Modeling neurodevelopmental disorder-associated human AGO1 mutations in Caenorhabditis elegans Argonaute alg-1.

MicroRNAs (miRNA) associate with Argonaute (AGO) proteins and repress gene expression by base pairing to sequences in the 3' untranslated regions of target genes. De novo coding variants in the human AGO genes AGO1 and AGO2 cause neurodevelopmental disorders (NDD) with intellectual disability, referred to as Argonaute syndromes. Most of the altered amino acids are conserved between the miRNA-associated AGO in Homo sapiens and Caenorhabditis elegans, suggesting that the human mutations could disrupt conserved functions in miRNA biogenesis or activity. We genetically modeled four human AGO1 mutations in C. elegans by introducing identical mutations into the C. elegans AGO1 homologous gene, alg-1. These alg-1 NDD mutations cause phenotypes in C. elegans indicative of disrupted miRNA processing, miRISC (miRNA silencing complex) formation, and/or target repression. We show that the alg-1 NDD mutations are antimorphic, causing developmental and molecular phenotypes stronger than those of alg-1 null mutants, likely by sequestrating functional miRISC components into non-functional complexes. The alg-1 NDD mutations cause allele-specific disruptions in mature miRNA profiles, accompanied by perturbation of downstream gene expression, including altered translational efficiency and/or messenger RNA abundance. The perturbed genes include those with human orthologs whose dysfunction is associated with NDD. These cross-clade genetic studies illuminate fundamental AGO functions and provide insights into the conservation of miRNA-mediated post-transcriptional regulatory mechanisms.

A deep learning approach to remove contrast from contrast-enhanced CT for proton dose calculation.

PURPOSE: Non-Contrast Enhanced CT (NCECT) is normally required for proton dose calculation while Contrast Enhanced CT (CECT) is often scanned for tumor and organ delineation. Possible tissue motion between these two CTs raises dosimetry uncertainties, especially for moving tumors in the thorax and abdomen. Here we report a deep-learning approach to generate NCECT directly from CECT. This method could be useful to avoid the NCECT scan, reduce CT simulation time and imaging dose, and decrease the uncertainties caused by tissue motion between otherwise two different CT scans. METHODS: A deep network was developed to convert CECT to NCECT. The network receives a 3D image from CECT images as input and generates a corresponding contrast-removed NCECT image patch. Abdominal CECT and NCECT image pairs of 20 patients were deformably registered and 8000 image patch pairs extracted from the registered image pairs were utilized to train and test the model. CTs of clinical proton patients and their treatment plans were employed to evaluate the dosimetric impact of using the generated NCECT for proton dose calculation. RESULTS: Our approach achieved a Cosine Similarity score of 0.988 and an MSE value of 0.002. A quantitative comparison of clinical proton dose plans computed on the CECT and the generated NCECT for five proton patients revealed significant dose differences at the distal of beam paths. V100% of PTV and GTV changed by 3.5% and 5.5%, respectively. The mean HU difference for all five patients between the generated and the scanned NCECTs was ∼4.72, whereas the difference between CECT and the scanned NCECT was ∼64.52, indicating a ∼93% reduction in mean HU difference. CONCLUSIONS: A deep learning approach was developed to generate NCECTs from CECTs. This approach could be useful for the proton dose calculation to reduce uncertainties caused by tissue motion between CECT and NCECT.

Auto3DCryoMap: an automated particle alignment approach for 3D cryo-EM density map reconstruction.

