Channel prior convolutional attention for medical image segmentation.

Characteristics such as low contrast and significant organ shape variations are often exhibited in medical images. The improvement of segmentation performance in medical imaging is limited by the generally insufficient adaptive capabilities of existing attention mechanisms. An efficient Channel Prior Convolutional Attention (CPCA) method is proposed in this paper, supporting the dynamic distribution of attention weights in both channel and spatial dimensions. Spatial relationships are effectively extracted while preserving the channel prior by employing a multi-scale depth-wise convolutional module. The ability to focus on informative channels and important regions is possessed by CPCA. A segmentation network called CPCANet for medical image segmentation is proposed based on CPCA. CPCANet is validated on two publicly available datasets. Improved segmentation performance is achieved by CPCANet while requiring fewer computational resources through comparisons with state-of-the-art algorithms. Our code is publicly available at https://github.com/Cuthbert-Huang/CPCANet.

Complementary consistency semi-supervised learning for 3D left atrial image segmentation.

A network based on complementary consistency training, CC-Net, has been proposed for semi-supervised left atrium image segmentation. CC-Net efficiently utilizes unlabeled data from the perspective of complementary information, addressing the limited ability of existing semi-supervised segmentation algorithms to extract information from unlabeled data. The complementary symmetrical structure of CC-Net includes a main model and two auxiliary models. The complementary consistency is formed by the model-level perturbation between the main model and the auxiliary models, enforcing their consistency. The complementary information obtained by the two auxiliary models helps the main model effectively focus on ambiguous areas, while the enforced consistency between models facilitates the acquisition of low-uncertainty decision boundaries. CC-Net has been validated in two public datasets. Compared to current state-of-the-art algorithms under specific proportions of annotated data, CC-Net demonstrates the best performance in semi-supervised segmentation. Our code is publicly available at https://github.com/Cuthbert-Huang/CC-Net.

[Diagnosis and treatment of vascular injury in limbs].

OBJECTIVE: To report the diagnosis methods and clinical treatment effects of blood vessel trunk damage in limbs. METHODS: From January 2001 to June 2006, 72 patients with vascular injury in limbs were treated. There were 50 males and 22 females, aged from 5-60 years (median 39 years) and including 44 cases of open injury and 28 cases of closed injury. The locations were subclavian artery in 1, femoral artery in 23, popliteal artery in 20, radia artery and ulna artery in 12, brachial artery in 11, axillary artery in 3 and anterior and posterior tibia artery in 2. The disease course was 30 minutes to 27 days. Injured arteries were repaired by suturing directly in 3 cases, by end-end anastomosis in 39 cases and by saphenous transplantation in 30 cases. The length of transplant veins was 3 cm to 8 cm. RESULTS: In 72 cases, 67 survived and 5 were given amputation. Forty-eight cases were followed up 6 months to 5 years. The blood flow rate and the diameter of blood vessel on the affected limbs were not different from that of normal limbs by colorful Doppler blood flow monitor. Forty cases recovered satisfactory limb function. Eight cases had different degrees of dysfunction, of them, four cases received functional reconstructive operation, and the function and appearance were improved. CONCLUSION: To investigate the mechanism and situation of injury, to examine patients carefully and analyze comprehensively are the key points of making earlier diagnosis for branch blood vessel damage; microsurgical repair of the injured blood vessel is the assurance of the blood flow rate. For the blood vessel above elbow and knee injured and lacked blood supply more than 4 hours and fascia syndrome, earlier opening the fascia cavity is the effective methods to recover the function of the limbs and to avoid disability.