Degenerative disc segmentation and diagnosis technology using important features from MRI of spine in images

Abstract

This paper focuses on the medical image segmentation techniques used in the study of spinal diseases. Medical reports have shown an increasing concern of the public on spinal diseases caused by disc degeneration. This paper presents an accurate and automated method to detect the abnormal disc. This method uses two standard models in conjunction with the threshold value to accurately identify the cartilage. Then we smooth out the images via morphological methods and find out the average height of the cartilage before we judge if a certain cartilages are lower in height than the normal range. Finally, we carefully label the degenerated parts of the disc. In comparison with the professional physician's manual segmentation, our image segmentation shows high accuracy, with the highest rate reaching 99.88.