Preclinical Diagnosis of Magnetic Resonance (MR) Brain Images via Discrete Wavelet Packet Transform with Tsallis Entropy and Generalized Eigenvalue Proximal Support Vector Machine (GEPSVM)
Background: Developing an accurate computer-aided diagnosis (CAD) system of MR brain images is essential for medical interpretation and analysis. In this study, we propose a novel automatic CAD system to distinguish abnormal brains from normal brains in MRI scanning. Methods: The proposed method sim...
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2015-03-01
|
| Series: | Entropy |
| Subjects: | |
| Online Access: | http://www.mdpi.com/1099-4300/17/4/1795 |
| _version_ | 1828115674557317120 |
|---|---|
| author | Yudong Zhang Zhengchao Dong Shuihua Wang Genlin Ji Jiquan Yang |
| author_facet | Yudong Zhang Zhengchao Dong Shuihua Wang Genlin Ji Jiquan Yang |
| author_sort | Yudong Zhang |
| collection | DOAJ |
| description | Background: Developing an accurate computer-aided diagnosis (CAD) system of MR brain images is essential for medical interpretation and analysis. In this study, we propose a novel automatic CAD system to distinguish abnormal brains from normal brains in MRI scanning. Methods: The proposed method simplifies the task to a binary classification problem. We used discrete wavelet packet transform (DWPT) to extract wavelet packet coefficients from MR brain images. Next, Shannon entropy (SE) and Tsallis entropy (TE) were harnessed to obtain entropy features from DWPT coefficients. Finally, generalized eigenvalue proximate support vector machine (GEPSVM), and GEPSVM with radial basis function (RBF) kernel, were employed as classifier. We tested the four proposed diagnosis methods (DWPT + SE + GEPSVM, DWPT + TE + GEPSVM, DWPT + SE + GEPSVM + RBF, and DWPT + TE + GEPSVM + RBF) on three benchmark datasets of Dataset-66, Dataset-160, and Dataset-255. Results: The 10 repetition of K-fold stratified cross validation results showed the proposed DWPT + TE + GEPSVM + RBF method excelled not only other three proposed classifiers but also existing state-of-the-art methods in terms of classification accuracy. In addition, the DWPT + TE + GEPSVM + RBF method achieved accuracy of 100%, 100%, and 99.53% on Dataset-66, Dataset-160, and Dataset-255, respectively. For Dataset-255, the offline learning cost 8.4430s and online prediction cost merely 0.1059s. Conclusions: We have proved the effectiveness of the proposed method, which achieved nearly 100% accuracy over three benchmark datasets. |
| first_indexed | 2024-04-11T12:44:06Z |
| format | Article |
| id | doaj.art-4ad0575fc2924fb78ad0a15cc6c8b3c9 |
| institution | Directory Open Access Journal |
| issn | 1099-4300 |
| language | English |
| last_indexed | 2024-04-11T12:44:06Z |
| publishDate | 2015-03-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Entropy |
| spelling | doaj.art-4ad0575fc2924fb78ad0a15cc6c8b3c92022-12-22T04:23:25ZengMDPI AGEntropy1099-43002015-03-011741795181310.3390/e17041795e17041795Preclinical Diagnosis of Magnetic Resonance (MR) Brain Images via Discrete Wavelet Packet Transform with Tsallis Entropy and Generalized Eigenvalue Proximal Support Vector Machine (GEPSVM)Yudong Zhang0Zhengchao Dong1Shuihua Wang2Genlin Ji3Jiquan Yang4School of Computer Science and Technology, Nanjing Normal University, Nanjing, Jiangsu 210023, ChinaTranslational Imaging Division & MRI Unit, Columbia University and New York State Psychiatric Institute, New York, NY 10032, USASchool of Computer Science and Technology, Nanjing Normal University, Nanjing, Jiangsu 210023, ChinaSchool of Computer Science and Technology, Nanjing Normal University, Nanjing, Jiangsu 210023, ChinaJiangsu Key Laboratory of 3D Printing Equipment and Manufacturing, Nanjing, Jiangsu 210042, ChinaBackground: Developing an accurate computer-aided diagnosis (CAD) system of MR brain images is essential for medical interpretation and analysis. In this study, we propose a novel automatic CAD system to distinguish abnormal brains from normal brains in MRI scanning. Methods: The proposed method simplifies the task to a binary classification problem. We used discrete wavelet packet transform (DWPT) to extract wavelet packet coefficients from MR brain