Detection of abnormalities in lumbar discs from clinical lumbar MRI with hybrid models

- Hybrid models which include feature extraction, feature selection and classification for determining the disc abnormalities of the lumbar region have been developed.
- F-score based feature selection (FSFS) and correlation-based feature selection (CBFS) were used to select best discriminative features.
- The results obtained suggest that the proposed hybrid models can be safely used in the detection of disc abnormalities.