Development and validation of a multi-modality fusion deep learning model for differentiating glioblastoma from solitary brain metastases / 中南大学学报(医学版)

Objective:Glioblastoma(GBM)and brain metastases(BMs)are the two most common malignant brain tumors in adults.Magnetic resonance imaging(MRI)is a commonly used method for screening and evaluating the prognosis of brain tumors,but the specificity and sensitivity of conventional MRI sequences in differential diagnosis of GBM and BMs are limited.In recent years,deep neural network has shown great potential in the realization of diagnostic classification and the establishment of clinical decision support system.This study aims to apply the radiomics features extracted by deep learning techniques to explore the feasibility of accurate preoperative classification for newly diagnosed GBM and solitary brain metastases(SBMs),and to further explore the impact of multimodality data fusion on classification tasks. Methods:Standard protocol cranial MRI sequence data from 135 newly diagnosed GBM patients and 73 patients with SBMs confirmed by histopathologic or clinical diagnosis were retrospectively analyzed.First,structural T1-weight,T1C-weight,and T2-weight were selected as 3 inputs to the entire model,regions of interest(ROIs)were manually delineated on the registered three modal MR images,and multimodality radiomics features were obtained,dimensions were reduced using a random forest(RF)-based feature selection method,and the importance of each feature was further analyzed.Secondly,we used the method of contrast disentangled to find the shared features and complementary features between different modal features.Finally,the response of each sample to GBM and SBMs was predicted by fusing 2 features from different modalities. Results:The radiomics features using machine learning and the multi-modal fusion method had a good discriminatory ability for GBM and SBMs.Furthermore,compared with single-modal data,the multimodal fusion models using machine learning algorithms such as support vector machine(SVM),Logistic regression,RF,adaptive boosting(AdaBoost),and gradient boosting decision tree(GBDT)achieved significant improvements,with area under the curve(AUC)values of 0.974,0.978,0.943,0.938,and 0.947,respectively;our comparative disentangled multi-modal MR fusion method performs well,and the results of AUC,accuracy(ACC),sensitivity(SEN)and specificity(SPE)in the test set were 0.985,0.984,0.900,and 0.990,respectively.Compared with other multi-modal fusion methods,AUC,ACC,and SEN in this study all achieved the best performance.In the ablation experiment to verify the effects of each module component in this study,AUC,ACC,and SEN increased by 1.6%,10.9%and 15.0%,respectively after 3 loss functions were used simultaneously. Conclusion:A deep learning-based contrast disentangled multi-modal MR radiomics feature fusion technique helps to improve GBM and SBMs classification accuracy.

Research on lung function prediction methodology combining transfer learning and multimodal feature fusion / 国际生物医学工程杂志

Objective:To design a lung function prediction method that combines transfer learning and multimodal feature fusion, aiming to improve the accuracy of lung function prediction in patients with idiopathic pulmonary fibrosis (IPF).Methods:CT images and clinical text data were reprocessed, and an adaptive module was designed to find the most suitable lung function attenuation function for IPF patients. The feature extraction module was utilized to comprehensively extract features. The feature extraction module comprises three sub-modules, including CT feature extraction, clinical text feature extraction, and lung function feature extraction. A multimodal feature prediction network was used to comprehensively evaluate the attenuation of lung function. The pre-trained model was fine-tuned to improve the predictive performance of the model.Results:Based on the OSIC pulmonary fibrosis progression competition dataset, it is found through the adaptive module that the linear attenuation hypothesis is more in line with the trend of pulmonary function decline in patients. Different modal data prediction experiments show that the model incorporating clinical text features has better predictive ability than the model using only CT images. The model combining CT images, clinical text features, and lung function features have optimal predictive results. The lung function prediction method combining transfer learning and multimodal feature fusion has modified version of the Laplace log likelihood (LLLm) of ?6.706 5, root mean squared error (RMSE) of 184.5, and mean absolute error (MAE) of 146.2, which outperforms other methods in terms of performance. The pre-trained model has higher prediction accuracy compared to the zero base training model.Conclusions:The lung function prediction method designed by combining transfer learning and multimodal feature fusion can effectively predict the lung function status of IPF patients at different weeks, providing important support for patient health management and disease diagnosis.

