Image enhancement of shoulder magnetic resonance imaging in rotator cuff injury diagnosis

Abstract

Purpose: Magnetic Resonance Imaging is the most common tool used to diagnose supraspinatus muscle rupture or tear. However, discriminating the features between the rupture and the tear in MR images is difficult, and leads to low diagnostic accuracy. In this article, image enhancement techniques are performed on the original images to improve diagnostic performance. Methods: Three types of histogram-based image enhancement techniques are employed to enhance rotor cuff MR images: (1) histogram equalization; (2) weighted histogram separation (WHS); and (3) coupled WHS. The peak signal-to-noise ratio (PSNR) was used to evaluate the quality of the enhanced images. The experimental group comprises the enhanced images with the highest PSNR and the original MR images. The control group comprises only the original MR images. Both the control group and experimental group were randomly presented to three orthopedic physicians for performance evaluation. The accuracy rate and F-measure were applied to measure the average classification performance. The McNemar test was then employed to test the significance levels of the proposed enhancement techniques. Results: Experimental results showed the original MR image combined with the coupled WHS images (experimental group) outperforms the original MR image (control group) both in accuracy rate and F-measure. The McNemar test shows that the experimental group significantly outperforms the control group in terms of classifying the injury by type. Conclusion: A coupled WHS image enhancement technique was developed to assist the diagnosis of rotator cuff MR imaging by type. Experimental results showed that the proposed enhancement techniques improve the average diagnostic performance and facilitate the classification of the injury by type.