of methods for multiclass support vector machines [J].

Hsu, CW ;

Lin, CJ .

IEEE TRANSACTIONS ON NEURAL NETWORKS, 2002, 13 (02) :415-425

[10]

Lu G., 2013, J BIOMEDICAL OPTICS, V19

← 1 2 →