Application of nanomaterials in tumor imaging diagnosis / 肿瘤

Malignant tumors have become one of the major diseases that seriously endanger human life.Early diagnosis and treatment can greatly improve the survival rate of patients.Imaging examinations based on fluorescence imaging,CT,photoacoustic imaging,MRI,and PET have been widely studied and applied in the diagnosis of tumors.However,early cancerous tissue and normal tissue have similar imaging signals,which is difficult to be accurately distinguished by conventional imaging.With the development and cross integration of physics,materials science,biology,and medicine,nanomaterials have shown broad application prospects in the diagnosis and treatment of diseases due to their unique physical and chemical properties.The enhanced permeability and retention effect in solid tumor,and the easy modification properties of nanomaterials allow them to accurately"recognize"tumor and accelerate its enrichment at the tumor site;the imaging characteristics allow them to be used as contrast agents to enhance the signal intensity of the tumor site;their responsiveness mechanism can also allow them to distinguish normal from cancerous cells according to the microenvironment in tumor cells.In addition,multimodality imaging based on nanomaterials can compensate for the shortcomings of single modality imaging and achieve real-time and omnidirectional imaging of tumors.With multiple functions integrated,nanomaterials are expected to enhance the imaging signals of early cancerous sites,improve signal-to-noise ratio,and achieve early diagnosis of tumors.

Multimodality imaging and specific targeting probes for primary liver cancer / 肿瘤

Primary liver cancer(PLC)is one of the most common malignant diseases with the highest incidence and mortality rate,which poses a serious threat to public health in China.Thus,it is crucial to realize the early and accurate diagnosis of PLC.In clinical practice,traditional imaging techniques can provide the morphological information of liver cancer tissues,but they still have some limitations.Multimodality imaging can provide more comprehensive diagnostic information by integrating the advantages of different imaging technologies.By using liver cancer-specific targeting probes,multimodality imaging technology can achieve higher sensitivity and specificity than traditional imaging techniques.It can not only help with the accurate diagnosis of liver cancer by providing the structural and functional information of PLC simultaneously,but also guide surgeons to make better intraoperative decisions for PLC patients by supporting real-time navigation imaging during surgery.Therefore,multimodality imaging is of great significance to the clinical diagnosis and treatment of PLC.This review mainly focuses on the multimodality imaging technology and specific targeting probes of PLC,and summarizes the current research progress in this field.

Research progress of imaging technology in the diagnosis and application of hepatic fibrosis / 中国医学装备

Liver fibrosis(LF),as a global public health issue,has become increasingly recognized and valued by the more and more publics.Almost all types of chronic liver diseases can cause LF.The active and effective interventions can delay or prevent the progression of LF disease conditions,and even achieve partial normalization outcome of that.The conventional"gold standard"of diagnosing LF is liver biopsy,but this examination method is invasive,which exists disadvantages included a certain risks and the lower patient acceptance.Therefore,it is difficult to widely carry out this examination in clinical practice.Imaging examination,as a non-invasive assessment method for LF,can achieve quantitative,qualitative and functional detection,which can provide convenience for diagnosing and treating LF.Common imaging examination methods include ultrasound,computed tomography(CT),magnetic resonance imaging(MRI),nuclear medicine,etc.This review summarizes the relevant researches that imaging technology assesses LF,and discusses the important role of that in clinical diagnosis,treatment and scientific research.

Una reflexión multimodal sobre los contenidos educativos construidos en imagen y video en el marco de una propuesta educativa para la salud / A Multimodal Reflection on the Educational Contents Constructed in Image and Video within the Framework of an Educational Proposal for Health

Resumen Cuando los procesos de construcción de contenidos digitales se producen con escaza participación de la comunidad, las decisiones sobre el significado pasan por la interpretación de técnicos y profesionales expertos que tienen otra lectura del mundo y en algunos casos se termina en procesos de exclusión desde el mismo significado que se presenta. Debido a la toma de decisiones que surge entre una temática y el modo que se elige, se presenta como reto una participación amplia de las comunidades para crear contenidos formativos en el marco de la Educativos para la Salud (EpS).

