Fully automatic brain tumor segmentation for 3D evaluation in augmented reality

OBJECTIVE For currently available augmented reality workflows, 3D models need to be created with manual or semiautomatic segmentation, which is a time-consuming process. The authors created an automatic segmentation algorithm that generates 3D models of skin, brain, ventricles, and contrast-enhancing tumor from a single T1-weighted MR sequence and embedded this model into an automatic workflow for 3D evaluation of anatomical structures with augmented reality in a cloud environment. In this study, the authors validate the accuracy and efficiency of this automatic segmentation algorithm for brain tumors and compared it with a manually segmented ground truth set. METHODS Fifty contrast-enhanced T1-weighted sequences of patients with contrast-enhancing lesions measuring at least 5 cm(3) were included. All slices of the ground truth set were manually segmented. The same scans were subsequently run in the cloud environment for automatic segmentation. Segmentation times were recorded. The accuracy of the algorithm was compared with that of manual segmentation and evaluated in terms of Sorensen-Dice similarity coefficient (DSC), average symmetric surface distance (ASSD), and 95th percentile of Hausdorff distance (HD95). RESULTS The mean +/- SD computation time of the automatic segmentation algorithm was 753 +/- 128 seconds. The mean +/- SD DSC was 0.868 +/- 0.07, ASSD was 1.31 +/- 0.63 mm, and HD95 was 4.80 +/- 3.18 mm. Meningioma (mean 0.89 and median 0.92) showed greater DSC than metastasis (mean 0.84 and median 0.85). Automatic segmentation had greater accuracy for measuring DSC (mean 0.86 and median 0.87) and HD95 (mean 3.62 mm and median 3.11 mm) of supratentorial metastasis than those of infratentorial metastasis (mean 0.82 and median 0.81 for DSC; mean 5.26 mm and median 4.72 mm for HD95). CONCLUSIONS The automatic cloud-based segmentation algorithm is reliable, accurate, and fast enough to aid neurosurgeons in everyday clinical practice by providing 3D augmented reality visualization of contrast-enhancing intracranial lesions measuring at least 5 cm(3). The next steps involve incorporation of other sequences and improving accuracy with 3D fine-tuning in order to expand the scope of augmented reality workflow.

Automated summary

The authors developed an automatic segmentation algorithm for creating 3D models of anatomical structures from a single T1-weighted MR sequence, which was validated for brain tumors and compared with manual segmentation. The algorithm proved to be accurate and efficient in cloud-based automatic segmentation, showing potential for aiding neurosurgeons in clinical practice.