Discrepancy between two-dimensional and three-dimensional digital subtraction angiography for the planning of endovascular coiling of small cerebral aneurysms <5 mm

Deep Learning-Based Digital Subtraction Angiography Characteristics in Nursing of Maintenance Hemodialysis Patients

This study is aimed at exploring the diagnostic value of digital subtraction angiography (DSA) based on faster region-based convolutional networks (Faster-RCNN) deep learning for maintenance hemodialysis (MHD) diseases and to provide a theoretical basis for clinical nursing. A total of 50 MHD patients who were clinically diagnosed in the Blood Purification Center were randomly divided into the control group and the experimental group (25 cases for each group). The control group was given routine nursing intervention, and the experimental group was given overall nursing intervention under the supervision of DSA. A faster RCNN multitarget detection network was constructed to analyze the average accuracy of various vascular structures in the test set. The self-rating anxiety scale (SAS) and self-rating depression scale (SDS) were used to evaluate the degree of anxiety and depression. The urine volume before and after the operation, local hematoma after a puncture, the incidence of complications, and nursing satisfaction were recorded. The results showed that the average accuracy of the vein, internal carotid artery, circle of Willis, venous sinus, and venous vessels was 0.876, 0.916, 0.994, 0.925, and 0.732, respectively. The success rate of surgery in the experiment group was higher than that in the control group, and the difference had statistical significance (P < 0.05). The SAS score and SDS score in the experimental group were significantly lower than those in the control group (P < 0.05). The total incidence rate of complications in the experimental group (16.00%) was significantly lower than that in the control group (44.00%) (P < 0.05). The satisfaction rate of the experimental group was significantly higher than that of the control group (P < 0.05). The Faster-RCNN model had the best effect in differentiating the circle of Willis and a poor effect in differentiating venous vessels. DSA based on Faster-RCNN can significantly improve the success rate of puncture in MHD patients. The implementation of holistic nursing intervention under its supervision can significantly reduce postoperative complications and improve patient satisfaction with nursing compared with routine nursing.

Points to consider when evaluating three-dimensional digital subtraction angiography of intracranial aneurysms and their effects on treatment

Background/aim

In this study, we aimed to investigate what should be regarded as potential determinants of treatment strategies when evaluating 3D digital subtraction angiography (DSA) images.

Material and methods

Our inclusion criteria were as follows: (1) presence of at least one intracranial aneurysm demonstrated by conventional angiography, (2) having both 2D and 3D images, and (3) being over 18 years old. First, two-dimensional (2D) and then 3D angiography images of 226 aneurysms of 150 patients were scanned. Morphological characteristics such as size, configurations, relationship with parent artery, baby counts, and other incidental findings were determined.

Results

Of the 226 aneurysms, 11 (4.9%) were only detected on 3D images. Four of these 11 additional aneurysms were believed to be babies of other aneurysms seen in 2D images. Middle cerebral artery (MCA) M1 segment was the most common localization in terms of missed aneurysms. Of the 28 aneurysms located in the communicating segment of the internal carotid artery, the absolute locations of 7 (25%) could not be detected in 2D images or detected in the wrong location. Of the 24 aneurysms located in the ophthalmic segment, the origin of 8 (33%) could not be clearly identified in 2D images. Truncus relationships of MCAs bifurcation/trifurcation aneurysms were seen in 41 of 63 aneurysms (65%) on 2D images, whereas all were confirmed on 3D images. Fenestrations not seen in 2D images were identified in 3D images of 4 patients (3%).

Conclusion

The superiority of 3D images compared to 2D images in determining the morphologic characteristics of intracranial aneurysms has been known for a long time. The contribution of 3D images to the treatment can be summarized as evaluating the parent artery relationship, revealing the number and shapes of aneurysm babies more clearly, detecting fenestrations, and shortening procedure time by finding the correct working angle.