Are risk factors necessary for pretest probability assessment of coronary artery disease? A patient similarity network analysis of the PROMISE trial

BackgroundPretest probability (PTP) calculators utilize epidemiological-level findings to provide patient-level risk assessment of obstructive coronary artery disease (CAD). However, their limited accuracies question whether dissimilarities in risk factors necessarily result in differences in CAD. Using patient similarity network (PSN) analyses, we wished to assess the accuracy of risk factors and imaging markers to identify ≥50% luminal narrowing on coronary CT angiography (CCTA) in stable chest-pain patients.MethodsWe created four PSNs representing: patient characteristics, risk factors, non-coronary imaging markers and calcium score. We used spectral clustering to group individuals with similar risk profiles. We compared PSNs to a contemporary PTP score incorporating calcium score and risk factors to identify ≥50% luminal narrowing on CCTA in the CT-arm of the PROMISE trial. We also conducted subanalyses in different age and sex groups.ResultsIn 3556 individuals, the calcium score PSN significantly outperformed patient characteristic, risk factor, and non-coronary imaging marker PSNs (AUC: 0.81 vs. 0.57, 0.55, 0.54; respectively, p ?< ?0.001 for all). The calcium score PSN significantly outperformed the contemporary PTP score (AUC: 0.81 vs. 0.78, p ?< ?0.001), and using 0, 1–100 and ?> ?100 cut-offs provided comparable results (AUC: 0.81 vs. 0.81, p ?= ?0.06). Similar results were found in all subanalyses.ConclusionCalcium score on its own provides better individualized obstructive CAD prediction than contemporary PTP scores incorporating calcium score and risk factors. Risk factors may not be able to improve the diagnostic accuracy of calcium score to predict ≥50% luminal narrowing on CCTA.     

Quantitative Automated Segmentation of Lipiodol Deposits on Cone-Beam CT Imaging Acquired during Transarterial Chemoembolization for Liver Tumors: A Deep Learning Approach

PurposeTo show that a deep learning (DL)–based, automated model for Lipiodol (Guerbet Pharmaceuticals, Paris, France) segmentation on cone-beam computed tomography (CT) after conventional transarterial chemoembolization performs closer to the “ground truth segmentation” than a conventional thresholding-based model.Materials and MethodsThis post hoc analysis included 36 patients with a diagnosis of hepatocellular carcinoma or other solid liver tumors who underwent conventional transarterial chemoembolization with an intraprocedural cone-beam CT. Semiautomatic segmentation of Lipiodol was obtained. Subsequently, a convolutional U-net model was used to output a binary mask that predicted Lipiodol deposition. A threshold value of signal intensity on cone-beam CT was used to obtain a Lipiodol mask for comparison. The dice similarity coefficient (DSC), mean squared error (MSE), center of mass (CM), and fractional volume ratios for both masks were obtained by comparing them to the ground truth (radiologist-segmented Lipiodol deposits) to obtain accuracy metrics for the 2 masks. These results were used to compare the model versus the threshold technique.ResultsFor all metrics, the U-net outperformed the threshold technique: DSC (0.65 ± 0.17 vs 0.45 ± 0.22, P < .001) and MSE (125.53 ± 107.36 vs 185.98 ± 93.82, P = .005). The difference between the CM predicted and the actual CM was 15.31 mm ± 14.63 versus 31.34 mm ± 30.24 (P < .001), with lesser distance indicating higher accuracy. The fraction of volume present ([predicted Lipiodol volume]/[ground truth Lipiodol volume]) was 1.22 ± 0.84 versus 2.58 ± 3.52 (P = .048) for the current model’s prediction and threshold technique, respectively.ConclusionsThis study showed that a DL framework could detect Lipiodol in cone-beam CT imaging and was capable of outperforming the conventionally used thresholding technique over several metrics. Further optimization will allow for more accurate, quantitative predictions of Lipiodol depositions intraprocedurally.     

基于交叉对比神经网络的心音分类

目的:通过交叉对比神经网络（CCNN）实现心音信号的自动分类，从而对心血管疾病进行早期诊断。方法:实验基于PhysioNet/Cinc 2016心音数据库。训练集和测试集数据来自互斥的健康受试者/病理患者，并以4:1的比例进行划分，输入CCNN。CCNN利用深度卷积神经网络进行特征提取，结合基于信息的相似度度量理论（IBS），对特征向量间的相似性进行度量并分类。结果:实验结果得出灵敏度为0.834 6，特异性为0.962 3，最终大赛综合得分为0.898 5。结论:CCNN使用交叉对比的输入模式扩充数据量，引入信号间的对比信息，同时在神经网络的训练过程中应用统计学思想，使网络具备良好的泛化性，更加适应医学数据量较少的场景，在心音分类中取得较好的结果。     

Automated total kidney volume measurements in pre-clinical magnetic resonance imaging for resourcing imaging data,annotations, and source code

1. Download : Download high-res image (287KB)
2. Download : Download full-size image

     

