Electronic Structure Modulation Via Iron-Incorporated NiO to Boost Urea Oxidation/Oxygen Evolution Reaction.

The urea-assisted water splitting not only enables a reduction in energy consumption during hydrogen production but also addresses the issue of environmental pollution caused by urea. Doping heterogeneous atoms in Ni-based electrocatalysts is considered an efficient means for regulating the electronic structure of Ni sites in catalytic processes. However, the current methodologies for synthesizing heteroatom-doped Ni-based electrocatalysts exhibit certain limitations, including intricate experimental procedures, prolonged reaction durations, and low product yield. Herein, Fe-doped NiO electrocatalysts were successfully synthesized using a rapid and facile solution combustion method, enabling the synthesis of 1.1107 g within a mere 5 min. The incorporation of iron atoms facilitates the modulation of the electronic environment around Ni atoms, generating a substantial decrease in the Gibbs free energy of intermediate species for the Fe-NiO catalyst. This modification promotes efficient cleavage of C-N bonds and consequently enhances the catalytic performance of UOR. Benefiting from the tunability of the electronic environment around the active sites and its efficient electron transfer, Fe-NiO electrocatalysts only needs 1.334 V to achieve 50 mA cm-2 during UOR. Moreover, Fe-NiO catalysts were integrated into a dual electrode urea electrolytic system, requiring only 1.43 V of cell voltage at 10 mA cm-2.

Tricoordinated Single-Atom Cobalt in Zeolite Boosting Propane Dehydrogenation.

Propane dehydrogenation (PDH) reaction has emerged as one of the most promising propylene production routes due to its high selectivity for propylene and good economic benefits. However, the commercial PDH processes usually rely on expensive platinum-based and poisonous chromium oxide based catalysts. The exploration of cost-effective and ecofriendly PDH catalysts with excellent catalytic activity, propylene selectivity, and stability is of great significance yet remains challenging. Here, we discovered a new active center, i.e., an unsaturated tricoordinated cobalt unit (≡Si-O)CoO(O-Mo) in a molybdenum-doped silicalite-1 zeolite, which afforded an unprecedentedly high propylene formation rate of 22.6 molC3H6 gCo-1 h-1 and apparent rate coefficient of 130 molC3H6 gCo-1 h-1 bar-1 with >99% of propylene selectivity at 550 °C. Such activity is nearly one magnitude higher than that of previously reported Co-based catalysts in which cobalt atoms are commonly tetracoordinated, and even superior to that of most of Pt-based catalysts under similar operating conditions. Density functional theory calculations combined with the state-of-the-art characterizations unravel the role of the unsaturated tricoordinated Co unit in facilitating the C-H bond-breaking of propane and propylene desorption. The present work opens new opportunities for future large-scale industrial PDH production based on inexpensive non-noble metal catalysts.

Confinement of CsPbBr3 Perovskite Nanocrystals into Extra-large-pore Zeolite for Efficient and Stable Photocatalytic Hydrogen Evolution.

Metal halide perovskites (MHPs), renowned for their outstanding optoelectronic properties, hold significant promise as photocatalysts for hydrogen evolution reaction (HER). However, the low stability and insufficient exposure of catalytically active sites of bulky MHPs seriously impair their catalytic efficiency. Herein, we utilized an extra-large-pore zeolite ZEO-1 (JZO) as a host to confine and stabilize the CsPbBr3 nanocrystals (3.4 nm) for boosting hydrogen iodide (HI) splitting. The as-prepared CsPbBr3@ZEO-1 featured sufficiently exposed active sites, superior stability in acidic media, along with intrinsic extra-large pores of ZEO-1 that were favorable for molecule/ion adsorption and diffusion. Most importantly, the unique nanoconfinement effect of ZEO-1 led to the narrowing of the band gap of CsPbBr3, allowing for more efficient light utilization. As a result, the photocatalytic HER rate of the as-prepared CsPbBr3@ZEO-1 photocatalyst was increased to 1734 µmol ⋅ h-1 ⋅ g-1 (CsPbBr3) under visible light irradiation compared with bulk CsPbBr3 (11 µmol ⋅ h-1 ⋅ g-1 (CsPbBr3)), and the long-term durability (36 h) can be achieved. Furthermore, Pt was incorporated with well-dispersed CsPbBr3 nanocrystals into ZEO-1, resulting in a significant enhancement in activity (4826 µmol ⋅ h-1 ⋅ g-1 (CsPbBr3)), surpassing most of the Pt-integrated perovskite-based photocatalysts. Density functional theory (DFT) calculations and charge-carrier dynamics investigation revealed that the dramatically boosted photocatalytic performance of Pt/CsPbBr3@ZEO-1 could be attributed to the promotion of charge separation and transfer, as well as to the substantially lowered energy barrier for HER. This work highlights the advantage of extra-large-pore zeolites as the nanoscale platform to accommodate multiple photoactive components, opening up promising prospects in the design and exploitation of novel zeolite-confined photocatalysts for energy harvesting and storage.