Abstract: When the processes of construction of digital contents are produced with little participation of community, decisions about the meaning go through the interpretation of technical and professional experts, who have another reading of the world and, in some cases, end up in processes of exclusion from the same meaning that is presented. Due to the decision making that arises between a theme and the way it is chosen, a broad participation of communities to create formative contents within the framework of Education for Health (EpS) is presented as a challenge.

Construction of a quantitative diagnosis model for predicting the nature of thyroid nodules based on multi-modality ultrasound images / 中华超声影像学杂志

Objective:To construct a quantitatively diagnostic nomogram model by analyzing the clinical information of patients and the features of multi-modality ultrasound images of thyroid lesions, so as to preoperatively predict the malignant probability of suspicious thyroid nodules and provide effective references for clinical decision-making.Methods:A total of 933 patients, 1 121 thyroid nodules of C-TIRADS 3-5 categories, who underwent surgery in the Second Affiliated Hospital of Harbin Medical University from September 1, 2020 to June 10, 2021 were collected. The nodules were randomly divided into training ( n=897) and test groups ( n=224) in 8∶2 ratio. Finally, the diagnostic performance was evaluated by area under the curve (AUC). Results:①After preliminary screening by univariate analysis, multivariate analysis showed that age, echogenicity, orientation, echogenic foci, margin, posterior features, and elastic score were significantly correlated with benign and malignant nodules (all P<0.001), and the difference of halo between benign and malignant nodules was also statistically significant ( P=0.012). ②The AUC of nomogram was up to 0.903(95% CI=0.862-0.944) in the test set, and 0.889(95% CI=0.832-0.946) and 0.960(95% CI=0.925-0.994) in nodules with maximum diameter of ≤10 mm and of >10 mm respectively, which showed high diagnostic performance. Conclusions:The nomogram model could accurately differentiate malignant from benign thyroid nodules preoperatively, with the highest diagnostic performance for the nodules with maximum diameter of >10 mm, and effectively avoid the unnecessary fine-needle biopsy and surgical operation.

Multimodality-based super-resolution reconstruction for routine brain magnetic resonance images / 南方医科大学学报

OBJECTIVE@#To propose a multi-modality-based super-resolution synthesis model for reconstruction of routine brain magnetic resonance images (MRI) with a low resolution and a high thickness into high-resolution images.@*METHODS@#Based on real paired low-high resolution MRI data (2D T1, 2D T2 FLAIR and 3D T1), a structure-constrained image mapping network was used to extract important features from the images with different modalities including the whole T1 and subcortical regions of T2 FLAIR to reconstruct T1 images with higher resolutions. The gray scale intensity and structural similarities between the super-resolution images and high-resolution images were used to enhance the reconstruction performance. We used the anatomical information acquired from segment maps of the super-resolution T1 image and the ground truth by a segmentation tool as a significant constraint for adaptive learning of the intrinsic tissue structure characteristics of the brain to improve the reconstruction performance of the model.@*RESULTS@#Our method showed the performance on the testing dataset than other methods with an average PSNR of 33.11 and SSIM of 0.996. The anatomical structure of the brain including the sulcus, gyrus, and subcortex were all reconstructed clearly using the proposed method, which also greatly enhanced the precision of MSCSR for brain volume measurement.@*CONCLUSION@#The proposed MSCSR model shows excellent performance for reconstructing super-resolution brain MR images based on the information of brain tissue structure and multimodality MR images.

Diagnostic value of 18F-fluorodeoxyglucose PET/MRI multimodal imaging in grading of adult diffuse gliomas / 中华神经医学杂志

