Contrastive Speaker Representation Learning with Hard Negative Sampling for Speaker Recognition.

Speaker recognition is a technology that identifies the speaker in an input utterance by extracting speaker-distinguishable features from the speech signal. Speaker recognition is used for system security and authentication; therefore, it is crucial to extract unique features of the speaker to achieve high recognition rates. Representative methods for extracting these features include a classification approach, or utilizing contrastive learning to learn the speaker relationship between representations and then using embeddings extracted from a specific layer of the model. This paper introduces a framework for developing robust speaker recognition models through contrastive learning. This approach aims to minimize the similarity to hard negative samples-those that are genuine negatives, but have extremely similar features to the positives, leading to potential mistaken. Specifically, our proposed method trains the model by estimating hard negative samples within a mini-batch during contrastive learning, and then utilizes a cross-attention mechanism to determine speaker agreement for pairs of utterances. To demonstrate the effectiveness of our proposed method, we compared the performance of a deep learning model trained with a conventional loss function utilized in speaker recognition with that of a deep learning model trained using our proposed method, as measured by the equal error rate (EER), an objective performance metric. Our results indicate that when trained with the voxceleb2 dataset, the proposed method achieved an EER of 0.98% on the voxceleb1-E dataset and 1.84% on the voxceleb1-H dataset.

Saikosaponin A Recovers Impaired Filaggrin Levels in Inflamed Skin by Downregulating the Expression of FRA1 and c-Jun.

Filaggrin (FLG) is an essential structural protein expressed in differentiated keratinocytes. Insufficient FLG expression contributes to the pathogenesis of chronic inflammatory skin diseases. Saikosaponin A (SSA), a bioactive oleanane-type triterpenoid, exerts anti-inflammatory activity. However, the effects of topically applied SSA on FLG expression in inflamed skin remain unclear. This study aimed to evaluate the biological activity of SSA in restoring reduced FLG expression. The effect of SSA on FLG expression in HaCaT cells was assessed through various biological methods, including reverse transcription PCR, quantitative real-time PCR, immunoblotting, and immunofluorescence staining. TNFα and IFNγ decreased FLG mRNA, cytoplasmic FLG protein levels, and FLG gene promoter-reporter activity compared to the control groups. However, the presence of SSA restored these effects. A series of FLG promoter-reporter constructs were generated to investigate the underlying mechanism of the effect of SSA on FLG expression. Mutation of the AP1-binding site (mtAP1) in the -343/+25 FLG promoter-reporter abrogated the decrease in reporter activities caused by TNFα + IFNγ, suggesting the importance of the AP1-binding site in reducing FLG expression. The SSA treatment restored FLG expression by inhibiting the expression and nuclear localization of FRA1 and c-Jun, components of AP1, triggered by TNFα + IFNγ stimulation. The ERK1/2 mitogen-activated protein kinase signaling pathway upregulates FRA1 and c-Jun expression, thereby reducing FLG levels. The SSA treatment inhibited ERK1/2 activation caused by TNFα + IFNγ stimulation and reduced the levels of FRA1 and c-Jun proteins in the nucleus, leading to a decrease in the binding of FRA1, c-Jun, p-STAT1, and HDAC1 to the AP1-binding site in the FLG promoter. The effect of SSA was evaluated in an animal study using a BALB/c mouse model, which induces human atopic-dermatitis-like skin lesions via the topical application of dinitrochlorobenzene. Topically applied SSA significantly reduced skin thickening, immune cell infiltration, and the expression of FRA1, c-Jun, and p-ERK1/2 compared to the vehicle-treated group. These results suggest that SSA can effectively recover impaired FLG levels in inflamed skin by preventing the formation of the repressor complex consisting of FRA1, c-Jun, HDAC1, and STAT1.

Pyrazolines inhibiting the activity of the early growth response-1 DNA-binding domain.

