In-band pumped Kerr-lens mode-locked Tm,Ho-codoped calcium aluminate laser.

We report on a Kerr-lens mode-locked Tm,Ho-codoped calcium aluminate laser with in-band pumping of the Tm ions by a spatially single-mode 1678 nm Raman fiber laser. The structurally disordered CaGdAlO4 host crystal is also codoped also with the passive Lu ion for additional inhomogeneous line broadening. The Tm,Ho,Lu:CaGdAlO4 laser generates soliton pulses as short as 79 fs at a central wavelength of 2073.6 nm via soft-aperture Kerr-lens mode-locking. The corresponding average output power amounts to 91 mW at a pulse repetition rate of ∼86 MHz. The average output power can be scaled to 842 mW at the expense of slightly longer pulses of 155 fs at 2045.9 nm, which corresponds to a peak power of ∼58 kW. To the best of our knowledge, this represents the first demonstration of an in-band pumped Kerr-lens mode-locked Tm,Ho solid-state laser at ∼2 µm.

An artificial intelligence model based on transrectal ultrasound images of biopsy needle tract tissues to differentiate prostate cancer.

PURPOSE: We aimed to develop an artificial intelligence (AI) model based on transrectal ultrasonography (TRUS) images of biopsy needle tract (BNT) tissues for predicting prostate cancer (PCa) and to compare the PCa diagnostic performance of the radiologist model and clinical model. METHODS: A total of 1696 2D prostate TRUS images were involved from 142 patients between July 2021 and May 2022. The ResNet50 network model was utilized to train classification models with different input methods: original image (Whole model), BNT (Needle model), and combined image [Feature Pyramid Networks (FPN) model]. The training set, validation set, and test set were randomly assigned, then randomized 5-fold cross-validation between the training set and validation set was performed. The diagnostic effectiveness of AI models and image combination was accessed by an independent testing set. Then, the optimal AI model and image combination were selected to compare the diagnostic efficacy with that of senior radiologists and the clinical model. RESULTS: In the test set, the area under the curve, specificity, and sensitivity of the FPN model were 0.934, 0.966, and 0.829, respectively; the diagnostic efficacy was improved compared with the Whole and Needle models, with statistically significant differences (P < 0.05), and was better than that of senior radiologists (area under the curve: 0.667). The FPN model detected more PCa compared with senior physicians (82.9% vs. 55.8%), with a 61.3% decrease in the false-positive rate and a 23.2% increase in overall accuracy (0.887 vs. 0.655). CONCLUSION: The proposed FPN model can offer a new method for prostate tissue classification, improve the diagnostic performance, and may be a helpful tool to guide prostate biopsy.

A deep learning-based calculation system for plaque stenosis severity on common carotid artery of ultrasound images.

OBJECTIVES: Assessment of plaque stenosis severity allows better management of carotid source of stroke. Our objective is to create a deep learning (DL) model to segment carotid intima-media thickness and plaque and further automatically calculate plaque stenosis severity on common carotid artery (CCA) transverse section ultrasound images. METHODS: Three hundred and ninety images from 376 individuals were used to train (235/390, 60%), validate (39/390, 10%), and test (116/390, 30%) on a newly proposed CANet model. We also evaluated the model on an external test set of 115 individuals with 122 images acquired from another hospital. Comparative studies were conducted between our CANet model with four state-of-the-art DL models and two experienced sonographers to re-evaluate the present model's performance. RESULTS: On the internal test set, our CANet model outperformed the four comparative models with Dice values of 95.22% versus 90.15%, 87.48%, 90.22%, and 91.56% on lumen-intima (LI) borders and 96.27% versus 91.40%, 88.94%, 91.19%, and 92.88% on media-adventitia (MA) borders. On the external test set, our model still produced excellent results with a Dice value of 92.41%. Good consistency of stenosis severity calculation was observed between CANet model and experienced sonographers, with Intraclass Correlation Coefficient (ICC) of 0.927 and 0.702, Pearson's Correlation Coefficient of 0.928 and 0.704 on internal and external test set, respectively. CONCLUSIONS: Our CANet model achieved excellent performance in the segmentation of carotid IMT and plaques as well as automated calculation of stenosis severity.

