Mechanical Constraints in Tumor Guide Emergent Spatial Patterns of Glioblastoma Cancer Stem Cells.

The mechanical constraints in the overcrowding glioblastoma (GBM) microenvironment have been implicated in the regulation of tumor heterogeneity and disease progression. Especially, such mechanical cues can alter cellular DNA transcription and give rise to a subpopulation of tumor cells called cancer stem cells (CSCs). These CSCs with stem-like properties are critical drivers of tumorigenesis, metastasis, and treatment resistance. Yet, the biophysical and molecular machinery underlying the emergence of CSCs in tumor remained unexplored. This work employed a two-dimensional micropatterned multicellular model to examine the impact of mechanical constraints arisen from geometric confinement on the emergence and spatial patterning of CSCs in GBM tumor. Our study identified distinct spatial distributions of GBM CSCs in different geometric patterns, where CSCs mostly emerged in the peripheral regions. The spatial pattern of CSCs was found to correspond to the gradients of mechanical stresses resulted from the interplay between the cell-ECM and cell-cell interactions within the confined environment. Further mechanistic study highlighted a Piezo1-RhoA-focal adhesion signaling axis in regulating GBM cell mechanosensing and the subsequent CSC phenotypic transformation. These findings provide new insights into the biophysical origin of the unique spatial pattern of CSCs in GBM tumor and offer potential avenues for targeted therapeutic interventions.

Aging-associated decline in vascular smooth muscle cell mechanosensation is mediated by Piezo1 channel.

Aging of the vasculature is associated with detrimental changes in vascular smooth muscle cell (VSMC) mechanosensitivity to extrinsic forces in their surrounding microenvironment. However, how chronological aging alters VSMCs' ability to sense and adapt to mechanical perturbations remains unexplored. Here, we show defective VSMC mechanosensation in aging measured with ultrasound tweezers-based micromechanical system, force instantaneous frequency spectrum, and transcriptome analyses. The study reveals that aged VSMCs adapt to a relatively inert mechanobiological state with altered actin cytoskeletal integrity, resulting in an impairment in their mechanosensitivity and dynamic mechanoresponse to mechanical perturbations. The aging-associated decline in mechanosensation behaviors is mediated by hyperactivity of Piezo1-dependent calcium signaling. Inhibition of Piezo1 alleviates vascular aging and partially restores the loss in dynamic contractile properties in aged cells. Altogether, our study reveals the signaling pathway underlying aging-associated aberrant mechanosensation in VSMC and identifies Piezo1 as a potential therapeutic mechanobiological target to alleviate vascular aging.

Combinations of lifestyle behaviors and cancer risk among Korean adults.

Combinations of lifestyle behaviors may lead to different cancer risks. This study aimed to identify the latent classes based on lifestyle behavior trajectories and to investigate the association between these latent classes and cancer risk. Participants in the 2002-2003 National Health Insurance Service general health examination were included. Data on smoking, alcohol drinking, body mass index (BMI), and physical activity measured four times between 2002 and 2009 were analyzed. Incident cancer cases were tracked from 2010 to 2018. Patterns of alcohol drinking, smoking, BMI, and physical activity and latent classes based on trajectories of smoking, alcohol drinking, BMI, and physical activity were identified. Among 2,735,110 adults (1,787,486 men and 947,624 women), 111,218 (69,089 men and 42,129 women) developed incident cancer. Six latent classes of lifestyle behavior were identified, with Class 1 (healthy class) involving only 0.2% of men and 0.5% of women. The highest risk class in males tended to be steady light drinkers and steady moderate smokers, have steady low frequency of physical activity, and be obese. This class showed a 1.47 times higher (95% CI = 1.29-1.69) risk of all cancers than did the healthy class. Among women, there was only an association between the highest risk class (tendency to be non-drinkers, light smokers) and colorectal cancer (HR = 1.70, 95% CI = 1.02-2.83). Only a small percentage of participants maintained a long-term healthy lifestyle. Identifying classes of behavior combinations and their links to cancer development is therefore critical for cancer prevention.

Biodegradable piezoelectric skin-wound scaffold.