BACKGROUND: Cryo-EM data generated by electron tomography (ET) contains images for individual protein particles in different orientations and tilted angles. Individual cryo-EM particles can be aligned to reconstruct a 3D density map of a protein structure. However, low contrast and high noise in particle images make it challenging to build 3D density maps at intermediate to high resolution (1-3 Å). To overcome this problem, we propose a fully automated cryo-EM 3D density map reconstruction approach based on deep learning particle picking. RESULTS: A perfect 2D particle mask is fully automatically generated for every single particle. Then, it uses a computer vision image alignment algorithm (image registration) to fully automatically align the particle masks. It calculates the difference of the particle image orientation angles to align the original particle image. Finally, it reconstructs a localized 3D density map between every two single-particle images that have the largest number of corresponding features. The localized 3D density maps are then averaged to reconstruct a final 3D density map. The constructed 3D density map results illustrate the potential to determine the structures of the molecules using a few samples of good particles. Also, using the localized particle samples (with no background) to generate the localized 3D density maps can improve the process of the resolution evaluation in experimental maps of cryo-EM. Tested on two widely used datasets, Auto3DCryoMap is able to reconstruct good 3D density maps using only a few thousand protein particle images, which is much smaller than hundreds of thousands of particles required by the existing methods. CONCLUSIONS: We design a fully automated approach for cryo-EM 3D density maps reconstruction (Auto3DCryoMap). Instead of increasing the signal-to-noise ratio by using 2D class averaging, our approach uses 2D particle masks to produce locally aligned particle images. Auto3DCryoMap is able to accurately align structural particle shapes. Also, it is able to construct a decent 3D density map from only a few thousand aligned particle images while the existing tools require hundreds of thousands of particle images. Finally, by using the pre-processed particle images, Auto3DCryoMap reconstructs a better 3D density map than using the original particle images.

DeepCryoPicker: fully automated deep neural network for single protein particle picking in cryo-EM.

BACKGROUND: Cryo-electron microscopy (Cryo-EM) is widely used in the determination of the three-dimensional (3D) structures of macromolecules. Particle picking from 2D micrographs remains a challenging early step in the Cryo-EM pipeline due to the diversity of particle shapes and the extremely low signal-to-noise ratio of micrographs. Because of these issues, significant human intervention is often required to generate a high-quality set of particles for input to the downstream structure determination steps. RESULTS: Here we propose a fully automated approach (DeepCryoPicker) for single particle picking based on deep learning. It first uses automated unsupervised learning to generate particle training datasets. Then it trains a deep neural network to classify particles automatically. Results indicate that the DeepCryoPicker compares favorably with semi-automated methods such as DeepEM, DeepPicker, and RELION, with the significant advantage of not requiring human intervention. CONCLUSIONS: Our framework combing supervised deep learning classification with automated un-supervised clustering for generating training data provides an effective approach to pick particles in cryo-EM images automatically and accurately.

Effect of Trimetazidine on Diabetic Patients with Coronary Heart Diseases: A Meta-Analysis of Randomized, Controlled Trials.

Objective To explore the therapeutic effects of trimetazidine (TMZ) on diabetic patients with coronary heart diseases.Methods We conducted a comprehensive electronic search of PubMed, EMBASE, and Cochrane databases between the inception dates of databases and May 2019 (last search conducted on 30 May 2019) to identify randomized controlled trials. The evaluation method recommended by Cochrane Collaboration for bias risk assessment was employed for quality assessment. Random or fixed models were used to investigate pooled mean differences in left ventricular function, serum glucose metabolism, serum lipid profile, myocardial ischemia episodes and exercise tolerance with effect size indicated by the 95% confidence interval (CI).Results Additional TMZ treatment contributed to considerable improvement of left ventricular ejection fraction (WMD=4.39, 95%CI: 3.83, 4.95, P<0.00001), left ventricular end diastolic diameter (WMD=-3.17, 95%CI: -4.90, -1.44, P=0.0003) and left ventricular end systolic diameter (WMD=-4.69, 95%CI: -8.66, -0.72, P=0.02). TMZ administration also significantly decreased fasting blood glucose (SMD=-0.43, 95%CI: -0.70, -0.17, P=0.001), glycosylated hemoglobin level (WMD=-0.59, 95%CI: -0.95, -0.24, P=0.001), serum level of total cholesterol (WMD=-20.36, 95%CI: -39.80, -0.92, P=0.04), low-density lipoprotein cholesterol (WMD=-20.12, 95%CI: -32.95, -7.30, P=0.002) and incidence of myocardial ischemia episodes (SMD=-0.84, 95%CI: -1.50, -0.18, P=0.01). However, there were no significant differences in serum triglyceride level, high-density lipoprotein cholesterol, exercise tolerance between the TMZ group and the control group. Conclusion TMZ treatment in diabetic patients with coronary heart disease is effective to improve cardiac function, serum glucose and lipid metabolism and clinical symptoms.

