The effect of ambient temperatures on hospital admissions for kidney diseases in Central Australia.

This study aimed to quantify risk of hospitalisations for kidney diseases related to ambient temperature in Central Australia, Northern Territory (NT). Daily hospitalisation data were extracted for Alice Springs Hospital, Central Australia, 2010-2021. The association between daily mean temperature and daily hospital admissions for total kidney and specific kidney conditions was assessed using a quasi-Poisson Generalized Linear Model combined with a distributed lag non-linear model. A total of 52,057 hospitalisations associated with kidney diseases were recorded. In general, risk of specific kidney related hospitalisations was immediate due to hot temperatures and prolonged due to cold temperatures. Relative to the minimum-risk temperature (5.1 °C), at 31 °C, cumulative relative risk (RR) of hospitalisations for total kidney disease (TKD) was 1.297 [95% CI 1.164,1.446] over lag0-1 days, for chronic kidney disease (CKD) cumulative RR was 1.269 [95% CI 1.115,1.444] and for kidney failure (KF) cumulative RR was 1.252 [95% CI 1.107,1.416] at lag 0, and for urinary tract infection (UTI) cumulative RR was 1.522 [95% CI 1.072,2.162] over lag0-7 days. At 16 °C and over lag0-7 days, cumulative RR of hospitalisations for TKD was 1.320 [95% CI 1.135,1.535], for CKD was 1.232 [95% CI 1.025,1.482], for RF was 1.233 [95% CI 1.035,1.470] and for UTI was 1.597 [95% CI 1.143, 2.231]. Both cold and hot temperatures were also associated with increased risks of kidney related total hospitalisations among First Nations Australians and women. Overall, temperature attributable to 13.7% (i.e. 7138 cases) of kidney related hospitalisations with higher attributable hospitalisations from cold temperature. Given the significant burden of kidney disease and projected increases in extreme temperatures associated with climate change in NT including Central Australia there is a need to implement public health and environmental health risk reduction strategies and awareness programs to mitigate potential adverse health effects of extreme temperatures.

Development and interpretation of a pathomics-driven ensemble model for predicting the response to immunotherapy in gastric cancer.

BACKGROUND: Only a subset of patients with gastric cancer experience long-term benefits from immune checkpoint inhibitors (ICIs). Currently, there is a deficiency in precise predictive biomarkers for ICI efficacy. The aim of this study was to develop and validate a pathomics-driven ensemble model for predicting the response to ICIs in gastric cancer, using H&E-stained whole slide images (WSI). METHODS: This multicenter study retrospectively collected and analyzed H&E-stained WSIs and clinical data from 584 patients with gastric cancer. An ensemble model, integrating four classifiers: least absolute shrinkage and selection operator, k-nearest neighbors, decision trees, and random forests, was developed and validated using pathomics features, with the objective of predicting the therapeutic efficacy of immune checkpoint inhibition. Model performance was evaluated using metrics including the area under the curve (AUC), sensitivity, and specificity. Additionally, SHAP (SHapley Additive exPlanations) analysis was used to explain the model's predicted values as the sum of the attribution values for each input feature. Pathogenomics analysis was employed to explain the molecular mechanisms underlying the model's predictions. RESULTS: Our pathomics-driven ensemble model effectively stratified the response to ICIs in training cohort (AUC 0.985 (95% CI 0.971 to 0.999)), which was further validated in internal validation cohort (AUC 0.921 (95% CI 0.839 to 0.999)), as well as in external validation cohort 1 (AUC 0.914 (95% CI 0.837 to 0.990)), and external validation cohort 2 (0.927 (95% CI 0.802 to 0.999)). The univariate Cox regression analysis revealed that the prediction signature of pathomics-driven ensemble model was a prognostic factor for progression-free survival in patients with gastric cancer who underwent immunotherapy (p<0.001, HR 0.35 (95% CI 0.24 to 0.50)), and remained an independent predictor after multivariable Cox regression adjusted for clinicopathological variables, (including sex, age, carcinoembryonic antigen, carbohydrate antigen 19-9, therapy regime, line of therapy, differentiation, location and programmed death ligand 1 (PD-L1) expression in all patients (p<0.001, HR 0.34 (95% CI 0.24 to 0.50)). Pathogenomics analysis suggested that the ensemble model is driven by molecular-level immune, cancer, metabolism-related pathways, and was correlated with the immune-related characteristics, including immune score, Estimation of STromal and Immune cells in MAlignant Tumor tissues using Expression data score, and tumor purity. CONCLUSIONS: Our pathomics-driven ensemble model exhibited high accuracy and robustness in predicting the response to ICIs using WSIs. Therefore, it could serve as a novel and valuable tool to facilitate precision immunotherapy.

