Fractals and the Chaos Theory in Oncology and the Analyzation of Tumors
Overview
Objectives Comparison of the fractal dimensions healthy tissue to cancerous tissue to find a trend or pattern and be used for earlier diagnosis or a different method of diagnosis. Methods ImageJ, a public domain Java-based program developed my the NIH for Computational Instrumentation and a computer capable of running ImageJ. TCIA (The Cancer Imaging Archive), a public domain with an archive of medical images of cancer available for download. Plugin for ImageJ (FracLac) which is used for fractal analysis. Scanned images from TCIA using ImageJ and FracLac to recieve the fractal dimension of said images for analysis. 3 images of cancerous imagery and 3 images of healthy images for 5 cancers and 8 images of cancerous and healthy images for brain cancer. Results ImageJ produced the fractal dimensions of the cancerous images to have a larger deviation and range compared to the healthy images which displayed more consistent and linear dimensions. A pattern of higher values of fractal dimensions and irregular dimensions show a link between fractals and the growth of cancer. Conclusions Using the data from the experiment, more testing can be done with different methods of fractal analysis to obtain a clearer differences between fractal dimensions in healthy tissue and cancerous tissue as well as strengthen the correlation between cancer and the concept of fractals. Using machine learning to recognize these patterns inside of tissue can lead to development in cancer diagnosis to even the smallest levels of biology as fractals are infinitely conplex. Difficulties could be that cancer baries from patient to patient and many factors go into diagnosis. Another obstacale may be the difficulty of obtaining the amount images for a machine to learn from.
Summary statement
Using fractal analysis on cancer scans such as ct and mri and the healthy counterparts, there was a pattern in the cancerous images which was more irregular and on average fractal dimensions within those images.
Help received
Dr. Rachel Auld, Dr. Kim Lawe
Competition history
- CSEF 2019
Resources
Related projects
ISEF · 2015
Predicting Cancer: A Mathematical Model for Breast Cancer Progression
ISEF · 2014
Using the Fractal Dimension to Diagnose Cancer
ISEF · 2015
Fractal Dimension Applied to radiographic Study of Nodules in the Breast
ISEF · 2022
Chaos in Cancer: Analyzing Network Morphology To Predict Tumor Angiogenesis Using Chaos Theory
ISEF · 2015
Improved Cancer Detection and Diagnosis through a Novel Combination of Cell Segmentation and Artificial Intelligence Techniques
CSEF · 2014
Quantitative Analysis of Macrocellular Biomarkers in Early Stage DCIS Cytopathology Images, Using Machine Learning
CSEF · 2013
Two Discrete Stochastic Cellular Automata Models of Cancer Stem Cell Proliferation
ISEF · 2014
Quantitative Analysis of Macro-Cellular Biomarkers in Early Stage Ductal Carcinoma in situ (DCIS) Immunohistochemical Cytopathology Images Using Machine Learning
Closest projects by meaning, across every fair and year in the corpus.
Browse more like this
Source: California Science & Engineering Fair public projects