Synthesis and anti-tumor activity of [1,4] dioxino [2,3-f] quinazoline derivatives as dual inhibitors of c-Met and VEGFR-2.

Both c-Met and VEGFR-2 were important targets for cancer therapies. In order to develop reversible and non-covalent c-Met and VEGFR-2 dual inhibitors, a series of [1,4]dioxino[2,3-f]quinazoline derivatives were designed and synthesized. The enzyme assay demonstrated that most target compounds had inhibition potency on both c-Met and VEGFR-2 with IC50 values in nanomolar range especially compounds 7m and 7k. Based on further cell proliferation assay in vitro, compound 7k showed significantly anti-tumor activity in vivo on a hepatocellular carcinoma (MHCC97H cells) xenograft mouse model. We docked the compound 7m with c-Met and VEGFR-2 kinases, and interpreted the SAR of these analogues. All results indicated that the target compounds were dual inhibitors of c-Met and VEGFR-2 kinases that held promising potential in cancer therapy.

Tongue Image Analysis and Its Mobile App Development for Health Diagnosis.

Computer-aided diagnosis provides a medical procedure that assists physicians in interpretation of medical images. This work focuses on computer-aided tongue image analysis specifically, based on Traditional Chinese Medicine (TCM). Tongue diagnosis is an important component of TCM. Computerized tongue diagnosis can aid medical practitioners in capturing quantitative features to improve reliability and consistency of diagnosis. Recently, researchers have started to develop computer-aided tongue analysis algorithms based on new advancement in digital photogrammetry, image analysis, and pattern recognition technologies. In this chapter, we will describe our recent work on tongue image analysis as well as a mobile app that we developed based on this technology.

Preparation and diagnostic use of a novel recombinant single-chain antibody against rabies virus glycoprotein.

Rabies virus (RABV) causes a fatal infectious disease, but effective protection may be achieved with the use of rabies immunoglobulin and a rabies vaccine. Virus-neutralizing antibodies (VNA), which play an important role in the prevention of rabies, are commonly evaluated by the RABV neutralizing test. For determining serum VNA levels or virus titers during the RABV vaccine manufacturing process, reliability of the assay method is highly important and mainly dependent on the diagnostic antibody. Most diagnostic antibodies are monoclonal antibodies (mAbs) made from hybridoma cell lines and are costly and time consuming to prepare. Thus, production of a cost-effective mAb for determining rabies VNA levels or RABV titers is needed. In this report, we describe the prokaryotic production of a RABV-specific single-chain variable fragment (scFv) protein with a His-tag (scFv98H) from a previously constructed plasmid in a bioreactor, including the purification and refolding process as well as the functional testing of the protein. The antigen-specific binding characteristics, affinity, and relative affinity of the purified protein were tested. The scFv98H antibody was compared with a commercial RABV nucleoprotein mAb for assaying the VNA level of anti-rabies serum samples from different sources or testing the growth kinetics of RABV strains for vaccine manufactured in China. The results indicated that scFv98H may be used as a novel diagnostic tool to assay VNA levels or virus titers and may be used as an alternative for the diagnostic antibody presently employed for these purposes.

Nuclei engineering for even halide distribution in stable perovskite/silicon tandem solar cells.

Wide-bandgap (WBG) absorbers in tandem configurations suffer from poor crystallinity and weak texture, which leads to severe mixed halide-cation ion migration and phase segregation during practical operation. We control WBG film growth insensitive to compositions by nucleating the 3C phase before any formation of bromine-rich aggregates and 2H phases. The resultant WBG absorbers show improved crystallinity and strong texture with suppressed nonradiative recombination and enhanced resistance to various aging stresses. Perovskite/silicon tandem solar cells achieve power conversion efficiencies of 29.4% (28.8% assessed by a third party) in a 25-square centimeter active area and 32.5% in a 1-square centimeter active area. These solar cells retained 98.3 and 90% of the original efficiency after 1301 and 800 hours of operation at 25° and 50°C, respectively, at the maximum power point (AM 1.5G illumination, full spectrum, 1-sun) when encapsulated.

