Curvelet based automatic segmentation of supraspinatus tendon from ultrasound image: a focused assistive diagnostic method

Abstract

BackgroundDisorders of rotator cuff tendons results in acute pain limiting the normal range of motion for shoulder. Of all the tendons in rotator cuff, supraspinatus (SSP) tendon is affected first of any pathological changes. Diagnosis of SSP tendon using ultrasound is considered to be operator dependent with its accuracy being related to operator’s level of experience.MethodsThe automatic segmentation of SSP tendon ultrasound image was performed to provide focused and more accurate diagnosis. The image processing techniques were employed for automatic segmentation of SSP tendon. The image processing techniques combines curvelet transform and mathematical concepts of logical and morphological operators along with area filtering. The segmentation assessment was performed using true positives rate, false positives rate and also accuracy of segmentation. The specificity and sensitivity of the algorithm was tested for diagnosis of partial thickness tears (PTTs) and full thickness tears (FTTs). The ultrasound images of SSP tendon were taken from medical center with the help of experienced radiologists. The algorithm was tested on 116 images taken from 51 different patients.ResultsThe accuracy of segmentation of SSP tendon was calculated to be 95.61% in accordance with the segmentation performed by radiologists, with true positives rate of 91.37% and false positives rate of 8.62%. The specificity and sensitivity was found to be 93.6%, 94% and 95%, 95.6% for partial thickness tears and full thickness tears respectively. The proposed methodology was successfully tested over a database of more than 116 US images, for which radiologist assessment and validation was performed.ConclusionsThe segmentation of SSP tendon from ultrasound images helps in focused, accurate and more reliable diagnosis which has been verified with the help of two experienced radiologists. The specificity and sensitivity for accurate detection of partial and full thickness tears has been considerably increased after segmentation when compared with existing literature.

Using Convolutional Neural Network for edge detection in musculoskeletal ultrasound images

“…Using GPU will help us in accelerating training and reduce implementation time. In addition, so far the current work has not used any kind of pre-processing like foveation [8], contrast enhancement or any active denoising to reduce the effects of speckle noise [4]. If carried out this kind of processing is likely to boost CNN performance, but at the expense of extra pre-processing computation: so a trade-off between these pros and cons still needs to be found to overcome the confusion that can happen due to speckle noise or low contrast.…”

“…Image processing and segmentation of MUI is not a trivial task due to speckle noise, and the low contrast and homogeneity of ultrasound gray level intensities [4]. The detection and elimination of speckle noise in ultrasound images is a challenge because it is multiplicative noise.…”

“…The first automatic segmentation technique on MUI was in 2014 [4]. This technique addressed at the beginning some issues related with MUI such as speckle noise reduction and contrast enhancement.…”

Using Fuzzy Inference system for detection the edges of Musculoskeletal Ultrasound Images

“…Several different methods for edge detection have been utilised on musculoskeletal US images. One of the preliminary works in musculoskeletal US image segmentation was introduced by Gupta [5]. This work was based on curvelet transforms and morphological image processing (dilation and erosion).…”

Tendon-motion tracking in an ultrasound image sequence using optical-flow-based block matching

“…Because ultrasound images are normally used to observe the characteristics and motion of different tissue types [5–7], images of two different upper-limb tendons, the flexor tendon in the finger and a common extensor tendon in the elbow, for tracking in this study. Tendinopathy of the flexor tendon will cause trigger finger, and in a common extensor tendon will cause tennis elbow.…”