Non-invasive imaging of mechanical properties of cancers in vivo based on transformations of the Eshelby's tensor using compression elastography.

Knowledge of the mechanical properties is of great clinical significance for diagnosis, prognosis and treatment of cancers. Recently, a new method based on Eshelby's theory to simultaneously assess Young's modulus (YM) and Poisson's ratio (PR) in tissues has been proposed. A significant limitation of this method is that accuracy of the reconstructed YM and PR is affected by the orientation/alignment of the tumor with the applied stress. In this paper, we propose a new method to reconstruct YM and PR in cancers that is invariant to the 3D orientation of the tumor with respect to the axis of applied stress. The novelty of the proposed method resides on the use of a tensor transformation to improve the robustness of Eshelby's theory and reconstruct YM and PR of tumors with high accuracy and in realistic experimental conditions. The method is validated using finite element simulations and controlled experiments using phantoms with known mechanical properties. The in vivo feasibility of the developed method is demonstrated in an orthotopic mouse model of breast cancer. Our results show that the proposed technique can estimate the YM and PR with overall accuracy of (97.06 ± 2.42) % under all tested tumor orientations. Animal experimental data demonstrate the potential of the proposed methodology in vivo. The proposed method can significantly expand the range of applicability of the Eshelby's theory to tumors and provide new means to accurately image and quantify mechanical parameters of cancers in clinical conditions.

Patterns and determinants of healthcare utilization and medication use before and during the COVID-19 crisis in Afghanistan, Bangladesh, and India.

BACKGROUND: COVID-19 rapidly spread through South Asian countries and overwhelmed the health systems that were unprepared for such an outbreak. Evidence from high-income countries showed that COVID-19 impacted healthcare utilization, including medication use, but empirical evidence is lacking in South Asia. This study aimed to investigate the effect of COVID-19 on healthcare utilization and medication use in South Asia. METHOD: The current study used longitudinal data from the 'Premise Health Service Disruption Survey' 2020 and 2021. The countries of interest were limited to Afghanistan, Bangladesh, and India. In these surveys, data related to healthcare utilization and medication use were collected for three-time points; 'Pre-COVID phase', 'Initial phase of COVID-19 outbreak', and 'One year of COVID-19 outbreak'. Generalized estimating equation (GEE) along with McNemar's test, Kruskal-Wallis test and χ2 test were applied in this study following the conceptualization of Andersen's healthcare utilization model. RESULT: The use of healthcare and medication was unevenly impacted by the COVID-19 epidemic in Afghanistan, Bangladesh, and India. Immediately after the COVID-19 outbreak, respondents in Bangladesh reported around four times higher incomplete healthcare utilization compared to pre-COVID phase. In contrast, respondents in Afghanistan reported lower incomplete utilization of healthcare in a similar context. In the post COVID-19 outbreak, non-adherence to medication use was significantly higher in Afghanistan (OR:1.7; 95%CI:1.6,1.9) and India (OR:1.3; 95%CI:1.1,1.7) compared to pre-COVID phase. Respondents of all three countries who sought assistance to manage non-communicable diseases (NCDs) had higher odds (Afghanistan: OR:1.5; 95%CI:1.3,1.8; Bangladesh: OR: 3.7; 95%CI:1.9,7.3; India: OR: 2.3; 95% CI: 1.4,3.6) of non-adherence to medication use after the COVID-19 outbreak compared to pre-COVID phase. CONCLUSION: The present study documented important evidence of the influence of COVID-19 epidemic on healthcare utilization and medication use in three countries of South Asia. Lessons learned from this study can feed into policy responses to the crisis and preparedness for future pandemics.