A validation of an entropy-based artificial intelligence for ultrasound data in breast tumors.

BACKGROUND: The application of artificial intelligence (AI) in the ultrasound (US) diagnosis of breast cancer (BCa) is increasingly prevalent. However, the impact of US-probe frequencies on the diagnostic efficacy of AI models has not been clearly established. OBJECTIVES: To explore the impact of using US-video of variable frequencies on the diagnostic efficacy of AI in breast US screening. METHODS: This study utilized different frequency US-probes (L14: frequency range: 3.0-14.0 MHz, central frequency 9 MHz, L9: frequency range: 2.5-9.0 MHz, central frequency 6.5 MHz and L13: frequency range: 3.6-13.5 MHz, central frequency 8 MHz, L7: frequency range: 3-7 MHz, central frequency 4.0 MHz, linear arrays) to collect breast-video and applied an entropy-based deep learning approach for evaluation. We analyzed the average two-dimensional image entropy (2-DIE) of these videos and the performance of AI models in processing videos from these different frequencies to assess how probe frequency affects AI diagnostic performance. RESULTS: The study found that in testing set 1, L9 was higher than L14 in average 2-DIE; in testing set 2, L13 was higher in average 2-DIE than L7. The diagnostic efficacy of US-data, utilized in AI model analysis, varied across different frequencies (AUC: L9 > L14: 0.849 vs. 0.784; L13 > L7: 0.920 vs. 0.887). CONCLUSION: This study indicate that US-data acquired using probes with varying frequencies exhibit diverse average 2-DIE values, and datasets characterized by higher average 2-DIE demonstrate enhanced diagnostic outcomes in AI-driven BCa diagnosis. Unlike other studies, our research emphasizes the importance of US-probe frequency selection on AI model diagnostic performance, rather than focusing solely on the AI algorithms themselves. These insights offer a new perspective for early BCa screening and diagnosis and are of significant for future choices of US equipment and optimization of AI algorithms.

The research on artificial intelligence-assisted breast diagnosis often relies on static images or dynamic videos obtained from ultrasound probes with different frequencies. However, the effect of frequency-induced image variations on the diagnostic performance of artificial intelligence models remains unclear. In this study, we aimed to explore the impact of using ultrasound images with variable frequencies on AI's diagnostic efficacy in breast ultrasound screening. Our approach involved employing a video and entropy-based feature breast network to compare the diagnostic efficiency and average two-dimensional image entropy of the L14 (frequency range: 3.0-14.0 MHz, central frequency 9 MHz), L9 (frequency range: 2.5-9.0 MHz, central frequency 6.5 MHz) linear array probe and L13 (frequency range: 3.6-13.5 MHz, central frequency 8 MHz), and L7 (frequency range: 3-7 MHz, central frequency 4.0 MHz) linear array probes. The results revealed that the diagnostic efficiency of AI models differed based on the frequency of the ultrasound probe. It is noteworthy that ultrasound images acquired with different frequency probes exhibit different average two-dimensional image entropy, while higher average two-dimensional image entropy positively affect the diagnostic performance of the AI model. We concluded that a dataset with higher average two-dimensional image entropy is associated with superior diagnostic efficacy for AI-based breast diagnosis. These findings contribute to a better understanding of how ultrasound image variations impact AI-assisted breast diagnosis, potentially leading to improved breast cancer screening outcomes.

Biodegradation of various grades of polyethylene microplastics by Tenebrio molitor and Tenebrio obscurus larvae: Effects on their physiology.