Discrimination of benign and malignant breast lesions on dynamic contrast-enhanced magnetic resonance imaging using deep learning.

PURPOSE: To evaluate the capability of deep transfer learning (DTL) and fine-tuning methods in differentiating malignant from benign lesions in breast dynamic contrast-enhanced magnetic resonance imaging (DCE-MRI). METHODS: The diagnostic efficiencies of the VGG19, ResNet50, and DenseNet201 models were tested under the same dataset. The model with the highest performance was selected and modified utilizing three fine-tuning strategies (S1-3). Fifty additional lesions were selected to form the validation set to verify the generalization abilities of these models. The accuracy (Ac) of the different models in the training and test sets, as well as the precision (Pr), recall rate (Rc), F1 score (), and area under the receiver operating characteristic curve (AUC), were primary performance indicators. Finally, the kappa test was used to compare the degree of agreement between the DTL models and pathological diagnosis in differentiating malignant from benign breast lesions. RESULTS: The Pr, Rc, f1, and AUC of VGG19 (86.0%, 0.81, 0.81, and 0.81, respectively) were higher than those of DenseNet201 (70.0%, 0.61, 0.63, and 0.61, respectively) and ResNet50 (61.0%, 0.59, 0.59, and 0.59). After fine-tuning, the Pr, Rc, f1, and AUC of S1 (87.0%, 0.86, 0.86, and 0.86, respectively) were higher than those of VGG19. Notably, the degree of agreement between S1 and pathological diagnosis in differentiating malignant from benign breast lesions was 0.720 (κ = 0.720), which was higher than that of DenseNet201 (κ = 0.440), VGG19 (κ = 0.640), and ResNet50 (κ = 0.280). CONCLUSION: The VGG19 model is an effective method for identifying benign and malignant breast lesions on DCE-MRI, and its performance can be further improved via fine-tuning. Overall, our findings insinuate that this technique holds potential clinical application value.

Encapsulation of Palladium Carbide Subnanometric Species in Zeolite Boosts Highly Selective Semihydrogenation of Alkynes.

The selective hydrogenation of alkynes to alkenes is a crucial step in the synthesis of fine chemicals. However, the widely utilized palladium (Pd)-based catalysts often suffer from poor selectivity. In this work, we demonstrate a carbonization-reduction method to create palladium carbide subnanometric species within pure silicate MFI zeolite. The carbon species can modify the electronic and steric characteristics of Pd species by forming the predominant Pd-C4 structure and, meanwhile, facilitate the desorption of alkenes by forming the Si-O-C structure with zeolite framework, as validated by the state-of-the-art characterizations and theoretical calculations. The developed catalyst shows superior performance in the selective hydrogenation of alkynes over mild conditions (298 K, 2 bar H2 ), with 99 % selectivity to styrene at a complete conversion of phenylacetylene. In contrast, the zeolite-encapsulated carbon-free Pd catalyst and the commercial Lindlar catalyst show only 15 % and 14 % selectivity to styrene, respectively, under identical reaction conditions. The zeolite-confined Pd-carbide subnanoclusters promise their superior properties in semihydrogenation of alkynes.

Comprehensive Analyses of Breads Supplemented with Tannic Acids.