Deciphering the Feature Representation of Deep Neural Networks for High-Performance AI.

AI driven by deep learning is transforming many aspects of science and technology. The enormous success of deep learning stems from its unique capability of extracting essential features from Big Data for decision-making. However, the feature extraction and hidden representations in deep neural networks (DNNs) remain inexplicable, primarily because of lack of technical tools to comprehend and interrogate the feature space data. The main hurdle here is that the feature data are often noisy in nature, complex in structure, and huge in size and dimensionality, making it intractable for existing techniques to analyze the data reliably. In this work, we develop a computational framework named contrastive feature analysis (CFA) to facilitate the exploration of the DNN feature space and improve the performance of AI. By utilizing the interaction relations among the features and incorporating a novel data-driven kernel formation strategy into the feature analysis pipeline, CFA mitigates the limitations of traditional approaches and provides an urgently needed solution for the analysis of feature space data. The technique allows feature data exploration in unsupervised, semi-supervised and supervised formats to address different needs of downstream applications. The potential of CFA and its applications for pruning of neural network architectures are demonstrated using several state-of-the-art networks and well-annotated datasets across different disciplines.

Self-supervised deep learning of gene-gene interactions for improved gene expression recovery.

Single-cell RNA sequencing (scRNA-seq) has emerged as a powerful tool to gain biological insights at the cellular level. However, due to technical limitations of the existing sequencing technologies, low gene expression values are often omitted, leading to inaccurate gene counts. Existing methods, including advanced deep learning techniques, struggle to reliably impute gene expressions due to a lack of mechanisms that explicitly consider the underlying biological knowledge of the system. In reality, it has long been recognized that gene-gene interactions may serve as reflective indicators of underlying biology processes, presenting discriminative signatures of the cells. A genomic data analysis framework that is capable of leveraging the underlying gene-gene interactions is thus highly desirable and could allow for more reliable identification of distinctive patterns of the genomic data through extraction and integration of intricate biological characteristics of the genomic data. Here we tackle the problem in two steps to exploit the gene-gene interactions of the system. We first reposition the genes into a 2D grid such that their spatial configuration reflects their interactive relationships. To alleviate the need for labeled ground truth gene expression datasets, a self-supervised 2D convolutional neural network is employed to extract the contextual features of the interactions from the spatially configured genes and impute the omitted values. Extensive experiments with both simulated and experimental scRNA-seq datasets are carried out to demonstrate the superior performance of the proposed strategy against the existing imputation methods.

FAOT-Net: A 1.5-Stage Framework for 3D Pelvic Lymph Node Detection With Online Candidate Tuning.

Accurate and automatic detection of pelvic lymph nodes in computed tomography (CT) scans is critical for diagnosing lymph node metastasis in colorectal cancer, which in turn plays a crucial role in its staging, treatment planning, surgical guidance, and postoperative follow-up of colorectal cancer. However, achieving high detection sensitivity and specificity poses a challenge due to the small and variable sizes of these nodes, as well as the presence of numerous similar signals within the complex pelvic CT image. To tackle these issues, we propose a 3D feature-aware online-tuning network (FAOT-Net) that introduces a novel 1.5-stage structure to seamlessly integrate detection and refinement via our online candidate tuning process and takes advantage of multi-level information through the tailored feature flow. Furthermore, we redesign the anchor fitting and anchor matching strategies to further improve detection performance in a nearly hyperparameter-free manner. Our framework achieves the FROC score of 52.8 and the sensitivity of 91.7% with 16 false positives per scan on the PLNDataset. Code will be available at: github.com/SCUsomebody/FAOT-Net/.