Polyethylene (PE) is the most productive plastic product and includes three major polymers including high-density polyethylene (HDPE), linear low-density polyethylene (LLDPE) and low-density polyethylene (LDPE) variation in the PE depends on the branching of the polymer chain and its crystallinity. Tenebrio obscurus and Tenebrio molitor larvae biodegrade PE. We subsequently tested larval physiology, gut microbiome, oxidative stress, and PE degradation capability and degradation products under high-purity HDPE, LLDPE, and LDPE powders (<300 µm) diets for 21 days at 65 ± 5% humidity and 25 ± 0.5 °C. Our results demonstrated the specific PE consumption rates by T. molitor was 8.04-8.73 mg PE ∙ 100 larvae-1⋅day-1 and by T. obscurus was 7.68-9.31 for LDPE, LLDPE and HDPE, respectively. The larvae digested nearly 40% of the ingested three PE and showed similar survival rates and weight changes but their fat content decreased by 30-50% over 21-day period. All the PE-fed groups exhibited adverse effects, such as increased benzoquinone concentrations, intestinal tissue damage and elevated oxidative stress indicators, compared with bran-fed control. In the current study, the digestive tract or gut microbiome exhibited a high level of adaptability to PE exposure, altering the width of the gut microbial ecological niche and community diversity, revealing notable correlations between Tenebrio species and the physical and chemical properties (PCPs) of PE-MPs, with the gut microbiome and molecular weight change due to biodegradation. An ecotoxicological simulation by T.E.S.T. confirmed that PE degradation products were little ecotoxic to Daphnia magna and Rattus norvegicus providing important novel insights for future investigations into the environmentally-friendly approach of insect-mediated biodegradation of persistent plastics.

Didymin alleviates metabolic dysfunction-associated fatty liver disease (MAFLD) via the stimulation of Sirt1-mediated lipophagy and mitochondrial biogenesis.

BACKGROUND: Metabolic dysfunction-associated fatty liver disease (MAFLD) is one of the most prevalent metabolic syndromes worldwide. However, no approved pharmacological treatments are available for MAFLD. Chenpi, one kind of dried peel of citrus fruits, has traditionally been utilized as a medicinal herb for liver diseases. Didymin is a newly identified oral bioactive dietary flavonoid glycoside derived from Chenpi. In this study, we investigated the therapeutic potential of Didymin as an anti-MAFLD drug and elucidated its underlying mechanisms. METHODS: High-fat diet (HFD)-induced MAFLD mice and alpha mouse liver 12 (AML12) cells were utilized to evaluate the effects and mechanisms of Didymin in the treatment of MAFLD. Liver weight, serum biochemical parameters, and liver morphology were examined to demonstrate the therapeutic efficacy of Didymin in MAFLD treatment. RNA-seq analysis was performed to identify potential pathways that could be affected by Didymin. The impact of Didymin on Sirt1 was corroborated through western blot, molecular docking analysis, microscale thermophoresis (MST), and deacetylase activity assay. Then, a Sirt1 inhibitor (EX-527) was utilized to confirm that Didymin alleviates MAFLD via Sirt1. Western blot and additional assays were used to investigate the underlying mechanisms. RESULTS: Our results suggested that Didymin may possess therapeutic potential against MAFLD in vitro and in vivo. By promoting Sirt1 expression as well as directly binding to and activating Sirt1, Didymin triggers downstream pathways that enhance mitochondrial biogenesis and function while reducing apoptosis and enhancing lipophagy. CONCLUSIONS: These suggest that Didymin could be a promising medication for MAFLD treatment. Furthermore, its therapeutic effects are mediated by Sirt1.

Carbon dots as multifunctional fluorescent probe for Fe3+ sensing in ubiquitous water environments and living cells as well as lysine detection via "on-off-on" mechanism.