A binary 2D perovskite passivation for efficient and stable perovskite/silicon tandem solar cells.

To achieve high power conversion efficiency in perovskite/silicon tandem solar cells, it is necessary to develop a promising wide-bandgap perovskite absorber and processing techniques in relevance. To date, the performance of devices based on wide-bandgap perovskite is still limited mainly by carrier recombination at their electron extraction interface. Here, we demonstrate assembling a binary two-dimensional perovskite by both alternating-cation-interlayer phase and Ruddlesden-Popper phase to passivate perovskite/C60 interface. The binary two-dimensional strategy takes effects not only at the interface but also in the bulk, which enables efficient charge transport in a wide-bandgap perovskite solar cell with a stabilized efficiency of 20.79% (1 cm2). Based on this absorber, a monolithic perovskite/silicon tandem solar cell is fabricated with a steady-state efficiency of 30.65% assessed by a third party. Moreover, the tandem devices retain 96% of their initial efficiency after 527 h of operation under full spectral continuous illumination, and 98% after 1000 h of damp-heat testing (85 °C with 85% relative humidity).

Comprehensive review of deep learning in orthopaedics: Applications, challenges, trustworthiness, and fusion.

Deep learning (DL) in orthopaedics has gained significant attention in recent years. Previous studies have shown that DL can be applied to a wide variety of orthopaedic tasks, including fracture detection, bone tumour diagnosis, implant recognition, and evaluation of osteoarthritis severity. The utilisation of DL is expected to increase, owing to its ability to present accurate diagnoses more efficiently than traditional methods in many scenarios. This reduces the time and cost of diagnosis for patients and orthopaedic surgeons. To our knowledge, no exclusive study has comprehensively reviewed all aspects of DL currently used in orthopaedic practice. This review addresses this knowledge gap using articles from Science Direct, Scopus, IEEE Xplore, and Web of Science between 2017 and 2023. The authors begin with the motivation for using DL in orthopaedics, including its ability to enhance diagnosis and treatment planning. The review then covers various applications of DL in orthopaedics, including fracture detection, detection of supraspinatus tears using MRI, osteoarthritis, prediction of types of arthroplasty implants, bone age assessment, and detection of joint-specific soft tissue disease. We also examine the challenges for implementing DL in orthopaedics, including the scarcity of data to train DL and the lack of interpretability, as well as possible solutions to these common pitfalls. Our work highlights the requirements to achieve trustworthiness in the outcomes generated by DL, including the need for accuracy, explainability, and fairness in the DL models. We pay particular attention to fusion techniques as one of the ways to increase trustworthiness, which have also been used to address the common multimodality in orthopaedics. Finally, we have reviewed the approval requirements set forth by the US Food and Drug Administration to enable the use of DL applications. As such, we aim to have this review function as a guide for researchers to develop a reliable DL application for orthopaedic tasks from scratch for use in the market.

Modeling neurodevelopmental disorder-associated hAGO1 mutations in C. elegans Argonaute ALG-1.