Objective:To investigate the diagnostic value of integrated 18F-fluorodeoxyglucose (FDG) PET/MRI multimodal imaging in the grading of adult diffuse gliomas. Methods:A retrospective analysis was performed; 29 patients accepted cranial 18F-FDG PET/MRI multimodal imaging and diagnosed as having adult diffuse gliomas in our center from January 2020 to December 2021 were chosen; their clinical and image data were collected. These patients were divided into low-grade group (WHO grading II, n=13) and high-grade group (WHO grading III and IV, n=16) according to the pathological results confirmed by surgery or biopsy. T1WI, T2WI, DWI, arterial spin labeling (ASL), magnetic resonance spectroscopy (MRS) and PET were performed in these patients. Differences in T1WI and T2WI signs between the two groups were compared. Differences in maximum standard uptake value (SUV max), apparent diffusion coefficient (ADC), choline/ N-acetylaspartate (Cho/NAA), NAA/creatine (Cr), Cho/Cr, relative cerebral blood flow (rCBF) between the two groups were compared. The diagnostic efficacies of above parameters in differentiating high-grade from low-grade adult diffuse gliomas were determined by receiver-operating characteristic (ROC) curves. The predictive probabilities for differentiating high-grade from low-grade adult diffuse gliomas using combined parameters were obtained by binary Logistic regression analysis. Results:There were no statistical differences in T1WI and T2WI signs, proportion of adjacent parenchyma edema, proportion of crossing the midline into the contralateral side, proportion of mass effect, proportion of cystic degeneration/necrosis, or site of growth between low-grade and high-grade groups ( P>0.05). The values of SUV max, ADC, Cho/NAA, Cho/Cr and rCBF were statistically different between the two groups, and the order of diagnostic efficiency was SUV max>ADC>Cho/NAA>rCBF>Cho/Cr>NAA/Cr. SUV max had the highest diagnostic efficacy in differentiating high-grade from low-grade adult diffuse gliomas with an area under the curve (AUC) of 0.894, a sensitivity of 75% and a specificity of 100%; the diagnostic efficacy of combined parameters (mean AUC>0.9) was higher than that of single parameter, and the combined parameters of SUV max and Cho/NAA showed the highest diagnostic efficacy with an AUC of 0.933, a sensitivity of 81.3% and a specificity of 92.3%. Conclusion:The 18F-FDG PET/MRI multimodal imaging is helpful in the grading diagnosis of adult diffuse gliomas, and combination of PET and MRS may play a greater role.

The clinical research of multi-modality assessment-based strategies for intravenous thrombolysis in acute mild ischemic stroke patients / 中风与神经疾病杂志

@#Objective　To evaluate the efficacy and safety of intravenous thrombolysis in acute mild ischemic stroke patients (National Institution of Health Stroke Scale≤5),moreover,to verify the effectiveness of multi-modality assessment in screening high-risk patients.Methods　We retrospectively included 227 patients identified with acute mild neurological deficits treated with or without intravenous thrombolysis.Odds ratios (OR) with their confidence intervals (CI) for different outcomes between groups were assessed by using multivariable binary logistic regression analyses.And the heterogeneity of treatment effect magnitude for excellent outcome［modified Rankin scale (mRS) 0~1 was estimated in different subgroups stratified by optimal cut-off value from receiver operating characteristic curve.Results　In multivariate analysis,intravenous thrombolysis could both achieve higher rate of excellent outcome(OR=3.302，95%CI1.488~7.326，P=0.003) and 7 day significant improvement (OR=2.566，95%CI1.287~5.118，P=0.007).However,there was no significant difference in the risk of early neurological deterioration,intracranial hemorrhage transformation or the 90 day stroke recurrence(P>0.05).It is indicated from the subgroup analysis that,compared with non-thrombolytic group,the classification of large artery atherosclerosis(OR=9.448，95%CI1.129~79.035，P=0.038) and baseline ABCD-2 score of 5 or more(OR=2.664，95%CI1.150~6.168，P=0.022) might benefit more from intravenous thrombolysis.Conclusion　For acute mild ischemic stroke patients,we reassured the safety and especially the efficacy of intravenous thrombolysis at 7 days and 90 days.Patients with ABCD-2 score of 5 or more and classification of large artery atherosclerosis might benefit more from intravenous thrombolytic therapy.

