Medical Diagnosis of Cerebral Palsy Rehabilitation Using Eye Images in Machine Learning Techniques
| Autor: | J. Arokia Renjit, P Illavarason, P. Mohan Kumar |
|---|---|
| Rok vydání: | 2019 |
| Předmět: |
Male
020205 medical informatics Medicine (miscellaneous) Health Informatics Image processing 02 engineering and technology Nystagmus Machine learning computer.software_genre Cerebral palsy Machine Learning Health Information Management 0202 electrical engineering electronic engineering information engineering medicine Image Processing Computer-Assisted Humans Eye Abnormalities Medical diagnosis Strabismus Child business.industry Cerebral Palsy Eye movement medicine.disease Statistical classification Child Preschool Female Artificial intelligence Neural Networks Computer medicine.symptom Performance improvement business computer Algorithms Information Systems |
| Zdroj: | Journal of medical systems. 43(8) |
| ISSN: | 1573-689X |
| Popis: | Cerebral Palsy (CP) is a non progressive neurological disorders commonly associated with a spectrum of developmental disabilities such as strabismus (misalignment of eye). The Eye image are captured through camera, this make the quick diagnosis and examination the periodical assessment for CP kids. By capturing the Eye Movement of 40 children with CP (aged 3–11 years) with relatively mild motor-impairment and also we have analyzed the performance of CP children periodically. Nowadays, Bio-Medical image processing and Machine learning Classification algorithm used for detection and diagnosis the certain diseases and plays the important tool to decrease the risk of any diseases. This work presents a computational methodology to automatically diagnose the Improvement of CP children and performance can be evaluated. The alternate medical evaluation techniques have shown their potential for the treatment and diagnosis of disease like strabismus and nystagmus for CP kids. The proposed method is used to measure and quantify the performance improvement by classify the abnormal eye condition of CP kids and these results attained by machine learning method. The results show the best classification accuracy of 94.17% calculated from Neural Network Classifier. Specificity Rate were absorbed as 0.9800 and Sensitivity Rate were absorbed as 0.9165 respectively. The proposed method for non-invasive and automatic detection of abnormalities in CP kids and evaluates the performance improvement more accurately. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|
Full text from SpringerLink