1. Ventricle shape analysis using modified WKS for atrophy detection
- Author
-
Jayaraman Thirumagal, Anup Sadhu, Manjunatha Mahadevappa, and Pranab Kumar Dutta
- Subjects
Computer science ,Quantitative Biology::Tissues and Organs ,Physics::Medical Physics ,0206 medical engineering ,Biomedical Engineering ,02 engineering and technology ,030218 nuclear medicine & medical imaging ,03 medical and health sciences ,0302 clinical medicine ,Wavelet ,Atrophy ,Heat kernel signature ,medicine ,Humans ,Brain Ventricle ,business.industry ,Brain ,Pattern recognition ,medicine.disease ,Magnetic Resonance Imaging ,020601 biomedical engineering ,Computer Science Applications ,Kernel (statistics) ,Graph (abstract data type) ,Artificial intelligence ,Signature (topology) ,business ,Algorithms ,Shape analysis (digital geometry) - Abstract
Brain ventricle is one of the biomarkers for detecting neurological disorders. Studying the shape of the ventricles will aid in the diagnosis process of atrophy and other CSF-related neurological disorders, as ventricles are filled with CSF. This paper introduces a spectral analysis algorithm based on wave kernel signature. This shape signature was used for studying the shape of segmented ventricles from the brain images. Based on the shape signature, the study groups were classified as normal subjects and atrophy subjects. The proposed algorithm is simple, effective, automated, and less time consuming. The proposed method performed better than the other methods heat kernel signature, scale invariant heat kernel signature, wave kernel signature, and spectral graph wavelet signature, which were used for validation purpose, by producing 94-95% classification accuracy by classifying normal and atrophy subjects correctly for CT, MR, and OASIS datasets.
- Published
- 2021
- Full Text
- View/download PDF