Multi-perspective region-based CNNs for vertebrae labeling in intraoperative long-length images.

PURPOSE: Effective aggregation of intraoperative x-ray images that capture the patient anatomy from multiple view-angles has the potential to enable and improve automated image analysis that can be readily performed during surgery. We present multi-perspective region-based neural networks that leverage knowledge of the imaging geometry for automatic vertebrae labeling in Long-Film images - a novel tomographic imaging modality with an extended field-of-view for spine imaging. METHOD: A multi-perspective network architecture was designed to exploit small view-angle disparities produced by a multi-slot collimator and consolidate information from overlapping image regions. A second network incorporates large view-angle disparities to jointly perform labeling on images from multiple views (viz., AP and lateral). A recurrent module incorporates contextual information and enforce anatomical order for the detected vertebrae. The three modules are combined to form the multi-view multi-slot (MVMS) network for labeling vertebrae using images from all available perspectives. The network was trained on images synthesized from 297 CT images and tested on 50 AP and 50 lateral Long-Film images acquired from 13 cadaveric specimens. Labeling performance of the multi-perspective networks was evaluated with respect to the number of vertebrae appearances and presence of surgical instrumentation. RESULTS: The MVMS network achieved an F1 score of >96% and an average vertebral localization error of 3.3 mm, with 88.3% labeling accuracy on both AP and lateral images - (15.5% and 35.0% higher than conventional Faster R-CNN on AP and lateral views, respectively). Aggregation of multiple appearances of the same vertebra using the multi-slot network significantly improved the labeling accuracy (p < 0.05). Using the multi-view network, labeling accuracy on the more challenging lateral views was improved to the same level as that of the AP views. The approach demonstrated robustness to the presence of surgical instrumentation, commonly encountered in intraoperative images, and achieved comparable performance in images with and without instrumentation (88.9% vs. 91.2% labeling accuracy). CONCLUSION: The MVMS network demonstrated effective multi-perspective aggregation, providing means for accurate, automated vertebrae labeling during spine surgery. The algorithms may be generalized to other imaging tasks and modalities that involve multiple views with view-angle disparities (e.g., bi-plane radiography). Predicted labels can help avoid adverse events during surgery (e.g., wrong-level surgery), establish correspondence with labels in preoperative modalities to facilitate image registration, and enable automated measurement of spinal alignment metrics for intraoperative assessment of spinal curvature.

Surgical management of metastatic spinal tumors.

BACKGROUND: The spine is the most common site of skeletal metastases. The evolution of surgical methods, medical treatment, and radiation therapy has led to improved survival, functional status, and quality of life for patients with cancer. The role of surgery in the treatment of patients with spinal metastases has evolved over time. METHODS: A review of publications describing the role of open surgery and vertebroplasty was performed and the results are summarized. RESULTS: The treatment goals of spinal metastases include the preservation and restoration of neurologic function and spinal stability. Modern imaging modalities provide accurate methods of tumor diagnosis. A variety of approaches and stabilization techniques are available and should be tailored to the location of the tumor and systemic comorbidities. CONCLUSIONS: As part of multidisciplinary treatment that includes radiation therapy and chemotherapy, surgery provides an effective method of restoration and preservation of neurologic function and spinal stability for patients with metastatic spinal tumors.