A medical imaging analysis system for trigger finger using an adaptive texture-based active shape model (ATASM) in ultrasound images

Study on the methodology of striae gravidarum severity evaluation

Background

Striae gravidarum is a common occurrence in pregnancy and many women expect to prevent its development. At present, laser treatment has been used to improve the appearance of striae gravidarum, but the choice of laser type, treatment time, and frequency depend on the therapeutic effect. How to obtain an effective evaluation of striae gravidarum during and after treatment is very important. However, there is no unified evaluation parameter about striae gravidarum. In this paper, we studied the methodology evaluation of striae gravidarum severity. First, the laser therapeutic apparatus was selected as the experimental equipment and different striae gravidarum photos during treatment were obtained. Second, the subject evaluation parameters were chosen based on the literature research and the dermatologists’ guidance. Then, the striae gravidarum photos were divided into different groups by dermatologists based on these parameters. Finally, the objective detection parameters were designed based on the photos feature and subject evaluation parameters. Then, the objective detection parameters were used as the input of the support vector machine and the evaluation results were compared.

Results

Based on the subject evaluation parameters, the experimental data could be divided into mild, moderate and severe groups. The experiment results showed that the striae gravidarum severity of two randomly patients were improved before and after treatment, which verified the validity of the parameters. In addition, the chosen objective detection parameters were different among different groups. With all the objective parameters as the support vector machine input, we could achieve the best recognition rate (82.71%) in the striae gravidarum severity classification. The four parameters (color difference, average density, average width, distribution area) calculated from the photos as the input could achieve acceptable accuracy (81.69%).

Conclusions

The subject evaluation parameters and objective detection parameters proposed in this paper can be used to evaluate the striae gravidarum severity, which is of great significance for the construction of auxiliary diagnostic instrument for striae gravidarum treatment.

Segmentation of finger tendon and synovial sheath in ultrasound image using deep convolutional neural network

BACKGROUND

Trigger finger is a common hand disease, which is caused by a mismatch in diameter between the tendon and the pulley. Ultrasound images are typically used to diagnose this disease, which are also used to guide surgical treatment. However, background noise and unclear tissue boundaries in the images increase the difficulty of the process. To overcome these problems, a computer-aided tool for the identification of finger tissue is needed.

RESULTS

Two datasets were used for evaluation: one comprised different cases of individual images and another consisting of eight groups of continuous images. Regarding result similarity and contour smoothness, our proposed deeply supervised dilated fully convolutional DenseNet (D2FC-DN) is better than ATASM (the state-of-art segmentation method) and representative CNN methods. As a practical application, our proposed method can be used to build a tendon and synovial sheath model that can be used in a training system for ultrasound-guided trigger finger surgery.

CONCLUSION

We proposed a D2FC-DN for finger tendon and synovial sheath segmentation in ultrasound images. The segmentation results were remarkably accurate for two datasets. It can be applied to assist the diagnosis of trigger finger by highlighting the tissues and generate models for surgical training systems in the future.

METHODS

We propose a novel finger tendon segmentation method for use with ultrasound images that can also be used for synovial sheath segmentation that yields a more complete description for analysis. In this study, a hybrid of effective convolutional neural network techniques are applied, resulting in a deeply supervised dilated fully convolutional DenseNet (D2FC-DN), which displayed excellent segmentation performance on the tendon and synovial sheath.