Revealing hidden patterns in deep neural network feature space continuum via manifold learning.

Deep neural networks (DNNs) extract thousands to millions of task-specific features during model training for inference and decision-making. While visualizing these features is critical for comprehending the learning process and improving the performance of the DNNs, existing visualization techniques work only for classification tasks. For regressions, the feature points lie on a high dimensional continuum having an inherently complex shape, making a meaningful visualization of the features intractable. Given that the majority of deep learning applications are regression-oriented, developing a conceptual framework and computational method to reliably visualize the regression features is of great significance. Here, we introduce a manifold discovery and analysis (MDA) method for DNN feature visualization, which involves learning the manifold topology associated with the output and target labels of a DNN. MDA leverages the acquired topological information to preserve the local geometry of the feature space manifold and provides insightful visualizations of the DNN features, highlighting the appropriateness, generalizability, and adversarial robustness of a DNN. The performance and advantages of the MDA approach compared to the existing methods are demonstrated in different deep learning applications.

Biology-aware mutation-based deep learning for outcome prediction of cancer immunotherapy with immune checkpoint inhibitors.

The response rate of cancer immune checkpoint inhibitors (ICI) varies among patients, making it challenging to pre-determine whether a particular patient will respond to immunotherapy. While gene mutation is critical to the treatment outcome, a framework capable of explicitly incorporating biology knowledge has yet to be established. Here we aim to propose and validate a mutation-based deep learning model for survival analysis on 1571 patients treated with ICI. Our model achieves an average concordance index of 0.59 ± 0.13 across nine types of cancer, compared to the gold standard Cox-PH model (0.52 ± 0.10). The "black box" nature of deep learning is a major concern in healthcare field. This model's interpretability, which results from incorporating the gene pathways and protein interaction (i.e., biology-aware) rather than relying on a 'black box' approach, helps patient stratification and provides insight into novel gene biomarkers, advancing our understanding of ICI treatment.

Leveraging cell-cell similarity for high-performance spatial and temporal cellular mappings from gene expression data.

Single-cell trajectory mapping and spatial reconstruction are two important developments in life science and provide a unique means to decode heterogeneous tissue formation, cellular dynamics, and tissue developmental processes. The success of these techniques depends critically on the performance of analytical tools used for high-dimensional (HD) gene expression data processing. Existing methods discern the patterns of the data without explicitly considering the underlying biological characteristics of the system, often leading to suboptimal solutions. Here, we present a cell-cell similarity-driven framework of genomic data analysis for high-fidelity spatial and temporal cellular mappings. The approach exploits the similarity features of the cells to discover discriminative patterns of the data. We show that for a wide variety of datasets, the proposed approach drastically improves the accuracies of spatial and temporal mapping analyses compared with state-of-the-art techniques.

Super-resolution biomedical imaging via reference-free statistical implicit neural representation.

Objective.Supervised deep learning for image super-resolution (SR) has limitations in biomedical imaging due to the lack of large amounts of low- and high-resolution image pairs for model training. In this work, we propose a reference-free statistical implicit neural representation (INR) framework, which needs only a single or a few observed low-resolution (LR) image(s), to generate high-quality SR images.Approach.The framework models the statistics of the observed LR images via maximum likelihood estimation and trains the INR network to represent the latent high-resolution (HR) image as a continuous function in the spatial domain. The INR network is constructed as a coordinate-based multi-layer perceptron, whose inputs are image spatial coordinates and outputs are corresponding pixel intensities. The trained INR not only constrains functional smoothness but also allows an arbitrary scale in SR imaging.Main results.We demonstrate the efficacy of the proposed framework on various biomedical images, including computed tomography (CT), magnetic resonance imaging (MRI), fluorescence microscopy, and ultrasound images, across different SR magnification scales of 2×, 4×, and 8×. A limited number of LR images were used for each of the SR imaging tasks to show the potential of the proposed statistical INR framework.Significance.The proposed method provides an urgently needed unsupervised deep learning framework for numerous biomedical SR applications that lack HR reference images.

