Aiming to feature redundancy problem in MRI Prostate Tumor ROI high dimension representation, a model, Prostate Tumor CAD Model based on NN with PCA feature-level fusion in MRI, is proposed in this paper. Firstly, geometry feature, statistical features, Hu invariant moment features, GLCM texture features, TAMURA texture features, frequency features are extracted from MRI prostate tumor ROI; Secondly PCA are used to obtain 8 dimension features in cumulative contribution rate 89.62%, and reducing the dimension of the feature vectors; Thirdly neural network is regarded as classifier to classify with BFGS, Levenberg-Marquardt, BP and GD training algorithm, Finally, MRI images of prostate patients are regarded as original data, prostate tumor CAD model based on NN with feature-level fusion are utilized to aid diagnosis. Experiment results illustrate that the ability to identify benign and malignant prostate tumor are improved at least 10% through Neural network with PCA feature-level fusion, and the strategy is effective, redundancy among features are reduces in some degree. There are positive significance for MRI prostate tumor CAD.
[1]
Liu Xiang,et al.
Biomedical Signal Processing and Control Cirrhosis Classification Based on Mri with Duplicative-feature Support Vector Machine (dfsvm)
,
2022
.
[2]
Carole Lartizien,et al.
Computer-aided diagnosis of prostate cancer in the peripheral zone using multiparametric MRI
,
2012,
Physics in medicine and biology.
[3]
Huiling Lu,et al.
Multi-features prostate tumor aided diagnoses based on ensemble-svm
,
2013,
2013 IEEE International Conference on Granular Computing (GrC).
[4]
Frank G Zöllner,et al.
SVM-based glioma grading: Optimization by feature reduction analysis.
,
2012,
Zeitschrift fur medizinische Physik.
[5]
P. Langley.
Selection of Relevant Features in Machine Learning
,
1994
.
[6]
Rafael Llobet,et al.
Computer-Aided Prostate Cancer Detection in Ultrasonographic Images
,
2003,
IbPRIA.
[7]
Kunio Doi,et al.
Computer-aided diagnosis in medical imaging: Historical review, current status and future potential
,
2007,
Comput. Medical Imaging Graph..