To identify compounds inhibiting the activity of the Early Growth Response (EGR)-1 DNA-binding domain, thirty-seven pyrazolines were prepared and their EGR-1 DNA-binding activities were measured. Pharmacophores were derived based on quantitative structure-activity relationship calculations. As compound 2, 1-(5-(4-methoxyphenyl)-4,5-dihydro-1H-pyrazol-3-yl)naphthalen-2-ol, showed the best inhibitory effects against the activity of the EGR-1 DNA-binding domain, the binding mode between compound 2 and EGR-1 was elucidated using in silico docking. The pharmacophores were matched to the binding modes. Electrophoretic mobility shift assays confirmed that compound 2 dose-dependently inhibited TNFα-induced EGR-1-DNA complex formation in HaCaT cells. Reverse transcription-polymerase chain reaction demonstrated that compound 2 effectively reduced the mRNA expression of EGR-1-regulated inflammatory genes, including thymic stromal lymphopoietin (TSLP), interleukin (IL)-1ß, IL-6, and IL-31, in TNFα-stimulated HaCaT cells. Therefore, compound 2 could be developed as an agent that inhibits the activity of the EGR-1 DNA-binding domain.

Prediction of Bone Marrow Metastases Using Computed Tomography (CT) Radiomics in Patients with Gastric Cancer: Uncovering Invisible Metastases.

We investigated whether radiomics of computed tomography (CT) image data enables the differentiation of bone metastases not visible on CT from unaffected bone, using pathologically confirmed bone metastasis as the reference standard, in patients with gastric cancer. In this retrospective study, 96 patients (mean age, 58.4 ± 13.3 years; range, 28-85 years) with pathologically confirmed bone metastasis in iliac bones were included. The dataset was categorized into three feature sets: (1) mean and standard deviation values of attenuation in the region of interest (ROI), (2) radiomic features extracted from the same ROI, and (3) combined features of (1) and (2). Five machine learning models were developed and evaluated using these feature sets, and their predictive performance was assessed. The predictive performance of the best-performing model in the test set (based on the area under the curve [AUC] value) was validated in the external validation group. A Random Forest classifier applied to the combined radiomics and attenuation dataset achieved the highest performance in predicting bone marrow metastasis in patients with gastric cancer (AUC, 0.96), outperforming models using only radiomics or attenuation datasets. Even in the pathology-positive CT-negative group, the model demonstrated the best performance (AUC, 0.93). The model's performance was validated both internally and with an external validation cohort, consistently demonstrating excellent predictive accuracy. Radiomic features derived from CT images can serve as effective imaging biomarkers for predicting bone marrow metastasis in patients with gastric cancer. These findings indicate promising potential for their clinical utility in diagnosing and predicting bone marrow metastasis through routine evaluation of abdominopelvic CT images during follow-up.

Effect of Corticosteroid Use on the Occurrence and Progression of Osteonecrosis of the Femoral Head: A Nationwide Nested Case-Control Study.

BACKGROUND: Although it is very well known that corticosteroids cause osteonecrosis of the femoral head (ONFH), it is unclear as to which patients develop ONFH. Additionally, there are no studies on the association between corticosteroid use and femoral head collapse in ONFH patients. We aimed to investigate the association between corticosteroid use and the risk of ONFH among the general population and what factors affect ONFH occurrence. Additionally, we aimed to demonstrate which factors affect femoral head collapse and total hip arthroplasty (THA) after ONFH occurrence. METHODS: A nationwide, nested case-control study was conducted with data from the National Health Insurance Service Physical Health Examination Cohort (2002 to 2019) in the Republic of Korea. We defined ONFH (N = 3,500) using diagnosis and treatment codes. Patients who had ONFH were matched 1:5 to form a control group based on the variables of birth year, sex, and follow-up duration. Additionally, in patients who have ONFH, we looked for risk factors for progression to THA. RESULTS: Compared with the control group, ONFH patients had a low household income and had more diabetes, hypertension, dyslipidemia, and heavy alcohol use (drinking more than 3 to 7 drinks per week). Systemic corticosteroid use (≥1,800 mg) was significantly associated with an increased risk of ONFH incidence. However, lipid profiles, corticosteroid prescription, and cumulative doses of corticosteroid did not affect the progression to THA. CONCLUSIONS: The ONFH risk increased rapidly when cumulative prednisolone use was ≥1,800 mg. However, oral or high-dose intravenous corticosteroid use and cumulative dose did not affect the prognosis of ONFH. Since the occurrence and prognosis of ONFH are complex and multifactorial processes, further study is needed.

