STEM enables mapping of single-cell and spatial transcriptomics data with transfer learning.

Profiling spatial variations of cellular composition and transcriptomic characteristics is important for understanding the physiology and pathology of tissues. Spatial transcriptomics (ST) data depict spatial gene expression but the currently dominating high-throughput technology is yet not at single-cell resolution. Single-cell RNA-sequencing (SC) data provide high-throughput transcriptomic information at the single-cell level but lack spatial information. Integrating these two types of data would be ideal for revealing transcriptomic landscapes at single-cell resolution. We develop the method STEM (SpaTially aware EMbedding) for this purpose. It uses deep transfer learning to encode both ST and SC data into a unified spatially aware embedding space, and then uses the embeddings to infer SC-ST mapping and predict pseudo-spatial adjacency between cells in SC data. Semi-simulation and real data experiments verify that the embeddings preserved spatial information and eliminated technical biases between SC and ST data. We apply STEM to human squamous cell carcinoma and hepatic lobule datasets to uncover the localization of rare cell types and reveal cell-type-specific gene expression variation along a spatial axis. STEM is powerful for mapping SC and ST data to build single-cell level spatial transcriptomic landscapes, and can provide mechanistic insights into the spatial heterogeneity and microenvironments of tissues.

Detection and subtyping of hepatic echinococcosis from plain CT images with deep learning: a retrospective, multicentre study.

BACKGROUND: Hepatic echinococcosis is a severe endemic disease in some underdeveloped rural areas worldwide. Qualified physicians are in short supply in such areas, resulting in low rates of accurate diagnosis of this condition. In this study, we aimed to develop and evaluate an artificial intelligence (AI) system for automated detection and subtyping of hepatic echinococcosis using plain CT images with the goal of providing interpretable assistance to radiologists and clinicians. METHODS: We developed EDAM, an echinococcosis diagnostic AI system, to provide accurate and generalisable CT analysis for distinguishing hepatic echinococcosis from hepatic cysts and normal controls (no liver lesions), as well as subtyping hepatic echinococcosis as alveolar or cystic echinococcosis. EDAM includes a slice-level prediction model for lesion classification and segmentation and a patient-level diagnostic model for patient classification. We collected a plain CT database (n=700: 395 cystic echinococcosis, 122 alveolar echinococcosis, 130 hepatic cysts, and 53 normal controls) for developing EDAM, and two additional independent cohorts (n=156) for external validation of its performance and generalisation ability. We compared the performance of EDAM with 52 experienced radiologists in diagnosing and subtyping hepatic echinococcosis. FINDINGS: EDAM showed reliable performance in patient-level diagnosis on both the internal testing data (overall area under the receiver operating characteristic curve [AUC]: 0·974 [95% CI 0·936-0·994]; accuracy: 0·952 [0·939-0·965] for cystic echinococcosis, 0·981 [0·973-0·989] for alveolar echinococcosis; sensitivity: 0·966 [0·951-0·979] for cystic echinococcosis, 0·944 [0·908-0·970] for alveolar echinococcosis) and the external testing set (overall AUC: 0·953 [95% CI 0·840-0·973]; accuracy: 0·929 [0·915-0·947] for cystic echinococcosis, 0·936 [0·919-0·950] for alveolar echinococcosis; sensitivity: 0·913 [0·879-0·944] for cystic echinococcosis, 0·868 [0·841-0·897] for alveolar echinococcosis). The sensitivity of EDAM was robust across images from different CT manufacturers. EDAM outperformed most of the enrolled radiologists in detecting both alveolar echinococcosis and cystic echinococcosis. INTERPRETATION: EDAM is a clinically applicable AI system that can provide patient-level diagnoses with interpretable results. The accuracy and generalisation ability of EDAM demonstrates its potential for clinical use, especially in underdeveloped areas. FUNDING: Project of Qinghai Provincial Department of Science and Technology of China, National Natural Science Foundation of China, and Tsinghua-Fuzhou Institute of Data Technology Project. TRANSLATION: For the Chinese translation of the abstract see Supplementary Materials section.

The Association between Dietary Inflammatory Index and Sex Hormones among Men in the United States.

PURPOSE: This study investigated the association between Dietary Inflammatory Index and sex hormones in a large, nationally representative adult male sample. MATERIALS AND METHODS: We utilized data from the 2013-2014 and 2015-2016 National Health and Nutrition Examination Survey. Males aged ≥20 years who provided a 24-hour dietary intake history and underwent serum sex hormone testing were included in analysis. Weighted proportions and multivariable analysis controlling for age, race, energy, smoking status, education level, body mass index and time of venipuncture were used to evaluate the associations between Dietary Inflammatory Index and sex hormones. RESULTS: For 4,151 participants, Dietary Inflammatory Index ranged from -5.05 to 5.48. Mean±SD total testosterone was 419.30±176.27 ng/dl. Mean±SD total testosterone was lower among men in the highest tertile compared with men in the lowest tertile group (410.42±171.97 vs 422.71±175.69, p <0.001). A per unit increase in Dietary Inflammatory Index was related to 4.0% (95% CI 0.5-7.6) higher odds of testosterone deficiency. In the fully adjusted multivariable model, males in Dietary Inflammatory Index tertile 3 (the most pro-inflammatory) had 29.6% (3.1-63.0) higher odds of testosterone deficiency than those in tertile 1 (p trend=0.025). Interaction tests revealed no significant effect of body mass index on the association of Dietary Inflammatory Index with testosterone deficiency and all sex hormone parameters. CONCLUSIONS: Men adhering to a more pro-inflammatory diet appear to have a higher risk of testosterone deficiency, indicating the important role of diet in male reproductive health.

Low lean mass and cognitive performance: data from the National Health and Nutrition Examination Surveys.

BACKGROUND: Low lean mass and cognitive impairment are both age-related diseases. In addition, these conditions share many risk factors. However, the association between them has been controversial in recent years. OBJECTIVE: To investigate the association between low lean mass and cognitive performance in U.S. adults using NHANES data from 1999 to 2002. METHODS: A total of 2550 participants were identified in the National Health and Nutrition Examination Survey Database (1999-2002). The independent variable was low lean mass, and the dependent variable was cognitive performance. Men and women were classified as having low lean mass if appendicular lean mass (ALM) adjusted for BMI (ALMBMI) was < 0.789 and < 0.512, respectively. Cognitive performance was assessed using the Digit Symbol Substitution Test (DSST). Higher scores on the DSST indicated better cognitive performance. The covariates included sex, age, race, poverty income ratio, comorbidity index, educational level, physical activity and smoking status. RESULTS: For the primary outcome, our multivariate linear regression analysis indicated that participants without low lean mass were associated with better cognitive performance (ß = 1.50; 95% CI [0.12-2.89]). Subgroup analysis results indicated that the association was similar in sex, age, race, poverty income ratio, comorbidity index, educational level, physical activity and smoking status. CONCLUSIONS: Participants without low lean mass were associated with better cognitive performance. We might be able to improve cognitive performance by treating low lean mass, thus providing an opportunity for intervention at a younger age.