Contact: +91-9711224068
International Journal of Applied Research
  • Multidisciplinary Journal
  • Printed Journal
  • Indexed Journal
  • Refereed Journal
  • Peer Reviewed Journal

ISSN Print: 2394-7500, ISSN Online: 2394-5869, CODEN: IJARPF

IMPACT FACTOR (RJIF): 8.4

Vol. 2, Issue 7, Part D (2016)

Endometrial cancer detection using fractal based texture analysis: A box counting Algorithm

Endometrial cancer detection using fractal based texture analysis: A box counting Algorithm

Author(s)
Dr. Ramya R, Dr. Shridhar R, Dr. Latha KC and Dr. Balasubramanian S
Abstract
Introduction: The aim of the present study is to relate morphologic features of endometrial adenocarcinoma to grade and depth of myometrial invasion using fractal analysis. Our final goal is to see whether surface growth patterns of this neoplasm possess fractal properties and to investigate whether the fractal dimension, which is thought to represent partly the local biologic behavior of the tumor, differs according to grade or stage of the disease.
Methods: A method was developed in the Visual Basic for extracting the suspicious region from the MRI based on texture. For the extracted image, the fractal dimension was calculated using Box-counting method. Fractal analysis was applied using the fractal analysis software after the MRI image was turned to gray scale. Surface of the tumor growing into the endometrial cavity was selected as region of interest (ROI) for each photograph. The fractal dimension of the ROIs was calculated by box-counting method with this software. Statistical t- test was calculated.
Results: From these results, it is concluded that:
1. Fractal Dimension can be used when the cancer is in the advanced stage.
2. Fractal dimension is Insensitive when the cancer is in the initial stage.
Conclusion: The measurement of fractal dimension is helpful in discriminating the lesions. Fractal dimension has been applied to identify micro-calcifications and tumours in the tissues of the body. Through this method, the size, location and seriousness of the abnormality or suspicious regions are estimated for better diagnosis
Pages: 243-245  |  1292 Views  72 Downloads
How to cite this article:
Dr. Ramya R, Dr. Shridhar R, Dr. Latha KC, Dr. Balasubramanian S. Endometrial cancer detection using fractal based texture analysis: A box counting Algorithm. Int J Appl Res 2016;2(7):243-245.
Call for book chapter
International Journal of Applied Research
Journals List Click Here Research Journals Research Journals