• A
  • A
  • A
  • ABC
  • ABC
  • ABC
  • А
  • А
  • А
  • А
  • А
Regular version of the site

Program of MRI Images Processing for the Cancer Detection

Student: Baigildin Roman

Supervisor: Vadim Valerievich Podbelskiy

Faculty: Faculty of Computer Science

Educational Programme: Software Engineering (Bachelor)

Final Grade: 10

Year of Graduation: 2018

To date, cancer is one of the most severe and deadly diseases which could be treated successfully at an early stage. MRI is the most advanced medical imaging method of early tumor detection. However, the classification and segmentation of tumors on MRI images are complicated and time-consuming process. There are applications which solve this problem but many of them are not available and adapted for a regular practice in Russian hospitals. Moreover, their functionality could not be extended through installing extensions and plugins. Not every existing application provides a remote access to MRI database and service of images processing. Thus, in diploma work, to solve this problem we analyzed existing methods of image processing, selected methods of segmentation based on clustering, region growing, binary thresholding and Gaussian mixture models, and developed an application that uses image processing techniques, clustering and fuzzy logic approaches in a tumor segmentation. The application enables users remotely to load and save MRI images, visualize them and apply to them third-party plugins to segment a tumor. Moreover, the application can serve as a client to load MRI images from remote peers. We successfully applied CUDA acceleration to the general-purpose computations and image processing to achieve the gain in a speed in several times in comparison with CPU. This paper contains 68 pages, 3 chapters, 36 images, 7 tables, 37 sources and 5 appendixes. Keywords: tumor segmentation, brain tumor, DICOM, MRI, image processing, clustering, fuzzy logic, CUDA, GPGPU

Full text (added May 28, 2018)

Student Theses at HSE must be completed in accordance with the University Rules and regulations specified by each educational programme.

Summaries of all theses must be published and made freely available on the HSE website.

The full text of a thesis can be published in open access on the HSE website only if the authoring student (copyright holder) agrees, or, if the thesis was written by a team of students, if all the co-authors (copyright holders) agree. After a thesis is published on the HSE website, it obtains the status of an online publication.

Student theses are objects of copyright and their use is subject to limitations in accordance with the Russian Federation’s law on intellectual property.

In the event that a thesis is quoted or otherwise used, reference to the author’s name and the source of quotation is required.

Search all student theses