Research on Mask-Wearing Detection Algorithm Based on Improved YOLOv5.

COVID-19 is highly contagious, and proper wearing of a mask can hinder the spread of the virus. However, complex factors in natural scenes, including occlusion, dense, and small-scale targets, frequently lead to target misdetection and missed detection. To address these issues, this paper proposes a YOLOv5-based mask-wearing detection algorithm, YOLOv5-CBD. Firstly, the Coordinate Attention mechanism is introduced into the feature fusion process to stress critical features and decrease the impact of redundant features after feature fusion. Then, the original feature pyramid network module in the feature fusion module was replaced with a weighted bidirectional feature pyramid network to achieve efficient bidirectional cross-scale connectivity and weighted feature fusion. Finally, we combined Distance Intersection over Union with Non-Maximum Suppression to improve the missed detection of overlapping targets. Experiments show that the average detection accuracy of the YOLOv5-CBD model is 96.7%-an improvement of 2.1% compared to the baseline model (YOLOv5).

Noncontrast dynamic magnetic resonance imaging for quantitative assessment of female sexual arousal.

PURPOSE: We evaluated a noncontrast, dynamic magnetic resonance imaging (MRI) technique for quantitative evaluation of the female sexual arousal response and compared these results with those of a previously described, contrast enhanced MRI technique. MATERIALS AND METHODS: Eight normal, healthy volunteer women underwent 2 separate MRI sessions, during which they were shown audiovisual material consisting of interleaved neutral and audiovisual sexual stimulation segments. Serial high resolution MRI of the genital structures was done at 3-minute intervals during a 45-minute period. Images were analyzed in blinded fashion and measurements of clitoral volume with time were obtained for each subject. Measured clitoral volumes together with the percent change in clitoral volume during audiovisual sexual stimulation for MRI sessions 1 and 2 were compared within subjects. Results were also compared to those of prior contrast enhanced MRI studies in the same subjects. RESULTS: There was excellent intrasubject reproducibility between sessions 1 and 2 using the noncontrast MRI technique (r = 0.99). There was also excellent agreement between the current noncontrast study and prior contrast enhanced studies with a correlation coefficient of 0.89. CONCLUSIONS: Dynamic, noncontrast MRI of the female genitalia appears to be a reproducible, nonintrusive and objective way to assess quantitatively the sexual arousal response in women without sexual difficulties.

Serial MR imaging with MS-325 for evaluating female sexual arousal response: determination of intrasubject reproducibility.

PURPOSE: To determine if a similar sexual arousal response in normal, healthy women could be obtained and monitored by serial magnetic resonance (MR) imaging at two separate sessions. MATERIALS AND METHODS: Serial imaging of the external genitalia was performed on nine healthy, sexually functional women at two separate MR sessions after administration of the contrast agent, MS-325. Images were obtained every three minutes during a 45-minute study period during each MR session. The second MR session began approximately 45 minutes after the end of the first MR session. While undergoing imaging, subjects viewed videotapes that contained neutral and sexually-explicit material through an audiovisual system. Analysis performed at each time point consisted of visual evaluation of the images, clitoral and femoral vein signal intensity measurements, relative regional blood volume calculations, and clitoral volume measurements. Statistical analysis of the results consisted of calculating correlation coefficients of the two MR sessions by using the least square fit method. RESULTS: All nine subjects reported sexual arousal on subjective questionnaires at each MR session. Post-contrast MS-325 MR images showed strong enhancement of the external genitalia at each session. There was excellent correlation between the two sessions for the clitoral volume measurements of all nine subjects. The correlation coefficient, r(2), was 0.95. CONCLUSION: The sexual arousal response in normal, healthy women can be monitored by serial imaging combined with the use of the contrast agent, MS-325, and similar results can be reproduced at two different MR sessions. This method holds promise for future studies of women with female sexual arousal dysfunction.

Magnetic resonance imaging anatomy of the female genitalia in premenopausal and postmenopausal women.