Patient-centered radiology reports with generative artificial intelligence: adding value to radiology reporting.

The purposes were to assess the efficacy of AI-generated radiology reports in terms of report summary, patient-friendliness, and recommendations and to evaluate the consistent performance of report quality and accuracy, contributing to the advancement of radiology workflow. Total 685 spine MRI reports were retrieved from our hospital database. AI-generated radiology reports were generated in three formats: (1) summary reports, (2) patient-friendly reports, and (3) recommendations. The occurrence of artificial hallucinations was evaluated in the AI-generated reports. Two radiologists conducted qualitative and quantitative assessments considering the original report as a standard reference. Two non-physician raters assessed their understanding of the content of original and patient-friendly reports using a 5-point Likert scale. The scoring of the AI-generated radiology reports were overall high average scores across all three formats. The average comprehension score for the original report was 2.71 ± 0.73, while the score for the patient-friendly reports significantly increased to 4.69 ± 0.48 (p < 0.001). There were 1.12% artificial hallucinations and 7.40% potentially harmful translations. In conclusion, the potential benefits of using generative AI assistants to generate these reports include improved report quality, greater efficiency in radiology workflow for producing summaries, patient-centered reports, and recommendations, and a move toward patient-centered radiology.

Clinical Activity of TGF-ß Inhibitor Vactosertib in Combination with Imatinib in Desmoid Tumors: A Multicenter Phase Ib/II Study.

PURPOSE: The study was to determine the activity and safety of the TGF-ß inhibitor vactosertib in combination with imatinib in patients with desmoid tumors. PATIENTS AND METHODS: In this investigator-initiated, open-label, multicenter, phase Ib/II trial, patients with desmoid tumors not amenable to locoregional therapies (surgery and/or radiotherapy) or with disease progression following at least one treatment were enrolled. Participants were administered 400 mg imatinib daily in combination with vactosertib (5 days on and 2 days off, twice a day) every 28 days. In phase Ib, the vactosertib dose was set at 100 mg (level -1) and 200 mg (level 1) to determine the recommended phase II dose (RP2D). Phase II assessed the efficacy, with the primary endpoint being progression-free rate (PFR) at 16 weeks. RESULTS: No dose-limiting toxicities were observed during phase Ib; therefore RP2D was defined at doses of 400 mg imatinib daily in combination with 200 mg vactosertib. Of the 27 patients evaluated, 7 (25.9%) achieved a confirmed partial response and 19 (70.4%) were stable. The PFR at 16 weeks and 1 year were 96.3% and 81.0%, respectively. Most toxicities were mild to moderate myalgia (n = 10, 37%), anemia (n = 10, 37%), and nausea (n = 9, 33.3%). Common grade 3 to 4 toxicities included neutropenia (n = 6, 22.2%) and anemia (n = 5, 18.5%). CONCLUSIONS: The vactosertib and imatinib combination was well tolerated, with promising clinical activity in patients with progressive, locally advanced desmoid tumors. This is the first study investigating a novel target agent, a TGF-ß inhibitor, in this rare and difficult-to-treat desmoid tumor.

The EGR1-Artemin Axis in Keratinocytes Enhances the Innervation of Epidermal Sensory Neurons during Skin Inflammation Induced by House Dust Mite Extract from Dermatophagoidesfarinae.