Electrical stimulation (ES) induces wound healing and skin regeneration. Combining ES with the tissue-engineering approach, which relies on biomaterials to construct a replacement tissue graft, could offer a self-stimulated scaffold to heal skin-wounds without using potentially toxic growth factors and exogenous cells. Unfortunately, current ES technologies are either ineffective (external stimulations) or unsafe (implanted electrical devices using toxic batteries). Hence, we propose a novel wound-healing strategy that integrates ES with tissue engineering techniques by utilizing a biodegradable self-charged piezoelectric PLLA (Poly (l-lactic acid)) nanofiber matrix. This unique, safe, and stable piezoelectric scaffold can be activated by an external ultrasound (US) to produce well-controlled surface-charges with different polarities, thus serving multiple functions to suppress bacterial growth (negative surface charge) and promote skin regeneration (positive surface charge) at the same time. We demonstrate that the scaffold activated by low intensity/low frequency US can facilitate the proliferation of fibroblast/epithelial cells, enhance expression of genes (collagen I, III, and fibronectin) typical for the wound healing process, and suppress the growth of S. aureus and P. aeruginosa bacteria in vitro simultaneously. This approach induces rapid skin regeneration in a critical-sized skin wound mouse model in vivo. The piezoelectric PLLA skin scaffold thus assumes the role of a multi-tasking, biodegradable, battery-free electrical stimulator which is important for skin-wound healing and bacterial infection prevention simultaneuosly.

Smoking Cessation, Quit Attempts and Predictive Factors among Vietnamese Adults in 2020.

OBJECTIVE: This study aims to describe the updated smoking cessation and quit attempt rates and associated factors among Vietnamese adults in 2020. METHODS: Data on tobacco use among adults in Vietnam in 2020 was derived from the Provincial Global Adult Tobacco Survey. The participants in the study were people aged 15 and older. A total of 81,600 people were surveyed across 34 provinces and cities. Multi-level logistic regression was used to examine the associations between individual and province-level factors on smoking cessation and quit attempts. RESULTS: The smoking cessation and quit attempt rates varied significantly across the 34 provinces. The average rates of people who quit smoking and attempted to quit were 6.3% and 37.2%, respectively. The factors associated with smoking cessation were sex, age group, region, education level, occupation, marital status, and perception of the harmful effects of smoking. Attempts to quit were significantly associated with sex, education level, marital status, perception of the harmful effects of smoking, and visiting health facilities in the past 12 months. CONCLUSIONS: These results may be useful in formulating future smoking cessation policies and identifying priority target groups for future interventions. However, more longitudinal and follow-up studies are needed to prove a causal relationship between these factors and future smoking cessation behaviors.

Aging-associated Decline in Vascular Smooth Muscle Cell Mechanosensation is Mediated by Piezo1 Channel.

Aging of the vasculature is associated with detrimental changes in vascular smooth muscle cell (VSMC) mechanosensitivity to extrinsic forces in their surrounding microenvironment. However, how chronological aging alters VSMCs' ability to sense and adapt to mechanical perturbations remains unexplored. Here, we show defective VSMC mechanosensation in aging measured with ultrasound tweezers-based micromechanical system, force instantaneous frequency spectrum and transcriptome analyses. The mechanobiological study reveals that aged VSMCs adapt a relatively inert solid-like state with altered actin cytoskeletal integrity, resulting in an impairment in their mechanosensitivity and dynamic mechanoresponse to mechanical perturbations. The aging-associated decline in mechanosensation behaviors is mediated by hyperactivity of Piezo1-dependent calcium signaling. Inhibition of Piezo1 alleviates vascular aging and partially restores the loss in dynamic contractile properties in aged cells. Altogether, our study reveals the novel signaling pathway underlying aging-associated aberrant mechanosensation in VSMC and identifies Piezo1 as a potential therapeutic mechanobiological target to alleviate vascular aging.

Mortality risk according to smoking trajectories after cancer diagnosis among Korean male cancer survivors: A population-based cohort study.

