Objective:To evaluate the performance of deep learning reconstruction (DLR) in visualizing lenticulostriate arteries (LSAs) on cerebral CT angiography (CTA).Methods:This cross-sectional study retrospectively analyzed cerebral CTA from 38 patients who underwent cerebral CTA at the Fourth Affiliated Hospital of Harbin Medical University between January and December 2023. Images were reconstructed using filtered back projection (FBP), three-dimensional adaptive iterative dose reduction (AIDR), and DLR-advanced inteuigent clear-IQ engine(AiCE) algorithms (FBP group, AIDR group, DLR-AiCE group). On axial images, the mean CT values, standard deviation (SD), signal-to-noise ratio (SNR), and contrast-to-noise ratio (CNR) were measured at the origin of LSAs, cerebrospinal fluid in lateral ventricles, temporal muscle, and head of the caudate nucleus. Subjective evaluations were performed for overall vascular visualization and LSAs delineation. Comparisons of subjective and objective evaluation indexes among the 3 groups were performed using the complex measurement ANOVA, Friedman test, or χ2 test. Results:The CT, SD, SNR and CNR values at the origin of LSAs, cerebrospinal fluid in lateral ventricles, temporal muscle, and head of the caudate nucleus demonstrated statistically significance among DLR-AiCE group, AIDR group and FBP group ( P<0.001), in which, except for the difference between the FBP group and the AIDR group in the CT value of the head of the caudate nucleus and the CT value of the cerebrospinal fluid of the lateral ventricle which was not statistically significant ( P>0.05), the remaining pairwise comparisons between the groups for each site measurements were statistically significant ( P<0.001). The difference in the overall comparison of the subjective scores of the overall vessels and LSAs in the images of the DLR-AiCE group, the AIDR group, and the FBP group was statistically significant ( P<0.001), and the two-by-two comparisons showed a statistically significant difference ( P<0.001) except for the difference in the subjective scores of LSAs between the FBP group and the AIDR group. Conclusion:The DLR-AiCE algorithm significantly reduces image noise and improves image quality, enabling superior visualization of LSAs, thereby enhancing diagnostic confidence.

Objective:To evaluate the performance of deep learning reconstruction (DLR) in visualizing lenticulostriate arteries (LSAs) on cerebral CT angiography (CTA).Methods:This cross-sectional study retrospectively analyzed cerebral CTA from 38 patients who underwent cerebral CTA at the Fourth Affiliated Hospital of Harbin Medical University between January and December 2023. Images were reconstructed using filtered back projection (FBP), three-dimensional adaptive iterative dose reduction (AIDR), and DLR-advanced inteuigent clear-IQ engine(AiCE) algorithms (FBP group, AIDR group, DLR-AiCE group). On axial images, the mean CT values, standard deviation (SD), signal-to-noise ratio (SNR), and contrast-to-noise ratio (CNR) were measured at the origin of LSAs, cerebrospinal fluid in lateral ventricles, temporal muscle, and head of the caudate nucleus. Subjective evaluations were performed for overall vascular visualization and LSAs delineation. Comparisons of subjective and objective evaluation indexes among the 3 groups were performed using the complex measurement ANOVA, Friedman test, or χ2 test. Results:The CT, SD, SNR and CNR values at the origin of LSAs, cerebrospinal fluid in lateral ventricles, temporal muscle, and head of the caudate nucleus demonstrated statistically significance among DLR-AiCE group, AIDR group and FBP group ( P<0.001), in which, except for the difference between the FBP group and the AIDR group in the CT value of the head of the caudate nucleus and the CT value of the cerebrospinal fluid of the lateral ventricle which was not statistically significant ( P>0.05), the remaining pairwise comparisons between the groups for each site measurements were statistically significant ( P<0.001). The difference in the overall comparison of the subjective scores of the overall vessels and LSAs in the images of the DLR-AiCE group, the AIDR group, and the FBP group was statistically significant ( P<0.001), and the two-by-two comparisons showed a statistically significant difference ( P<0.001) except for the difference in the subjective scores of LSAs between the FBP group and the AIDR group. Conclusion:The DLR-AiCE algorithm significantly reduces image noise and improves image quality, enabling superior visualization of LSAs, thereby enhancing diagnostic confidence.

