Cross media retrieval engines have gained massive popularity with rapid development of the Internet. Users may perform queries in a corpus consisting of audio, video, and textual information. To make such systems practically possible for large mount of multimedia data, two critical issues must be carefully considered: (a) reduce the storage as much as possible; (b) model the relationship of the heterogeneous media data. Recently academic community have proved that encoding the data into compact binary codes can drastically reduce the storage and computational cost. However, it is still unclear how to integrate multiple information sources properly into the binary code encoding scheme. In this paper, we study the cross media indexing problem by learning the discriminative hashing functions to map the multi-view datum into a shared hamming space. Not only meaningful within-view similarity is required to be preserved, we also incorporate the between-view correlations into the encoding scheme, where we map the similar points close together and push apart the dissimilar ones. To this end, we propose a novel hashing algorithm called Iterative Multi-View Hashing (IMVH) by taking these information into account simultaneously. To solve this joint optimization problem efficiently, we further develop an iterative scheme to deal with it by using a more flexible quantization model. In particular, an optimal alignment is learned to maintain the between-view similarity in the encoding scheme. And the binary codes are obtained by directly solving a series of binary label assignment problems without continuous relaxation to avoid the unnecessary quantization loss. In this way, the proposed algorithm not only greatly improves the retrieval accuracy but also performs strong robustness. An extensive set of experiments clearly demonstrates the superior performance of the proposed method against the state-of-the-art techniques on both multimodal and unimodal retrieval tasks.
The worldwide growth of cancer incidence can be explained in part by changes in the prevalence and distribution of risk factors. There are geographical gaps in the estimates of cancer prevalence, which could be filled with innovative methods. We used deep learning (DL) features extracted from satellite images to predict cancer prevalence at the census tract level in seven cities in the United States. We trained the model using detailed cancer prevalence estimates from 2018 available in the CDC (Center for Disease Control) 500 Cities project. Data from 3500 census tracts covering 14,483,366 inhabitants were included. Features were extracted from 170,210 satellite images with deep learning. This method explained up to 64.37% (median = 43.53%) of the variation of cancer prevalence. Satellite features are highly correlated with individual socioeconomic and health measures that are linked to cancer prevalence (age, smoking and drinking status, and obesity). A higher similarity between two environments is associated with better generalization of the model (p = 1.10–6). This method can be used to accurately estimate cancer prevalence at a high spatial resolution without using surveys at a fraction of the cost.
Single cell RNA sequencing is a promising technique to determine the states of individual cells and classify novel cell subtypes. In current sequence data analysis, however, genes with low expressions are omitted, which leads to inaccurate gene counts and hinders downstream analysis. Recovering these omitted expression values presents a challenge because of the large size of the data. Here, we introduce a data-driven gene expression recovery framework, referred to as self-consistent expression recovery machine (SERM), to impute the missing expressions. Using a neural network, the technique first learns the underlying data distribution from a subset of the noisy data. It then recovers the overall expression data by imposing a self-consistency on the expression matrix, thus ensuring that the expression levels are similarly distributed in different parts of the matrix. We show that SERM improves the accuracy of gene imputation with orders of magnitude enhancement in computational efficiency in comparison to the state-of-the-art imputation techniques.
Conventional water–fat separation approaches suffer long computational times and are prone to water/fat swaps. To solve these problems, we propose a deep learning-based dual-echo water–fat separation method. With IRB approval, raw data from 68 pediatric clinically indicated dual echo scans were analyzed, corresponding to 19382 contrast-enhanced images. A densely connected hierarchical convolutional network was constructed, in which dual-echo images and corresponding echo times were used as input and water/fat images obtained using the projected power method were regarded as references. Models were trained and tested using knee images with 8-fold cross validation and validated on out-of-distribution data from the ankle, foot, and arm. Using the proposed method, the average computational time for a volumetric dataset with ~400 slices was reduced from 10 min to under one minute. High fidelity was achieved (correlation coefficient of 0.9969, error of 0.0381, SSIM of 0.9740, pSNR of 58.6876) and water/fat swaps were mitigated. I is of particular interest that metal artifacts were substantially reduced, even when the training set contained no images with metallic implants. Using the models trained with only contrast-enhanced images, water/fat images were predicted from non-contrast-enhanced images with high fidelity. The proposed water–fat separation method has been demonstrated to be fast, robust, and has the added capability to compensate for metal artifacts.