MicroRNAs (miRNA) are endogenous non-coding RNAs important for post-transcriptional regulation of gene expression. miRNAs associate with Argonaute proteins to bind to the 3' UTR of target genes and confer target repression. Recently, multiple de novo coding variants in the human Argonaute gene AGO1 ( hAGO1 ) have been reported to cause a neurodevelopmental disorder (NDD) with intellectual disability (ID). Most of the altered amino acids are conserved between the miRNA-associated Argonautes in H. sapiens and C. elegans , suggesting the hAGO1 mutations could disrupt evolutionarily conserved functions in the miRNA pathway. To investigate how the hAGO1 mutations may affect miRNA biogenesis and/or functions, we genetically modeled four of the hAGO1 de novo variants (referred to as NDD mutations) by introducing the identical mutations to the C. elegans hAGO1 homolog, alg-1 . This array of mutations caused distinct effects on C. elegans miRNA functions, miRNA populations, and downstream gene expression, indicative of profound alterations in aspects of miRNA processing and miRISC formation and/or activity. Specifically, we found that the alg-1 NDD mutations cause allele-specific disruptions in mature miRNA profiles both in terms of overall abundances and association with mutant ALG-1. We also observed allele-specific profiles of gene expression with altered translational efficiency and/or mRNA abundance. The sets of perturbed genes include human homologs whose dysfunction is known to cause NDD. We anticipate that these cross-clade genetic studies may advance the understanding of fundamental Argonaute functions and provide insights into the conservation of miRNA-mediated post-transcriptional regulatory mechanisms.

Automated Tongue Feature Extraction for ZHENG Classification in Traditional Chinese Medicine.

ZHENG, Traditional Chinese Medicine syndrome, is an integral and essential part of Traditional Chinese Medicine theory. It defines the theoretical abstraction of the symptom profiles of individual patients and thus, used as a guideline in disease classification in Chinese medicine. For example, patients suffering from gastritis may be classified as Cold or Hot ZHENG, whereas patients with different diseases may be classified under the same ZHENG. Tongue appearance is a valuable diagnostic tool for determining ZHENG in patients. In this paper, we explore new modalities for the clinical characterization of ZHENG using various supervised machine learning algorithms. We propose a novel-color-space-based feature set, which can be extracted from tongue images of clinical patients to build an automated ZHENG classification system. Given that Chinese medical practitioners usually observe the tongue color and coating to determine a ZHENG type and to diagnose different stomach disorders including gastritis, we propose using machine-learning techniques to establish the relationship between the tongue image features and ZHENG by learning through examples. The experimental results obtained over a set of 263 gastritis patients, most of whom suffering Cold Zheng or Hot ZHENG, and a control group of 48 healthy volunteers demonstrate an excellent performance of our proposed system.

Contour interpolation by deep learning approach.

Purpose: Contour interpolation is an important tool for expediting manual segmentation of anatomical structures. The process allows users to manually contour on discontinuous slices and then automatically fill in the gaps, therefore saving time and efforts. The most used conventional shape-based interpolation (SBI) algorithm, which operates on shape information, often performs suboptimally near the superior and inferior borders of organs and for the gastrointestinal structures. In this study, we present a generic deep learning solution to improve the robustness and accuracy for contour interpolation, especially for these historically difficult cases. Approach: A generic deep contour interpolation model was developed and trained using 16,796 publicly available cases from 5 different data libraries, covering 15 organs. The network inputs were a 128 × 128 × 5 image patch and the two-dimensional contour masks for the top and bottom slices of the patch. The outputs were the organ masks for the three middle slices. The performance was evaluated on both dice scores and distance-to-agreement (DTA) values. Results: The deep contour interpolation model achieved a dice score of 0.95 ± 0.05 and a mean DTA value of 1.09 ± 2.30 mm , averaged on 3167 testing cases of all 15 organs. In a comparison, the results by the conventional SBI method were 0.94 ± 0.08 and 1.50 ± 3.63 mm , respectively. For the difficult cases, the dice score and DTA value were 0.91 ± 0.09 and 1.68 ± 2.28 mm by the deep interpolator, compared with 0.86 ± 0.13 and 3.43 ± 5.89 mm by SBI. The t-test results confirmed that the performance improvements were statistically significant ( p < 0.05 ) for all cases in dice scores and for small organs and difficult cases in DTA values. Ablation studies were also performed. Conclusions: A deep learning method was developed to enhance the process of contour interpolation. It could be useful for expediting the tasks of manual segmentation of organs and structures in the medical images.

Critical contribution of 3' non-seed base pairing to the in vivo function of the evolutionarily conserved let-7a microRNA.