Metáforas da lama: multimodalidade e argumentação em discursos sobre sustentabilidade e rompimento de barragens de rejeitos de minério de ferro / Metaphors of the mud: multimodality and argumentation in discourses about sustainability and the rupture of tailings dams of iron ore

As barragens de rejeito de minério de ferro fazem parte do processo de mineração no Brasil. Trata-se de uma técnica antiga envolvendo diversas tecnologias para torná-la mais segura. A constante vigília e cuidado sobre essas estruturas tornaram-se uma rotina frequente das mineradoras para evitar possíveis rupturas dessas barragens. Após o rompimento da barragem de rejeitos de minério em Brumadinho-MG e Mariana-MG muitos discursos com elementos metafóricos acerca da sustentabilidade e a prática de uso de barragens de rejeitos foram sustentados por uma intencionalidade discursiva voltada para a crítica social. O objetivo deste estudo é identificar e analisar o uso de metáforas conceptuais presentes como elementos multimodais na argumentação textual, numa perspectiva sociocognitiva e interacional da linguagem. Para isso, adota-se uma pesquisa expo-facto. O viés teórico da intencionalidade discursiva na linha de Searle; o caráter de modelos mentais, representações sociais e conhecimento sociocultural tal com prevê Van Dijk, a visão sociosemiótica de Geeraerts para compreender como argumentação por meio do campo imagético das charges é construída e sustentada socialmente e o dialogismo na perspectiva de Meyer a partir da argumentação. Nessa perspectiva sociocognitiva e interacional, o texto é pensado como uma construção linguístico-discursiva na qual a intencionalidade está relacionada com os modelos mentais resultantes de representações construídas a partir da experiencia do sujeito em sociedade e das práticas interacionais. Nesse contexto, o texto contempla uma gama de operações cognitivas interligadas como direciona Marscuschi. Constitui-se um corpus de charges publicadas na mídia brasileira, orientadas para a temática do rompimento de barragens de rejeitos de minério de ferro para a análise do aparecimento de metáforas conceptuais. Conclui-se que as metáforas se constituem recursos multimodais na orientação argumentativa e revelam metáforas do medo e da lama envolvendo um discurso do horror sobre a tragédia das cidades de Brumadinho e Mariana.

Iron ore tailings dams are part of the mining process in Brazil. It is an old technique involving several technologies to make it more secure. Constant vigilance and care about these structures have become a frequent routine for mining companies to avoid possible failures of these dams. After the collapse of the ore tailings dam in Brumadinho (MG) and Mariana (MG) cities, many discourses with metaphorical elements about sustainability and the practice of using tailings dams were supported by a discursive intentionality focused on social criticism. The aim of this study is to identify and analyze the use of conceptual metaphors present as multimodal elements in textual argumentation, in a sociocognitive and interactional perspective of language. For this, it is adopted from expo-facto research. The theoretical bias of discursive intentionality along the lines of Searle; the character of mental models, social representations,and sociocultural knowledge as predicted by Van Dijk, the sociosemiotic vision of Geeraerts (2016) to understand how argumentation through the imagery field of cartoons is constructed and socially supported and dialogism in perspective of Meyer from the argumentation. In this sociocognitive and interactional perspective, the text is thought of as a linguistic-discursive construction in which intentionality is related to mental models resulting from representations built from the subject's experience in society and interactional practices. In this context, the text contemplates a range of interconnected cognitive operations as directed by Marscuschi. A corpus of cartoons published in the Brazilian media is constituted, oriented to the theme of breaking up iron ore tailings dams for the analysis of the appearance of conceptual metaphors. It is concluded that metaphors are multimodal resources in the argumentative orientation and reveal metaphors offear and mud involving a horror speech about the tragedy of the cities of Brumadinho and Mariana.

Imaging study of lymphomatosis cerebri characterized by diffuse lesions of bilateral cerebral white matter / 中华神经科杂志

