The traditional denoising algorithm for ultrasound images would lost a lot of details and weak edge information when suppressing speckle noise. A new denoising algorithm of adaptive threshold based on curvelet transform is proposed in this paper. The algorithm utilizes differences of coefficients' local variance between texture and smooth region in each layer of ultrasound image to define fuzzy regions and membership functions. In the end, using the adaptive threshold that determine by the membership function to denoise the ultrasound image. The experimental text shows that the algorithm can reduce the speckle noise effectively and retain the detail information of original image at the same time, thus it can greatly enhance the performance of B ultrasound instrument.
Algorithms ; Diagnostic Imaging ; Image Processing, Computer-Assisted ; Ultrasonics

Objective:To investigate the diagnostic performance of a new artificial intelligence (AI) model incorporating SAM-YOLOV 5 deep learning network and image processing techniques for Breast Imaging Reporting and Data System (BI-RADS) 4 category breast masses in dynamic ultrasound classification.Methods:A total of 530 pathologically proven breast lesions of BI-RADS category 4 in 458 patients were retrospectively collected from May 2019 to June 2023 at the First Affiliated Hospital of Shantou University Medical College. The model was trained and tested at ratio of 7∶3, the area under the ROC curve (AUC), sensitivity, specificity, positive predictive value and negative predictive value of the model were determined. Firstly, the test results of the model were compared with a single static image, then, compared with the three conventional deep learning networks as well as senior and junior radiologists. The diagnostic efficiency of the new model in BI-RADS categories 4a, 4b, and 4c masses were analyzed.Results:The AUC, sensitivity, specificity, positive predictive value and negative predictive value of the new model based on dynamic ultrasound video were higher than those using a single ultrasound static imaging (all P<0.05). Based on dynamic ultrasound video, the AUC, sensitivity, specificity, positive predictive value and negative predictive value of the new model were significantly higher than those of YOLOV 5, VGG 16, Resnet 50 and the junior group (all P<0.05), lower than the senior group (just specificity and negative predictive value, P<0.05). The diagnostic efficiency of new model for BI-RADS category 4b masses was the lowest. Conclusions:Based on the SAM-YOLOV 5 deep learning network and image processing techniques, the new model has a high diagnostic value for breast mass dynamic ultrasound classification and is expected to be used in assisting clinical diagnosis.