scholarly journals Parallel K-Means Clustering for Brain Cancer Detection Using Hyperspectral Images

Electronics ◽  
2018 ◽  
Vol 7 (11) ◽  
pp. 283 ◽  
Author(s):  
Emanuele Torti ◽  
Giordana Florimbi ◽  
Francesca Castelli ◽  
Samuel Ortega ◽  
Himar Fabelo ◽  
...  

The precise delineation of brain cancer is a crucial task during surgery. There are several techniques employed during surgical procedures to guide neurosurgeons in the tumor resection. However, hyperspectral imaging (HSI) is a promising non-invasive and non-ionizing imaging technique that could improve and complement the currently used methods. The HypErspectraL Imaging Cancer Detection (HELICoiD) European project has addressed the development of a methodology for tumor tissue detection and delineation exploiting HSI techniques. In this approach, the K-means algorithm emerged in the delimitation of tumor borders, which is of crucial importance. The main drawback is the computational complexity of this algorithm. This paper describes the development of the K-means clustering algorithm on different parallel architectures, in order to provide real-time processing during surgical procedures. This algorithm will generate an unsupervised segmentation map that, combined with a supervised classification map, will offer guidance to the neurosurgeon during the tumor resection task. We present parallel K-means clustering based on OpenMP, CUDA and OpenCL paradigms. These algorithms have been validated through an in-vivo hyperspectral human brain image database. Experimental results show that the CUDA version can achieve a speed-up of ~ 150 × with respect to a sequential processing. The remarkable result obtained in this paper makes possible the development of a real-time classification system.

IEEE Access ◽  
2020 ◽  
Vol 8 ◽  
pp. 8485-8501 ◽  
Author(s):  
Giordana Florimbi ◽  
Himar Fabelo ◽  
Emanuele Torti ◽  
Samuel Ortega ◽  
Margarita Marrero-Martin ◽  
...  

2016 ◽  
Author(s):  
Himar Fabelo ◽  
Samuel Ortega ◽  
Silvester Kabwama ◽  
Gustavo M. Callico ◽  
Diederik Bulters ◽  
...  

Sensors ◽  
2019 ◽  
Vol 19 (24) ◽  
pp. 5481 ◽  
Author(s):  
Beatriz Martinez ◽  
Raquel Leon ◽  
Himar Fabelo ◽  
Samuel Ortega ◽  
Juan F. Piñeiro ◽  
...  

Hyperspectral imaging (HSI) is a non-ionizing and non-contact imaging technique capable of obtaining more information than conventional RGB (red green blue) imaging. In the medical field, HSI has commonly been investigated due to its great potential for diagnostic and surgical guidance purposes. However, the large amount of information provided by HSI normally contains redundant or non-relevant information, and it is extremely important to identify the most relevant wavelengths for a certain application in order to improve the accuracy of the predictions and reduce the execution time of the classification algorithm. Additionally, some wavelengths can contain noise and removing such bands can improve the classification stage. The work presented in this paper aims to identify such relevant spectral ranges in the visual-and-near-infrared (VNIR) region for an accurate detection of brain cancer using in vivo hyperspectral images. A methodology based on optimization algorithms has been proposed for this task, identifying the relevant wavelengths to achieve the best accuracy in the classification results obtained by a supervised classifier (support vector machines), and employing the lowest possible number of spectral bands. The results demonstrate that the proposed methodology based on the genetic algorithm optimization slightly improves the accuracy of the tumor identification in ~5%, using only 48 bands, with respect to the reference results obtained with 128 bands, offering the possibility of developing customized acquisition sensors that could provide real-time HS imaging. The most relevant spectral ranges found comprise between 440.5–465.96 nm, 498.71–509.62 nm, 556.91–575.1 nm, 593.29–615.12 nm, 636.94–666.05 nm, 698.79–731.53 nm and 884.32–902.51 nm.


Author(s):  
Haishan Zeng ◽  
Jianhua Zhao ◽  
Michael A. Short ◽  
David I. McLean ◽  
Stephen Lam ◽  
...  

2011 ◽  
Vol 63-64 ◽  
pp. 603-606
Author(s):  
Zhong Qu ◽  
Qing Wei Ma

In this paper, we extract slight movement object of real-time video images by using skin color detection and clustering methods. The ideological of edge detection locate the range of the moving object, then by using clustering algorithm and skin color detection and some other methods extract the object template and complement the integrity of the object template, according to the object template and the original image put color onto a new background model. The simulation results show that the proposed method ensure the quality requirements of real-time processing and has a certain robustness, so this method satisfy the needs of the project.


Sign in / Sign up

Export Citation Format

Share Document