Search

Unreduced gametes through chromosome doubling play a major role in the process of plant polyploidization. Our previous work confirmed that Camellia oleifera can produce natural 2n pollen, and it is possible to induce the 2n pollen formation by high temperature treatment. This study focused on the optimization of the 2n pollen induction technique and the mechanisms of high temperature-induced 2n pollen formation in C. oleifera. We found that the optimal protocol for inducing 2n pollen via high temperature was to perform 45 °C with 4 h at the prophase I stage of the pollen mother cells (PMCs). Meanwhile, high temperature significantly decreased the yield and fertility of 2n pollen. Through the observation of meiosis, abnormal chromosome and cytological behaviour was discovered under high-temperature treatment, and we confirmed that the formation of 2n pollen is caused by abnormal cell plate. Based on weighted gene co-expression network analysis, fifteen hub genes related to cell cycle control were identified. After male flower buds were exposed to heat shock, polygalacturonase gene (CoPGX3) was significantly upregulated. We inferred that high temperature causes the CoPGX3 gene to be overexpressed and that CoPGX3 is redistributed into the cytosol where it degrades cytoplasmic pectin, which leads to an abnormal cell plate. Furthermore, abnormal cytokinesis resulted in the formation of dyads and triads, and PMCs divided to produce 2n pollen. Our findings provide new insights into the mechanism of 2n pollen induced by high temperature in a woody plant and lay a foundation for further ploidy breeding of C. oleifera.

Background: Various heart diseases ultimately lead to chronic heart failure (CHF). In CHF, the inflammatory response is associated with pyroptosis, which is mediated by the NOD-like receptor protein 3 (NLRP3) inflammasome. Fu Xin decoction (FXD) is commonly used in clinical practice to treat CHF and improve inflammatory conditions. However, the specific pharmacological mechanisms of action for FXD in these processes have yet to be fully understood. Purpose: The objective of this study was to examine the protective mechanism of FXT against CHF, both in H9c2 cells and mice. Method: A CHF mouse model was established, and the effect of FXD was observed via gavage. Cardiac function was evaluated using echocardiography, while serum BNP and LDH levels were analyzed to assess the severity of CHF. Hematoxylin and eosin staining (H&E) and Masson staining were performed to evaluate myocardial pathological changes, and TdT-mediated dUTP Nick-End Labeling staining was used to detect DNA damage. Additionally, doxorubicin was utilized to induce myocardial cell injury in H9c2 cells, establishing a relevant model. CCK8 was used to observe cell viability and detect LDH levels in the cell supernatant. Subsequently, the expression of pyroptosis-related proteins was detected using immunohistochemistry, immunofluorescence, and western blotting. Finally, the pharmacological mechanism of FXD against CHF was further validated by treating H9c2 cells with an NLRP3 activator and inducing NLRP3 overexpression. Result: According to current research findings, echocardiography demonstrated a significant improvement of cardiac function by FXD, accompanied by reduced levels of BNP and LDH, indicating the amelioration of cardiac injury in CHF mice. FXD exhibited the ability to diminish serum CRP and MCP inflammatory markers in CHF mice. The results of HE and Masson staining analyses revealed a significant reduction in pathological damage of the heart tissue following FXD treatment. The CCK8 assay demonstrated the ability of FXD to enhance H9c2 cell viability, improve cell morphology, decrease LDH levels in the cell supernatant, and alleviate cell damage. Immunohistochemistry, Western blotting, and immunofluorescence staining substantiated the inhibitory effect of FXD on the NLRP3/caspase-1/GSDMD pyroptosis signaling pathway in both CHF and H9c2 cell injury models. Ultimately, the administration of the NLRP3 activator (Nigericin) and the overexpression of NLRP3 counteract the effects of FXD on cardiac protection and pyroptosis inhibition in vitro. Conclusion: FXD exhibits a cardioprotective effect, improving CHF and alleviating pyroptosis by inhibiting the NLRP3/caspase-1/GSDMD pathway.

