OBJECTIVE: Early detection is paramount to reduce the high death rate of ovarian cancer. Unfortunately, current detection tool is not sensitive. New techniques such as deoxyribonucleic acid (DNA) micro-array and proteomics data are difficult to analyze due to high dimensionality, whereas conventional methods such as blood test are neither sensitive nor specific. METHODS: Thus, a functional model of human pattern recognition known as complementary learning fuzzy neural network (CLFNN) is proposed to aid existing diagnosis methods. In contrast to conventional computational intelligence methods, CLFNN exploits the lateral inhibition between positive and negative samples. Moreover, it is equipped with autonomous rule generation facility. An example named fuzzy adaptive learning control network with another adaptive resonance theory (FALCON-AART) is used to illustrate the performance of CLFNN. RESULTS: The confluence of CLFNN-micro-array, CLFNN-blood test, and CLFNN-proteomics demonstrate good sensitivity and specificity in the experiments. The diagnosis decision is accurate and consistent. CLFNN also outperforms most of the conventional methods. CONCLUSIONS: This research work demonstrates that the confluence of CLFNN-DNA micro-array, CLFNN-blood tests, and CLFNN-proteomic test improves the diagnosis accuracy with higher consistency. CLFNN exhibits good performance in ovarian cancer diagnosis in general. Thus, CLFNN is a promising tool for clinical decision support.
OBJECTIVE: Early detection is paramount to reduce the high death rate of ovarian cancer. Unfortunately, current detection tool is not sensitive. New techniques such as deoxyribonucleic acid (DNA) micro-array and proteomics data are difficult to analyze due to high dimensionality, whereas conventional methods such as blood test are neither sensitive nor specific. METHODS: Thus, a functional model of human pattern recognition known as complementary learning fuzzy neural network (CLFNN) is proposed to aid existing diagnosis methods. In contrast to conventional computational intelligence methods, CLFNN exploits the lateral inhibition between positive and negative samples. Moreover, it is equipped with autonomous rule generation facility. An example named fuzzy adaptive learning control network with another adaptive resonance theory (FALCON-AART) is used to illustrate the performance of CLFNN. RESULTS: The confluence of CLFNN-micro-array, CLFNN-blood test, and CLFNN-proteomics demonstrate good sensitivity and specificity in the experiments. The diagnosis decision is accurate and consistent. CLFNN also outperforms most of the conventional methods. CONCLUSIONS: This research work demonstrates that the confluence of CLFNN-DNA micro-array, CLFNN-blood tests, and CLFNN-proteomic test improves the diagnosis accuracy with higher consistency. CLFNN exhibits good performance in ovarian cancer diagnosis in general. Thus, CLFNN is a promising tool for clinical decision support.
Authors: U Rajendra Acharya; S Vinitha Sree; Sanjeev Kulshreshtha; Filippo Molinari; Joel En Wei Koh; Luca Saba; Jasjit S Suri Journal: Technol Cancer Res Treat Date: 2013-12-06