Diagnostic performance evaluation of adult Chiari malformation type I based on convolutional neural networks.

PURPOSE: This study aimed to evaluate the diagnostic performance of convolutional neural network (CNN) models in Chiari malformation type I (CMI) and to verify whether CNNs can identify the morphological features of the craniocervical junction region between patients with CMI and healthy controls (HCs). To date, numerous indicators based on manual measurements are used for the diagnosis of CMI. However, the corresponding postoperative efficacy and prognostic evaluations have remained inconsistent. From a diagnostic perspective, CNN models may be used to explore the relationship between the clinical features and image morphological parameters. METHODS: This study included a total of 148 patients diagnosed with CMI at our institution and 205 HCs were included. T1-weighted sagittal magnetic resonance imaging (MRI) images were used for the analysis. A total of 220 and 355 slices were acquired from 98 patients with CMI and 155 HCs, respectively, to train and validate the CNN models. In addition, median sagittal images obtained from 50 patients with CMI and 50 HCs were selected to test the models. We applied original cervical MRI images (CI) and images of posterior cranial fossa and craniocervical junction area (CVI) to train the CI- and CVI-based CNN models. Transfer learning and data augmentation were used for model construction and each model was retrained 10 times. RESULTS: Both the CI- and CVI-based CNN models achieved high diagnostic accuracy. In the validation dataset, the models had diagnostic accuracy of 100% and 97% (p = 0.005), sensitivity of 100% and 98% (p = 0.016), and specificity of 100% (p = 0.929), respectively. In the test dataset, the accuracy was 97% and 96% (p = 0.25), sensitivity was 97% and 92% (p = 0.109), and specificity was 100% (p = 0.123), respectively. For patients with cerebellar subungual herniation less than 5 mm, three out of the 10 CVI-based retrained models reached 100% sensitivity. CONCLUSIONS: Our results revealed that the CNN models demonstrated excellent diagnostic performance for CMI. The models had higher sensitivity than the application of cerebellar tonsillar herniation alone and could identify features in the posterior cranial fossa and craniocervical junction area of patients. Our preliminary experiments provided a feasible method for the diagnosis and study of CMI using CNN models. However, further studies are needed to identify the morphologic characteristics of patients with different clinical outcomes, as well as patients who may benefit from surgery.

Multi-View Laser Point Cloud Global Registration for a Single Object.

Global registration is an important step in the three-dimensional reconstruction of multi-view laser point clouds for moving objects, but the severe noise, density variation, and overlap ratio between multi-view laser point clouds present significant challenges to global registration. In this paper, a multi-view laser point cloud global registration method based on low-rank sparse decomposition is proposed. Firstly, the spatial distribution features of point clouds were extracted by spatial rasterization to realize loop-closure detection, and the corresponding weight matrix was established according to the similarities of spatial distribution features. The accuracy of adjacent registration transformation was evaluated, and the robustness of low-rank sparse matrix decomposition was enhanced. Then, the objective function that satisfies the global optimization condition was constructed, which prevented the solution space compression generated by the column-orthogonal hypothesis of the matrix. The objective function was solved by the Augmented Lagrange method, and the iterative termination condition was designed according to the prior conditions of single-object global registration. The simulation analysis shows that the proposed method was robust with a wide range of parameters, and the accuracy of loop-closure detection was over 90%. When the pairwise registration error was below 0.1 rad, the proposed method performed better than the three compared methods, and the global registration accuracy was better than 0.05 rad. Finally, the global registration results of real point cloud experiments further proved the validity and stability of the proposed method.

Real-time ultrasound-MRI fusion image virtual navigation for locating intraspinal tumour in a pregnant woman.

BACKGROUND: Standard fluoroscopic guidance (C-arm fluoroscopy) has been routinely used for intraoperative localization of spinal level for surgical removal of intraspinal tumour, while it is not suitable for selected patients, e.g. pregnant women, who need to avoid radiation exposure. Fusion imaging of real-time ultrasound (US) and magnetic resonance imaging (MRI) is a radiation-free technique which has been reported to have good localization accuracy in managing several conditions. CLINICAL PRESENTATION: A 37-year-old pregnant patient, presented with a progressively aggravating lower back pain for 20 days and was incapable of lying supine with lower extremities swelling for 1 week, was referred to our hospital in her 18th week of gestation. Lumbar MRI identified an L1 level intraspinal lesion, and surgery was planned. To avoid the ionizing radiation generated by fluoroscopy, volume navigation technique (VNT) based fusion imaging of US and MRI was used to localize the intraspinal lesion, which was removed entirely via minimally invasive interlaminar approach. Pathological examination confirmed the diagnosis of ependymoma of the conus medullaris. Her symptoms were largely relieved after the operation, and a healthy baby was delivered at the 40th week of pregnancy. CONCLUSION: We presented the first case of using VNT based fusion imaging of real-time US/MRI to guide the surgical resection of an intraspinal tumour. Future study with larger patient number is needed to validate this technique as an alternative to fluoroscopy in patients who need to avoid radiation exposure.