Purpose To explore the application value of combining 18F-FDG PET images with interpretable deep learning radiomics(IDLR)models in the differential diagnosis of primary Parkinson's disease(IPD)and atypical Parkinson's syndrome.Materials and Methods This cross-sectional study was conducted using the Parkinson's Disease PET Imaging Benchmark Database from Huashan Hospital,Fudan University from March 2015 to February 2023.A total of 330 Parkinson's disease patients underwent 18F-FDG PET imaging,both 18F-FDG PET imaging and clinical scale information were collected for all subjects.The study included two cohorts,a training group(n=270)and a testing group(n=60),with a total of 211 cases in the IPD group,59 cases in the progressive supranuclear palsy(PSP)group,and a group of 60 patients with multiple system atrophy(MSA).The clinical information between different groups were compared.An IDLR model was developed to extract feature indicators.Under the supervision of radiomics features,IDLR features were selected from the features collected by neural network extractors,and a binary support vector machine model was constructed for the selected features in images of in testing group.The constructed IDLR model,traditional radiomics model and standard uptake ratio model were separately used to calculate the performance metrics and area under curve values of deep learning models for pairwise classification between IPD/PSP/MSA groups.The study conducted independent classification and testing in two cohorts using 100 10-fold cross-validation tests.Brain-related regions of interest were displayed through feature mapping,using gradient weighted class activation maps to highlight and visualize the most relevant information in the brain.The output heatmaps of different disease groups were examined and compared with clinical diagnostic locations.Results The IDLR model showed promising results for differentiating between Parkinson's syndrome patients.It achieved the best classification performance and had the highest area under the curve values compared to other comparative models such as the standard uptake ratio model(Z=1.22-3.23,all P<0.05),and radiomics model(Z=1.31-2.96,all P<0.05).The area under the curve values for the IDLR model in differentiating MSA and IPD were 0.935 7,for MSA and PSP were 0.975 4,for IPD and PSP were 0.982 5 in the test set.The IDLR model also showed consistency between its filtered feature maps and the visualization of gradient-weighted class activation mapping slice thermal maps in the radiomics regions of interest.Conclusion The IDLR model has the potential for differential diagnosis between IPD and atypical Parkinson's syndrome in 18F-FDG PET images.

Objective:To compare the effects of different reference brain regions on the semi-quantitative SUV ratio (SUVR) of 18F-Florzolotau PET images of Alzheimer′s disease (AD). Methods:The 18F-Florzolotau PET images of 28 (13 males, 15 females, age (57.3±9.5) years) normal controls (NC), 19 patients (4 males, 15 females, age (73.3±7.3) years) with β-amyloid (Aβ)-positive mild cognitive impairment (MCI) and 40 patients (19 males, 21 females, age (61.9±9.1) years) with AD were collected from Huashan Hospital, Fudan University between November 2018 and July 2020. Six semi-quantitative reference brain regions were defined, including whole cerebellum (WC), cerebellar gray matter (GM), cerebellar white matter (WM), parametric estimation of reference signal intensity (PERSI), WC after partial volume correction (WC_pvc), cerebellar GM after partial volume correction (GM_pvc). SUVR was calculated for 14 ROIs, which included the whole brain defined by the automated anatomical labeling (AAL) template, fusiform, inferior temporal, lingual, middle temporal, occipital, parahippocampal, parietal, posterior cingulate, precuneus defined by the AAL template, and Meta ROI composed of the above brain regions, and braak_Ⅰ-Ⅱ, braak_Ⅲ-Ⅳ, braak_Ⅴ-Ⅵ defined by the Desikan Killiany template. AUC was used to evaluate the classification ability of SUVR, and the correlation between SUVR and clinical scale scores were assessed by Spearman rank correlation analysis. Results:The SUVRs of most brain regions showed a steady upward trend in the AD disease spectrum. In the classification task of NC and MCI, the overall performance of SUVR based on WC_pvc was relatively optimal (AUCs: 0.975-1.000). In the classification task of NC and AD, SUVRs of 10 ROIs based on the WC_pvc method showed the relatively best performance (AUCs: 0.976-1.000). The correlation between SUVR of fusiform based on cerebellar WM and mini-mental state examination (MMSE) score was the strongest ( rs=-0.72, P<0.001), and the SUVR of precuneus based on WC_pvc showed the strongest correlation with clinical dementia rating (CDR) score ( rs=0.78, P<0.001). Conclusion:The SUVR based on WC_pvc method performs well in classification and correlation tasks, and is recommended to be used in semi-quantification of 18F-Florzolotau PET images of AD.