Cadmium (Cd) contamination presents a significant challenge in global agriculture. This study explores the efficacy of chemical induction, specifically using sodium chloride (NaCl), to limit Cd uptake in tobacco (Nicotiana tabacum) and assesses its impact on essential divalent metal ions (DMIs). We conducted a comprehensive analysis encompassing ion absorption, root histology, and biochemistry to understand the influence of this method. Our results revealed that NaCl induction led to a notable 30 % decrease in Cd absorption, while maintaining minimal impact on zinc (Zn) uptake. Intriguingly, the absence of essential DMIs, such as calcium (Ca), magnesium (Mg), and Zn, was found to diminish the plant's capacity to absorb Cd. Furthermore, moderate NaCl induction resulted in an increased diameter of the root stele and enhanced lignin content, indicating a restriction of Cd absorption through the apoplastic pathway. Conversely, a compensatory absorption mechanism via the symplastic pathway appeared to be activated in the absence of essential elements. These findings highlight the potential of chemical induction as a strategy to mitigate agricultural Cd risks, offering insights into the complex interplay between plant ion transport pathways and metal uptake regulation.

BackgroundHashimoto’s thyroiditis (HT), a common form of thyroid autoimmunity, is strongly associated with deteriorating clinical status and impaired quality of life. The escalating global prevalence, coupled with the complexity of disease mechanisms, necessitates a comprehensive, bibliometric analysis to elucidate the trajectory, hotspots, and future trends in HT research.ObjectiveThis study aims to illuminate the development, hotspots, and future directions in HT research through systematic analysis of publications, institutions, authors, journals, references, and keywords. Particular emphasis is placed on novel treatment strategies for HT and its complications, highlighting the potential role of genetic profiling and immunomodulatory therapies.MethodsWe retrieved 8,726 relevant documents from the Web of Science Core Collection database spanning from 1 January 1990 to 7 March 2023. Following the selection of document type, 7,624 articles were included for bibliometric analysis using CiteSpace, VOSviewer, and R software.ResultsThe temporal evolution of HT research is categorized into three distinct phases: exploration (1990-1999), rapid development (1999-2000), and steady growth (2000-present). Notably, the United States, China, Italy, and Japan collectively contributed over half (54.77%) of global publications. Among the top 10 research institutions, four were from Italy (4/10), followed by China (2/10) and the United States (2/10). Recent hotspots, such as the roles of gut microbiota, genetic profiling, and nutritional factors in HT management, the diagnostic dilemmas between HT and Grave’s disease, as well as the challenges in managing HT complicated by papillary thyroid carcinoma and type 1 diabetes mellitus, are discussed.ConclusionAlthough North America and Europe have a considerable academic impact, institutions from emerging countries like China are demonstrating promising potential in HT research. Future studies are anticipated to delve deeper into the differential diagnosis of HT and Grave’s disease, the intricate relationship between gut microbiota and HT pathogenesis, clinical management of HT with papillary thyroid carcinoma or type 1 diabetes, and the beneficial effects of dietary modifications and micronutrients supplementation in HT. Furthermore, the advent of genetic profiling and advanced immunotherapies for managing HT offers promising avenues for future research.

Objective: Provide data support for the source tracing and pollution prevention of Pseudomonas aeruginosa in drinking water in Hunan Province. Methods: According to the national food safety standards of GB 8538—2016, the bottled water was tested randomly collected from partial cities and counties in Hunan Province, and the whole genome sequencing and molecular traceability of the 18 strains of Pseudomonas aeruginosa were detected. The carrying of virulence genes and drug resistance genes was detected. Results: It was confirmed that four strains of Pseudomonas aeruginosa showed consistency in terms of geographical distance, genetic distance, pathogenic and drug-resistant genotypes, and it was presumed that there was the same source. Conclusion: The traceability analysis of Pseudomonas aeruginosa in drinking water and the analysis of virulence and drug resistance genes in drinking water can be realized by whole gene sequencing based on 16S rRNA and single-copy orthologous genes.

