The computed tomography angiography (CTA) postprocessing manually recognized by technologists is extremely labor intensive and error prone. We propose an artificial intelligence reconstruction system supported by an optimized physiological anatomical-based 3D convolutional neural network that can automatically achieve CTA reconstruction in healthcare services. This system is trained and tested with 18,766 head and neck CTA scans from 5 tertiary hospitals in China collected between June 2017 and November 2018. The overall reconstruction accuracy of the independent testing dataset is 0.931. It is clinically applicable due to its consistency with manually processed images, which achieves a qualification rate of 92.1%. This system reduces the time consumed from 14.22 ± 3.64 min to 4.94 ± 0.36 min, the number of clicks from 115.87 ± 25.9 to 4 and the labor force from 3 to 1 technologist after five months application. Thus, the system facilitates clinical workflows and provides an opportunity for clinical technologists to improve humanistic patient care.

Background Studies have rarely investigated stenosis detection from head and neck CT angiography scans because accurate interpretation is time consuming and labor intensive. Purpose To develop an automated convolutional neural network-based method for accurate stenosis detection and plaque classification in head and neck CT angiography images and compare its performance with that of radiologists. Materials and Methods A deep learning (DL) algorithm was constructed and trained with use of head and neck CT angiography images that were collected retrospectively from four tertiary hospitals between March 2020 and July 2021. CT scans were partitioned into training, validation, and independent test sets at a ratio of 7:2:1. An independent test set of CT angiography scans was collected prospectively between October 2021 and December 2021 in one of the four tertiary centers. Stenosis grade categories were as follows: mild stenosis (<50%), moderate stenosis (50%-69%), severe stenosis (70%-99%), and occlusion (100%). The stenosis diagnosis and plaque classification of the algorithm were compared with the ground truth of consensus by two radiologists (with more than 10 years of experience). The performance of the models was analyzed in terms of accuracy, sensitivity, specificity, and areas under the receiver operating characteristic curve. Results There were 3266 patients (mean age ± SD, 62 years ± 12; 2096 men) evaluated. The consistency between radiologists and the DL-assisted algorithm on plaque classification was 85.6% (320 of 374 cases [95% CI: 83.2, 88.6]) on a per-vessel basis. Moreover, the artificial intelligence model assisted in visual assessment, such as increasing confidence in the degree of stenosis. This reduced the time needed for diagnosis and report writing of radiologists from 28.8 minutes ± 5.6 to 12.4 minutes ± 2.0 (P < .001). Conclusion A deep learning algorithm for head and neck CT angiography interpretation accurately determined vessel stenosis and plaque classification and had equivalent diagnostic performance when compared with experienced radiologists. © RSNA, 2023 Supplemental material is available for this article.

Although acupuncture is considered to be effective and safe for Alzheimer’s disease (AD) and mild cognitive impairment (MCI), the mechanism underlying its therapeutic effect is still unknown. Most studies clarifying the neuronal pathway produced by acupuncture were still applied to healthy subjects with limited single acupuncture point stimulation, which was inconsistency with clinical practice. Thus, in our present study, we investigate the differences between brain activity changes in AD and MCI patients caused by multi‐acupuncture point Siguan (four gates), in order to provide visualized evidence for neuronal specificity of clinical acupuncture. Forty‐nine subjects were recruited, including 21 AD patients, 14 MCI patients, and 14 healthy controls (HC). AD and MCI patients were randomly divided into two groups, respectively: real acupuncture point group (14 AD and 8 MCI) and sham acupuncture point group (7 AD and 6 MCI). We adopted a 16‐minute, single‐block, experimental design for acquiring functional MRI images. We found, in AD and MCI patients, Siguan (four gates) elicited extensive activations and deactivations in cognitive‐related areas, visual‐related areas, the sensorimotor‐related area, basal ganglia, and cerebellum. Compared with HC, AD and MCI patients showed similar activations in cognitive‐related brain areas (inferior frontal gyrus, supramarginal gyrus, and rolandic operculum) as well as deactivations in cognitive‐related areas, visual‐related areas, basal ganglia, and cerebellum, which were not found in HC. Compared with sham acupuncture points, real acupuncture points produced more specific brain changes with both activated and deactivated brain activities in AD and MCI. The preliminary results in our study verified the objective evidence for neuronal specificity of acupuncture in AD and MCI patients.

Cognitive performance in individuals with mild Alzheimer disease improved following transcranial alternating current stimulation, with increased functional MRI connectivity within cortical networks and between the hippocampus and specific cortical regions.

Objective: Altered functional activities and hypometabolism have been found in medial temporal lobe epilepsy patients with hippocampal sclerosis (mTLE‐HS). Hybrid PET/MR scanners provide opportunities to explore the relationship between resting‐state energy consumption and functional activities, but whether repeated seizures disturb the bioenergetic coupling and its relationship with seizure outcomes remain unknown.Methods: ¹⁸F‐FDG PET and resting‐state functional MRI (rs‐fMRI) scans were performed with hybrid PET/MR in 26 patients with mTLE‐HS and in healthy controls. Energy consumption was quantified by ¹⁸F‐FDG standardized uptake value ratio(SUVR) relative to cerebellum. Spontaneous neural activities were estimated using regional homogeneity (ReHo), fractional amplitude of low frequency fluctuations (fALFF) from rs‐fMRI. Between‐group differences in SUVR and rs‐fMRI derived metrics were evaluated by two‐sample t test. Voxel‐wise spatial correlations were explored between SUVR and ReHo, fALFF across gray matter and compared between groups. Furthermore, the relationships between altered fALFF/SUVR and ReHo/SUVR coupling and surgical outcomes were evaluated.Results: Both the patients and healthy controls showed significant positive correlations between SUVR and rs‐fMRI metrics. Spatial correlations between SUVR and fMRI‐derived metrics across gray matter were significantly higher in patients with mTLE‐HS compared with healthy controls (fALFF/SUVR, P < 0.001; ReHo/SUVR, P = 0.022). Higher fALFF/SUVR couplings were found in patients who had Engel class IA after surgery than all other (P = 0.025), while altered ReHo/SUVR couplings (P = 0.097) were not.Conclusion: These findings demonstrated altered bioenergetic coupling across gray matter and its relationship with seizure outcomes, which may provide novel insights into pathogenesis of mTLE‐HS and potential biomarkers for epilepsy surgery planning.

Clarifying the intrinsic mechanisms of acupuncture’s clinical effects has recently been gaining popularity. Here, we choose the Siguan acupoint (a combination of bilateral LI4 and Liv3) and its sham point to evaluate multiacupoint specificity. Thirty‐one healthy volunteers were randomly divided into real acupoint (21 subjects) and sham acupoint (10 subjects) groups. Our study used a single block experimental design to avoid the influence of posteffects. Functional magnetic resonance imaging data were acquired during acupuncture stimulation. Results showed extensive increase in neuronal activities with Siguan acupuncture and significant differences between stimulation at real and sham points. Brain regions that were activated more by real acupuncture stimulation than by sham point acupuncture included somatosensory cortex (the superior parietal lobule and postcentral gyrus), limbic‐paralimbic system (the calcarine gyrus, precuneus, cingulate cortex, and parahippocampal gyrus), visual‐related cortex (the fusiform and occipital gyri), basal ganglia, and the cerebellum. In this way, our study suggests Siguan may elicit specific activities in human brain.