Base pairing of the seed region (g2-g8) is essential for microRNA targeting; however, the in vivo function of the 3' non-seed region (g9-g22) is less well understood. Here, we report a systematic investigation of the in vivo roles of 3' non-seed nucleotides in microRNA let-7a, whose entire g9-g22 region is conserved among bilaterians. We find that the 3' non-seed sequence functionally distinguishes let-7a from its family paralogs. The complete pairing of g11-g16 is essential for let-7a to fully repress multiple key targets, including evolutionarily conserved lin-41, daf-12, and hbl-1. Nucleotides at g17-g22 are less critical but may compensate for mismatches in the g11-g16 region. Interestingly, a certain minimal complementarity to let-7a 3' non-seed sequence can be required even for sites with perfect seed pairing. These results provide evidence that the specific configurations of both seed and 3' non-seed base pairing can critically influence microRNA-mediated gene regulation in vivo.

Analgesic Effects of Epidural Labor Analgesia at Different Periods and Its Effects on Maternal and Infant Outcomes and MiRNA-146b Level.

This paper aimed to analyze the analgesic effects of continuous epidural labor analgesia (ELA) at different periods and its effects on postpartum depression, maternal and infant outcomes, and maternal blood pressure. Giving birth in our hospital from September 2017 to August 2019, 119 primiparas with spontaneous delivery were enrolled and divided into an observation group (65 cases) and a control group (54 cases). Patients in the observation group received epidural block analgesia in advance, whereas those in the control group received epidural block analgesia routinely. At 25 days after delivery, breast milk samples were collected, in which miRNA-146b level was detected by PCR. The patients were compared between the two groups with respect to progress of labor, analgesic effects during 3 stages of labor, labor outcomes, adverse reactions, and levels of NO, ANP, and ET-1 in the parturients' umbilical artery blood. Compared with those in the control group, patients in the observation group had a remarkably higher miRNA-146b level in the breast milk (P < 0.05), remarkably lower average Visual Analogue Scale (VAS) scores during the active phase and the second stage of labor (P < 0.05), and remarkably higher levels of NO, ANP, and ET-1 (P < 0.05). There were no statistically significant differences in adverse reactions and modes of delivery between the two groups (P < 0.05). ELA starting from the latent phase can improve the miRNA-146b level in maternal breast milk, alleviate labor pain of parturients, and shorten stages of labor. Therefore, our study is worthy of clinical promotion. We still need to do more experiments and use more data to conclude more scientific results in future research work.

[Effects of dezocine on cardiac myocytes injury induced by hypoxia and reoxygenation in rats and its mechanism].