High-grade pediatric brain tumors exhibit the highest cancer mortality rates in children. While conventional MRI has been widely adopted for examining pediatric high-grade brain tumors clinically, accurate neuroimaging detection and differentiation of tumor histopathology for improved diagnosis, surgical planning, and treatment evaluation, remains an unmet need in their clinical management. We employed a novel Diffusion Histology Imaging (DHI) approach employing diffusion basis spectrum imaging (DBSI) derived metrics as the input classifiers for deep neural network analysis. DHI aims to detect, differentiate, and quantify heterogeneous areas in pediatric high-grade brain tumors, which include normal white matter (WM), densely cellular tumor, less densely cellular tumor, infiltrating edge, necrosis, and hemorrhage. Distinct diffusion metric combination would thus indicate the unique distributions of each distinct tumor histology features. DHI, by incorporating DBSI metrics and the deep neural network algorithm, classified pediatric tumor histology with an overall accuracy of 85.8%. Receiver operating analysis (ROC) analysis suggested DHIs great capability in distinguishing individual tumor histology with AUC values (95% CI) of 0.984 (0.982-0.986), 0.960 (0.956-0.963), 0.991 (0.990-0.993), 0.950 (0.944-0.956), 0.977 (0.973-0.981) and 0.976 (0.972-0.979) for normal WM, densely cellular tumor, less densely cellular tumor, infiltrating edge, necrosis and hemorrhage, respectively. Our results suggest that DBSI-DNN, or DHI, accurately characterized and classified multiple tumor histologic features in pediatric high-grade brain tumors. If these results could be further validated in patients, the novel DHI might emerge as a favorable alternative to the current neuroimaging techniques to better guide biopsy and resection as well as monitor therapeutic response in patients with high-grade brain tumors.

Abstract Background Charlson Comorbidity Index (CCI) is positively associated with all-cause readmission in patients with heart failure (HF) in western countries. However, there is a scarcity of strong scientific evidence supporting the correlation in China. This study aimed at testing this hypothesis in Chinese. Methods We conducted a secondary analysis of 1,946 patients with HF in Zigong Fourth People’s Hospital in China between December 2016 to June 2019. Logistic regression models were used to study the hypotheses, with adjustments for the four regression models. We also explore the linear trend and possible nonlinear relationship between CCI and readmission within six months. We further conducted subgroup analysis and tests for interaction to examine the possible interaction between CCI and the endpoint. Additionally, CCI alone and several combinations of variables based on CCI were used to predict the endpoint. Under the curve (AUC), sensitivity and specificity were reported to evaluate the performance of the predicted model. Results In the adjusted II model, CCI was an independent prognostic factor for readmission within six months in patients with HF (OR = 1.14, 95% CI: 1.03–1.26, P = 0.011). Trend tests revealed that there was a significant linear trend for the association. A nonlinear association was identified between them and the inflection point of CCI was 1. Subgroup analyses and tests for interaction indicated that cystatin played an interactive role in the association. ROC analysis indicated neither CCI alone nor combinations of variables based on CCI were adequate for prediction. Conclusion CCI was independently positively correlated with readmission within six months in patients with HF in Chinese population. However, CCI has limited value on predicting readmission within six months in patients with HF.

