Enhancing nasal endoscopy: Classification, detection, and segmentation of anatomic landmarks using a convolutional neural network.

KEY POINTS: A convolutional neural network (CNN)-based model can accurately localize and segment turbinates in images obtained during nasal endoscopy (NE). This model represents a starting point for algorithms that comprehensively interpret NE findings.

A Pain Reporting Tool for School-Aged Baseball Pitchers.

Rates of injury to school-aged athletes are of concern to pediatric providers and can be prevented when players, coaches, and parents recognize and address pain. The aim of the present study was to evaluate the use of a pain-reporting tool. In this study, 34 baseball players aged 10-16 years reported pain surrounding 135 separate pitching experiences. Those participating in another sport on the same day as pitching rated pain intensity as significantly higher than those who did not. Approximately 19 pitches were thrown before participants noticed pain. Ice and analgesics were used appropriately to manage pain. School nurses are well positioned to discuss pain reporting and common injuries with young athletes, parents, and athletic coaches. Sharing proactive ways to elicit information about pain is suggested. Implications for future research include the study of young athlete experiences with pain and development of educational initiatives regarding the importance of reporting pain.

Circular ultrasound compounding by designed matrix weighting.

Spatial compounding is an imaging technique that aims to improve image contrast by combining partially decor-related images acquired at different angles or positions. In conventional spatial compounding, data sets are combined with equal weighting. Here, we describe an alternative method of reconstruction using algorithms which weight the data based on a "quality" matrix. The quality matrix is derived from beamforming characteristics. For each data set, the reliability of the data is assumed to vary spatially. By compounding the data based on the quality matrix, a complete image is formed. Here, we describe the construction of a rotational translation stage and tissue-mimicking phantoms that are used in conjunction with a commercial medical ultrasound machine to test our reconstruction algorithms. The new algorithms were found to increase the contrast-to-speckle ratio of simulated cysts and tumors by 61% from raw data, and to significantly increase edge definition of small embedded targets. The new method shows promise as a computationally efficient method of improving contrast and resolution in ultrasound images. The method should be particularly useful in breast imaging, where images from multiple angles can be acquired without interference from bone or air.

Maximal dynamic grip force and wrist torque: the effects of gender, exertion direction, angular velocity, and wrist angle.

The objective of this study was to examine the effects of gender, exertion direction, angular velocity and wrist angle on simultaneous grip force and wrist torque under the isokinetic condition. The study used 20 participants (10 males and 10 females) and included 6 angular velocities (15, 30, 45, 60, 75, and 90 degrees /s) and 2 wrist exertion directions (flexion and extension) over the wrist range of motion of 70 degrees flexion to 60 degrees extension in 5 degrees increments. Similar to other studies, males and flexion exertion produced larger forces than females and extension exertion, respectively. However, the largest forces were generated at near extreme flexion of the wrist and the dependent variable of angular velocity was not practically significant. These results can contribute to the evaluation of cumulative trauma syndromes, but there is a need for more research on the dynamic measures of the hand and wrist complex and for standard development for dynamic force measurement.