Epidermal hyperinnervation is a critical feature of pruritus during skin inflammation. However, the mechanisms underlying epidermal hyperinnervation are unclear. This study investigates the role of the transcription factor EGR1 in epidermal innervation by utilizing wild-type (Egr1+/+) and Egr1-null (Egr1‒/‒) mice topically applied Dermatophagoides farinae extract from dust mite. Our findings revealed that Egr1‒/‒ mice exhibited reduced scratching behaviors and decreased density of epidermal innervation compared with Egr1+/+ mice. Furthermore, we identified artemin, a neurotrophic factor, as an EGR1 target responsible for Dermatophagoides farinae extract-induced hyperinnervation. It has been demonstrated that Dermatophagoides farinae extract stimulates toll-like receptors in keratinocytes. To elucidate the cellular mechanism, we stimulated keratinocytes with Pam3CSK4, a toll-like receptor 1/2 ligand. Pam3CSK4 triggered a toll-like receptor 1/2-mediated signaling cascade involving IRAK4, IκB kinase, MAPKs, ELK1, EGR1, and artemin, leading to increased neurite outgrowth and neuronal migration. In addition, increased expression of EGR1 and artemin was observed in the skin tissues of patients with atopic dermatitis. These findings highlight the significance of the EGR1-artemin axis in keratinocytes, promoting the process of epidermal innervation and suggesting it as a potential therapeutic target for alleviating itch and pain associated with house dust mite-induced skin inflammation.

Sarcopenia prediction using shear-wave elastography, grayscale ultrasonography, and clinical information with machine learning fusion techniques: feature-level fusion vs. score-level fusion.

This study aimed to develop and evaluate a sarcopenia prediction model by fusing numerical features from shear-wave elastography (SWE) and gray-scale ultrasonography (GSU) examinations, using the rectus femoris muscle (RF) and categorical/numerical features related to clinical information. Both cohorts (development, 70 healthy subjects; evaluation, 81 patients) underwent ultrasonography (SWE and GSU) and computed tomography. Sarcopenia was determined using skeletal muscle index calculated from the computed tomography. Clinical and ultrasonography measurements were used to predict sarcopenia based on a linear regression model with the least absolute shrinkage and selection operator (LASSO) regularization. Furthermore, clinical and ultrasonography features were combined at the feature and score levels to improve sarcopenia prediction performance. The accuracies of LASSO were 70.57 ± 5.00-81.54 ± 4.83 (clinical) and 69.00 ± 4.52-69.73 ± 5.47 (ultrasonography). Feature-level fusion of clinical and ultrasonography (accuracy, 70.29 ± 6.63 and 83.55 ± 4.32) showed similar performance with clinical features. Score-level fusion by AdaBoost showed the best performance (accuracy, 73.43 ± 6.57-83.17 ± 5.51) in the development and evaluation cohorts, respectively. This study might suggest the potential of machine learning fusion techniques to enhance the accuracy of sarcopenia prediction models and improve clinical decision-making in patients with sarcopenia.

Durvalumab plus pazopanib combination in patients with advanced soft tissue sarcomas: a phase II trial.

We aimed to determine the activity of the anti-VEGF receptor tyrosine-kinase inhibitor, pazopanib, combined with the anti-PD-L1 inhibitor, durvalumab, in metastatic and/or recurrent soft tissue sarcoma (STS). In this single-arm phase 2 trial (NCT03798106), treatment consisted of pazopanib 800 mg orally once a day and durvalumab 1500 mg once every 3 weeks. Primary outcome was overall response rate (ORR) and secondary outcomes included progression-free survival (PFS), overall survival, disease control rate, immune-related response criteria, and safety. The ORR was 30.4% and the trial met the pre-specified endpoint. The median PFS was 7.7 months (95% confidence interval: 5.7-10.4). The common treatment-related adverse events of grades 3-4 included neutropenia (9 [19.1%]), elevated aspartate aminotransferase (7 [14.9%]), alanine aminotransferase (5 [10.6%]), and thrombocytopenia (4 [8.5%]). In a prespecified transcriptomic analysis, the B lineage signature was a significant key determinant of overall response (P = 0.014). In situ analysis also showed that tumours with high CD20+ B cell infiltration and vessel density had a longer PFS (P = 6.5 × 10-4) than those with low B cell infiltration and vessel density, as well as better response (50% vs 12%, P = 0.019). CD20+ B cell infiltration was identified as the only independent predictor of PFS via multivariate analysis. Durvalumab combined with pazopanib demonstrated promising efficacy in an unselected STS cohort, with a manageable toxicity profile.

Clinical Applications, Challenges, and Recommendations for Artificial Intelligence in Musculoskeletal and Soft-Tissue Ultrasound: AJR Expert Panel Narrative Review.