images. Next, Shannon entropy (SE) and Tsallis entropy (TE) were harnessed to obtain entropy features from DWPT coefficients. Finally, generalized eigenvalue proximate support vector machine (GEPSVM), and GEPSVM with radial basis function (RBF) kernel, were employed as classifier. We tested the four proposed diagnosis methods (DWPT + SE + GEPSVM, DWPT + TE + GEPSVM, DWPT + SE + GEPSVM + RBF, and DWPT + TE + GEPSVM + RBF) on three benchmark datasets of Dataset-66, Dataset-160, and Dataset-255. Results: The 10 repetition of K-fold stratified cross validation results showed the proposed DWPT + TE + GEPSVM + RBF method excelled not only other three proposed classifiers but also existing state-of-the-art methods in terms of classification accuracy. In addition, the DWPT + TE + GEPSVM + RBF method achieved accuracy of 100%, 100%, and 99.53% on Dataset-66, Dataset-160, and Dataset-255, respectively. For Dataset-255, the offline learning cost 8.4430s and online prediction cost merely 0.1059s. Conclusions: We have proved the effectiveness of the proposed method, which achieved nearly 100% accuracy over three benchmark datasets.http://www.mdpi.com/1099-4300/17/4/1795Shannon entropyTsallis entropymagnetic resonance imagingcomputer-aided diagnosisdiscrete wavelet packet transformsupport vector machinekernel techniquepattern recognitionclassification |
| spellingShingle | Yudong Zhang Zhengchao Dong Shuihua Wang Genlin Ji Jiquan Yang Preclinical Diagnosis of Magnetic Resonance (MR) Brain Images via Discrete Wavelet Packet Transform with Tsallis Entropy and Generalized Eigenvalue Proximal Support Vector Machine (GEPSVM) Entropy Shannon entropy Tsallis entropy magnetic resonance imaging computer-aided diagnosis discrete wavelet packet transform support vector machine kernel technique pattern recognition classification |
| title | Preclinical Diagnosis of Magnetic Resonance (MR) Brain Images via Discrete Wavelet Packet Transform with Tsallis Entropy and Generalized Eigenvalue Proximal Support Vector Machine (GEPSVM) |
| title_full | Preclinical Diagnosis of Magnetic Resonance (MR) Brain Images via Discrete Wavelet Packet Transform with Tsallis Entropy and Generalized Eigenvalue Proximal Support Vector Machine (GEPSVM) |
| title_fullStr | Preclinical Diagnosis of Magnetic Resonance (MR) Brain Images via Discrete Wavelet Packet Transform with Tsallis Entropy and Generalized Eigenvalue Proximal Support Vector Machine (GEPSVM) |
| title_full_unstemmed | Preclinical Diagnosis of Magnetic Resonance (MR) Brain Images via Discrete Wavelet Packet Transform with Tsallis Entropy and Generalized Eigenvalue Proximal Support Vector Machine (GEPSVM) |
| title_short | Preclinical Diagnosis of Magnetic Resonance (MR) Brain Images via Discrete Wavelet Packet Transform with Tsallis Entropy and Generalized Eigenvalue Proximal Support Vector Machine (GEPSVM) |
| title_sort | preclinical diagnosis of magnetic resonance mr brain images via discrete wavelet packet transform with tsallis entropy and generalized eigenvalue proximal support vector machine gepsvm |
| topic | Shannon entropy Tsallis entropy magnetic resonance imaging computer-aided diagnosis discrete wavelet packet transform support vector machine kernel technique pattern recognition classification |
| url | http://www.mdpi.com/1099-4300/17/4/1795 |
| work_keys_str_mv | AT yudongzhang preclinicaldiagnosisofmagneticresonancemrbrainimagesviadiscretewaveletpackettransformwithtsallisentropyandgeneralizedeigenvalueproximalsupportvectormachinegepsvm AT zhengchaodong preclinicaldiagnosisofmagneticresonancemrbrainimagesviadiscretewaveletpackettransformwithtsallisentropyandgeneralizedeigenvalueproximalsupportvectormachinegepsvm AT shuihuawang preclinicaldiagnosisofmagneticresonancemrbrainimagesviadiscretewaveletpackettransformwithtsallisentropyandgeneralizedeigenvalueproximalsupportvectormachinegepsvm AT genlinji preclinicaldiagnosisofmagneticresonancemrbrainimagesviadiscretewaveletpackettransformwithtsallisentropyandgeneralizedeigenvalueproximalsupportvectormachinegepsvm AT jiquanyang preclinicaldiagnosisofmagneticresonancemrbrainimagesviadiscretewaveletpackettransformwithtsallisentropyandgeneralizedeigenvalueproximalsupportvectormachinegepsvm |