DREB is a plant-specific transcription factor family that plays a pleiotropic regulatory role in response to abiotic stresses such as drought and cold. In this study, we identified 51 DREB genes of Camellia oleifera. These CoDREBs ranged from 88 to 518 amino acids (average/median 259/237 aa). The predicted molecular weights (MW) of the CoDREB proteins ranged from 9.7 kDa to 59.6 kDa, and the isoelectric points (pI) ranged from 4.62 to 10.44. A gene structure analysis showed that 43/51 (84.3%) CoDREBs were intronless, and the number of exons varied from one to three. Then, we focused on the response of CoDREB genes in terms of plant drought and cold acclimation. Under short-/long-term drought stress, CoDREB1.2/4.1/4.4/4.8/4.12/4.15/5.1/5.3/5.5/6.2 have different regulations in response to long-term drought response, and CoDREB1.4/2.5/4.6/4.1/6.3/6.5 specifically in the short term. Additionally, in response to mild/severe drought and followed by recovery, we found that CoDREBs may be involved in a complex drought-responsive regulatory network. Under cold stress, CoDREB5.2 and CoDREB6.5 are significantly up-regulated, and CoDREB may participate in the regulation of the low-temperature response of C. oleifera.

PURPOSE: Glioblastoma (GBM) is one of the deadliest cancers with no cure. While conventional MRI has been widely adopted to examine GBM clinically, accurate neuroimaging assessment of tumor histopathology for improved diagnosis, surgical planning, and treatment evaluation remains an unmet need in the clinical management of GBMs. EXPERIMENTAL DESIGN: We employ a novel diffusion histology imaging (DHI) approach, combining diffusion basis spectrum imaging (DBSI) and machine learning, to detect, differentiate, and quantify areas of high cellularity, tumor necrosis, and tumor infiltration in GBM. RESULTS: Gadolinium-enhanced T1-weighted or hyperintense fluid-attenuated inversion recovery failed to reflect the morphologic complexity underlying tumor in patients with GBM. Contrary to the conventional wisdom that apparent diffusion coefficient (ADC) negatively correlates with increased tumor cellularity, we demonstrate disagreement between ADC and histologically confirmed tumor cellularity in GBM specimens, whereas DBSI-derived restricted isotropic diffusion fraction positively correlated with tumor cellularity in the same specimens. By incorporating DBSI metrics as classifiers for a supervised machine learning algorithm, we accurately predicted high tumor cellularity, tumor necrosis, and tumor infiltration with 87.5%, 89.0%, and 93.4% accuracy, respectively. CONCLUSIONS: Our results suggest that DHI could serve as a favorable alternative to current neuroimaging techniques in guiding biopsy or surgery as well as monitoring therapeutic response in the treatment of GBM.

Grafting serves as a pervasive methodology in the propagation of jujube plants, yet the nuanced molecular mechanisms that dictate rootstock-scion interactions remain inadequately understood. We examined the transcriptomic landscapes of jujube heterograft combinations. Contrary to self-grafting conditions, early-stage heterografting yielded no discernible advantageous effects on scion biomass accretion. Interestingly, the rootstock’s biomass was significantly impacted by the scion, varying by species. The differentially expressed genes (DEGs) across graft combinations were mainly enriched for the vegetative growth of rootstocks, secondary metabolism, and resistance improvement of scions. Weighted gene co-expression network analysis (WGCNA) identified 27 hub genes which were negatively correlated with plant growth and biomass enlargement, serving as negative regulators, while the genes, L484_001734, ATHB-15, and BPC1, were involved in positive regulation. With biomass measurements, the transcriptomic data supported that an incomplete vascular recovery during early grafting led to nutrient accumulation at the graft junction, temporarily limiting plant growth while providing development resources for callus. In summary, our work has demonstrated that the intricate biological connections between the rootstock and scion guarantee the effective jujube grafting process by elucidating the molecular processes involved in the process.

