Multi-view graph pooling with coarsened graph disentanglement.

Multi-view graph pooling utilizes information from multiple perspectives to generate a coarsened graph, exhibiting superior performance in graph-level tasks. However, existing methods mainly focus on the types of multi-view information to improve graph pooling operations, lacking explicit control over the pooling process and theoretical analysis of the relationships between views. In this paper, we rethink the current paradigm of multi-view graph pooling from an information theory perspective, subsequently introducing GDMGP, an innovative method for multi-view graph pooling derived from the principles of graph disentanglement. This approach effectively simplifies the original graph into a more structured, disentangled coarsened graph, enhancing the clarity and utility of the graph representation. Our approach begins with the design of a novel view mapper that dynamically integrates the node and topology information of the original graph. This integration enhances its information sufficiency. Next, we introduce a view fusion mechanism based on conditional entropy to accurately regulate the task-relevant information in the views, aiming to minimize information loss in the pooling process. Finally, to further enhance the expressiveness of the coarsened graph, we disentangle the fused view into task-relevant and task-irrelevant subgraphs through mutual information minimization, retaining the task-relevant subgraph for downstream tasks. We theoretically demonstrate that the performance of the coarsened graph generated by our GDMGP is superior to that of any single input view. The effectiveness of GDMGP is further validated by experimental results on seven public datasets.

Minimally Invasive Transforaminal Lumbar Interbody Fusion and Unilateral Fixation for Degenerative Lumbar Disease.

OBJECTIVE: To evaluate the clinical effect of the minimally invasive transforaminal lumbar interbody fusion combined with posterolateral fusion and unilateral fixation using a tubular retractor in the management of degenerative lumbar disease. METHODS: A retrospective analysis was conducted to analyze the clinical outcome of 58 degenerative lumbar disease patients who were treated with minimally invasive transforaminal lumbar interbody fusion combined with posterolateral fusion and unilateral fixation during December 2012 to January 2015. The spine was unilaterally approached through a 3.0-cm skin incision centered on the disc space, located 2.5 cm lateral to the midline, and the multifidus muscles and longissimus dorsi were stripped off. After transforaminal lumbar interbody fusion and posterolateral fusion the unilateral pedicle screw fixation was performed. The visual analogue scale (VAS) for back and leg pain, the Oswestry disability index (ODI), and the MacNab score were applied to evaluate clinical effects. The operation time, peri-operative bleeding, postoperative time in bed, hospitalization costs, and the change in the intervertebral height were analyzed. Radiological fusion based on the Bridwell grading system was also assessed at the last follow-up. The quality of life of the patients before and after the operation was assessed using the short form-36 scale (SF-36). RESULTS: Fifty-eight operations were successfully performed, and no nerve root injury or dural tear occurred. The average operation time was 138 ± 33 min, intraoperative blood loss was 126 ± 50 mL, the duration from surgery to getting out of bed was 46 ± 8 h, and hospitalization cost was 1.6 ± 0.2 ten thousand yuan. All of the 58 patients were followed up for 7-31 months, with an average of 14.6 months. The postoperative VAS scores and ODI score were significantly improved compared with preoperative data (P < 0.05). The evaluation of the MacNab score was excellent in 41 patients, good in 15, and fair in 2, suggesting an effective rate of 96.6%. The intervertebral height had reduced 0.2 ± 1.2 mm by the last follow-up, and there were 55 Grade I and II cases based on the Bridwell evaluation criterion. The fusion rate was 94.8%, and no screw breakage and loosening occurred. The scores of physical pain, general health, social, and emotional functioning were significantly increased at the last follow-up. CONCLUSION: Minimally invasive transforaminal lumbar interbody fusion combined with posterolateral fusion and unilateral fixation provide a new choice for degenerative lumbar disease, and the short-term clinical outcome is satisfactory.