Prevalence, pattern, and correlates of dyslipidemia in Bangladeshi individuals.

BACKGROUND: The burden of dyslipidemia in Bangladesh remains inadequately characterized. OBJECTIVES: To determine and describe the prevalence and pattern of dyslipidemia and its associated risk factors among an adult Bangladeshi population. DESIGN: Population-based, cross-sectional study. Participants were adults living in all eight administrative divisions of Bangladesh. The total sample size was 7084 (53.1 % women, 46.9% urban residents). Primary outcome measures were triglycerides (TG), high-density lipoprotein cholesterol (HDL-C), low-density lipoprotein cholesterol (LDL-C), and the use of lipid lowering medication. In addition, control of LDL-C and control of non high-density lipoprotein cholesterol (non-HDL-C) were investigated. RESULTS: The overall dyslipidemia prevalence was 76.7%, with 35.7% showing a high TG level, 18.5% showing a high LDL-C level, 63.8% showing a low HDL-C level, and 7.2% of the participants showing all three lipid abnormalities. Sylhet division had the highest prevalence (83.8%) of overall dyslipidemia, while Rangpur had the lowest prevalence (69.3%). The control of LDL-C (<50 mg/dL) and non-HDL-C (<80 mg/dL) among adults with a previous history of atherosclerotic cardiovascular diseases (ASCVD) were 5.1% and 6.9% respectively. The regression models showed that male sex and age 45-59 years were significant predictors of overall dyslipidemia. Both smokers and smokeless tobacco users were significant factors for overall dyslipidemia and high TG. A high waist-hip ratio was associated with overall dyslipidemia and all other subtypes of dyslipidemia. CONCLUSION: The high prevalence of dyslipidemia in Bangladesh necessitates lifestyle interventions to prevent and control this cardiovascular risk factor.

Non-invasive tumor microenvironment evaluation and treatment response prediction in gastric cancer using deep learning radiomics.

The tumor microenvironment (TME) plays a critical role in disease progression and is a key determinant of therapeutic response in cancer patients. Here, we propose a noninvasive approach to predict the TME status from radiological images by combining radiomics and deep learning analyses. Using multi-institution cohorts of 2,686 patients with gastric cancer, we show that the radiological model accurately predicted the TME status and is an independent prognostic factor beyond clinicopathologic variables. The model further predicts the benefit from adjuvant chemotherapy for patients with localized disease. In patients treated with checkpoint blockade immunotherapy, the model predicts clinical response and further improves predictive accuracy when combined with existing biomarkers. Our approach enables noninvasive assessment of the TME, which opens the door for longitudinal monitoring and tracking response to cancer therapy. Given the routine use of radiologic imaging in oncology, our approach can be extended to many other solid tumor types.

Cascade of diabetes care in Bangladesh, Bhutan and Nepal: identifying gaps in the screening, diagnosis, treatment and control continuum.

Diabetes has become a major cause of morbidity and mortality in South Asia. Using the data from the three STEPwise approach to Surveillance (STEPS) surveys conducted in Bangladesh, Bhutan, and Nepal during 2018-2019, this study tried to quantify the gaps in diabetes screening, awareness, treatment, and control in these three South Asian countries. Diabetes care cascade was constructed by decomposing the population with diabetes (diabetes prevalence) in each country into five mutually exclusive and exhaustive categories: (1) unscreened and undiagnosed, (2) screened but undiagnosed, (3) diagnosed but untreated, (4) treated but uncontrolled, (5) treated and controlled. In Bangladesh, Bhutan, and Nepal, among the participants with diabetes, 14.7%, 35.7%, and 4.9% of the participants were treated and controlled, suggesting that 85.3%, 64.3%, and 95.1% of the diabetic population had unmet need for care, respectively. Multivariable logistic regression models were used to explore factors associated with awareness of the diabetes diagnosis. Common influencing factors for awareness of the diabetes diagnosis for Bangladesh and Nepal were living in urban areas [Bangladesh-adjusted odd ratio (AOR):2.1; confidence interval (CI):1.2, 3.6, Nepal-AOR:6.2; CI:1.9, 19.9].