Objective:To investigate multimodality imaging characteristics and clinical features of lymphomatosis cerebri (LC) and reasons for misdiagnosis,with the goal of potentially facilitating an early and accurate diagnosis for this often-missed disease.Methods:Clinical data and cerebral multimodality imaging findings from 11 patients with LC proven basing on pathology in the Affiliated Hospital of Guizhou Medical University from November 30, 2011 to December 28, 2020 were retrospectively extracted, analyzed, and reviewed in combination with the literatures.Results:The common presenting symptoms with subacute onset included cognitive decline (8/11), gait disturbance (9/11), and behavioral disturbance (5/11). Test of cerebrospinal fluid showed that the number of cells and the level of protein increased (8/10), the sugar content (2/10) and chloride (4/10) decreased. The imaging manifestations of 11 patients with LC were diffuse lesions of bilateral cerebral white matter in the both deep and lobar lesion distribution, involving the cerebral cortex and subcortical white matter in eight cases (8/11), basal ganglia in seven cases (7/11), thalamus in five cases (5/11), cerebellum in six cases and brain stem in six cases (6/11). All 11 patients showed equal or slightly low-density shadows on CT plain scan and slightly longer T 1WI and T 2WI signals on magnetic resonance imaging. Six cases (6/11) had no obvious enhancement in the early stage, and five cases and six follow-up cases showed heterogenous spots, patches, nodules or clusters of distinct enhancement. Diffusion-weighted imaging showed non restricted diffusion in nine (9/11) cases initially diagnosed, and restricted diffusion in two cases (2/11) and nine follow-up cases, which were hyperintense on diffusion-weighted imaging and hypointense on apparent diffusion coefficient maps. Five patients (5/5) presented a marked decrease in N-acetyl aspartic acid (NAA)/creatine (Cr) and increase in choline (Cho)/Cr on hydrogen proton magnetic resonance spectrum, including an increase in lipid/Cr in three cases. One case (1/3) showed no abnormal increase in lesion metabolism, and two cases (2/3) showed slightly increased uptake on positron emission tomography/CT. Conclusions:Diffuse bilateral cerebral lesions especially in deep and lobar region, without enhancement or with patchy enhancement, marked decrease in NAA/Cr and increase in Cho/Cr and Lip/Cr are suggestive of LC. Misdiagnosis may be mainly due to insufficient understanding and improper brain biopsy.

Application of multi-modal digital MOOCs teaching in the standardized residency training of obstetrics and gynecology / 中华医学教育探索杂志

Objective:To explore the application of multi-modal digital massive open online courses (MOOCs) mode in the standardized residency training of obstetrics and gynecology.Methods:A total of 40 residents who entered the training program of obstetrics and gynecology from September 2018 to February 2020 were selected as the control group, and 40 residents from March 2020 to August 2020 were selected as the study group. The control group adopted the traditional teaching method, and the study group adopted the multi-modal digital MOOCs teaching method. The scores of theoretical examination and skill operation examination after the standardized training, clinical ability examination before and after the standardized training and teaching satisfaction were compared between the two groups. SPSS 22.0 was performed for t test and chi-square test. Results:After the standardized training, the scores of theoretical knowledge [(88.53±6.04) vs. (79.67±5.52)] and skill operation [(85.52±6.33) vs. (71.15±7.86)] in the study group were significantly higher than those in the control group ( P < 0.05). After the standardized training, the scores of all kinds of clinical ability of the two groups were higher than before ( P < 0.05), and the scores of all items in study group were higher ( P < 0.05). The satisfaction of all aspects of teaching in the study group was higher than that in the control group ( P < 0.05). Conclusion:The application of multi-modal digital MOOCs teaching mode in the standardized residency training of obstetrics and gynecology can strengthen the learning and mastering of theoretical knowledge, operational skills and the cultivation of clinical ability, and significantly improve the quality of teaching with high teaching satisfaction.

Interpretation of the 2020 American society of colon and rectal surgeons clinical practice guidelines for the management of rectal cancer / 中华胃肠外科杂志

Located in the pelvic cavity and contiguous to the anal sphincter complex and urogenital organs, the rectum has more intricate anatomical features compared with the colon. Consequently, the treatment of rectal cancer involves more consideration, including pelvic radiation, lateral lymph node dissection, transanal access, postoperative function, sphincter preservation, and nonoperative management. Based on the last set of American society of colon and rectal surgeons (ASCRS) practice parameters for the management of rectal cancer published in 2013, the 2020 guidelines present evidence-based updates for both long-existing and emerging controversies on surgical management of rectal cancer. These updates include the indication for local resection, lymph node dissection for radical proctectomy, minimally invasive surgery, the "watch and wait" strategy for patients with clinical complete response, and prevention of anastomotic leak. Meanwhile, the guidelines recommend a risk-stratified approach for perioperative therapies for non-metastatic disease, and an individualized multimodality treatment based on treatment intent for synchronous metastatic disease.