INTRODUCTION: Previous research on post-diagnosis smoking among cancer survivors mainly relied on smoking status, which may not fully reflect the impact of changes in smoking levels. This study aimed to evaluate mortality risk according to smoking trajectories among Korean male cancer survivors, using a trajectory approach to comprehensively capture smoking patterns. METHODS: The study included 110555 men diagnosed with cancer between 2002 and 2018 from the Korean National Health Information Database. Group-based trajectory modelling was used to identify post-diagnosis smoking trajectories among pre-diagnosis current smokers (n=45331). Cox hazards models were fitted to evaluate mortality risk according to smoking trajectories for pooled cancers, pooled smoking-related cancers, smoking-unrelated cancers, and gastric, colorectal, liver, and lung cancers. RESULTS: Smoking trajectories included light-smoking quitters, heavy-smoking quitters, consistent moderate smokers, and decreasing heavy smokers. Smoking significantly increased all-cause and cancer mortality risks in cancer patients for pooled cancers, pooled smoking-related cancers, and pooled smoking-unrelated cancers. Compared to non-smokers, all-cause mortality risk for pooled cancers significantly increased according to smoking trajectories:(AHR=1.33; 95% CI: 1.27-1.40), (AHR=1.39; 95% CI: 1.34-1.44), (AHR=1.44; 95% CI: 1.34-1.54), and (AHR=1.47; 95% CI: 1.36-1.60), respectively. Smoking increased all-cause and cancer mortality risks in gastric and colorectal cancer patients and cancer-specific mortality in lung cancer patients. The significant associations of smoking trajectories with all-cause and cancer mortality risks were primarily observed in 5-year survivors but not in short-term survivors. Among heavy smokers, smoking cessation significantly reduced all-cause mortality risk in the long-term. CONCLUSIONS: The post-diagnosis smoking trajectory independently predicts cancer prognosis among male cancer patients. Proactive cessation support should be strengthened, particularly for those who smoke heavily.

Trajectory of physical activity frequency and cancer risk: Findings from a population-based cohort study.

BACKGROUND: Physical activity (PA) changes throughout an individual's life, but the association between such changes and cancer risk seems to be overlooked in the literature. Thus, this study aimed to examine the association between the trajectories of PA frequency and cancer incidence among middle-aged Korean adults. METHODS: A total of 1,476,335 eligible participants (992,151 men and 484,184 women) aged ≥40 years from the National Health Insurance Service cohort (2002-2018) were included. Assessment of PA frequency was a self-reported measure, based on the question: "How many times per week do you perform exercise that makes you sweat?". PA frequency trajectories (i.e., trajectory classes of change in PA frequency) from 2002 to 2008 were identified using group-based trajectory modeling. Cox proportional hazards regression was used to assess the associations between the PA trajectories and cancer incidence. RESULTS: Five PA frequency trajectories over 7 years were identified: persistently low (men:73.5%; women:74.7%), persistently moderate (men:16.2%; women:14.6%), high-to-low (men:3.9%; women:3.7%), low-to-high (men:3.5%; women:3.8%), and persistently high (men:2.9%; women:3.3%). Compared with persistently low frequency, maintaining a high PA frequency was associated with a lower risk of all cancers (Hazard ratio (HR) = 0.92, 95%CI = 0.87-0.98) and breast cancer (HR = 0.82, 95%CI = 0.70-0.96) among women. There was a lower risk for thyroid cancer among men in the high-to-low (HR = 0.83, 95%CI = 0.71-0.98), low-to-high (HR = 0.80, 95%CI = 0.67-0.96), and high PA trajectories (HR = 0.82, 95%CI = 0.68-0.99). There was a significant association between moderate trajectory and lung cancer in men (HR = 0.88, 95%CI = 0.80-0.95), in both smoking and non-smoking men. CONCLUSION: Long-term persistent high frequency of PA as part of the daily routine should be widely promoted and encouraged to reduce the risk for all cancer development in women.

Estimation of the Acoustic Transducer Beam Aperture by Using the Geometric Backscattering Model for Side-Scan Sonar Systems.