Artificial intelligence (AI) is increasingly used in clinical practice for musculoskeletal imaging tasks, such as disease diagnosis and image reconstruction. AI applications in musculoskeletal imaging have focused primarily on radiography, CT, and MRI. Although musculoskeletal ultrasound stands to benefit from AI in similar ways, such applications have been relatively underdeveloped. In comparison with other modalities, ultrasound has unique advantages and disadvantages that must be considered in AI algorithm development and clinical translation. Challenges in developing AI for musculoskeletal ultrasound involve both clinical aspects of image acquisition and practical limitations in image processing and annotation. Solutions from other radiology subspecialties (e.g., crowdsourced annotations coordinated by professional societies), along with use cases (most commonly rotator cuff tendon tears and palpable soft-tissue masses), can be applied to musculoskeletal ultrasound to help develop AI. To facilitate creation of high-quality imaging datasets for AI model development, technologists and radiologists should focus on increasing uniformity in musculoskeletal ultrasound performance and increasing annotations of images for specific anatomic regions. This Expert Panel Narrative Review summarizes available evidence regarding AI's potential utility in musculoskeletal ultrasound and challenges facing its development. Recommendations for future AI advancement and clinical translation in musculoskeletal ultrasound are discussed.

Highly accelerated knee magnetic resonance imaging using deep neural network (DNN)-based reconstruction: prospective, multi-reader, multi-vendor study.

In this prospective, multi-reader, multi-vendor study, we evaluated the performance of a commercially available deep neural network (DNN)-based MR image reconstruction in enabling accelerated 2D fast spin-echo (FSE) knee imaging. Forty-five subjects were prospectively enrolled and randomly divided into three 3T MRIs. Conventional 2D FSE and accelerated 2D FSE sequences were acquired for each subject, and the accelerated FSE images were reconstructed and enhanced with DNN-based reconstruction software (FSE-DNN). Quantitative assessments and diagnostic performances were independently evaluated by three musculoskeletal radiologists. For statistical analyses, paired t-tests, and Pearson's correlation were used for image quality comparison and inter-reader agreements. Accelerated FSE-DNN reduced scan times by 41.0% on average. FSE-DNN showed better SNR and CNR (p < 0.001). Overall image quality of FSE-DNN was comparable (p > 0.05), and diagnostic performances of FSE-DNN showed comparable lesion detection. Two of cartilage lesions were under-graded or over-graded (n = 2) while there was no significant difference in other image sets (n = 43). Overall inter-reader agreement between FSE-conventional and FSE-DNN showed good agreement (R2 = 0.76; p < 0.001). In conclusion, DNN-based reconstruction can be applied to accelerated knee imaging in multi-vendor MRI scanners, with reduced scan time and comparable image quality. This study suggests the potential for DNN-accelerated knee MRI in clinical practice.

Machine Learning Predicts Pathologic Complete Response to Neoadjuvant Chemotherapy for ER+HER2- Breast Cancer: Integrating Tumoral and Peritumoral MRI Radiomic Features.

BACKGROUND: This study aimed to predict pathologic complete response (pCR) in neoadjuvant chemotherapy for ER+HER2- locally advanced breast cancer (LABC), a subtype with limited treatment response. METHODS: We included 265 ER+HER2- LABC patients (2010-2020) with pre-treatment MRI, neoadjuvant chemotherapy, and confirmed pathology. Using data from January 2016, we divided them into training and validation cohorts. Volumes of interest (VOI) for the tumoral and peritumoral regions were segmented on preoperative MRI from three sequences: T1-weighted early and delayed contrast-enhanced sequences and T2-weighted fat-suppressed sequence (T2FS). We constructed seven machine learning models using tumoral, peritumoral, and combined texture features within and across the sequences, and evaluated their pCR prediction performance using AUC values. RESULTS: The best single sequence model was SVM using a 1 mm tumor-to-peritumor VOI in the early contrast-enhanced phase (AUC = 0.9447). Among the combinations, the top-performing model was K-Nearest Neighbor, using 1 mm tumor-to-peritumor VOI in the early contrast-enhanced phase and 3 mm peritumoral VOI in T2FS (AUC = 0.9631). CONCLUSIONS: We suggest that a combined machine learning model that integrates tumoral and peritumoral radiomic features across different MRI sequences can provide a more accurate pretreatment pCR prediction for neoadjuvant chemotherapy in ER+HER2- LABC.