A review on integration methods for single-cell data / 生物医学工程学杂志

The emergence of single-cell sequencing technology enables people to observe cells with unprecedented precision. However, it is difficult to capture the information on all cells and genes in one single-cell RNA sequencing (scRNA-seq) experiment. Single-cell data of a single modality cannot explain cell state and system changes in detail. The integrative analysis of single-cell data aims to address these two types of problems. Integrating multiple scRNA-seq data can collect complete cell types and provide a powerful boost for the construction of cell atlases. Integrating single-cell multimodal data can be used to study the causal relationship and gene regulation mechanism across modalities. The development and application of data integration methods helps fully explore the richness and relevance of single-cell data and discover meaningful biological changes. Based on this, this article reviews the basic principles, methods and applications of multiple scRNA-seq data integration and single-cell multimodal data integration. Moreover, the advantages and disadvantages of existing methods are discussed. Finally, the future development is prospected.

Clinical study on diagnosis of myocardial fibrosis by soluble suppression of tumorigenicity 2, galectin-3 combined with magnetic resonance multimodality / 中国医师进修杂志

Objective:To explore the application value of soluble tumor suppressor 2 (SST2), galectin-3 combined with magnetic resonance multimodality in the diagnosis of myocardial fibrosis.Methods:The clinical data of 88 patients with cardiomyopathy from January 2017 to December 2019 in Handan Central Hospital of Hebei Province were retrospectively analyzed as the experimental group, and 100 healthy people in the same period were selected as the control group. According to the results of cardiac magnetic resonance imaging (CMRI)-late gadolinium enhanced (LGE), the patients with cardiomyopathy were divided into LGE positive and LGE negative. The arrhythmia rate was evaluated by ambulatory electrocardiogram. The New York Heart Association (NYHA) cardiac function grade was recorded. The left ventricular ejection fraction (LVEF) and left ventricular end diastolic diameter (LVEDD) were detected by echocardiography. The SST2, galectin-3 and N-terminal pro-brain natriuretic peptide (NT-proBNP) were detected by enzyme-linked immunosorbent assay (ELISA). The receiver operating characteristic (ROC) curve was drawn to analyze the efficacy of SST2 and Galectin-3 in predicting myocardial fibrosis in patients with cardiomyopathy.Results:CMRI-LGE results of 88 patients with cardiomyopathy showed that LGE was positive in 42 cases and negative in 46 cases. The arrhythmia rate, LVEDD, SST2 and galectin-3 in experimental group were significantly higher than those in control group: 67.05% (59/88) vs. 2.00% (2/100), (46.55 ± 5.99) mm vs. (27.92 ± 2.05) mm, (61.83 ± 10.57) μg/L vs. (24.99 ± 7.69) μg/L and (18.65 ± 3.39) μg/L vs. (7.12 ± 1.33) μg/L, the LVEF was significantly lower than that in control group: (55.11 ± 8.36)% vs. (68.83 ± 9.45)%, and there were statistical differences ( P<0.01). The arrhythmia rate, NYHA cardiac function grade, LVEDD, SST2 and galectin-3 in patients with LGE positive were significantly higher than those in patients with LGE negative: 88.10% (37/42) vs. 47.83% (22/46), (3.10 ± 0.53) grade vs. (2.11 ± 0.61) grade, (48.88 ± 5.95) mm vs. (44.41 ± 5.24) mm, (65.58 ± 11.73) μg/L vs. (58.40 ± 8.10) μg/L and (21.00 ± 2.72) μg/L vs. (16.51 ± 2.39) μg/L, the LVEF was significantly lower than that in patients with LGE negative: (52.15 ± 8.23)% vs. (57.82 ± 7.60)%, and there were statistical differences ( P<0.01). ROC curve analysis result showed that the optimal critical values of serum SST2 and galectin-3 for predicting myocardial fibrosis in patients with cardiomyopathy were 65.07 μg/L and 18.46 μg/L, the area under the curve was 0.714 (95% CI 0.604 to 0.825, P = 0.001) and 0.894 (95% CI 0.828 to 0.960, P = 0.001), the sensitivity was 61.9% and 85.7%, and the specificity was 80.4% and 82.6%. Conclusions:Magnetic resonance multimodality has a good ability in detecting myocardial fibrosis, and serum SST2 and galectin-3 have good predictive value for myocardial fibrosis. SST2 and galectin-3 combined with magnetic resonance multimodality has important clinical significance in the diagnosis of myocardial fibrosis.

