BIDCell: Biologically-informed self-supervised learning for segmentation of subcellular spatial transcriptomics data.

Recent advances in subcellular imaging transcriptomics platforms have enabled high-resolution spatial mapping of gene expression, while also introducing significant analytical challenges in accurately identifying cells and assigning transcripts. Existing methods grapple with cell segmentation, frequently leading to fragmented cells or oversized cells that capture contaminated expression. To this end, we present BIDCell, a self-supervised deep learning-based framework with biologically-informed loss functions that learn relationships between spatially resolved gene expression and cell morphology. BIDCell incorporates cell-type data, including single-cell transcriptomics data from public repositories, with cell morphology information. Using a comprehensive evaluation framework consisting of metrics in five complementary categories for cell segmentation performance, we demonstrate that BIDCell outperforms other state-of-the-art methods according to many metrics across a variety of tissue types and technology platforms. Our findings underscore the potential of BIDCell to significantly enhance single-cell spatial expression analyses, enabling great potential in biological discovery.

Effect of extrusion on the protein structure and digestibility of extruded soybean protein.

BACKGROUND: Extrusion is the main method for the preparation of plant-based meat. Current studies have focused on the effect of different extrusion parameters on the texture and quality of plant-based meat, but there has been less research on their digestibility. This study determined the textural properties of extruded soybean protein (ESPro) for different extrusion parameters and the digestibility after in vitro simulated digestion experiments. The effect of extrusion on the structure and digestibility of ESPro and the relationship between them were elucidated. RESULTS: The results demonstrated a significant improvement in the digestibility of ESPro through extrusion, with the highest values for cohesiveness, springiness, chewiness, fibrous degree, digestibility, and proportion of digested peptides with <1 kDa molecular weight at an extrusion temperature of 160 °C and a screw speed of 30 rpm (ESPro1). In addition, ß-sheet content in the secondary structure of the ESPro showed a significant negative association with ESPro digestibility. CONCLUSION: In this study, extrusion could improve the digestibility of ESPro by altering the protein structure. This advancement holds the potential for more effective applications in plant-based meats. © 2023 Society of Chemical Industry.

Assessing mammal population densities in response to urbanization using camera trap distance sampling.

Environmental filtering is deemed to play a predominant role in regulating the abundance and distribution of animals during the urbanization process. However, the current knowledge about the effects of urbanization on the population densities of terrestrial mammals is limited. In this study, we compared two invasive mammals (dogs Canis lupus familiaris and cats Felis silvestris) and three indigenous mammals (Siberian weasels Mustela sibirica, Amur hedgehogs Erinaceus amurensis, and Tolai hares Lepus tolai) in response to urbanization using camera trap distance sampling (CTDS) in the rural-urban landscape of Tianjin, China. We used generalized additive mixed models (GAMMs) to test the specific responses of their densities to levels of urbanization. Invasive dogs (2.63 individuals/km2, 95% CI: 0.91-7.62) exhibited similar density estimations to cats (2.15 individuals/km2, 95% CI: 1.31-3.50). Amur hedgehogs were the most abundant species (6.73 individuals/km2, 95% CI: 3.15-14.38), followed by Tolai hares (2.22 individuals/km2, 95% CI: 0.87-5.68) and Siberian weasels (2.15 individuals/km2, 95% CI: 1.06-4.36). The densities of cats, Siberian weasels, and Amur hedgehogs increased with the level of urbanization. The population densities of dogs and cats were only influenced by urban-related variables, while the densities of Siberian weasels and Amur hedgehogs were influenced by both urban-related variables and nature-related variables. Our findings highlight that the CTDS is a suitable and promising method for wildlife surveys in rural-urban landscapes, and urban wildlife management needs to consider the integrated repercussions of urban- and nature-related factors, especially the critical impacts of green space habitats at finer scales.

CT-based Radiogenomics Framework for COVID-19 Using ACE2 Imaging Representations.