In this paper, we propose an algorithm for estimating the beam aperture of the acoustic transducers by using the geometric backscattering model for side-scan sonar systems. The geometric backscattering model is developed to describe the propagation paths of the signal transmitted from the transducers towards the seabed and backscatters to the hydrophones. To evaluate our proposed algorithm, we have developed a side-scan sonar system. The side-scan sonar system uses two transducers, operating on two different frequencies and focusing on two different wave beams, to scan the images of the seabed. The proposed algorithm provides the estimated beam apertures of each transducer. Our obtained results agree quite well with the parameters provided by the manufacturers. Moreover, these results are used to calibrate the scanned images. We provide the scanned sonar 3D images of the Dong Do lakebed, Vietnam, to justify our proposal.

Alcoholic liver disease in relation to cancer incidence and mortality: Findings from a large, matched cohort study in South Korea.

AIM: To estimate the risk of cancer incidence and mortality among patients with alcoholic liver disease in South Korea. METHODS: A matched cohort study was conducted, including 1,042,185 men (alcoholic liver disease cases: 208,437; controls: 833,748) and 100,400 women (alcoholic liver disease cases: 20,080; controls: 80,320), matched for sex, age, smoking, alcohol consumption, and body mass index at a 1:4 ratio. The risk of cancer incidence and mortality in the alcoholic liver disease group was assessed using Cox proportional hazards regression models. RESULTS: Both men and women with alcoholic liver disease had an elevated risk of all-cancer and liver cancer incidence and mortality in comparison with the control group. In men, alcoholic liver disease was associated with a significantly higher risk of development of 10 cancer types, including lip, oral cavity, and pharynx; esophagus; liver; gallbladder and biliary tract; pancreas; larynx; lung; kidney; thyroid gland; and leukemia. Subgroup analysis by hepatitis B and C infection showed increased hazard ratios of all cancer incidences and mortality in the alcoholic liver disease group, regardless of hepatitis B or C infection status. In both sexes, a higher number and more years of hospital or clinic visits for alcoholic liver disease were associated with an increased risk of incidence and mortality from all cancers and liver cancer. A more profound dose-response relationship between alcoholic liver disease and alcohol consumption was observed in women than in men. CONCLUSIONS: Our findings emphasize the need for a clinical surveillance program and the early detection of cancer in patients with alcoholic liver disease.

Cancer Risk According to Alcohol Consumption Trajectories: A Population-based Cohort Study of 2.8 Million Korean Men.

BACKGROUND: Alcohol drinking behaviors change temporally and can lead to changes in related cancer risks; previous studies have been unable to identify the association between the two using a single-measurement approach. Thus, this study aimed to investigate the association of drinking trajectories with the cancer risk in Korean men. METHODS: A trajectory analysis using group-based trajectory modeling was performed on 2,839,332 men using data on alcohol drinking levels collected thrice during the Korean National Health Insurance Service's general health screening program conducted between 2002 and 2007. Cox proportional hazards regression was performed to evaluate the associations between drinking trajectories and cancer incidence, after adjustments for age, income, body mass index, smoking status, physical activity, family history of cancer, and comorbidities. RESULTS: During 10.5 years of follow-up, 189,617 cancer cases were recorded. Six trajectories were determined: non-drinking, light, moderate, decreasing-heavy, increasing-heavy, and steady-heavy. Light-to-heavy alcohol consumption increased the risk for all cancers combined in a dose-dependent manner (adjusted hazard ratio [aHR] 1.03; 95% confidence interval [CI], 1.02-1.05 for light drinking, aHR 1.06; 95% CI 1.05-1.08 for moderate drinking, aHR 1.19; 95% CI, 1.16-1.22 for decreasing-heavy drinking, aHR 1.23; 95% CI, 1.20-1.26 for increasing-heavy drinking, and aHR 1.33; 95% CI, 1.29-1.38 for steady-heavy drinking [P-trend <0.001]). Light-to-heavy alcohol consumption was linked to lip, oral cavity, pharyngeal, esophageal, colorectal, laryngeal, stomach, and gallbladder and biliary tract cancer risks, while heavy alcohol consumption was associated with hepatic, pancreatic, and lung cancer risks. An inverse association was observed for thyroid cancer. The cancer risks were lower for decreasing-heavy drinkers, compared to steady-heavy drinkers. CONCLUSION: No safe drinking limits were identified for cancer risks; reduction in heavy intake had protective effects.