The biosynthesis and distribution of lignans in medicinal plants, particularly in Schisandra sphenanthera, hold significant pharmacological importance. This study bridges the knowledge gap in understanding the tissue-specific biosynthesis and distribution of these compounds, with a focus on Gomisin J. Our phytochemical analysis revealed a distinct accumulation pattern of Gomisin J, predominantly in the roots, contrasting with the distribution of Pregomisin and Dihydroguaiaretic acid. This finding highlights the roots’ unique role in lignan storage and biosynthesis. Further, differential gene expression analysis across various tissues illuminated the biosynthetic pathways and regulatory mechanisms of these lignans. Utilizing Weighted Gene Co-expression Network Analysis (WGCNA), we identified the MEtan module as a key player, strongly correlated with Gomisin J levels. This module’s in-depth examination revealed the crucial involvement of four cytochrome P450 (CYP) enzymes and eight transcription factors. Notably, the CYP genes DN6828 and DN2874-i3 exhibited up-regulation in roots across both male and female plants, while DN51746 was specifically up-regulated in male roots, indicating a potential gender-specific aspect in Gomisin J biosynthesis. Comparative analysis with functionally characterized CYP71A homologs suggests these CYP genes might be involved in distinct biosynthetic pathways, including terpenoids, alkaloids, and phenylpropanoids, and potentially in lignan biosynthesis. This hypothesis, supported by their more than 55% identity with CYP71As and strong correlation with Gomisin J concentration, opens avenues for novel discoveries in lignan biosynthesis, pending further functional characterization. Our research provides a comprehensive understanding of the genetic and metabolic mechanisms underlying the tissue-specific distribution of lignans in Schisandra sphenanthera, offering valuable insights for their pharmacological exploitation.

Kadsura coccinea is a medicinal plant from the Schisandraceae family that is native to China and has great pharmacological potential due to its lignans. However, there are significant knowledge gaps regarding the genetic and molecular mechanisms of lignans. We used transcriptome sequencing technology to analyze root, stem, and leaf samples, focusing on the identification and phylogenetic analysis of Cytochrome P450 (CYP) genes. High-quality data containing 158,385 transcripts and 68,978 unigenes were obtained. In addition, 36,293 unigenes in at least one database, and 23,335 across five databases (Nr, KEGG, KOG, TrEMBL, and SwissProt) were successfully annotated. The KEGG pathway classification and annotation of these unigenes identified 10,825 categorized into major metabolic pathways, notably phenylpropanoid biosynthesis, which is essential for lignan synthesis. A key focus was the identification and phylogenetic analysis of 233 Cytochrome P450 (CYP) genes, revealing their distribution across 38 families in eight clans, with roots showing specific CYP gene expression patterns indicative of their role in lignan biosynthesis. Sequence alignment identified 22 homologous single genes of these CYPs, with 6 homologous genes of CYP719As and 1 of CYP81Qs highly expressed in roots. Our study significantly advances the understanding of the biosynthesis of dibenzocyclooctadiene lignans, offering valuable insights for future pharmacological research and development.

Understanding the molecular mechanisms that regulate flower growth, development, and opening is of paramount importance, yet these processes remain less explored at the genetic level. Flower development in Hydrangea paniculata ‘Vanilla Strawberry’ is finely tuned through hormonal signals, yet the genetic underpinnings are not well defined. This study addresses the gap by examining the influence of gibberellic acid (GA3), salicylic acid (SA), and ethylene (ETH) on the flowering traits and underlying molecular responses. Treatment with 100 mg/L SA significantly improved chlorophyll content and bolstered the accumulation of soluble sugars and proteins, advancing the flowering onset by 6 days and lengthening the flowering period by 11 days. Concurrently, this treatment enhanced inflorescence dimensions, increasing length, width, and petal area by 22.76%, 26.74%, and 27.45%, respectively. Contrastingly, 100 mg/L GA3 expanded inflorescence size but postponed flowering initiation and decreased inflorescence count. Higher concentrations of SA and GA3, as well as any concentration of ETH, resulted in delayed flowering and inferior inflorescence attributes. A physiological analysis over 50 days revealed that these regulators variably affected sugar and protein levels and modified antioxidant enzyme activities. An RNA-seq analysis during floral development highlighted significant transcriptomic reprogramming, with SA treatment downregulating Myb transcription factors, implicating them in the modulation of flowering timing and stress adaptation. These findings illuminate the complex interplay between hormonal treatments, gene expression, and flowering phenotypes in Hydrangea paniculata, offering valuable perspectives for ornamental horticulture optimization.