Mild cognitive impairment (MCI) is the transitional stage between healthy aging and dementia, enjoying high risk of progression to Alzheimer's disease (AD). Therefore, MCI stage becomes the most important node for early identification, diagnosis and prevention of AD. At present, MCI clinical diagnosis lacks neuroimaging markers with non-invasive, timely and economic advantages. Recent studies suggest that microstructural and/or functional changes may occur in brain regions such as the hippocampus, amygdala, cingulate gyrus, thalamus, putamen, caudate nucleus and corpus callosum during MCI stage, and imaging features of these abnormal changes may serve as neuroimaging markers for early diagnosis of MCI. This article reviews the research progress on the abnormal changes of MCI related brain regions in neuroimaging.

Objective: To investigate the clinical features, morphological characteristics, immunophenotype, and differential diagnosis of goblet cell adenocarcinoma (GCA) in the digestive system. Methods: The clinicopathological data, morphological characteristics, immunophenotypes of 22 cases of GCA in the digestive system diagnosed from January 2010 to January 2021 were collected. Meanwhile, 25 cases of neuroendocrine neoplasm (NEN) and 24 cases of adenocarcinoma were used as controls. Relevant literature was also reviewed. Results: There were 16 males and 6 females, aged from 36 to 79 years with an average of 56 years. The anatomical sites of the 22 GCA were mostly appendix (17 cases) and occasionally extra-appendix (5 cases), including 3 cases in stomach, 1 case in duodenum and 1 case in anal. All 17 cases of appendiceal GCA were pure GCA. Among the 5 cases of extra-appendiceal GCA, One case of gastric GCA was pure, two cases of gastric GCA with NEN or adenocarcinoma, duodenal GCA with NEN and adenocarcinoma, anal GCA with NEN.Low-grade GCAs were composed of goblet, Paneth and neuroendocrine cells, which were arranged in intestinal crypt tubular or cluster structures and distributed in the wall of digestive system. The tubular and cluster structures lacked adhesion. Goblet cells were columnar, located in the base, with clear cytoplasm, small nuclei, inconspicuous atypia, and uncommon mitoses. Extracellular mucus and signet-ring cells with nuclear variations could be seen in some cases. Nerve fiber bundle invasion and tumor thrombus in vessels were often present. High-grade GCAs lacked tubular and cluster structures, and their histological structures were more complex. Tumor cells expressed mixed neuroendocrine and glandular epithelial markers. Similar to the expression patterns of synaptophysin and chromogranin A, CD200 and INSM1 were also dot-like or patch-positive in GCA. Conclusions: GCA is an infrequent tumor of the digestive system and shows the bi-directional differentiation characteristics of neuroendocrine and glandular epithelium. Accurate diagnosis and staging are related to its prognosis.
Adenocarcinoma/pathology* ; Appendiceal Neoplasms/surgery* ; Carcinoid Tumor/surgery* ; Chromogranin A ; Female ; Goblet Cells/pathology* ; Humans ; Male ; Neuroendocrine Tumors/pathology* ; Repressor Proteins ; Synaptophysin

Objective:To investigate the diagnostic value of diffusion weighted imaging and 1H magnetic resonance spectroscopy for the neonatal hypoxic ischemic encephalopathy (HIE).Methods:37 cases of patients with neonatal hypoxic ischemic encephalopathy admitted in our hospital were selected as the study group,another 40 healthy neonates were selected as the control group,both groups of neonates underwent diffusion-weighted imaging and 1H magnetic resonance spectroscopy,ordinary MR1 and diffusion weighted imaging findings of neonates in the study group were observed,the neonatal cerebral metabolic compounds relative concentration were observed and compared between two groups.Results:The detection rate of diffusion-weighted imaging was significantly higher compared with the ordinary MRI (P＜0.05).The relative ratio of brain metabolic compounds NAA/Cr of study group were obviously lower than those of the control group,while the Cho/Cr,MI/Cr,Glu-Glr/Cr,Lac/Cr were significantly higher (P＜0.05).Conclusion:Diffusion weighted imaging combined with 1H magnetic resonance spectroscopy could improve the diagnostic accuracy of neonatal hypoxic ischemic encephalopathy,the analysis of the concentrations of brain metabolic compounds could contribute to evaluate the severity of HIE.