Objective:A voxel-level quantification method based on the tau IQ algorithm and Braak staging, excluding β-amyloid (Aβ) imaging, was developed to achieve specific tau quantification. Methods:This cross-sectional study included 92 subjects (35 males, 57 females; age (62.9±10.4) years) from the Nuclear Medicine/PET Center of Huashan Hospital, Fudan University between November 2018 and July 2020. The cohort comprised 28 cognitively normal (CN) individuals, 20 patients with mild cognitive impairment (MCI), and 44 patients with Alzheimer′s disease (AD). All participants underwent 18F-florzolotau PET imaging, Mini-Mental State Examination (MMSE), and Clinical Dementia Rating (CDR) scoring. A longitudinal tau dataset was constructed based on Braak staging. Voxel-level logistic regression fitting provided a baseline matrix, decomposed via least squares to yield the Tau load coefficient. One-way analysis of variance (with post hoc Tukey) was used to compare Tau load and SUV ratio (SUVR) among groups. ROC curve analysis was used to evaluate classification between CN, MCI and AD. Spearman rank correlation was used to assess the relationships between Tau load, SUVR, and MMSE scores or CDR scores. Results:The Tau load in the CN group was close to 0 and significantly lower than that in the MCI and AD groups ( F=55.03, P<0.001; post hoc tests all P<0.001). Significant differences were also observed in the SUVR across all ROIs ( F values: 36.46-55.38, all P<0.001). Compared to SUVR, Tau load demonstrated greater intergroup differences. In ROC curve analyses between each pair of CN, MCI, and AD groups, Tau load consistently achieved the highest AUC (0.754-1.000). Both Tau load and SUVR for each ROI were negatively correlated with MMSE scores ( rs values: from -0.698 to -0.583, all P<0.05) and positively correlated with CDR scores ( rs values: 0.648-0.783, all P<0.05), with Tau load showing the highest absolute correlation coefficients. Conclusion:Compared to the traditional semi-quantitative SUVR method, the Braak-tau IQ algorithm does not require a specific reference brain region to achieve specific tau quantification.

Cross-modality reconstruction of medical images refers to predicting the image from one modality to another so as to achieve more accurate personalized medicine. Generative adversarial networks is the most commonly used deep learning technique in cross-modality reconstruction. It can generate realistic images by learning features from implicit distributions that follow the distributions of real data and then reconstruct the image of another modality rapidly. With the sharp increase in clinical demand for multi-modality medical image, this technology has been widely used in the task of cross modal reconstruction between different medical image modalities, such as magnetic resonance imaging, computed tomography and positron emission computed tomography. It can achieve accurate and efficient cross-modality image reconstruction in different parts of the body, such as the brain, heart, etc. In addition, although GAN has achieved some success in cross-modality reconstruction, its stability, generalization ability, and accuracy still need further research and improvement.
Brain/diagnostic imaging* ; Image Processing, Computer-Assisted/methods* ; Magnetic Resonance Imaging/methods* ; Positron-Emission Tomography ; Tomography, X-Ray Computed

Objective:To explore the potential application of combining 18F-FDG PET imaging and radiomics in the diagnosis of Parkinson′s disease (PD) and atypical parkinsonian syndromes (APS). Methods:A total of 154 subjects of two cohorts (training set and validation set) were enrolled from Huashan Hospital, Fudan University from March 2015 to August 2020 in this cross-sectional study, including 40 normal controls (NC; 23 males and 17 females, age: (60.2±10.5) years), 40 PD patients (20 males and 20 females, age: (64.7±6.3) years), 40 progressive supranuclear palsy (PSP) patients (20 males and 20 females, age: (64.1±5.9) years), and 34 multiple system atrophy (MSA) patients (19 males and 15 females, age: (65.0±9.2) years). 18F-FDG PET images and clinical scale were selected, and one-way analysis of variance was used to compare differences of clinical scale among groups. Radiomic features extraction and feature selection were carried out. Two and three classification models were constructed based on logistic regression, and the ROC curves of clinical model, radiomics model and combined model were calculated. Independent classification tests were conducted 100 times with 5-fold cross validation in two cohorts. Results:There were significant differences in the scores of unified PD Rating Scale (UPDRS) and Hoehn-Yahr rating scale (H&Y) among different groups in cohort 1 and cohort 2 respectively ( F values: 4.83-17.95, all P<0.05). A total of 2 444 imaging features were extracted from each subject, and after features selection, 15 features for classification were obtained. In the two classification experiment, the AUCs of the three models in binary classification of PD/MSA/PSP/NC group were 0.56-0.68, 0.74-0.93 and 0.72-0.93, respectively. The classification effects of the radiomics model were significantly better than those of the clinical model ( z values: 1.71-2.85, all P<0.05). In the three classification experiment, the sensitivity of the radiomics model reached 80%, 80% and 77% for PD, MSA and PSP, respectively. Conclusion:18F-FDG imaging combined with radiomics has potential in the diagnosis of PD and APS.