Understanding the signaling pathways activated in response to these combined stresses and their crosstalk is crucial to breeding crop varieties with dual or multiple tolerances. However, most studies to date have predominantly focused on individual stress factors, leaving a significant gap in understanding plant responses to combined biotic and abiotic stresses. The bHLH family plays a multifaceted regulatory role in plant response to both abiotic and biotic stresses. In order to comprehensively identify and analyze the bHLH gene family in rice, we identified putative OsbHLHs by multi-step homolog search, and phylogenic analysis, molecular weights, isoelectric points, conserved domain screening were processed using MEGAX version 10.2.6. Following, integrative transcriptome analysis using 6 RNA-seq data including Xoo infection, heat, and cold stress was processed. The results showed that 106 OsbHLHs were identified and clustered into 17 clades. Os04g0301500 and Os04g0489600 are potential negative regulators of Xoo resistance in rice. In addition, Os04g0301500 was involved in non-freezing temperatures (around 4°C) but not to 10°C cold stresses, suggesting a complex interplay with temperature signaling pathways. The study concludes that Os04g0301500 may play a crucial role in integrating biotic and abiotic stress responses in rice, potentially serving as a key regulator of plant resilience under changing environmental conditions, which could be important for further multiple stresses enhancement and molecular breeding through genetic engineering in rice.

With the rapid development of science, technology, and engineering, large amounts of data have been generated in many fields in the past 20 years. In the process of medical research, data are constantly generated, and large amounts of real-world data form a “data disaster.” Effective data analysis and mining are based on data availability and high data quality. The premise of high data quality is the need to clean the data. Data cleaning is the process of detecting and correcting “dirty data,” which is the basis of data analysis and management. Moreover, data cleaning is a common technology for improving data quality. However, the current literature on real-world research provides little guidance on how to efficiently and ethically set up and perform data cleaning. To address this issue, we proposed a data cleaning framework for real-world research, focusing on the 3 most common types of dirty data (duplicate, missing, and outlier data), and a normal workflow for data cleaning to serve as a reference for the application of such technologies in future studies. We also provided relevant suggestions for common problems in data cleaning.