A review on the application of UK Biobank in neuroimaging / 生物医学工程学杂志

UK Biobank (UKB) is a forward-looking epidemiological project with over 500, 000 people aged 40 to 69, whose image extension project plans to re-invite 100, 000 participants from UKB to perform multimodal brain magnetic resonance imaging. Large-scale multimodal neuroimaging combined with large amounts of phenotypic and genetic data provides great resources to conduct brain health-related research. This article provides an in-depth overview of UKB in the field of neuroimaging. Firstly, neuroimage collection and imaging-derived phenotypes are summarized. Secondly, typical studies of UKB in neuroimaging areas are introduced, which include cardiovascular risk factors, regulatory factors, brain age prediction, normality, successful and morbid brain aging, environmental and genetic factors, cognitive ability and gender. Lastly, the open challenges and future directions of UKB are discussed. This article has the potential to open up a new research field for the prevention and treatment of neurological diseases.

Supradesnivel del segmento ST como forma de presentación atípica de un tumor cardíaco: rol diagnóstico de la multimodalidad de imagen / ST segment elevation as an atypical presentation of a cardiac tumor: diagnostic role of a multimodal imaging approach / Elevação do segmento ST como apresentação de tumor cardíaco: papel diagnóstico da multimodalidade de imagem

Los tumores cardíacos malignos son neoplasias poco frecuentes que pueden presentarse de diversas formas, lo que dificulta su diagnóstico. La ecocardiografía y la resonancia magnética cardíaca son técnicas fundamentales para el diagnóstico, la caracterización y la evaluación de su extensión tumoral. La identificación de la línea tumoral es esencial al iniciar un tratamiento oncológico dirigido. Si bien el "estándar de oro" para este fin es el estudio anatomopatológico (obtenido por biopsia o resección quirúrgica), en los casos en que esto no es posible, la resonancia magnética cardíaca es la técnica no invasiva que proporciona un mejor abordaje diagnóstico. El tratamiento de elección es la resección quirúrgica y el pronóstico, en general, es malo. Presentamos el caso de una paciente con un tumor cardíaco de presentación clínica atípica, en la que un abordaje imagenológico multimodal aporta información clave y complementaria para el diagnóstico y la caracterización tisular.

Malignant cardiac tumors are rare neoplasms that can present in various forms, making their diagnosis difficult. Echocardiography and cardiac magnetic resonance imaging are fundamental techniques for the diagnosis, characterization, and evaluation of tumor extension. Identification of the tumor line is essential when initiating targeted cancer therapy. Although the "gold standard" for this purpose is the pathological study (obtained by biopsy or surgical resection), in cases where this is not possible, cardiac resonance is the non-invasive technique that provides a better diagnostic approach. The treatment of choice is surgical resection and the prognosis is generally poor. We present the case of a patient with an atypical clinical presentation, in which a multimodal approach provides key and complementary information for tumor diagnosis and tissue characterization.

Os tumores cardíacos malignos são neoplasias raras que podem se apresentar de várias formas, dificultando seu diagnóstico. A ecocardiografia e a ressonância magnética cardíaca são técnicas fundamentais para o diagnóstico, caracterização e avaliação da extensão tumoral. A identificação da linha do tumor é essencial ao iniciar a terapia direcionada do câncer. Embora o "padrão ouro" para esse fim seja o estudo patológico (obtido por biópsia ou ressecção cirúrgica), nos casos em que isso não seja possível, a ressonância cardíaca é a técnica não invasiva que proporciona melhor abordagem diagnóstica. O tratamento de escolha é a ressecção cirúrgica e o pronóstico geralmente é ruim. Apresentamos o caso de uma paciente com apresentação clínica atípica, em que a abordagem multimodal fornece informações essenciais e complementares para o diagnóstico do tumor e caracterização do tecido.