Dual-Path Attention Compensation U-Net for Stroke Lesion Segmentation.

For the segmentation task of stroke lesions, using the attention U-Net model based on the self-attention mechanism can suppress irrelevant regions in an input image while highlighting salient features useful for specific tasks. However, when the lesion is small and the lesion contour is blurred, attention U-Net may generate wrong attention coefficient maps, leading to incorrect segmentation results. To cope with this issue, we propose a dual-path attention compensation U-Net (DPAC-UNet) network, which consists of a primary network and auxiliary path network. Both networks are attention U-Net models and identical in structure. The primary path network is the core network that performs accurate lesion segmentation and outputting of the final segmentation result. The auxiliary path network generates auxiliary attention compensation coefficients and sends them to the primary path network to compensate for and correct possible attention coefficient errors. To realize the compensation mechanism of DPAC-UNet, we propose a weighted binary cross-entropy Tversky (WBCE-Tversky) loss to train the primary path network to achieve accurate segmentation and propose another compound loss function called tolerance loss to train the auxiliary path network to generate auxiliary compensation attention coefficient maps with expanded coverage area to perform compensate operations. We conducted segmentation experiments using the 239 MRI scans of the anatomical tracings of lesions after stroke (ATLAS) dataset to evaluate the performance and effectiveness of our method. The experimental results show that the DSC score of the proposed DPAC-UNet network is 6% higher than the single-path attention U-Net. It is also higher than the existing segmentation methods of the related literature. Therefore, our method demonstrates powerful abilities in the application of stroke lesion segmentation.

[Periodontal status in patients with oral submucous fibrosis].

OBJECTIVE: To investigate the periodontal status in patients with oral submucous fibrosis (OSF), and to provide reference for the treatment and prophylaxis in patients with OSF and betel chewers. METHODS: Fifty samples clinically and pathologically diagnosed as OSF patients were selected as the OSF group, another 50 age-matched healthy volunteers in the similar living condition were compared with the OSF patients and non-betel nut chewers were classified as the control group. The 5 periodontal clinical parameters were collected and recorded, including plaque index, periodontal probing depth, clinical attachment loss, gingival index, and tooth count of bleeding of probing. RESULTS: There was a significant difference in plaque index (PLI) between the OSF group (2.14+/-0.64) and the control group (1.7+/-0.89) (P<0.01). Periodontal probing depth (PD) was (1.98+/-0.70) mm in the control group, and (5.57+/-2.39) mm in the OSF group, with significant difference in PD (P<0.01). There was no significant difference in clinical attachment loss, gingival index, and tooth count of bleeding on probing between the 2 groups (P>0.05). CONCLUSION: OSF patients tend to accumulate plaque, and have deep periodontal pocket, periodontal inflammation or severe periodontal damage.