Iron and amino acids are essential nutrients for living organisms, and their deficiency or excess can cause a range of diseases. Therefore, there is considerable interest in developing sensing assays capable of detecting these nutrients with sensitivity, selectivity, and multifunctionality even in complex environments. In this report, hydrothermally synthesized blue fluorescent carbon dots (C-dots) from zinc gluconate were utilized for the detection of Fe3+ and lysine via "on-off" and "on-off-on" mechanisms, respectively. Specifically, the Fe3+ sensing assay achieved a broad linear range of 0-200 µM and a low limit of detection (LOD) of 1.9 µM. It is worth mentioning that the assay was also well adapted to natural aqueous environments (e.g., lake water), and its linear detection range could be extended to 0-1000 µM with a LOD of 3.3 µM. Furthermore, the assay was also effective for intracellular Fe3+ tracking. Most importantly, the assay could also be applied for the quantitative detection of lysine with a linear range of 0-1200 µM and LOD of 8.6 µM. Systematic mechanistic studies revealed that Fe3+ sensing was based on a static quenching process between C-dots and Fe3+, whereas a stronger complexation might have formed between Fe3+ and Lys, leading to the release of C-dots and thus the recovery of fluorescence.

Molecular imprinting-based Ru@SiO2-embedded covalent organic frameworks composite for electrochemiluminescence detection of cyanidin-3-O-glucoside.

Cyanidin-3-O-glucoside (C3G), a natural antioxidant, plays multiple physiological or pathological roles in maintaining human health; thereby, designing advanced sensors to achieve specific recognition and high-sensitivity detection of C3G is significant. Herein, an imprinted-type electrochemiluminescence (ECL) sensing platform was developed using core-shell Ru@SiO2-CMIPs, which were prepared by covalent organic framework (COF)-based molecularly imprinted polymers (CMIPs) embedded in luminescent Ru@SiO2 cores. The C3G-imprinted COF shell not only helps generate a steady-enhanced ECL signal, but also enables specific recognition of C3G. When C3G is bound to Ru@SiO2-CMIPs with abundant imprinted cavities, resonance energy transfer (RET) behavior is triggered, resulting in a quenched ECL response. The constructed Ru@SiO2-CMIPs nanoprobes exhibit ultra-high sensitivity, absolute specificity, and an ultra-low detection limit (0.15 pg mL-1) for analyzing C3G in food matrices. This study provides a means to construct an efficient and reliable molecular imprinting-based ECL sensor for food analysis.

Diagnostic Performance of Deep Learning in Video-Based Ultrasonography for Breast Cancer: A Retrospective Multicentre Study.

OBJECTIVE: Although ultrasound is a common tool for breast cancer screening, its accuracy is often operator-dependent. In this study, we proposed a new automated deep-learning framework that extracts video-based ultrasound data for breast cancer screening. METHODS: Our framework incorporates DenseNet121, MobileNet, and Xception as backbones for both video- and image-based models. We used data from 3907 patients to train and evaluate the models, which were tested using video- and image-based methods, as well as reader studies with human experts. RESULTS: This study evaluated 3907 female patients aged 22 to 86 years. The results indicated that the MobileNet video model achieved an AUROC of 0.961 in prospective data testing, surpassing the DenseNet121 video model. In real-world data testing, it demonstrated an accuracy of 92.59%, outperforming both the DenseNet121 and Xception video models, and exceeding the 76.00% to 85.60% accuracy range of human experts. Additionally, the MobileNet video model exceeded the performance of image models and other video models across all evaluation metrics, including accuracy, sensitivity, specificity, F1 score, and AUC. Its exceptional performance, particularly suitable for resource-limited clinical settings, demonstrates its potential for clinical application in breast cancer screening. CONCLUSIONS: The level of expertise reached by the video models was greater than that achieved by image-based models. We have developed an artificial intelligence framework based on videos that may be able to aid breast cancer diagnosis and alleviate the shortage of experienced experts.

Worm-Based Diagnosis Combining Microfluidics toward Early Cancer Screening.