Objective:To analyze the immunotherapy and clinical characteristics of coronavirus disease 2019 (COVID-19) patients, and focus on exploring the effects of immunotherapy and mesenchymal stem cells (MSC) transplantation in the critically ill patients' treatment.Methods:Fity-five COVID-19 patients were admitted to the Fifth People's Hospital of Wuxi from January 23rd to March 31st, 2020 as the research object. The demographic characteristics of the cases and the methods of immunotherapy were analyzed, focusing on the immunized indicators, positivity of pathogens and clinical indicators of critically ill COVID-19 patient, and the effects of immunotherapy and stem cell transplantation were evaluated.Results:Aged, male and people with comorbidities were the main risk factors in the development of severe and critical COVID-19. All of confirmed COVID-19 cases (n = 55) had been treated with interferon-α (IFN-α), of which 81.8% (n = 45, mild and ordinary) of the patients were recovered, 14.6% (n = 8) of the patients were converted to severe, 3.6% (n = 2) of the patients were converted to critical, and some severe patients were treated with gamma globulin and albumin as adjuvant treatment. Critically ill patients were not only treated with IFN-α, gamma globulin and albumin, but also treated with convalescent plasma and MSC transplantation. Due to pulmonary hemorrhage and persistently low blood oxygen saturation, terminal lung transplantation therapy was implemented. The total number of lymphocytes, CD4 +, CD8 + T lymphocytes, natural killer (NK) cells and B cells in peripheral blood of the two critical COVID-19 patients were significantly reduced, and the functions of lung, liver, and kidney were severely damaged on admission, manifested as significant increase of the levels of blood C-reactive protein (CRP), alanine aminotransferase (ALT), aspartate aminotransferase (AST), and blood urea nitrogen (BUN), etc. and decrease of blood oxygen saturation, and type Ⅰ respiratory failure, and the noninvasive assisted ventilation was needed to improve. After adjuvant immunotherapy such as gamma globulin, the nucleic acid of 2019 novel coronavirus (2019-nCoV) turned into negative. The CRP of one critically ill patient was significantly lower than the value at admission (minimum of 21 mg/L). But the lung inflammation progressed rapidly, and the pathological results of the lung tissue from the lung transplantation showed hemorrhage and irreversible fibrosis. The ability to secrete immunoglobulin A (IgA) was significantly reduced. Liver function had been significantly improved and stabilized after treatment with convalescent plasma during the recovery period. MSC transplantation treatment reduced the BUN level by > 50% compared with the previous period, and the total number of lymphocytes in the patient increased by more than 2 times (rose from 0.23×10 9/L to 0.57×10 9/L), but the total amount of lymphocytes was still lower than the normal reference value (< 1.1×10 9/L). The lung inflammation lesions were obviously absorbed, and the vital signs were stable. Conclusions:In addition to IFN, gamma globulin, antiserum and MSC transplantation therapy can help clear the virus and reduce inflammation. Although MSC transplantation fail to completely change the immunecompromised state of critically ill patients, it controlled the progression of inflammation in the liver and kidneys.

Objective:To reveal the abnormal topology of brain network in Alzheimer′s disease (AD), and evaluate the laterality of tau protein deposition in brains of AD patients based on 18F-APN-1607 PET brain imaging combined with graph theory. Methods:From November 2018 to January 2020, 23 clinically diagnosed AD patients (9 males, 14 females; age (61.3±10.7) years) and 13 normal controls (NC) (9 males, 4 females; age (61.6±4.5) years) who underwent 18F-APN-1607 PET imaging in Huashan Hospital, Fudan University were analyzed in this cross-sectional study. The brain network analysis method based on graph theory was used to construct the tau network of the NC group and the AD group, the network attributes (clustering coefficient, shortest path length, local efficiency, and small-worldness) were calculated, and the asymmetry index (AI) of each group to evaluate the laterality of tau protein deposition was obtained. Permutation test (1 000 times) was used to analyze the differences in brain network parameters between the NC group and the AD group. Results:The tau network of the AD group had obvious topological disorder, and the connections in the olfactory cortex and temporal lobe were weakened, while in the posterior cingulate gyrus, anterior wedge, and parietal occipital lobe, the connections were enhanced. Compared with NC group, clustering coefficient ( t values: 2.28-2.69), local efficiency ( t values: 2.34-3.06) and small-worldness ( t values: 2.26-3.32) were significantly decreased in AD group (all P<0.05) with the sparsity of 20%-50%, while the shortest path length was significantly increased ( t values: 2.13-2.85; all P<0.05). There was significant tau laterality in the posterior cingulate gyrus, superior parietal gyrus, paracentral lobule, superior temporal gyrus and middle temporal gyrus (AI: 10.5%(8.1%, 13.9%), 14.1%(7.6%, 20.3%), -12.4%(-15.7%, -7.8%), -10.8%(-15.3%, -2.1%) , -12.1%(-17.9%, -6.6%), respectively). Conclusion:The tau network analysis based on 18F-APN-1607 may be used to reveal abnormal topological changes of AD patients, and the tau deposition in the posterior cingulate gyrus, superior parietal gyrus, paracentral lobule, superior temporal gyrus and middle temporal gyrus has obvious laterality in AD patients.

