Nonlinear algorithm of pattern recognition for computer-aided diagnosis of breast cancer
The process of the diagnosis of a malignant tumor in the mammary gland consists of three stages: 1) First, on the basis of a scrape from a mucous coat of the oral cavity we must obtain a data set containing about 10-30 cells. 2) On the second stage, we use the Feulgan reaction to obtain the DNA (deoxyribonucleic acid) scanogram of the interphase nuclei of the above cells. We then record the main indices (all together 15) of the scanograms of the interphase nuclei of these cells: \(x_1\), \(x_2, \dots, x_{15}\). We call the vector \(x_c= (x_1, x_2, \dots, x_{15})\) the indication vector of the cell \(C\). (It is not necessary to use only these indices; other indices could be suggested which might provide more information and better accuracy for estimating the probability of the onset of malignancy in breast tumor.) Thus, for every cell, for example cell number \(i\), we get 15 indices \(x_1^{(i)}, x_2^{(i)}, \dots, x_{15}^{(i)}\), where \(i=1,2, \dots,n\) \((10\leq n\leq 30)\). 3) On the third stage we apply the special algorithms of statistical and geometrical theory of pattern recognition for detecting malignant tissue in the mammary gland and for differencing the diagnosis of breast cancer from fibroadenoma.
- Computer-aided diagnosis of breast cancer. II: Tests and experiments
- scientific article; zbMATH DE number 2130829
- Computer citogenetic diagnostics of breast cancer and fibrocystic mastopathy with the areas of buccal epithelium
- scientific article; zbMATH DE number 2148620
- Breast Cancer Diagnosis and Prognosis Via Linear Programming
- Algorithm of stochastic estimation for computer-aided diagnosis of hereditary diseases
- Syndrome approach for computer recognition of fuzzy systems and its application to immunological diagnostics and prognosis of human cancer
- Subset-conjunctive rules for breast cancer diagnosis
- Computer citogenetic diagnostics of breast cancer and fibrocystic mastopathy with the areas of buccal epithelium
- Breast Cancer Diagnosis and Prognosis Via Linear Programming
- Exploring breast cancer diagnosis with fractal analysis and classification methods
- Breast lump recognition algorithms based on ultrasound radio-frequency signals
- Computer-aided diagnosis of breast cancer. II: Tests and experiments
- Advances in Neural Networks – ISNN 2005
- Applying a modified version of Lyapunov exponent for cancer diagnosis in biomedical images: the case of breast mammograms
This page was built for publication: Nonlinear algorithm of pattern recognition for computer-aided diagnosis of breast cancer
Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q4378806)
