No abstract

Objective: The formats of tracking displays exert important influences on tracking performance. Few previous studies explored the 3-D tracking display formats. The present study aimed to construct the 3-D formats for the manual pursuit and compensatory tracking displays by adding the depth information. Based on the results of tracking performance, we further optimized the preferable tracking format. Method: Three experiments were conducted. Experiment 1 was a confirmatory experiment to compare the effects of the two display formats on 2-D manual tracking performance with previous studies. Experiment 2 extended the investigation to a 3-D display by adding a depth cue indicating the relative size of the control marker and target. Experiment 3 was an optimisation experiment in which an improved 3-D tracking display was modified, i.e., an extra depth cue was complemented to clearly signify the relative position of the target and the control marker. Results: Pursuit tracking performance was better than compensatory tracking performance in both 2-D (Experiment 1) and 3-D space (Experiment 2). It also found that the extra depth cue significantly improved the tracking success rate and the subjective satisfaction of the pursuit display format in 3-D space (Experiment 3). Conclusions: These findings indicated that the depth cues could be used in tracking display in 3-D space and have important implications for the design of some motor training and tracking systems.What is already known about this topic?1. The formats of tracking displays exert important influences on tracking performance in 2-D space. 2. Pursuit tracking is considered superior to compensatory tracking in 2-D space. 3. The addition of depth cues was assumed to improve the tracking performance in 3-D space.

Medical imaging technology has become one of the indispensable computer-assisted intervention methods in clinical disease diagnosis and treatment, including identifying and locating lesion areas, detecting and segmenting tissue and organ lesions in different modalities. The wide application of medical image analysis in clinical examination and medical auxiliary diagnosis has effectively improved the diagnostic efficiency of doctors. In this paper, we propose a novel and effective model to achieve semantic segmentation of cataract datasets. This model uses the self-supervised method BYOL for parameter pre-training, which improves the model’s ability to extract image consistency features. In addition, we have added a lightweight Coordinate attention mechanism to the backbone network to enable the model to independently learn the correlation between the channel and the space and enhance the ability of network feature expression. Experiments are conducted on the cataract endoscopy fine-grained segmentation data set, showing the effectiveness of the proposed method for segment the organs and surgical instruments in the cataract surgical microscope image, which demonstrates the accuracy and robustness of the proposed method.

No abstract