Tannic acid (TA) has been recently considered as a new dough additive for improving the bread-making quality of wheat. However, the effects of TA supplementation on the sensory quality parameters (color, crumb grain structure, and sensory properties) of bread have not been studied. Further, the potential of TA supplementation in bread-making quality improvement has not been evaluated by using commercial flour. In the present study, three commercial wheat flours (namely, XL, QZG, and QZZ) with different gluten qualities were used to evaluate the effects of TA supplementation (in concentrations of 0.1% and 0.3%, respectively). TA supplementation did not change the proximate composition of the breads but increased the volumes and specific volumes of XL and QZG breads. TA supplementation enhanced antioxidant activities, with 0.3% TA significantly increasing the antioxidant capacities of bread made from all three flour samples by approximately four-fold (FRAP method)/three-fold (ABTS method). Positive effects of TA on the reduction in crumb hardness, gumminess, and chewiness were observed in the XL bread, as determined by the texture profile analysis. For the analyses on visual and sensory attributes, our results suggest that TA did not affect the crust color, but only slightly reduced the L* (lightness) and b* (yellowness) values of the crumb and increased the a* (redness) value. TA supplementation also increased the porosity, total cell area, and mean cell area. Satisfactorily, the sensory evaluation results demonstrate that TA-supplemented breads did not exhibit negative sensory attributes when compared to the non-TA-added breads; rather, the attributes were even increased. In summary, TA-supplemented breads generally had not only better baking quality attributes and enhanced antioxidant activities, but, more importantly, presented high consumer acceptance in multiple commercial flour samples. Our results support the commercial potential of TA to be used as a dough improver.

Integrative gene duplication and genome-wide analysis as an approach to facilitate wheat reverse genetics: An example in the TaCIPK family.

INTRODUCTION: Reverse genetic studies conducted in the plant with a complex or polyploidy genome enriched with large gene families (like wheat) often meet challenges in identifying the key candidate genes related to important traits and prioritizing the genes for functional experiments. OBJECTIVE: To overcome the above-mentioned challenges of reverse genetics, this work aims to establish an efficient multi-species strategy for genome-wide gene identification and prioritization of the key candidate genes. METHODS: We established the integrative gene duplication and genome-wide analysis (iGG analysis) as a strategy for pinpointing key candidate genes deserving functional research. The iGG captures the evolution, and the expansion/contraction of large gene families across phylogeny-related species and integrates spatial-temporal expression information for gene function inference. Transgenic approaches were also employed to functional validation. RESULTS: As a proof-of-concept for the iGG analysis, we took the wheat calcineurin B-like protein-interacting protein kinases (CIPKs) family as an example. We identified CIPKs from seven monocot species, established the orthologous relationship of CIPKs between rice and wheat, and characterized Triticeae-specific CIPK duplicates (e.g., CIPK4 and CIPK17). Integrated with our analysis of CBLs and CBL-CIPK interaction, we revealed that divergent expressions of TaCBLs and TaCIPKs could play an important role in keeping the stoichiometric balance of CBL-CIPK. Furthermore, we validated the function of TaCIPK17-A2 in the regulation of drought tolerance by using transgenic approaches. Overexpression of TaCIPK17 enhanced antioxidant capacity and improved drought tolerance in wheat. CONCLUSION: The iGG analysis leverages evolutionary and comparative genomics of crops with large genomes to rapidly highlight the duplicated genes potentially associated with speciation, domestication and/or particular traits that deserve reverse-genetic functional studies. Through the identification of Triticeae-specific TaCIPK17 duplicates and functional validation, we demonstrated the effectiveness of the iGG analysis and provided a new target gene for improving drought tolerance in wheat.

A straight-forward gene mining strategy to identify TaCIPK19 as a new regulator of drought tolerance in wheat.

Drought stress is one of the most impactful abiotic stresses to global wheat production. Therefore, identifying key regulators such as the calcineurin B-like protein interacting protein kinase (CIPK) in the signaling cascades known to coordinate developmental cues and environmental stimuli represents a useful approach to improve drought tolerance. However, functional studies have been very limited partly due to the difficulties in prioritizing candidate genes from the large TaCIPK family. To address this issue, we demonstrate a straight-forward strategy by analyzing gene expression patterns in response to phytohormones or stresses and identified TaCIPK19 as a new regulator to improve drought tolerance. The effects of TaCIPK19 on drought tolerance were evaluated in both tobacco and wheat through transgenic approach. Ectopic expression of TaCIPK19 in tobacco greatly improves drought tolerance with enhanced ABA biosynthesis/signaling and ROS scavenging capacity. TaCIPK19 overexpression in wheat also confers the drought tolerance at both seedling and mature stages with enhanced ROS scavenging capacity. Additionally, potential CBL partners interacting with TaCIPK19 were investigated. Collectively, our finding exemplifies a straight-forward approach to facilitate reverse genetics related to abiotic stress improvement and demonstrates TaCIPK19 as a new candidate gene to improve ROS scavenging capacity and drought tolerance, which is useful for genetic improvement and breeding application in wheat.

