With the scientific and modernization of acupuncture,various kinds of acupuncture medical equipment continue to innovate,especially with the emergence of intelligent acupuncture diagnosis and treatment units,automatic detection of acupuncture needles in the"needle retention"stage of acupuncture clinical practice has become a hot demand.Aiming at the problems that the input image size is too large,the acupuncture needles are slender,and the acupuncture needles are densely distributed,the Acupuncture Needle Object Detection Model(ANODM),an improved YOLOv5 model for acupuncture needles,is proposed in this paper.① In the preprocessing stage,the image is divided into multiple patches for prediction,respectively.② At the model structure level,a new small object detection layer is added to the original three detection layers to improve the recognition ability of small objects.The ordinary convolution of the backbone network is replaced by the dialated convolution to increase the sensitivity field.Features of different stages are fused.③ In the post-processing stage,Soft-NMS is used to reduce the miss rate of positive samples,and cosine similarity match is used to reduce the error rate of negative samples.The experimental results show that,compared with the original YOLOv5,the detection accuracy of the improved YOLOv5 in this paper is improved by 4.2%on the acupuncture needle small object dataset,which can better complete the acupuncture needle small target detection task.

With the scientific and modernization of acupuncture,various kinds of acupuncture medical equipment continue to innovate,especially with the emergence of intelligent acupuncture diagnosis and treatment units,automatic detection of acupuncture needles in the"needle retention"stage of acupuncture clinical practice has become a hot demand.Aiming at the problems that the input image size is too large,the acupuncture needles are slender,and the acupuncture needles are densely distributed,the Acupuncture Needle Object Detection Model(ANODM),an improved YOLOv5 model for acupuncture needles,is proposed in this paper.① In the preprocessing stage,the image is divided into multiple patches for prediction,respectively.② At the model structure level,a new small object detection layer is added to the original three detection layers to improve the recognition ability of small objects.The ordinary convolution of the backbone network is replaced by the dialated convolution to increase the sensitivity field.Features of different stages are fused.③ In the post-processing stage,Soft-NMS is used to reduce the miss rate of positive samples,and cosine similarity match is used to reduce the error rate of negative samples.The experimental results show that,compared with the original YOLOv5,the detection accuracy of the improved YOLOv5 in this paper is improved by 4.2%on the acupuncture needle small object dataset,which can better complete the acupuncture needle small target detection task.

Objective To assess the feasibility of semi-quantitative scoring system for contrast-enhanced ultrasound (CEUS)quantitative analysis's color images in the differential diagnosis of breast nodules.Methods Totally 244 BI-RADS 4 breast solid lesions received CEUS before core needle biopsy or surgical resection were included.A semi-quantitative scoring system for color images of CEUS quantitative analysis were built.The scores were given as follows:1 )Color type and its distribution (0 to 4);2)Color scope (0 to 1 );3)Color margin (0 to 1 );4)Color shape (0 to1 ).The total score for each lesion would be from 0 to 7.And the differenital value between benign and malignant lesions were assessed.Results The total semi-quantitative scores of 102 malignant tumors (5.1 ±1 .7)was significant higher than that of benign lesions (3.34±0.7)(P < 0.05 ).In 102 malignant lesions,the total scores of 81 lesions (79.41 %)were more than 4 points,and in 142 benign lesions,the total scores of 89 lesions (62.67%)were less than 4 points.Depending on the Wilcox rank sum test (Mann-Whitney)analysis,the distribution of total scores between benign and malignant lesions was significant different (P <0.000 1).Total score 4 was selected as the best cutoff,the area under ROC curve was 0.749,on which the sensitivity,specificity and accuracy were 79.4%,62.7% and 69.67%,respectively.Conclusions The semi-quantitative scoring system of CEUS quantitative analysis color images showed good sensitivity but not satisfied specificity and accuracy in differential diagnosis between malignant and benign breast lesions.