Coronavirus disease 2019 (COVID-19) is caused by Severe Acute Respiratory Syndrome Coronavirus 2 which enters the body via the angiotensin-converting enzyme 2 (ACE2) and altering its gene expression. Altered ACE2 plays a crucial role in the pathogenesis of COVID-19. Gene expression profiling, however, is invasive and costly, and is not routinely performed. In contrast, medical imaging such as computed tomography (CT) captures imaging features that depict abnormalities, and it is widely available. Computerized quantification of image features has enabled 'radiogenomics', a research discipline that identifies image features that are associated with molecular characteristics. Radiogenomics between ACE2 and COVID-19 has yet to be done primarily due to the lack of ACE2 expression data among COVID-19 patients. Similar to COVID-19, patients with lung adenocarcinoma (LUAD) exhibit altered ACE2 expression and, LUAD data are abundant. We present a radiogenomics framework to derive image features (ACE2-RGF) associated with ACE2 expression data from LUAD. The ACE2-RGF was then used as a surrogate biomarker for ACE2 expression. We adopted conventional feature selection techniques including ElasticNet and LASSO. Our results show that: i) the ACE2-RGF encoded a distinct collection of image features when compared to conventional techniques, ii) the ACE2-RGF can classify COVID-19 from normal subjects with a comparable performance to conventional feature selection techniques with an AUC of 0.92, iii) ACE2-RGF can effectively identify patients with critical illness with an AUC of 0.85. These findings provide unique insights for automated COVID-19 analysis and future research.

[Photo-Degradation Mechanism and Pathway for Tetracycline in Simulated Seawater Under Irradiation of Visible Light].

To explore the mechanism and pathway for pollutant degradation in seawater by heterogeneous photocatalysts, the degradation of tetracycline (TC) in pure water and simulated seawater with different mesoporous TiO2 under the excitation of visible light was first investigated; then the effect of different salt ions on the photocatalytic degradation process was clarified. Combined with radical trapping experiments, electron spin resonance (ESR) spectroscopy, and intermediate product analysis, the main active species for photodegrading pollutants and the pathway of TC degradation in simulated seawater were investigated. The results showed that the photodegradation for TC in simulated seawater was significantly inhibited. Compared with the TC photodegradation in pure water, the reaction rate of the chiral mesoporous TiO2 photocatalyst for TC was reduced by approximately 70%, whereas the achiral mesoporous TiO2 photocatalyst could hardly degrade TC in seawater. Anions in simulated seawater had little effect on photodegradation, but Mg2+ and Ca2+ ions significantly inhibited the TC photodegradation process. Whether in water or simulated seawater, the active species generated by the catalyst after excitation by visible light were mainly holes, and each salt ion did not inhibit the generation of active species; thus, the degradation pathway both in simulated seawater and in water was the same. However, Mg2+ and Ca2+ would be enriched around the highly electronegative atoms in TC molecules, hindering the attack of holes to highly electronegative atoms in TC molecules, thereby inhibiting the photocatalytic degradation efficiency.

Isolation and identification of an α-glucosidase inhibitory peptide from extruded soybean protein and its hypoglycemic activity in T2DM mice.

Although extruded soybean protein (ESPro) is currently used during the production of plant-based meats, studies involving its hypoglycemic activity in vitro and in vivo are minimal. In this study, the α-glucosidase inhibitory activity of ESPro with different extrusion parameters was compared and ESPro1 (160 °C, 30 rpm) was found to have the highest inhibitory activity. Then, simulated digestion and ultrafiltration of ESPro1 were carried out in vitro and an ESPro1 digestion product (<1 kDa) with the highest inhibitory activity was obtained. Gel filtration chromatography separation was further performed to obtain an ESPro1 F3 fraction with the highest inhibitory activity. Finally, six peptides with α-glucosidase inhibitory activity were screened from the ESPro1 F3 fraction and synthesized using solid-phase synthesis, among which LLRPPK showed the highest inhibitory activity (46.98 ± 0.63%). During a four-week dietary intervention in type 2 diabetes mellitus (T2DM) mice, ESPro attenuated the trend of weight loss, reduced blood glucose, alleviated insulin resistance, and improved glucose tolerance, while ESPro1 reduced blood glucose levels by 22.33% at 28 d. Furthermore, ESPro1 significantly increased the serum high-density lipoprotein cholesterol (HDL-C) levels, decreased the low-density lipoprotein cholesterol (LDL-C) levels, up-regulated the superoxide dismutase (SOD) and glutathione peroxidase (GSH-Px) activity, reduced the malondialdehyde (MDA) content, down-regulated the alanine aminotransferase (ALT) and aspartate aminotransferase (AST) activity, and alleviated liver and pancreatic injury in T2DM mice. Overall, ESPro1 (160 °C, 30 rpm) displayed a superior hypoglycemic effect in vivo and in vitro and may have a beneficial impact on T2DM treatment.

Deep multimodal graph-based network for survival prediction from highly multiplexed images and patient variables.

