NFnetFu: A novel workflow for microbiome data fusion

Microbiome data analysis and its interpretation into meaningful biological insights remain very challenging for numerous reasons, perhaps most prominently, due to the need to account for multiple factors, including collinearity, sparsity (excessive zeros) and effect size, that the complex experimental workflow and subsequent downstream data analysis require. Moreover, a meaningful microbiome data analysis necessitates the development of interpretable models that incorporate inferences across available data as well as background biomedical knowledge. We developed a multimodal framework that considers sparsity (excessive zeros), lower effect size, intrinsically microbial correlations, i.e., collinearity, as well as background biomedical knowledge in the form of a cluster-infused enriched network architecture. Finally, our framework also provides a candidate taxa/Operational Taxonomic Unit (OTU) that can be targeted for future validation experiments. We have developed a tool, the term NFnetFU (Neuro Fuzzy network Fusion), that encompasses our framework and have made it freely available at https://github.com/VartikaBisht6197/NFnetFu.

High-resolution 3D abdominal segmentation with random patch network fusion

Deep learning for three dimensional (3D) abdominal organ segmentation on high-resolution computed tomography (CT) is a challenging topic, in part due to the limited memory provide by graphics processing units (GPU) and large number of parameters and in 3D fully convolutional networks (FCN). Two prevalent strategies, lower resolution with wider field of view and higher resolution with limited field of view, have been explored but have been presented with varying degrees of success. In this paper, we propose a novel patch-based network with random spatial initialization and statistical fusion on overlapping regions of interest (ROIs). We evaluate the proposed approach using three datasets consisting of 260 subjects with varying numbers of manual labels. Compared with the canonical "coarse-to-fine" baseline methods, the proposed method increases the performance on multi-organ segmentation from 0.799 to 0.856 in terms of mean DSC score (p-value < 0.01 with paired t-test). The effect of different numbers of patches is evaluated by increasing the depth of coverage (expected number of patches evaluated per voxel). In addition, our method outperforms other state-of-the-art methods in abdominal organ segmentation. In conclusion, the approach provides a memory-conservative framework to enable 3D segmentation on high-resolution CT. The approach is compatible with many base network structures, without substantially increasing the complexity during inference. Given a CT scan with at high resolution, a low-res section (left panel) is trained with multi-channel segmentation. The low-res part contains down-sampling and normalization in order to preserve the complete spatial information. Interpolation and random patch sampling (mid panel) is employed to collect patches. The high-dimensional probability maps are acquired (right panel) from integration of all patches on field of views.