Silanol-Engineered Nonclassical Growth of Zeolite Nanosheets from Oriented Attachment of Amorphous Protozeolite Nanoparticles.

Zeolite nonclassical growth via particle attachment has been proposed for two decades, yet the attachment mechanism and kinetic regulation remain elusive. Here, nonclassical growth of an MFI-type zeolite has been achieved by using amorphous protozeolite (PZ) nanoparticles containing encapsulated TPA+ templates and abundant silanols (Si-OH) as sole precursors under hydrothermal conditions. The silanol characteristics of the precursor were studied by two-dimensional (2D) solid-state nuclear magnetic resonance (NMR) correlation spectroscopy, which were proven to play critical roles in determining precursor attachment behavior and crystal growth orientation. Under mechanical ball-milling or tablet-pressing process, pressure drove the fusion of spherical PZ into platelet-like integrated PZ (IPZ) coupled with transformations of external silanols from evenly distributed to curvature-dependent distributed and internal silanols from isolated to spatially proximate. Compared to isolated silanols, the spatially proximate silanols possessed a stronger correlation with TPA+, benefiting the formation of Si-O-Si bonds via silanol condensation. Subsequently, driven by minimization of surface energy, particle attachment of the platelet-like IPZ precursor preferentially occurred at high-curvature surfaces with high-density silanols, leading to anisotropic rates of nonclassical growth and thus the formation of high-aspect-ratio MFI-type zeolite nanosheets. Advanced electron microscopy provided direct evidence of attachment of amorphous IPZ precursors to crystalline intermediate surfaces along the c-axis direction with the formation of amorphous-crystalline interfaces, followed by interface elimination and structural evolution to a single-crystalline phase. Our findings not only unravel the zeolite nonclassical growth mechanism but also reveal the critical role of silanol chemistry in kinetic regulation, which is of great importance for pursuing a tailored zeolite synthesis.

Reducing the number of unnecessary biopsies for mammographic BI-RADS 4 lesions through a deep transfer learning method.

BACKGROUND: In clinical practice, reducing unnecessary biopsies for mammographic BI-RADS 4 lesions is crucial. The objective of this study was to explore the potential value of deep transfer learning (DTL) based on the different fine-tuning strategies for Inception V3 to reduce the number of unnecessary biopsies that residents need to perform for mammographic BI-RADS 4 lesions. METHODS: A total of 1980 patients with breast lesions were included, including 1473 benign lesions (185 women with bilateral breast lesions), and 692 malignant lesions collected and confirmed by clinical pathology or biopsy. The breast mammography images were randomly divided into three subsets, a training set, testing set, and validation set 1, at a ratio of 8:1:1. We constructed a DTL model for the classification of breast lesions based on Inception V3 and attempted to improve its performance with 11 fine-tuning strategies. The mammography images from 362 patients with pathologically confirmed BI-RADS 4 breast lesions were employed as validation set 2. Two images from each lesion were tested, and trials were categorized as correct if the judgement (≥ 1 image) was correct. We used precision (Pr), recall rate (Rc), F1 score (F1), and the area under the receiver operating characteristic curve (AUROC) as the performance metrics of the DTL model with validation set 2. RESULTS: The S5 model achieved the best fit for the data. The Pr, Rc, F1 and AUROC of S5 were 0.90, 0.90, 0.90, and 0.86, respectively, for Category 4. The proportions of lesions downgraded by S5 were 90.73%, 84.76%, and 80.19% for categories 4 A, 4B, and 4 C, respectively. The overall proportion of BI-RADS 4 lesions downgraded by S5 was 85.91%. There was no significant difference between the classification results of the S5 model and pathological diagnosis (P = 0.110). CONCLUSION: The S5 model we proposed here can be used as an effective approach for reducing the number of unnecessary biopsies that residents need to conduct for mammographic BI-RADS 4 lesions and may have other important clinical uses.

Integrated omic analysis provides insights into the molecular regulation of stress tolerance by partial root-zone drying in rice.