Early cancer diagnosis increases therapy efficiency and saves huge medical costs. Traditional blood-based cancer markers and endoscopy procedures demonstrate limited capability in the diagnosis. Reliable, non-invasive, and cost-effective methods are in high demand across the world. Worm-based diagnosis, utilizing the chemosensory neuronal system of C. elegans, emerges as a non-invasive approach for early cancer diagnosis with high sensitivity. It facilitates effectiveness in large-scale cancer screening for the foreseeable future. Here, we review the progress of a unique route of early cancer diagnosis based on the chemosensory neuronal system of C. elegans. We first introduce the basic procedures of the chemotaxis assay of C. elegans: synchronization, behavior assay, immobilization, and counting. Then, we review the progress of each procedure and the various cancer types for which this method has achieved early diagnosis. For each procedure, we list examples of microfluidics technologies that have improved the automation, throughput, and efficiency of each step or module. Finally, we envision that microfluidics technologies combined with the chemotaxis assay of C. elegans can lead to an automated, cost-effective, non-invasive early cancer screening technology, with the development of more mature microfluidic modules as well as systematic integration of functional modules.

A Video-based Automated Tracking and Analysis System of Plaque Burden in Carotid Artery Using Deep Learning: A Comparison with Senior Sonographers.

BACKGROUND AND OBJECTIVE: The incidence of stroke is rising, and it is the second major cause of mortality and the third leading cause of disability around the globe. The goal of this study was to rapidly and accurately identify carotid plaques and automatically quantify plaque burden using our automated tracking and segmentation US-video system. METHODS: We collected 88 common carotid artery transection videos (11048 frames) with a history of atherosclerosis or risk factors for atherosclerosis, which were randomly divided into training, test, and validation sets using a 6:3:1 ratio. We first trained different segmentation models to segment the carotid intima and adventitia, and calculate the maximum plaque burden automatically. Finally, we statistically analyzed the plaque burden calculated automatically by the best model and the results of manual labeling by senior sonographers. RESULTS: Of the three Artificial Intelligence (AI) models, the Robust Video Matting (RVM) segmentation model's carotid intima and adventitia Dice Coefficients (DC) were the highest, reaching 0.93 and 0.95, respectively. Moreover, the RVM model has shown the strongest correlation coefficient (0.61±0.28) with senior sonographers, and the diagnostic effectiveness between the RVM model and experts was comparable with paired-t test and Bland-Altman analysis [P= 0.632 and ICC 0.01 (95% CI: -0.24~0.27), respectively]. CONCLUSION: Our findings have indicated that the RVM model can be used in ultrasound carotid video. The RVM model can automatically segment and quantify atherosclerotic plaque burden at the same diagnostic level as senior sonographers. The application of AI to carotid videos offers more precise and effective methods to evaluate carotid atherosclerosis in clinical practice.

Olefin skeletal rearrangement enabling access to multiarylated N-sulfonyl amidines.

A base-promoted olefin skeletal rearrangement strategy from para-quinone methides (p-QMs) and N-fluoroarenesulfonamides is reported, enabling direct nitrogen insertion of olefins to produce a series of multiarylated (Z)-N-sulfonyl amidines with complete stereoselectivity and generally good yields. Using p-QMs without o-hydroxy substituents gave triarylated N-sulfonyl amidines, whereas tetraarylated N,N'-disulfonyl amidines were synthesized with the existence of o-hydroxy groups.

New insights into substrates shaped nutrients removal, species interactions and community assembly mechanisms in tidal flow constructed wetlands treating low carbon-to-nitrogen rural wastewater.

A limited understanding of microbial interactions and community assembly mechanisms in constructed wetlands (CWs), particularly with different substrates, has hampered the establishment of ecological connections between micro-level interactions and macro-level wetland performance. In this study, CWs with distinct substrates (zeolite, CW_A; manganese ore, CW_B) were constructed to investigate the nutrient removal efficiency, microbial interactions, metabolic mechanisms, and ecological assembly for treating rural sewage with a low carbon-to-nitrogen ratio. CW_B showed higher removal of ammonia nitrogen and total nitrogen by about 1.75-6.75 % and 3.42-5.18 %, respectively, compared to CW_A. Candidatus_Competibacter (denitrifying glycogen-accumulating bacteria) was the dominant microbial genus in CW_A, whereas unclassified_f_Blastocatellaceae (involved in carbon and nitrogen transformation) dominated in CW_B. The null model revealed that stochastic processes (drift) dominated community assembly in both CWs; however, deterministic selection accounted for a higher proportion in CW_B. Compared to those in CW_A, the interactions between microbes in CW_B were more complex, with more key microbes involved in carbon, nitrogen, and phosphorus conversion; the synergistic cooperation of functional bacteria facilitated simultaneous nitrification-denitrification. Manganese ores favour biofilm formation, increase the activity of the electron transport system, and enhance ammonia oxidation and nitrate reduction. These results elucidated the ecological patterns exhibited by microbes under different substrate conditions thereby contributing to our understanding of how substrates shape distinct microcosms in CW systems. This study provides valuable insights for guiding the future construction and management of CWs.