The spatial architecture of the tumour microenvironment and phenotypic heterogeneity of tumour cells have been shown to be associated with cancer prognosis and clinical outcomes, including survival. Recent advances in highly multiplexed imaging, including imaging mass cytometry (IMC), capture spatially resolved, high-dimensional maps that quantify dozens of disease-relevant biomarkers at single-cell resolution, that contain potential to inform patient-specific prognosis. Existing automated methods for predicting survival, on the other hand, typically do not leverage spatial phenotype information captured at the single-cell level. Furthermore, there is no end-to-end method designed to leverage the rich information in whole IMC images and all marker channels, and aggregate this information with clinical data in a complementary manner to predict survival with enhanced accuracy. To that end, we present a deep multimodal graph-based network (DMGN) with two modules: (1) a multimodal graph-based module that considers relationships between spatial phenotype information in all image regions and all clinical variables adaptively, and (2) a clinical embedding module that automatically generates embeddings specialised for each clinical variable to enhance multimodal aggregation. We demonstrate that our modules are consistently effective at improving survival prediction performance using two public breast cancer datasets, and that our new approach can outperform state-of-the-art methods in survival prediction.

Graph-Based Intercategory and Intermodality Network for Multilabel Classification and Melanoma Diagnosis of Skin Lesions in Dermoscopy and Clinical Images.

The identification of melanoma involves an integrated analysis of skin lesion images acquired using clinical and dermoscopy modalities. Dermoscopic images provide a detailed view of the subsurface visual structures that supplement the macroscopic details from clinical images. Visual melanoma diagnosis is commonly based on the 7-point visual category checklist (7PC), which involves identifying specific characteristics of skin lesions. The 7PC contains intrinsic relationships between categories that can aid classification, such as shared features, correlations, and the contributions of categories towards diagnosis. Manual classification is subjective and prone to intra- and interobserver variability. This presents an opportunity for automated methods to aid in diagnostic decision support. Current state-of-the-art methods focus on a single image modality (either clinical or dermoscopy) and ignore information from the other, or do not fully leverage the complementary information from both modalities. Furthermore, there is not a method to exploit the 'intercategory' relationships in the 7PC. In this study, we address these issues by proposing a graph-based intercategory and intermodality network (GIIN) with two modules. A graph-based relational module (GRM) leverages intercategorical relations, intermodal relations, and prioritises the visual structure details from dermoscopy by encoding category representations in a graph network. The category embedding learning module (CELM) captures representations that are specialised for each category and support the GRM. We show that our modules are effective at enhancing classification performance using three public datasets (7PC, ISIC 2017, and ISIC 2018), and that our method outperforms state-of-the-art methods at classifying the 7PC categories and diagnosis.

Retraction: a systematic review and meta-analysis of indirect comparison between miRNA and ctDNA in diagnosis of epithelial ovarian cancer.

[This retracts the article DOI: 10.21037/tcr-21-2609.].

Multimodal Spatial Attention Module for Targeting Multimodal PET-CT Lung Tumor Segmentation.

Multimodal positron emission tomography-computed tomography (PET-CT) is used routinely in the assessment of cancer. PET-CT combines the high sensitivity for tumor detection of PET and anatomical information from CT. Tumor segmentation is a critical element of PET-CT but at present, the performance of existing automated methods for this challenging task is low. Segmentation tends to be done manually by different imaging experts, which is labor-intensive and prone to errors and inconsistency. Previous automated segmentation methods largely focused on fusing information that is extracted separately from the PET and CT modalities, with the underlying assumption that each modality contains complementary information. However, these methods do not fully exploit the high PET tumor sensitivity that can guide the segmentation. We introduce a deep learning-based framework in multimodal PET-CT segmentation with a multimodal spatial attention module (MSAM). The MSAM automatically learns to emphasize regions (spatial areas) related to tumors and suppress normal regions with physiologic high-uptake from the PET input. The resulting spatial attention maps are subsequently employed to target a convolutional neural network (CNN) backbone for segmentation of areas with higher tumor likelihood from the CT image. Our experimental results on two clinical PET-CT datasets of non-small cell lung cancer (NSCLC) and soft tissue sarcoma (STS) validate the effectiveness of our framework in these different cancer types. We show that our MSAM, with a conventional U-Net backbone, surpasses the state-of-the-art lung tumor segmentation approach by a margin of 7.6% in Dice similarity coefficient (DSC).

A systematic review and meta-analysis of indirect comparison between miRNA and ctDNA in diagnosis of epithelial ovarian cancer.

