Ultrasound imaging is widely used in clinical diagnosis because of its advantages of convenience， low cost and non-radiation， however， speckle noise in the image may adversely affect clinical diagnosis or subsequent image analysis.As a typical denoising technology， when using Non-Local Means Filter（NLMF）for speckle removal of ultrasonic image，there will be shortcomings such as high time consumption and difficulty in setting filtering parameters. Therefore， a Multi-scale Fast Non-Local Means Filter （MF-NLMF） algorithm was proposed to remove speckle noise of ultrasonic image. A Fast NLMF （F-NLMF） algorithm was first give out to reduce the computing time by using the mutual correlation filtering technique. Then multiple window parameters were set to obtain multiple speckle removal results， and the model parameters were able to be adjusted adaptively according to the window size. The final speckle removal image was obtained by fusing the multiple speckle removal results. Experimental results show that under the same experimental conditions， the F-NLMF algorithm reduces the computing time by at least 96.04% compared with the traditional NLMF algorithm. Compared with other six algorithms such as Iterative Bayesian Non-Local Mean Filtering （IBNLMF）， the proposed MF-NLMF has the speckle removal image with the Peak Signal-to-Noise Ratio （PSNR） value improved by more than 0.73 dB， the Feature SIMilarity index （FSIM） value increased by more than 0.011， the Contrast-to-Noise Ratio （CNR） and Signal-to-Noise Ratio （SNR） values raised by more than 0.000 5 and 0.001 6 respectively.