Partial root-zone drying (PRD) is an effective water-saving irrigation strategy that improves stress tolerance and facilitates efficient water use in several crops. It has long been considered that abscisic acid (ABA)-dependent drought resistance may be involved during partial root-zone drying. However, the molecular mechanisms underlying PRD-mediated stress tolerance remain unclear. It's hypothesized that other mechanisms might contribute to PRD-mediated drought tolerance. Here, rice seedlings were used as a research model and the complex transcriptomic and metabolic reprogramming processes were revealed during PRD, with several key genes involved in osmotic stress tolerance identified by using a combination of physiological, transcriptome, and metabolome analyses. Our results demonstrated that PRD induces transcriptomic alteration mainly in the roots but not in the leaves and adjusts several amino-acid and phytohormone metabolic pathways to maintain the balance between growth and stress response compared to the polyethylene glycol (PEG)-treated roots. Integrated analysis of the transcriptome and metabolome associated the co-expression modules with PRD-induced metabolic reprogramming. Several genes encoding the key transcription factors (TFs) were identified in these co-expression modules, highlighting several key TFs, including TCP19, WRI1a, ABF1, ABF2, DERF1, and TZF7, involved in nitrogen metabolism, lipid metabolism, ABA signaling, ethylene signaling, and stress regulation. Thus, our work presents the first evidence that molecular mechanisms other than ABA-mediated drought resistance are involved in PRD-mediated stress tolerance. Overall, our results provide new insights into PRD-mediated osmotic stress tolerance, clarify the molecular regulation induced by PRD, and identify genes useful for further improving water-use efficiency and/or stress tolerance in rice.

Genome-wide characterization of the VQ genes in Triticeae and their functionalization driven by polyploidization and gene duplication events in wheat.

Valine-glutamine motif-containing (VQ) proteins are transcriptional cofactors widely involved in plant growth, development, and response to various stresses. Although the VQ family has been genome-wide identified in some species, but the knowledge regarding duplication-driven functionalization of VQ genes among evolutionarily related species is still lacking. Here, 952 VQ genes have been identified from 16 species, emphasizing seven Triticeae species including the bread wheat. Comprehensive phylogenetic and syntenic analyses allow us to establish the orthologous relationship of VQ genes from rice (Oryza sativa) to bread wheat (Triticum aestivum). The evolutionary analysis revealed that whole-genome duplication (WGD) drives the expansion of OsVQs, while TaVQs expansion is associated with a recent burst of gene duplication (RBGD). We also analyzed the motif composition and molecular properties of TaVQ proteins, enriched biological functions, and expression patterns of TaVQs. We demonstrate that WGD-derived TaVQs have become divergent in both protein motif composition and expression pattern, while RBGD-derived TaVQs tend to adopt specific expression patterns, suggesting their functionalization in certain biological processes or in response to specific stresses. Furthermore, some RBGD-derived TaVQs are found to be associated with salt tolerance. Several of the identified salt-related TaVQ proteins were located in the cytoplasm and nucleus and their salt-responsive expression patterns were validated by qPCR analysis. Yeast-based functional experiments confirmed that TaVQ27 may be a new regulator to salt response and regulation. Overall, this study lays the foundation for further functional validation of VQ family members within the Triticeae species.

A multi-omic resource of wheat seed tissues for nutrient deposition and improvement for human health.

As a globally important staple crop, wheat seeds provide us with nutrients and proteins. The trend of healthy dietary has become popular recently, emphasizing the consumption of whole-grain wheat products and the dietary benefits. However, the dynamic changes in nutritional profiles of different wheat seed regions (i.e., the embryo, endosperm and outer layers) during developmental stages and the molecular regulation have not been well studied. Here, we provide this multi-omic resource of wheat seeds and describe the generation, technical assessment and preliminary analyses. This resource includes a time-series RNA-seq dataset of the embryo, endosperm and outer layers of wheat seeds and their corresponding metabolomic dataset, covering the middle and late stages of seed development. Our RNA-seq experiments profile the expression of 63,708 genes, while the metabolomic data includes the abundance of 984 metabolites. We believe that this was the first reported transcriptome and metabolome dataset of wheat seeds that helps understand the molecular regulation of the deposition of beneficial nutrients and hence improvements for nutritional and processing quality traits.

Current advances in the molecular regulation of abiotic stress tolerance in sorghum via transcriptomic, proteomic, and metabolomic approaches.