BACKGROUND: To evaluate the clinical value of microRNA (miR) and circulating tumor RNA (ctDNA) in the diagnosis of epithelial ovarian cancer (EOC) by meta-analysis and indirect comparison based on common reference criteria. METHODS: The PubMed, EMBASE, MEDLINE, Cochrane Library, Chinese biology medicine (CBM), China national knowledge infrastructure (CNKI), Wanfang, and Chinese Weipu (VIP) databases were searched by computer. The retrieval time limit was from the date of establishment of the database to September 2020. Two researchers independently screened the literature and extracted the basic data according to the inclusion and exclusion criteria formulated in advance, and evaluated the literature quality according to the quality assessment of diagnostic accuracy research (quadas-2). The Meta disc 1.4 and Stata 12.0 software programs were used for meta-analysis to calculate the combined sensitivity, combined specificity, combined positive likelihood ratio, combined negative likelihood ratio and combined diagnostic odds ratio (DOR). The summary receiver operating characteristic (SROC) curve was drawn using Revman 5.3 software, and the stability of the results was evaluated by sensitivity analysis. The publication bias was evaluated by Deek's funnel asymmetric test. The relative diagnostic odds ratio (RDOR) results of indirect comparison between microRNA and ctDNA were obtained using R software. RESULTS: Nineteen articles were included, including a total of 1,351 EOC patients and 1,194 controls. The heterogeneity test showed that there was obvious heterogeneity caused by non-threshold effect. The random effects model was used for meta-analysis of microRNA in the diagnosis of EOC. The results showed that there was no significant difference between microRNA and ctDNA in the accuracy of EOC diagnosis. The asymmetric test of Deek's funnel chart showed that there was no significant publication bias. DISCUSSION: There are some limitations in this study, there is no blind diagnostic test, and the intensity of indirect comparison evidence is lower than that of direct comparison evidence. The accuracy of diagnostic tests and the imperfection of mesh meta-analysis statistical methods. MicroRNA and ctDNA have similar clinical diagnostic value for EOC.

Fully Automatic Left Atrium Segmentation From Late Gadolinium Enhanced Magnetic Resonance Imaging Using a Dual Fully Convolutional Neural Network.

Atrial fibrillation (AF) is the most prevalent form of cardiac arrhythmia. Current treatments for AF remain suboptimal due to a lack of understanding of the underlying atrial structures that directly sustain AF. Existing approaches for analyzing atrial structures in 3-D, especially from late gadolinium-enhanced (LGE) magnetic resonance imaging, rely heavily on manual segmentation methods that are extremely labor-intensive and prone to errors. As a result, a robust and automated method for analyzing atrial structures in 3-D is of high interest. We have, therefore, developed AtriaNet, a 16-layer convolutional neural network (CNN), on 154 3-D LGE-MRIs with a spatial resolution of 0.625 mm ×0.625 mm ×1.25 mm from patients with AF, to automatically segment the left atrial (LA) epicardium and endocardium. AtriaNet consists of a multi-scaled, dual-pathway architecture that captures both the local atrial tissue geometry and the global positional information of LA using 13 successive convolutions and three further convolutions for merging. By utilizing computationally efficient batch prediction, AtriaNet was able to successfully process each 3-D LGE-MRI within 1 min. Furthermore, benchmarking experiments have shown that AtriaNet has outperformed the state-of-the-art CNNs, with a DICE score of 0.940 and 0.942 for the LA epicardium and endocardium, respectively, and an inter-patient variance of <0.001. The estimated LA diameter and volume computed from the automatic segmentations were accurate to within 1.59 mm and 4.01 cm3 of the ground truths. Our proposed CNN was tested on the largest known data set for LA segmentation, and to the best of our knowledge, it is the most robust approach that has ever been developed for segmenting LGE-MRIs. The increased accuracy of atrial reconstruction and analysis could potentially improve the understanding and treatment of AF.

Segmentation of histological images and fibrosis identification with a convolutional neural network.

Segmentation of histological images is one of the most crucial tasks for many biomedical analyses involving quantification of certain tissue types, such as fibrosis via Masson's trichrome staining. However, challenges are posed by the high variability and complexity of structural features in such images, in addition to imaging artifacts. Further, the conventional approach of manual thresholding is labor-intensive, and highly sensitive to inter- and intra-image intensity variations. An accurate and robust automated segmentation method is of high interest. We propose and evaluate an elegant convolutional neural network (CNN) designed for segmentation of histological images, particularly those with Masson's trichrome stain. The network comprises 11 successive convolutional - rectified linear unit - batch normalization layers. It outperformed state-of-the-art CNNs on a dataset of cardiac histological images (labeling fibrosis, myocytes, and background) with a Dice similarity coefficient of 0.947. With 100 times fewer (only 300,000) trainable parameters than the state-of-the-art, our CNN is less susceptible to overfitting, and is efficient. Additionally, it retains image resolution from input to output, captures fine-grained details, and can be trained end-to-end smoothly. To the best of our knowledge, this is the first deep CNN tailored to the problem of concern, and may potentially be extended to solve similar segmentation tasks to facilitate investigations into pathology and clinical treatment.