Application of ensemble learning for predicting GABAA receptor agonists.

BACKGROUND: Over the past few decades, agonists binding to the benzodiazepine site of the GABAA receptor have been successfully developed as clinical drugs. Different modulators (agonist, antagonist, and reverse agonist) bound to benzodiazepine sites exhibit different or even opposite pharmacological effects, however, their structures are so similar that it is difficult to distinguish them based solely on molecular skeleton. This study aims to develop classification models for predicting the agonists. METHODS: 306 agonists or non-agonists were collected from literature. Six machine learning algorithms including RF, XGBoost, AdaBoost, GBoost, SVM, and ANN algorithms were employed for model development. Using six descriptors including 1D/2D Descriptors, ECFP4, 2D-Pharmacophore, MACCS, PubChem, and Estate fingerprint to characterize chemical structures. The model interpretability was explored by SHAP method. RESULTS: The best model demonstrated an AUC value of 0.905 and an MCC value of 0.808 for the test set. The PubMac-based model (PubMac-GB) achieved best AUC values of 0.935 for test set. The SHAP analysis results emphasized that MaccsFP62, ECFP_624, ECFP_724, and PubchemFP213 were the crucial molecular features. Applicability domain analysis was also performed to determine reliable prediction boundaries for the model. The PubMac-GB model was applied to virtual screening for potential GABAA agonists and the top 100 compounds were given. CONCLUSION: Overall, our ensemble learning-based model (PubMac-GB) achieved comparable performance and would be helpful in effectively identifying agonists of GABAA receptors.

Multi-modality deep learning model reaches high prediction accuracy in the diagnosis of ovarian cancer.

We evaluated the diagnostic performance of a multimodal deep-learning (DL) model for ovarian mass differential diagnosis. This single-center retrospective study included 1,054 ultrasound (US)-detected ovarian tumors (699 benign and 355 malignant). Patients were randomly divided into training (n = 675), validation (n = 169), and testing (n = 210) sets. The model was developed using ResNet-50. Three DL-based models were proposed for benign-malignant classification of these lesions: single-modality model that only utilized US images; dual-modality model that used US images and menopausal status as inputs; and multi-modality model that integrated US images, menopausal status, and serum indicators. After 5-fold cross-validation, 210 lesions were tested. We evaluated the three models using the area under the curve (AUC), accuracy, sensitivity, and specificity. The multimodal model outperformed the single- and dual-modality models with 93.80% accuracy and 0.983 AUC. The Multimodal ResNet-50 DL model outperformed the single- and dual-modality models in identifying benign and malignant ovarian tumors.

Mesenchymal stromal cells ameliorate mitochondrial dysfunction in α cells and hyperglucagonemia in type 2 diabetes via SIRT1/FoxO3a signaling.