Objective: To investigate the mechanisms of dezocine on regulating H9C2 oxidative stress and apoptosis of rat cardiac myocytes induced by hypoxia-reoxygenation(H/R) by regulating the expressions of microRNA-7a- 5p(miR-7a-5p)/ubiquitin E3 ligase tripartite motif 10(TRIM10). Methods: H9C2 cells were divided into control group (cultured normally), H/R group (treated with hypoxia for 3 h and then reoxygenation for 4 h), different doses of dezocine intervention group (H9c2 cells were pretreated with dezocine at the concentrations of 10-7, 10-6 and 10-5 mmol/L for 24 h, and then treated with H/R), H/R+miR-7a-5p group (H9C2 cells were transfected with miR-7a-5p mimics and then treated with H/R), H/R+miR-NC group (H9C2 cells were transfected with miR-NC and then treated with H/R), H/R+Dezocine+anti-miR-7a-5p group (H9c2 cells transfected with anti-miR-7a-5p were pretreated with 10-5 mmol/L dezocine for 24 h, and then treated with H/R), H/R+dezocine+ anti-miR-NC Group (H9c2 cells transfected with anti-miR-NC were pretreated with 10-5 mmol/L dezocine for 24 h, and then treated with H/R). Each group of cells was set with 3 replicate wells, and the experiment was repeated 3 times. The content of malondialdehyde(MDA) and activity of superoxide dismutase(SOD) and glutathione peroxidas(GSH-Px) were detected by the enzyme-linked immunosorbent assay. The cells apoptosis was detected by flow cytometry. The protein expressions of B-cell lymphoma-2(Bcl-2), Bcl-2-associated X protein(Bax) and TRIM10 were detected by Western blot, and the expressions of miR-7a-5p and TRIM10 mRNA were detected by real-time quantitative PCR(RT-qPCR). The double luciferase reporter gene experiment was used to verify the regulatory relationship between miR-7a-5p and TRIM10. Results: Compared with the control group, the MDA content, apoptosis rate, the expression of Bax protein, and the expression of TRIM10 mRNA and protein in the H/R group were all increased (P＜0.05), while the activities of SOD and GSH-Px, and the expressions of Bcl-2 protein and miR-7a-5p were all decreased (P＜0.05). Compared with the H/R group, the MDA content, apoptosis rate, the expression of Bax protein, and the expression of TRIM10 mRNA and protein in the different doses of dezocine intervention group were decreased (P＜0.05), while the activities of SOD and GSH-Px, and the expressions of Bcl-2 protein and miR-7a-5p were all increased (P＜0.05), and there were significant differences in each index between the different doses of dezocine intervention groups (P＜ 0.05). Compared with the H/R+miR-NC group, the MDA content, apoptosis rate, the protein expressions of Bax and TRIM10 in the H/R+miR-7a-5p group were decreased (P＜0.05), while the activities of SOD and GSH-Px, and the expression of Bcl-2 protein were all increased (P＜0.05). Compared with the H/R+dezocine+anti- miR-NC group, the MDA content, apoptosis rate, the protein expressions of Bax and TRIM10 in the H/R+dezocine+anti-miR-7a-5p group were all increased (P＜0.05), while the activities of SOD and GSH-Px, and the expression of Bcl-2 protein were all decreased (P＜0.05). Conclusion: Dezocine can reduce oxidative stress and apoptosis of rat cardiomyocytes H9C2 induced by H/R, which may play a role in regulating the miR-7a-5p / TRIM10 axis.

Digital tongue image analyses for health assessment.

Traditional Chinese Medicine (TCM), as an effective alternative medicine, utilizes tongue diagnosis as a major method to assess the patient's health status by examining the tongue's color, shape, and texture. Tongue images can also give the pre-disease indications without any significant disease symptoms, which provides a basis for preventive medicine and lifestyle adjustment. However, traditional tongue diagnosis has limitations, as the process may be subjective and inconsistent. Hence, computer-aided tongue diagnoses have a great potential to provide more consistent and objective health assessments. This paper reviewed the current trends in TCM tongue diagnosis, including tongue image acquisition hardware, tongue segmentation, feature extraction, color correction, tongue classification, and tongue diagnosis system. We also present a case of TCM constitution classification based on tongue images.

Deepening into the suitability of using pre-trained models of ImageNet against a lightweight convolutional neural network in medical imaging: an experimental study.

Transfer learning (TL) has been widely utilized to address the lack of training data for deep learning models. Specifically, one of the most popular uses of TL has been for the pre-trained models of the ImageNet dataset. Nevertheless, although these pre-trained models have shown an effective performance in several domains of application, those models may not offer significant benefits in all instances when dealing with medical imaging scenarios. Such models were designed to classify a thousand classes of natural images. There are fundamental differences between these models and those dealing with medical imaging tasks regarding learned features. Most medical imaging applications range from two to ten different classes, where we suspect that it would not be necessary to employ deeper learning models. This paper investigates such a hypothesis and develops an experimental study to examine the corresponding conclusions about this issue. The lightweight convolutional neural network (CNN) model and the pre-trained models have been evaluated using three different medical imaging datasets. We have trained the lightweight CNN model and the pre-trained models with two scenarios which are with a small number of images once and a large number of images once again. Surprisingly, it has been found that the lightweight model trained from scratch achieved a more competitive performance when compared to the pre-trained model. More importantly, the lightweight CNN model can be successfully trained and tested using basic computational tools and provide high-quality results, specifically when using medical imaging datasets.