经典名方泽泻汤的HPLC指纹图谱及多指标含量测定研究

目的建立经典名方泽泻汤的HPLC指纹图谱,结合化学模式识别技术对其进行分析,并测定泽泻汤中3种成分23-乙酰泽泻醇B、23-乙酰泽泻醇C和白术内酯Ⅲ的含量,为泽泻汤质量控制提供科学依据。方法采用Waters WAT054275C18色谱柱(250 mm×4.6 mm,5μm),以乙腈-水为流动相进行梯度洗脱,建立15批泽泻汤的HPLC指纹图谱,并采用"中药色谱指纹图谱相似度评价系统"、SPSS22.0及SIMCA14.1软件对15批泽泻汤的HPLC指纹图谱进行相似度评价及聚类分析(CA)、偏最小二乘判别分析(PLS-DA)等化学模式识别。同时测定23-乙酰泽泻醇B、23-乙酰泽泻醇C和白术内酯Ⅲ的含量。结果建立了15批泽泻汤的HPLC指纹图谱,相似度均0.94,标定了18个共有峰,指认出3个色谱峰,分别为11号峰白术内酯Ⅲ、15号峰23-乙酰泽泻醇C、16号峰23-乙酰泽泻醇B,CA和PLS-DA将15批泽泻汤样品分为2类,同时15批泽泻汤中23-乙酰泽泻醇B、23-乙酰泽泻醇C和白术内酯Ⅲ的质量分数分别为0.321～0.569、0.075～0.139、0.106～0.142 mg/g。结论 HPLC指纹图谱结合多成分同时测定的方法,快速、简便、重复性好,为泽泻汤及其制剂的质量评价提供参考。     

Assessment of Lung Tumour Motion and Volume Size Dependencies Using Various Evaluation Measures

The purpose of the study was to assess internal target volume changes through the breathing cycle and associated tumour motion for lung patients and to establish possible correlations between different parameters. Respiration-induced volume changes with breathing cycle and the associated tumour motion were analyzed for 11 patients. Selected phases were the maximum and average intensity projections and the 10 phases of equal duration and separation obtained through the respiratory cycle. Tumour centre of mass (COM) motion planes were generated using least square fitting, and their angles and orientations were then compared between the cases studied. Trajectories that are composed by the points of COM location in different phases were identified, and their interrelation was assessed through different similarity measures. The results were used to determine if there is any correlation between parameters chosen and if the margins conventionally used for the planning target volume creation successfully encompassed lung tumour motion and volume change. The results show that the extent of tumour motion was related to its volume and location. The tumour displacement was predominantly left and inferior. Planar fitting to COM motion data through respiratory phases demonstrated some correlation in best fit motion plane positions between different data sets. In the plane fit comparison, for each patient, the lower root mean square error values showed that a good planar fit can be achieved for the COM motion path. The evaluation of the inhale and exhale trajectories may allow, for certain tumour locations and size, contouring on only inhalation or exhalation phases, knowing that tumour motion will be adequately covered on the other phases. Taking all the data into account and knowing the tumour size and location, a good estimate can be made of the motion plane position in the three-dimensional space and the required dosimetric margins.     

Prioritization of candidate disease genes by combining topological similarity and semantic similarity

The identification of gene–phenotype relationships is very important for the treatment of human diseases. Studies have shown that genes causing the same or similar phenotypes tend to interact with each other in a protein–protein interaction (PPI) network. Thus, many identification methods based on the PPI network model have achieved good results. However, in the PPI network, some interactions between the proteins encoded by candidate gene and the proteins encoded by known disease genes are very weak. Therefore, some studies have combined the PPI network with other genomic information and reported good predictive performances. However, we believe that the results could be further improved. In this paper, we propose a new method that uses the semantic similarity between the candidate gene and known disease genes to set the initial probability vector of a random walk with a restart algorithm in a human PPI network. The effectiveness of our method was demonstrated by leave-one-out cross-validation, and the experimental results indicated that our method outperformed other methods. Additionally, our method can predict new causative genes of multifactor diseases, including Parkinson’s disease, breast cancer and obesity. The top predictions were good and consistent with the findings in the literature, which further illustrates the effectiveness of our method.     

基于基因表达谱相似性的四物汤重定位及抗乳腺癌有效成分群辨识＊

目的 发现四物汤的新药理作用并辨识其有效成分群。方法 于GEO和Cmap数据库获取四物汤和1309个小分子药物的基因表达谱，计算差异表达基因及四物汤与1309个小分子药物的基因表达谱间的相似性，相似性较高的小分子药物的药理作用为四物汤的新药理作用。相似性较高的小分子药物的靶点作为四物汤发挥新药理作用的靶标，利用分子对接技术辨识四物汤的有效成分群。结果 四物汤具有抗乳腺癌的作用，其有效成分群为荭草苷、芍药苷和半乳糖醛酸等，并通过文献调研验证了辨识结果的可靠性。结论 本研究将为扩大四物汤的临床应用范围及质量控制奠定基础，为乳腺癌的治疗提供新方法。