Dysregulation of α cells results in hyperglycemia and hyperglucagonemia in type 2 diabetes mellitus (T2DM). Mesenchymal stromal cell (MSC)-based therapy increases oxygen consumption of islets and enhances insulin secretion. However, the underlying mechanism for the protective role of MSCs in α-cell mitochondrial dysfunction remains unclear. Here, human umbilical cord MSCs (hucMSCs) were used to treat 2 kinds of T2DM mice and αTC1-6 cells to explore the role of hucMSCs in improving α-cell mitochondrial dysfunction and hyperglucagonemia. Plasma and supernatant glucagon were detected by enzyme-linked immunosorbent assay (ELISA). Mitochondrial function of α cells was assessed by the Seahorse Analyzer. To investigate the underlying mechanisms, Sirtuin 1 (SIRT1), Forkhead box O3a (FoxO3a), glucose transporter type1 (GLUT1), and glucokinase (GCK) were assessed by Western blotting analysis. In vivo, hucMSC infusion improved glucose and insulin tolerance, as well as hyperglycemia and hyperglucagonemia in T2DM mice. Meanwhile, hucMSC intervention rescued the islet structure and decreased α- to ß-cell ratio. Glucagon secretion from αTC1-6 cells was consistently inhibited by hucMSCs in vitro. Meanwhile, hucMSC treatment activated intracellular SIRT1/FoxO3a signaling, promoted glucose uptake and activation, alleviated mitochondrial dysfunction, and enhanced ATP production. However, transfection of SIRT1 small interfering RNA (siRNA) or the application of SIRT1 inhibitor EX-527 weakened the therapeutic effects of hucMSCs on mitochondrial function and glucagon secretion. Our observations indicate that hucMSCs mitigate mitochondrial dysfunction and glucagon hypersecretion of α cells in T2DM via SIRT1/FoxO3a signaling, which provides novel evidence demonstrating the potential for hucMSCs in treating T2DM.

Sonography-based multimodal information platform for identifying the surgical pathology of ductal carcinoma in situ.

BACKGROUND: The risk of ductal carcinoma in situ (DCIS) identified by biopsy often increases during surgery. Therefore, confirming the DCIS grade preoperatively is necessary for clinical decision-making. PURPOSE: To train a three-classification deep learning (DL) model based on ultrasound (US), combining clinical data, mammography (MG), US, and core needle biopsy (CNB) pathology to predict low-grade DCIS, intermediate-to-high-grade DCIS, and upstaged DCIS. MATERIALS AND METHODS: Data of 733 patients with 754 DCIS cases confirmed by biopsy were retrospectively collected from May 2013 to June 2022 (N1), and other data (N2) were confirmed by biopsy as low-grade DCIS. The lesions were randomly divided into training (n=471), validation (n=142), and test (n = 141) sets to establish the DCIS-Net. Information on the DCIS-Net, clinical (age and sign), US (size, calcifications, type, breast imaging reporting and data system [BI-RADS]), MG (microcalcifications, BI-RADS), and CNB pathology (nuclear grade, architectural features, and immunohistochemistry) were collected. Logistic regression and random forest analyses were conducted to develop Multimodal DCIS-Net to calculate the specificity, sensitivity, accuracy, receiver operating characteristic curve, and area under the curve (AUC). RESULTS: In the test set of N1, the accuracy and AUC of the multimodal DCIS-Net were 0.752-0.766 and 0.859-0.907 in the three-classification task, respectively. The accuracy and AUC for discriminating DCIS from upstaged DCIS were 0.751-0.780 and 0.829-0.861, respectively. In the test set of N2, the accuracy and AUC of discriminating low-grade DCIS from upstaged low-grade DCIS were 0.769-0.987 and 0.818-0.939, respectively. DL was ranked from one to five in the importance of features in the multimodal-DCIS-Net. CONCLUSION: By developing the DCIS-Net and integrating it with multimodal information, diagnosing low-grade DCIS, intermediate-to high-grade DCIS, and upstaged DCIS is possible. It can also be used to distinguish DCIS from upstaged DCIS and low-grade DCIS from upstaged low-grade DCIS, which could pave the way for the DCIS clinical workflow.

Didymin protects pancreatic beta cells by enhancing mitochondrial function in high-fat diet-induced impaired glucose tolerance.

