The methods of measuring laryngeal elevation during swallowing are time-consuming. We aimed to propose a quick-to-use neural network (NN) model for measuring laryngeal elevation quantitatively using anatomical structures auto-segmented by Mask region-based convolutional NN (R-CNN) in videofluoroscopic swallowing study. Twelve videofluoroscopic swallowing study video clips were collected. One researcher drew the anatomical structure, including the thyroid cartilage and vocal fold complex (TVC) on respective video frames. The dataset was split into 11 videos (4686 frames) for model development and one video (532 frames) for derived model testing. The validity of the trained model was evaluated using the intersection over the union. The mean intersections over union of the C1 spinous process and TVC were 0.73 ± 0.07 [0–0.88] and 0.43 ± 0.19 [0–0.79], respectively. The recall rates for the auto-segmentation of the TVC and C1 spinous process by the Mask R-CNN were 86.8% and 99.8%, respectively. Actual displacement of the larynx was calculated using the midpoint of the auto-segmented TVC and C1 spinous process and diagonal lengths of the C3 and C4 vertebral bodies on magnetic resonance imaging, which measured 35.1 mm. Mask R-CNN segmented the TVC with high accuracy. The proposed method measures laryngeal elevation using the midpoint of the TVC and C1 spinous process, auto-segmented by Mask R-CNN. Mask R-CNN auto-segmented the TVC with considerably high accuracy. Therefore, we can expect that the proposed method will quantitatively and quickly determine laryngeal elevation in clinical settings.

No abstract

We investigated the diffusion tensor image (DTI) parameters of superior longitudinal fasciculus (SLF) and inferior fronto-occipital fasciculus (IFOF), and their relationships with hemispatial neglect. Thirteen patients with first-ever ischemic stroke who had the right hemispheric lesion were included. Neglect was assessed using the Albert test and figure discrimination test of Motor-free Visual Perception Test 3 (MVPT-3). The SLF and IFOF were separated by diffusion tensor tractography (DTT) and tract volume (TV) was calculated. We measured the fractional anisotropy (FA) and apparent diffusion coefficient (ADC) values in the total area, seed region of interest (ROI), and target ROI, respectively. Among thirteen patients, seven demonstrated signs of hemispatial neglect on neglect test. Tractography reconstruction showed significantly low TV of the right IFOF in patients with hemispatial neglect. FA values of the right SLF and the right IFOF were significantly lower in neglect patients. ADC values were not significantly different in two groups. This study suggests that damage of SLF and IFOF is associated with hemispatial neglect in right hemispheric stroke patients. DTI may be useful for predicting the severities of hemispatial neglect using values such as TV and FA of each tract.

This study aims to investigate the relationship between ipsilesional upper extremity (UE) motor function and the integrity of the subregions of the corpus callosum in hemiparetic stroke patients with motor deficits of the dominant or non-dominant ipsilesional side. Twenty participants with unilateral UE deficits after stroke were included. Each of the 10 participants had lesions on the left and right sides. The ipsilesional UE function was assessed with the Jebsen-Taylor hand function test (JHFT), the 9-hole peg test (9HPT), and grip and pinch strength tests. Fractional anisotropy (FA) was calculated for the integrity of the 5 subregions of the corpus callosum. Pearson’s correlation analysis was conducted to investigate the relationship between UE function and the integrity of the callosal subregions. The results of JHFT and 9HPT showed a significant correlation with the FA value of the corpus callosum I projecting to the frontal lobe in the left lesion group (p < 0.05). There was no correlation between the ipsilesional UE motor function and the FA value of the ulnar subregion in the right lesion group (p > 0.05). These results showed that the motor deficits of the ipsilesional UE correlated with the integrity of callosal fiber projection to the prefrontal area when the ipsilesional side was non-dominant.