Fusing Modalities by Multiplexed Graph Neural Networks for Outcome Prediction in TuberculosisThe eight-volume set LNCS 13431, 13432, 13433, 13434, 13435, 13436, 13437, and 13438 constitutes the refereed proceedings of the 25th International Conference on Medical Image Computing and Computer-Assisted ...
Reliable large-scale cell detection and segmentation are achieved using deep neural networks. Cell phenotyping is performed by analyzing unique biomarker combinations over appropriate subcellular compartments. This approach can accelerate pre-clinical drug evaluation and system-level brain histology studies by...
The cells were then clustered by first building a k-nearest-neighbor graph with 15 neighbors (using cosine distance) and then clustered using Louvain’s community detection implemented in the igraph package with default parameters24. Processing and analysis of CosMX data Data corresponding to the ...
To enable de novo discovery of cell subpopulations not present in reference datasets, we first perform unsupervised graph clustering (Blondel et al., 2008, Traag et al., 2015). We selected the resolution parameter such that clustering resulted in partitions that were relatively invariant to small ...
To provide a high-level view of the cell-type interaction landscape, the total counts of contacts between every pair of cell types in the Delaunay neighborhood graph (Gabriel and Sokal, 1969) (Figure 4A and associated Mendeley dataset) for each condition was determined. The specificity of cell...
Fusing Modalities byMultiplexed Graph Neural Networks forOutcome Prediction inTuberculosisIn a complex disease such as tuberculosis, the evidence for the disease and its evolution may be present in multiple modalities such as clinical, genomic, or imaging data. Effective patient-tailored outcome ...
Predictive modelling of highly multiplexed tumour tissue images by graph neural networksThe progression and treatment response of cancer largely depends on the complex tissue structure that surrounds cancer cells in a tumour, known as the tumour microenvironment (TME). Recent technical......
Coreograph accomplishes this using a U-Net deep learning architecture21 (Fig. 1e). Each core is its own multichannel image that can be further processed by MCMICRO (Supplementary Fig. 4). The robustness of neural networks makes it possible for Coreograph to identify cores even in highly ...
Tun, K. Graph package (MATLAB Central File Exchange, accessed 5 May 2021); https://www.mathworks.com/matlabcentral/fileexchange/12648-graph-package Download references Acknowledgements We thank R. Yuste, R. Tomer, L. Wei, F. Hu and C. Chen for helpful discussions. W.M. acknowledges suppor...
The graph shows highly enriched biological processes among the human N-glycoproteins (colored in red). The node size is according to the number of proteins corresponding to each biological process, and the intensity of the color is according to the p value. The developed SRM assays are accessibl...