Clustering of Brain Tumor Based on Analysis of MRI Images Using Robust Principal Component Analysis (ROBPCA) Algorithm

• Published in: BioMed research international Vol. 2021; no. 1; p. 5516819
• Main Authors: Hamzenejad, Ali, Ghoushchi, Saeid Jafarzadeh, Baradaran, Vahid
• Format: Journal Article
• Language: English
• Published: United States Hindawi 2021; John Wiley & Sons, Inc
• Subjects: Algorithms; Alzheimer Disease - diagnostic imaging; Alzheimer Disease - pathology; Alzheimer's disease; Analysis; Brain; Brain - diagnostic imaging; Brain - pathology; Brain cancer; Brain Neoplasms - diagnostic imaging; Brain Neoplasms - pathology; Brain research; Brain tumors; Care and treatment; Classification; Cluster Analysis; Clustering; Clusters (Chemistry); Diagnosis; Glioma; Glioma - diagnostic imaging; Glioma - pathology; Health aspects; Humans; Huntington Disease - diagnostic imaging; Huntington Disease - pathology; Image Processing, Computer-Assisted - methods; Machine learning; Magnetic resonance imaging; Magnetic Resonance Imaging - methods; Medical imaging; Meningeal Neoplasms - diagnostic imaging; Meningeal Neoplasms - pathology; Meningioma; Meningioma - diagnostic imaging; Meningioma - pathology; Methods; Nanotechnology; Neural networks; Neuroimaging; Noise; Optimization; Parkinson's disease; Principal Component Analysis - methods; Principal components analysis; Risk factors; ROC Curve; Tumors; Wavelet transforms; Iran
• ISSN: 2314-6133; 2314-6141; 2314-6141
• DOI: 10.1155/2021/5516819

Automated detection of brain tumor location is essential for both medical and analytical uses. In this paper, we clustered brain MRI images to detect tumor location. To obtain perfect results, we presented an unsupervised robust PCA algorithm to clustered images. The proposed method clusters brain MR image pixels to four leverages. The algorithm is implemented for five brain diseases such as glioma, Huntington, meningioma, Pick, and Alzheimer’s. We used ten images of each disease to validate the optimal identification rate. According to the results obtained, 2% of the data in the bad leverage part of the image were determined, which acceptably discerned the tumor. Results show that this method has the potential to detect tumor location for brain disease with high sensitivity. Moreover, results show that the method for the Glioma images has approximately better results than others. However, according to the ROC curve for all selected diseases, the present method can find lesion location.