EGR1 Regulation of Vasculogenic Mimicry in the MDA-MB-231 Triple-Negative Breast Cancer Cell Line through the Upregulation of KLF4 Expression.

Vasculogenic mimicry (VM) is an intriguing phenomenon observed in tumor masses, in which cancer cells organize themselves into capillary-like channels that closely resemble the structure and function of blood vessels. Although VM is believed to contribute to alternative tumor vascularization, the detailed regulatory mechanisms controlling these cellular processes remain poorly understood. Our study aimed to investigate the role of Early Growth Response 1 (EGR1) in regulating VM in aggressive cancer cells, specifically MDA-MB-231 triple-negative breast cancer cells. Our study revealed that EGR1 promotes the formation of capillary-like tubes by MDA-MB-231 cells in a 3-dimensional Matrigel matrix. EGR1 was observed to upregulate Kruppel-like factor 4 (KLF4) expression, which regulates the formation of the capillary-like tube structure. Additionally, our findings highlight the involvement of the ERK1/2 and p38 mitogen-activated protein kinase pathways in mediating the expression of EGR1 and KLF4, underscoring their crucial role in VM in MDA-MB-231 cells. Understanding these regulatory mechanisms will provide valuable insights into potential therapeutic targets for preventing VM during the treatment of triple-negative breast cancer.

Detection of Pacemaker and Identification of MRI-conditional Pacemaker Based on Deep-learning Convolutional Neural Networks to Improve Patient Safety.

With the increased availability of magnetic resonance imaging (MRI) and a progressive rise in the frequency of cardiac device implantation, there is an increased chance that patients with implanted cardiac devices require MRI examination during their lifetime. Though MRI is generally contraindicated in patients who have undergone pacemaker implantation with electronic circuits, the recent introduction of MR Conditional pacemaker allows physicians to take advantage of MRI to assess these patients during diagnosis and treatment. When MRI examinations of patients with pacemaker are requested, physicians must confirm whether the device is a conventional pacemaker or an MR Conditional pacemaker by reviewing chest radiographs or the electronic medical records (EMRs). The purpose of this study was to evaluate the utility of a deep convolutional neural network (DCNN) trained to detect pacemakers on chest radiographs and to determine the device's subclassification. The DCNN perfectly detected pacemakers on chest radiographs and the accuracy of the subclassification of pacemakers using the internal and external test datasets were 100.0% (n = 106/106) and 90.1% (n = 279/308). The DCNN can be applied to the radiologic workflow for double-checking purposes, thereby improving patient safety during MRI and preventing busy physicians from making errors.

Preliminary study for prediction of benign vertebral compression fracture age by quantitative water fraction using modified Dixon sequences: an imaging biomarker of fracture age.

PURPOSE: This study aimed to evaluate whether quantitative water fraction parameters could predict fracture age in patients with benign vertebral compression fractures (VCFs). METHODS: A total of 38 thoracolumbar VCFs in 27 patients imaged using modified Dixon sequences for water fraction quantification on 3-T MRI were retrospectively reviewed. To calculate quantitative parameters, a radiologist independently measured the regions of interest in the bone marrow edema (BME) of the fractures. Furthermore, five features (BME, trabecular fracture line, condensation band, cortical or end plate fracture line, and paravertebral soft-tissue change) were analyzed. The fracture age was evaluated based on clear-onset symptoms and previously available images. A correlation analysis between the fracture age and water fraction was evaluated using a linear regression model, and a multivariable analysis of the dichotomized fracture age model was performed. RESULTS: The water fraction ratio was the only significant factor and was negatively correlated with the fracture age of VCFs in multiple linear regression (p = 0.047), whereas the water fraction was not significantly correlated (p = 0.052). Water fraction and water fraction ratio were significant factors in differentiating the fracture age of 1 year in multiple logistic regression (odds ratio 0.894, p = 0.003 and odds ratio 0.986, p = 0.019, respectively). Using a cutoff of 0.524 for the water fraction, the area under the curve, sensitivity, and specificity were 0.857, 85.7%, and 87.1%, respectively. CONCLUSIONS: Water fraction is a good imaging biomarker for the fracture healing process. The water fraction ratio of the compression fractures can be used to predict the fracture age of benign VCFs.