Assessment of compression-induced solid stress, fluid pressure and mechanopathological parameters in cancersin vivousing poroelastography.

Objective.Compression-induced solid stress (SSc) and fluid pressure (FPc) during ultrasound poroelastography (USPE) experiments are correlated with two markers of cancer growth and treatment effectiveness: growth-induced solid stress (SSg) and interstitial fluid pressure (IFP). The spatio-temporal distributions of SSg and IFP are determined by the transport properties of the vessels and interstitium in the tumor microenvironment.Approach.We propose a new USPE method for the non-invasive imaging of the local cancer mechanical parameters and dynamics of fluid flow. When performing poroelastography experiments, it may be difficult to implement a typical creep compression protocol, which requires to maintain a constant normally applied force. In this paper, we investigate the use of a stress relaxation protocol, which might be a more convenient choice for clinical poroelastography applications.Main results.Based on our finite element and ultrasound simulations study, we demonstrate that the SSc, FPc and their spatio-temporal distribution related parameters, interstitial permeability and vascular permeability, can be determined from stress relaxation experiments with errors below 10% as compared to the ground truth and accuracy similar to that of corresponding creep tests, respectively. We also demonstrate the feasibility of the new methodology forin vivoexperiments using a small animal cancer model.Significance.The proposed non-invasive USPE imaging methods may become an effective tool to assess local tumor pressure and mechanopathological parameters in cancers.

Non-invasive imaging of interstitial fluid transport parameters in solid tumors in vivo.

In this paper, new and non-invasive imaging methods to assess interstitial fluid transport parameters in tumors in vivo are developed, analyzed and experimentally validated. These parameters include extracellular volume fraction (EVF), interstitial fluid volume fraction (IFVF) and interstitial hydraulic conductivity (IHC), and they are known to have a critical role in cancer progression and drug delivery effectiveness. EVF is defined as the volume of extracellular matrix per unit volume of the tumor, while IFVF refers to the volume of interstitial fluid per unit bulk volume of the tumor. There are currently no established imaging methods to assess interstitial fluid transport parameters in cancers in vivo. We develop and test new theoretical models and imaging techniques to assess fluid transport parameters in cancers using non-invasive ultrasound methods. EVF is estimated via the composite/mixture theory with the tumor being modeled as a biphasic (cellular phase and extracellular phase) composite material. IFVF is estimated by modeling the tumor as a biphasic poroelastic material with fully saturated solid phase. Finally, IHC is estimated from IFVF using the well-known Kozeny-Carman method inspired by soil mechanics theory. The proposed methods are tested using both controlled experiments and in vivo experiments on cancers. The controlled experiments were performed on tissue mimic polyacrylamide samples and validated using scanning electron microscopy (SEM). In vivo applicability of the proposed methods was demonstrated using a breast cancer model implanted in mice. Based on the controlled experimental validation, the proposed methods can estimate interstitial fluid transport parameters with an error below 10% with respect to benchmark SEM data. In vivo results demonstrate that EVF, IFVF and IHC increase in untreated tumors whereas these parameters are observed to decrease over time in treated tumors. The proposed non-invasive imaging methods may provide new and cost-effective diagnostic and prognostic tools to assess clinically relevant fluid transport parameters in cancers in vivo.

Multibranch CNN With MLP-Mixer-Based Feature Exploration for High-Performance Disease Diagnosis.