PURPOSE: Prolonged exposure to plasma free fatty acids (FFAs) leads to impaired glucose tolerance (IGT) which can progress to type 2 diabetes (T2D) in the absence of timely and effective interventions. High-fat diet (HFD) leads to chronic inflammation and oxidative stress, impairing pancreatic beta cell (PBC) function. While Didymin, a flavonoid glycoside derived from citrus fruits, has beneficial effects on inflammation dysfunction, its specific role in HFD-induced IGT remains yet to be elucidated. Hence, this study aims to investigate the protective effects of Didymin on PBCs. METHODS: HFD-induced IGT mice and INS-1 cells were used to explore the effect and mechanism of Didymin in alleviating IGT. Serum glucose and insulin levels were measured during the glucose tolerance and insulin tolerance tests to evaluate PBC function and insulin resistance. Next, RNA-seq analysis was performed to identify the pathways potentially influenced by Didymin in PBCs. Furthermore, we validated the effects of Didymin both in vitro and in vivo. Mitochondrial electron transport inhibitor (Rotenone) was used to further confirm that Didymin exerts its ameliorative effect by enhancing mitochondria function. RESULTS: Didymin reduces postprandial glycemia and enhances 30-minute postprandial insulin levels in IGT mice. Moreover, Didymin was found to enhance mitochondria biogenesis and function, regulate insulin secretion, and alleviate inflammation and apoptosis. However, these effects were abrogated with the treatment of Rotenone, indicating that Didymin exerts its ameliorative effect by enhancing mitochondria function. CONCLUSIONS: Didymin exhibits therapeutic potential in the treatment of HFD-induced IGT. This beneficial effect is attributed to the amelioration of PBC dysfunction through improved mitochondrial function.

Machine Learning in Hypertrophic Cardiomyopathy: Nonlinear Model From Clinical and CMR Features Predicting Cardiovascular Events.

BACKGROUND: The cumulative burden of hypertrophic cardiomyopathy (HCM) is significant, with a noteworthy percentage (10%-15%) of patients with HCM per year experiencing major adverse cardiovascular events (MACEs). A current risk stratification scheme for HCM had only limited accuracy in predicting sudden cardiac death (SCD) and failed to account for a broader spectrum of adverse cardiovascular events and cardiac magnetic resonance (CMR) parameters. OBJECTIVES: This study sought to develop and evaluate a machine learning (ML) framework that integrates CMR imaging and clinical characteristics to predict MACEs in patients with HCM. METHODS: A total of 758 patients with HCM (67% male; age 49 ± 14 years) who were admitted between 2010 and 2017 from 4 medical centers were included. The ML model was built on the internal discovery cohort (533 patients with HCM, admitted to Fuwai Hospital, Beijing, China) by using the light gradient-boosting machine and internally evaluated using cross-validation. The external test cohort consisted of 225 patients with HCM from 3 medical centers. A total of 14 CMR imaging features (strain and late gadolinium enhancement [LGE]) and 23 clinical variables were evaluated and used to inform the ML model. MACEs included a composite of arrhythmic events, SCD, heart failure, and atrial fibrillation-related stroke. RESULTS: MACEs occurred in 191 (25%) patients over a median follow-up period of 109.0 months (Q1-Q3: 73.0-118.8 months). Our ML model achieved areas under the curve (AUCs) of 0.830 and 0.812 (internally and externally, respectively). The model outperformed the classic HCM Risk-SCD model, with significant improvement (P < 0.001) of 22.7% in the AUC. Using the cubic spline analysis, the study showed that the extent of LGE and the impairment of global radial strain (GRS) and global circumferential strain (GCS) were nonlinearly correlated with MACEs: an elevated risk of adverse cardiovascular events was observed when these parameters reached the high enough second tertiles (11.6% for LGE, 25.8% for GRS, -17.3% for GCS). CONCLUSIONS: ML-empowered risk stratification using CMR and clinical features enabled accurate MACE prediction beyond the classic HCM Risk-SCD model. In addition, the nonlinear correlation between CMR features (LGE and left ventricular pressure gradient) and MACEs uncovered in this study provides valuable insights for the clinical assessment and management of HCM.