Deep-Learning-Based Detection of Vertebral Fracture and Osteoporosis Using Lateral Spine X-Ray Radiography.

Osteoporosis and vertebral fractures (VFs) remain underdiagnosed. The addition of deep learning methods to lateral spine radiography (a simple, widely available, low-cost test) can potentially solve this problem. In this study, we develop deep learning scores to detect osteoporosis and VF based on lateral spine radiography and investigate whether their use can improve referral of high-risk individuals to bone-density testing. The derivation cohort consisted of patients aged 50 years or older who underwent lateral spine radiography in Severance Hospital, Korea, from January 2007 to December 2018, providing a total of 26,299 lateral spine plain X-rays for 9276 patients (VF prevalence, 18.6%; osteoporosis prevalence, 40.3%). Two individual deep convolutional neural network scores to detect prevalent VF (VERTE-X pVF score) and osteoporosis (VERTE-X osteo score) were tested on an internal test set (20% hold-out set) and external test set (another hospital cohort [Yongin], 395 patients). VERTE-X pVF, osteo scores, and clinical models to detect prevalent VF or osteoporosis were compared in terms of the areas under the receiver-operating-characteristics curves (AUROCs). Net reclassification improvement (NRI) was calculated when using deep-learning scores to supplement clinical indications for classification of high-risk individuals to dual-energy X-ray absorptiometry (DXA) testing. VERTE-X pVF and osteo scores outperformed clinical models in both the internal (AUROC: VF, 0.93 versus 0.78; osteoporosis, 0.85 versus 0.79) and external (VF, 0.92 versus 0.79; osteoporosis, 0.83 versus 0.65; p < 0.01 for all) test sets. VERTE-X pVF and osteo scores improved the reclassification of individuals with osteoporosis to the DXA testing group when applied together with the clinical indications for DXA testing in both the internal (NRI 0.10) and external (NRI 0.14, p < 0.001 for all) test sets. The proposed method could detect prevalent VFs and osteoporosis, and it improved referral of individuals at high risk of fracture to DXA testing more than clinical indications alone. © 2023 The Authors. Journal of Bone and Mineral Research published by Wiley Periodicals LLC on behalf of American Society for Bone and Mineral Research (ASBMR).

Effect of Hybrid Compounds of Stilbene and Pentadienone on Inhibition of Tubulin Polymerization.

INTRODUCTION: Tubulin polymerization inhibitors induce cancer cell death; therefore, they can be developed as chemotherapeutic agents. We hypothesized that hybrid compounds, including the trans-stilbene moiety contained in resveratrol and penta-1,4-dien-3-one contained in curcumin, could inhibit tubulin polymerization. METHODS: Twenty-six hybrid stilbene and pentadienone compounds were designed and synthesized. The cytotoxicity of the hybrid compounds against MDA-MB-231 human breast cancer cells was determined using a clonogenic long-term survival assay. The relationship between cytotoxicity and structural properties was evaluated. Biological activities, including inhibition of tubulin polymerization and cell cycle progression, were investigated to select compounds with excellent anticancer properties. The molecular binding mode between the selected compound and the α, ß-tubulin dimers was investigated. RESULTS: Twenty-six hybrid stilbene and pentadienone compounds were designed and synthesized. Among them, compound 13 exhibited the highest inhibitory effect on the clonogenicity of MDA-MB-231 cells. Compound 13 induced the destabilization of tubulins and inhibited cell cycle progression at the G2/M phase. Through in silico molecular docking analysis, compound 13 was predicted to bind to the colchicine binding site of α, ß-tubulin. CONCLUSION: The stilbene and pentadienone hybrid compound 13 has a binding mode similar to that of colchicine. Compound 13 inhibited the clonogenicity of MDA-MB-231 cells through a mechanism that destabilizes tubulin polymerization, leading to cell cycle arrest at the G2/M phase.