Objective:Exploring tau related disease pattern (tauRDP) in the brain of Alzheimer′s disease (AD) patients based on 18F-APN-1607 PET scan. Methods:18F-APN-1607 PET images were collected from 17 AD patients (6 males and 11 females, age: (61.7±12.3) years, Mini-Mental State Examination (MMSE) score: 17.6±7.9) and 10 normal controls (NC; 6 males and 4 females, age: (61.2±4.7) years) from Huashan Hospital of Fudan University. The scaled subprofile model (SSM) based on principal component analysis (PCA) technique was used to construct the tauRDP. Then the expression value of tauRDP in each sample was calculated. The differences on tauRDP expression values between AD patients and NC were compared by independent-sample t test. Pearson correlation analysis was used to analyze the correlation between tauRDP expression values and MMSE values in AD patients. Results:The tauRDP area mainly included: precentral gyrus, dorsolateral superior frontal gyrus, middle frontal gyrus, inferior frontal gyrus of opercular part, inferior frontal gyrus of triangular part, supplementary motor area, medial superior frontal gyrus, left median cingulate and paracingulate gyri, right cuneus, superior occipital gyrus, middle occipital gyrus, postcentral gyrus, superior parietal gyrus inferior parietal, but supramarginal and angular gyri, supramarginal gyrus, angular gyrus, precuneus and middle temporal gyrus. There were significant differences ( t=4.395, P<0.001) between AD group (12.6±8.0) and NC group (0.0±1.0) in tauRDP expression values. The tauRDP expression values were correlated with MMSE values in AD group significantly ( r=-0.566, P=0.018). Conclusions:TauRDP established basing on SSM/PCA method can be used to quantitatively express the abnormal spatial distributions of tau deposition. Expression value of tauRDP has the potential to initially assess the severity of AD.

Objective: To explore the topological abnormality of brain metabolic network in patients with idiopathic rapid eye movement sleep behavior disorder (iRBD) and compare it with the topology of brain metabolic network in patients with Parkinson′s disease (PD). Methods: The ¹⁸F-fluorodeoxyglucose (FDG) PET brain images of 19 patients with iRBD diagnosed with polysomnography (PSG) (iRBD group; 15 males, 4 females, average age: 64.9 years), 19 patients with PD (PD group; 12 males, 7 females, average age: 62.2 years) and 19 gender and age-matched healthy controls (HC group; 15 males, 4 females, average age: 63.1 years) in Huashan Hospital from September 2014 to June 2015 were retrospectively analyzed. According to the complex brain network method based on graph theory, the brain metabolic networks of each group was constructed and the network parameters (clustering coefficient, characteristic path length, local efficiency, global efficiency and small-world property, etc) were evaluated quantitatively. The 500 times non-parametric permutation test was used to determine the differences in network parameters between groups. Results: The brain metabolic networks of iRBD group and PD group both had abnormal topological structure, which showed that the characteristic path length (for example, when sparsity=34%, HC vs iRBD vs PD groups: 1.517 vs 1.552 vs 1.561) and local efficiency (for example, when sparsity=30%, HC vs iRBD vs PD groups: 0.802 vs 0.824 vs 0.831) were significantly increased (both P<0.05), the global efficiency (for example, when sparsity=36%, HC vs iRBD vs PD groups: 0.672 vs 0.658 vs 0.656) was significantly decreased (P<0.05). The topology was more aggravated in PD group compared with that in iRBD group. Conclusion The graph-based complex brain network analysis can reveal the abnormal topological structure of the brain metabolic network in which iRBD progresses to PD.

With the advent of social aging, the development of intelligent multifunctional nursing beds that are suitable for hospitals, nursing homes, homes and the like has a wide range of applications, this paper presents an intelligent nursing bed design based on Internet of Things technology. The design uses STM32F103 as the central processor. The design is divided into nursing bed module based on tri-fold structure, central control module based on data processing, weight scale module based on weight detection, power supply module based on system power supply and host computer module based on user operation. The design uses a closed control mode, greatly improving the bed control accuracy. Experimental tests showed that under the action of the intelligent control bed control system, the error rate of bed position information driven bedboard can be less than 2%, which has high accuracy and stability.
Beds ; Equipment Design ; Hospitals ; Internet ; Monitoring, Physiologic ; Nursing Homes ; Technology