PURPOSE: We used contrast enhanced magnetic resonance imaging (MRI) of the female genital organs to describe normal anatomy and differences between premenopausal and postmenopausal women. MATERIALS AND METHODS: A total of 12 healthy premenopausal and 9 healthy postmenopausal women underwent MRI. A 1.5 Tesla system with phased array coils anterior and posterior to the pelvis was used to produce T1-weighted images before and after intravenous administration of MS-325 (Epix Medical, Cambridge, Massachusetts), a new gadolinium based blood pool contrast agent. Select structural dimensions were measured for reference. RESULTS: The clitoris and vestibular bulbs were well delineated on T1-weighted post-contrast images. The clitoral unit formed a brightly enhancing, wishbone-shaped structure lying just anterior to the inverted V of the bulbs, which surrounded the urethra and vagina. The urethral complex had a target-like appearance with layers that were discernible on T1 post-contrast images. The urethra, vagina and rectum formed a distinct complex within uniformly enhancing soft tissue. The vagina was well visualized in premenopausal subjects but without distinguishable mucosal rugae or clearly separate layers in postmenopausal subjects. Postmenopausal subjects were also observed to have smaller labia minora width, vestibular bulb width, vaginal width and wall thickness, and cervical diameter. Pelvic and genital structures were not well visualized on T1 noncontrast images. CONCLUSIONS: To our knowledge we describe detailed female genital anatomy for the first time using MRI with MS-325 contrast medium. The clitoris, vestibular bulbs, labia majora and minora, urethra, vagina, cervix and rectum are well visualized on T1 post-contrast images. The observed genital anatomy on MRI was consistent with descriptions in current anatomical texts. Differences in the female genitalia between premenopausal and postmenopausal women were discernible on MRI. These data are important for future studies using MRI for evaluating anatomical anomalies, postoperative changes and female sexual function.

Dynamic MR imaging of the sexual arousal response in women.

The purpose of our studies was to evaluate whether MR imaging could be used to noninvasively observe and measure the sexual arousal response in normal women. We tested the feasibility as well as the reproducibility of rapid, dynamic, serial high-resolution MR imaging of the genital structures during presentation of neutral and sexually stimulating video material. Results show that these MRI techniques can visualize significant changes in clitoral volume during the stimulus segment of the video presentation. Quantitative measurements made of these changes were robust and reproducible. These studies suggest that MRI techniques may be a useful tool to improve our understanding of the physiology involved with the sexual arousal response in women. These MRI techniques may also prove useful as a surrogate end point marker for testing efficacy of future new treatments for women with sexual arousal disorder.

Female genitalia: dynamic MR imaging with use of MS-325 initial experiences evaluating female sexual response.

PURPOSE: To determine whether magnetic resonance (MR) imaging with MS-325, a recently developed blood pool contrast agent, can depict sexual arousal response in healthy women. MATERIALS AND METHODS: Serial MR imaging of the external genitalia was performed in 12 healthy sexually functional women before and after administration of MS-325. MR images were obtained every 3 minutes during a 45-minute examination. During the examination, the subjects viewed neutral and erotic video material while they were in the magnet bore. MR image analysis at each interval consisted of vaginal wall, vaginal mucosa, and clitoris assessments; femoral vein signal intensity measurements; relative regional blood volume (rRBV) calculations; and clitoral volume measurements. Statistical analysis of the results was performed with a t test. RESULTS: On subjective questionnaires, all subjects in the test group reported being sexually aroused. MS-325-enhanced MR images showed strong contrast enhancement of the external genitalia. The rRBV in the glans clitoris of seven of 10 subjects and in the clitoral body of eight of these subjects increased significantly (P <.05) during erotic visual stimulation. All 10 subjects had a significant (P <.05) increase in clitoral size. There were no significant differences in any measures between the pre- and postmenopausal study groups. CONCLUSION: The sexual arousal response in healthy women can be monitored at serial MR imaging with MS-325. This examination holds promise for future studies of sexual arousal dysfunction in women.