Objective: This study aims to investigate the predictive factors and efficacy of traditional Chinese medicine Shengji Ointment in the treatment of diabetic foot ulcers in the elderly population, with the intent of formulating an effective predictive model for deep diabetic foot ulcer healing. The importance of this research lies in its provision of new perspectives and tools for addressing the severe health impact of diabetic foot ulcers in the elderly population, considering the complexity and diversity of its treatment methods.Methods: The study includes 180 elderly patients with Wagner grade 3-4 diabetic foot ulcers that involve the tendon or fascia. The dependent variable is the initiation time of granulation tissue development. Independent variables encompass demographic information, a treatment strategy including Shengji Ointment, pre-treatment trauma assessment data, routine blood count, and biochemical index test results. Lasso regression is employed for variable selection, and Cox regression is utilized for the construction of a prediction model. A nomogram is generated to authenticate the model.Results: The Chinese Medicine treatment approach, ulcer location, creatinine levels, BMI, and haemoglobin levels are identified as independent predictors of granulation tissue development in diabetic foot ulcers. The combined treatment of Chinese herbal Shengji ointment and bromelain positively influenced granulation tissue development. The location of plantar ulcers, impaired renal functionality, obesity, and anaemia are established as independent risk factors that might influence the speed and probability of ulcer healing. The area under the time-dependent ROC curve fluctuates between 0.7 and 0.8, demonstrating substantial discrimination and calibration of the model.Conclusion: The study ascertains that a combined treatment strategy incorporating Shengji Ointment demonstrates greater effectiveness than the use of cleansing gel debridement alone in facilitating the healing of Wagner grade 3 or higher diabetic foot ulcers. Furthermore, the predictive model developed in this research serves as a valuable tool in evaluating the efficacy of Chinese Medicine treatments like Shengji Ointment for diabetic foot ulcers in the elderly. It aids clinicians in effectively assessing and adjusting treatment strategies, thereby proving its significant application value in clinical practice.Clinical Trial Registration: (https://www.chictr.org.cn/hvshowproject.html?id=73862&v=1.5&u_atoken=b403af53-d3b9-41ae-a7e2-db5498609b0c&u_asession=01tNh69p235bMUO4CmHIXcv8Hxirl5-557Duue9QB5lGfl3mf8IvPlcs2kN2zC30voX0KNBwm7Lovlpxjd_P_q4JsKWYrT3W_NKPr8w6oU7K_AyPrQhedMUWBMR2-ZDL_KO0uwDPR9XlF566xraDvT9mBkFo3NEHBv0PZUm6pbxQU&u_asig=05Kd_Q8fjv-24MVbZpOS9ef3xuCCN-tSVH5eUoJKgNLM7E0-n0zMpW6xLq9gh9aUhkKEEA15rdDoCydncF99APBwVSaTPgEG_V_B1iT4wimdCTxV_4ZVbTlDewxyQtE4YgU4-Oza7KPi94RJ64Utel0yZfqg3Tlm-bVxFNOY-zXFP9JS7q8ZD7Xtz2Ly-b0kmuyAKRFSVJkkdwVUnyHAIJzSYJ6SfhFl0WMTCCasZ7zV2I2qfyrp5m-SELPVeREKgX_6yRmLu26qT8kGfcS-Yaeu3h9VXwMyh6PgyDIVSG1W-7D_Sko5YQtpDbs3uvezYkZcUUY4o9-zDPaoYelmMDs8u7I4TPvtCXaPp44YUJcQ9bHr-_RmKA5V8nji3daArhmWspDxyAEEo4kbsryBKb9Q&u_aref=NNH1nHSUCE6pNvCilV%2F1MD0aERs%3D), identifier (ChiCTR2000039327).

OBJECTIVE: Multiple sclerosis (MS) lesions are heterogeneous with regard to inflammation, demyelination, axonal injury, and neuronal loss. We previously developed a diffusion basis spectrum imaging (DBSI) technique to better address MS lesion heterogeneity. We hypothesized that the profiles of multiple DBSI metrics can identify lesion-defining patterns. Here we test this hypothesis by combining a deep learning algorithm using deep neural network (DNN) with DBSI and other imaging methods. METHODS: Thirty-eight MS patients were scanned with diffusion-weighted imaging, magnetization transfer imaging, and standard conventional MRI sequences (cMRI). A total of 499 regions of interest were identified on standard MRI and labeled as persistent black holes (PBH), persistent gray holes (PGH), acute black holes (ABH), acute gray holes (AGH), nonblack or gray holes (NBH), and normal appearing white matter (NAWM). DBSI, diffusion tensor imaging (DTI), and magnetization transfer ratio (MTR) were applied to the 43,261 imaging voxels extracted from these ROIs. The optimized DNN with 10 fully connected hidden layers was trained using the imaging metrics of the lesion subtypes and NAWM. RESULTS: Concordance, sensitivity, specificity, and accuracy were determined for the different imaging methods. DBSI-DNN derived lesion classification achieved 93.4% overall concordance with predetermined lesion types, compared with 80.2% for DTI-DNN model, 78.3% for MTR-DNN model, and 74.2% for cMRI-DNN model. DBSI-DNN also produced the highest specificity, sensitivity, and accuracy. CONCLUSIONS: DBSI-DNN improves the classification of different MS lesion subtypes, which could aid clinical decision making. The efficacy and efficiency of DBSI-DNN shows great promise for clinical applications in automatic MS lesion detection and classification.