Sorghum (Sorghum bicolor L. Moench), a monocot C4 crop, is an important staple crop for many countries in arid and semi-arid regions worldwide. Because sorghum has outstanding tolerance and adaptability to a variety of abiotic stresses, including drought, salt, and alkaline, and heavy metal stressors, it is valuable research material for better understanding the molecular mechanisms of stress tolerance in crops and for mining new genes for their genetic improvement of abiotic stress tolerance. Here, we compile recent progress achieved using physiological, transcriptome, proteome, and metabolome approaches; discuss the similarities and differences in how sorghum responds to differing stresses; and summarize the candidate genes involved in the process of responding to and regulating abiotic stresses. More importantly, we exemplify the differences between combined stresses and a single stress, emphasizing the necessity to strengthen future studies regarding the molecular responses and mechanisms of combined abiotic stresses, which has greater practical significance for food security. Our review lays a foundation for future functional studies of stress-tolerance-related genes and provides new insights into the molecular breeding of stress-tolerant sorghum genotypes, as well as listing a catalog of candidate genes for improving the stress tolerance for other key monocot crops, such as maize, rice, and sugarcane.

The additive interactions between high-molecular-weight glutenin subunits and tannic acid improve the wheat quality.

Wheat gluten proteins, especially high-molecular-weight glutenin subunits (HMW-GS), are the main contributor to flour processing quality. Tannic acid (TA) consisting of a central glucose unit and ten gallic acid molecules is a phenolic acid that improves the processing quality. However, the underlying mechanism of TA's improvement remains largely unknown. Here, we showed that TA's improving effects on gluten aggregation, dough-mixing and bread-making properties were directly associated with the kinds of HMW-GS expressed in wheat seeds in HMW-GS near-isogenic lines (NILs). We established a biochemical framework, elucidated the additive effects of HMW-GS-TA interaction and discovered that TA cross-linked specifically with wheat glutenins but not gliadins, and reduced gluten surface hydrophobicity and SH content depending on the kinds of expressed HMW-GS in the wheat seeds. We also demonstrated that hydrogen bonds play an essential role in TA-HMW-GS interactions and improvement of wheat processing quality. Additionally, the effects of TA on the antioxidant capacity and on nutrient (protein and starch) digestibility were also investigated in the NILs of HMW-GS. TA increased antioxidant capacity but did not affect the digestion of starches and proteins. Our results revealed that TA more effectively strengthened wheat gluten in the presence of more HMW-GS kinds, highlighting TA's potential as an improver toward healthy and quality bread and demonstrating that manipulating hydrogen bonds was a previously overlooked approach to improve wheat quality.

Toward Exploring and Utilizing the Nutritional and Functional Properties of Cereal Crops.

Cereal crops are of great importance in the development of human civilization and fall into two groups, major crops and minor crops [...].

Classification of Breast Lesions on DCE-MRI Data Using a Fine-Tuned MobileNet.

It is crucial to diagnose breast cancer early and accurately to optimize treatment. Presently, most deep learning models used for breast cancer detection cannot be used on mobile phones or low-power devices. This study intended to evaluate the capabilities of MobileNetV1 and MobileNetV2 and their fine-tuned models to differentiate malignant lesions from benign lesions in breast dynamic contrast-enhanced magnetic resonance images (DCE-MRI).

An established protocol for generating transgenic wheat for wheat functional genomics via particle bombardment.

Wheat is one of the most important food crops in the world and is considered one of the top targets in crop biotechnology. With the high-quality reference genomes of wheat and its relative species and the recent burst of genomic resources in Triticeae, demands to perform gene functional studies in wheat and genetic improvement have been rapidly increasing, requiring that production of transgenic wheat should become a routine technique. While established for more than 20 years, the particle bombardment-mediated wheat transformation has not become routine yet, with only a handful of labs being proficient in this technique. This could be due to, at least partly, the low transformation efficiency and the technical difficulties. Here, we describe the current version of this method through adaptation and optimization. We report the detailed protocol of producing transgenic wheat by the particle gun, including several critical steps, from the selection of appropriate explants (i.e., immature scutella), the preparation of DNA-coated gold particles, and several established strategies of tissue culture. More importantly, with over 20 years of experience in wheat transformation in our lab, we share the many technical details and recommendations and emphasize that the particle bombardment-mediated approach has fewer limitations in genotype dependency and vector construction when compared with the Agrobacterium-mediated methods. The particle bombardment-mediated method has been successful for over 30 wheat genotypes, from the tetraploid durum wheat to the hexaploid common wheat, from modern elite varieties to landraces. In conclusion, the particle bombardment-mediated wheat transformation has demonstrated its potential and wide applications, and the full set of protocol, experience, and successful reports in many wheat genotypes described here will further its impacts, making it a routine and robust technique in crop research labs worldwide.