Deep learning-based diagnosis is becoming an indispensable part of modern healthcare. For high-performance diagnosis, the optimal design of deep neural networks (DNNs) is a prerequisite. Despite its success in image analysis, existing supervised DNNs based on convolutional layers often suffer from their rudimentary feature exploration ability caused by the limited receptive field and biased feature extraction of conventional convolutional neural networks (CNNs), which compromises the network performance. Here, we propose a novel feature exploration network named manifold embedded multilayer perceptron (MLP) mixer (ME-Mixer), which utilizes both supervised and unsupervised features for disease diagnosis. In the proposed approach, a manifold embedding network is employed to extract class-discriminative features; then, two MLP-Mixer-based feature projectors are adopted to encode the extracted features with the global reception field. Our ME-Mixer network is quite general and can be added as a plugin to any existing CNN. Comprehensive evaluations on two medical datasets are performed. The results demonstrate that their approach greatly enhances the classification accuracy in comparison with different configurations of DNNs with acceptable computational complexity.

Learning image representations for content-based image retrieval of radiotherapy treatment plans.

Objective.In this work, we propose a content-based image retrieval (CBIR) method for retrieving dose distributions of previously planned patients based on anatomical similarity. Retrieved dose distributions from this method can be incorporated into automated treatment planning workflows in order to streamline the iterative planning process. As CBIR has not yet been applied to treatment planning, our work seeks to understand which current machine learning models are most viable in this context.Approach.Our proposed CBIR method trains a representation model that produces latent space embeddings of a patient's anatomical information. The latent space embeddings of new patients are then compared against those of previous patients in a database for image retrieval of dose distributions. All source code for this project is available on github.Main results.The retrieval performance of various CBIR methods is evaluated on a dataset consisting of both publicly available image sets and clinical image sets from our institution. This study compares various encoding methods, ranging from simple autoencoders to more recent Siamese networks like SimSiam, and the best performance was observed for the multitask Siamese network.Significance.Our current results demonstrate that excellent image retrieval performance can be obtained through slight changes to previously developed Siamese networks. We hope to integrate CBIR into automated planning workflow in future works.

Cartography of Genomic Interactions Enables Deep Analysis of Single-Cell Expression Data.

Remarkable advances in single cell genomics have presented unique challenges and opportunities for interrogating a wealth of biomedical inquiries. High dimensional genomic data are inherently complex because of intertwined relationships among the genes. Existing methods, including emerging deep learning-based approaches, do not consider the underlying biological characteristics during data processing, which greatly compromises the performance of data analysis and hinders the maximal utilization of state-of-the-art genomic techniques. In this work, we develop an entropy-based cartography strategy to contrive the high dimensional gene expression data into a configured image format, referred to as genomap, with explicit integration of the genomic interactions. This unique cartography casts the gene-gene interactions into the spatial configuration of genomaps and enables us to extract the deep genomic interaction features and discover underlying discriminative patterns of the data. We show that, for a wide variety of applications (cell clustering and recognition, gene signature extraction, single cell data integration, cellular trajectory analysis, dimensionality reduction, and visualization), the proposed approach drastically improves the accuracies of data analyses as compared to the state-of-the-art techniques.

Small-Object Sensitive Segmentation Using Across Feature Map Attention.

Semantic segmentation is an important step in understanding the scene for many practical applications such as autonomous driving. Although Deep Convolutional Neural Networks-based methods have significantly improved segmentation accuracy, small/thin objects remain challenging to segment due to convolutional and pooling operations that result in information loss, especially for small objects. This article presents a novel attention-based method called Across Feature Map Attention (AFMA) to address this challenge. It quantifies the inner-relationship between small and large objects belonging to the same category by utilizing the different feature levels of the original image. The AFMA could compensate for the loss of high-level feature information of small objects and improve the small/thin object segmentation. Our method can be used as an efficient plug-in for a wide range of existing architectures and produces much more interpretable feature representation than former studies. Extensive experiments on eight widely used segmentation methods and other existing small-object segmentation models on CamVid and Cityscapes demonstrate that our method substantially and consistently improves the segmentation of small/thin objects.