Medical Image Contrast Enhancement Using Spline Concept: Data from the Osteoarthritis Initiative
Hong‐Seng Gan, Tan Tian Swee, Mohammed Rafiq Abdul Kadir, Ahmad Helmy Abdul Karim, Khairil Amir Sayuti, Liang-Xuan Wong, Weng-Kit Tham · Journal of Medical Imaging and Health Informatics · 2014
Excellent visual quality of medical image is important for subsequent image interpretation and diagnosis planning. Hence, preservation of brightness and considerable tissue contrast improvement are essential for this purpose. Previous histogram equalization methods tend to focus on brightness preservation and neglect the need to address excessive contrast enhancement. However, gray level medical images are highly sensitive to redundant adjustment of image contrast. In this work, we propose to implement cubic spline to reduce the difference in pixel intensity prior to histogram equalization while retaining the partition of histogram to prevent dramatic mean brightness shift in resultant image. Qualitative results indicate that our proposed contrast enhancement method is capable of avoiding extreme brightness elevation and excessive tissue contrast improvement to provide holistic views of the knee MR images. In future, we would like to recommend the development of adaptive data interval to substitute the uniform data point intervals.