Detection and classification of breast lesions with You Only Look Once version 5.

Aim: To explore the ability of You Only Look Once version 5 (YOLOv5) to detect and classify breast lesions on dynamic contrast-enhanced MRI. Methods: Four YOLOv5 submodels were examined. A total of 2124 and 2226 images of benign and malignant lesions were obtained, respectively. Precision, recall rate and mean average precision were used to evaluate model performance. Results: The precision (0.916) and mean average precision _0.5 (0.894) of YOLOv5s were higher than those of YOLOv5m (0.832, 0.794), YOLOv5l (0.843, 0.803) and YOLOv5x (0.854, 0.821). In the validation set, YOLOv5s required 1.1 ms to detect lesions per image. Conclusion: YOLOv5s was the fastest and had the highest precision among the four YOLOv5 submodels for the detection and classification of breast lesions on dynamic contrast-enhanced MRI. It has a greater clinical application value.

You Only Look Once version 5 (YOLOv5) is the latest YOLO series, which may be a useful tool for detecting and classifying breast lesions on dynamic contrast-enhanced MRI (DCE-MRI) and help clinicians make a rapid, accurate diagnosis and provide treatment. Data were retrospectively collected from a single-center study. The performances of the four submodels (YOLOv5s, YOLOv5m, YOLOv5l and YOLOv5x) were compared. The diagnostic performances of YOLOv5s were comparable with some convolutional neural network models for breast lesion identification in breast ultrasonography and mammography. This study may provide novel insights into the detection and classification of breast lesions on DCE-MRI. Thus, a sufficiently large series of data and high-quality DCE-MRIs are warranted. Owing to its applications in artificial intelligence-assisted imaging diagnosis, this method has promising prospects.

Differentiation of breast lesions on dynamic contrast-enhanced magnetic resonance imaging (DCE-MRI) using deep transfer learning based on DenseNet201.

In order to achieve better performance, artificial intelligence is used in breast cancer diagnosis. In this study, we evaluated the efficacy of different fine-tuning strategies of deep transfer learning (DTL) based on the DenseNet201 model to differentiate malignant from benign lesions on breast dynamic contrast-enhanced magnetic resonance imaging (DCE-MRI). We collected 4260 images of benign lesions and 4140 images of malignant lesions of the breast pertaining to pathologically confirmed cases. The benign and malignant groups was randomly divided into a training set and a testing set at a ratio of 9:1. A DTL model based on the DenseNet201 model was established, and the effectiveness of 4 fine-tuning strategies (S0: strategy 0, S1: strategy; S2: strategy; and S3: strategy) was compared. Additionally, DCE-MRI images of 48 breast lesions were selected to verify the robustness of the model. Ten images were obtained for each lesion. The classification was considered correct if more than 5 images were correctly classified. The metrics for model performance evaluation included accuracy (Ac) in the training and testing sets, precision (Pr), recall rate (Rc), f1 score (f1), and area under the receiver operating characteristic curve (AUROC) in the validation set. The Ac of the 4 fine-tuning strategies reached 100.00% in the training set. The S2 strategy exhibited good convergence in the testing set. The Ac of S2 was 98.01% in the testing set, which was higher than those of S0 (93.10%), S1 (90.45%), and S3 (93.90%). The average classification Pr, Rc, f1, and AUROC of S2 in the validation set were (89.00%, 80.00%, 0.81, and 0.79, respectively) higher than those of S0 (76.00%, 67.00%, 0.69, and 0.65, respectively), S1 (60.00%, 60.00%, 0.60, 0.66, and respectively), and S3 (77.00%, 73.00%, 0.74, 0.72, respectively). The degree of coincidence between S2 and the histopathological method for differentiating between benign and malignant breast lesions was high (κ = 0.749). The S2 strategy can improve the robustness of the DenseNet201 model in relatively small breast DCE-MRI datasets, and this is a reliable method to increase the Ac of discriminating benign from malignant breast lesions on DCE-MRI.