Exposure to Electronic Cigarette Advertisements and Use of Electronic Cigarettes: A Meta-analysis of Prospective Studies.

INTRODUCTION: Electronic cigarette (EC) advertisements remain unregulated and approach consumers in TV commercials, print ads, radio, and other forms of digital marketing. AIMS AND METHODS: This study aimed to assess whether exposure to EC advertisements is associated with the use of EC by using a meta-analysis of prospective studies. We searched PubMed, EMBASE, and Web of Science to locate eligible studies in November 2021. Pooled adjusted odds ratios (aORs) with 95% confidence intervals (CIs) were calculated using a random-effects meta-analysis. RESULTS: Out of 1635 articles searched from databases, we included seven prospective studies that met inclusion criteria in the final analysis. Four out of seven studies involved participants under 18 years of age. In the meta-analysis of all studies, exposure to EC advertisements was significantly associated with the increased use of ECs (aOR = 1.53, 95% CI 1.22 to 1.92; I2 = 60.1%). In the subgroup meta-analyses by source of advertisements, there was no significant association between exposure to EC advertisements on TV, radio, or billboards and the use of EC, while exposure to EC advertisements in retail stores and on Internet or social media significantly increased the use of EC. CONCLUSIONS: Exposure to EC advertisements was associated with the increased use of ECs, specifically in retail stores and on Internet or social media among adolescents and young adults. Because EC use could serve as a gateway to cigarette smoking in adolescents and young adults, more strict regulations and restrictions on EC advertisements are needed. IMPLICATIONS: Concurrent with the rise in electronic cigarette (EC) sales, advertising expenditures for ECs have been increased in the past decade, and there is controversy over the association between exposure to EC advertisements and the use of ECs. This meta-analysis of seven prospective studies showed that exposure to EC advertisements was significantly associated with the increased use of ECs, specifically in retail stores and on Internet or social media among adolescents and young adults. Because, EC use could serve as a gateway to cigarette smoking in adolescents and young adults, more strict regulations and restrictions on EC advertisements are needed.

Comment on Topical Dapsone for Folliculitis Decalvans.

Folliculitis decalvans (FD) represents a chronic and recurrent pustulofollicular scalp inflammation resulting in scarring alopecia. The presence of a bacterial bioflilm at the interface of the hair shaft may provide an explanation for the chronicity and high relapse rate of FD, even after prolonged systemic antibiotic treatments. We originally read with enthusiasm Melián-Olivera et al.'s retrospective study of patients with FD treated with topical dapsone published in the Journal of the American Academy of Dermatology. However, we experienced an unsuccessful trial of 5% dapsone gel in a patient with FD resulting in worsening of the disease with a pustular flareup and questioned why positive study reports with novel therapeutic options in dermatology often fail in practice. The authors admitted the limitations of their study: small sample size, retrospective, uncontrolled nature of the study, and concomitant use of other treatments. Clinical research ultimately aims at improving the patient outcome. For this purpose, trials must evaluate the outcomes that genuinely reflect the clinical utility of drugs. Therefore, we postulate stricter criteria for treatment trials and statistics in dermatology before publication in peer-reviewed scientific journals to avoid frustrations of physicians and patients alike.

The Problem with Capitalism in the Trichological Sciences.

Karl Marx and Friedrich Engels exposed a pattern of societal conduct they chose to name capitalistic bourgeoisie. The bourgeoisie created a common language of communication through collaboration, gathered in circles such as free academies, scientific academies, literary circles, and the media, that provided forums for the emerging bourgeoisie to conceive of new social orders. One aspect of bourgeoisie culture is conspicuous consumption, central to which, is a culture of prestige through material consumption. Capitalism is an economic system based on private ownership and the operation for profit. Characteristic features of capitalism include competitive market, commercialism, property rights recognition, capital accumulation, material consumption, culture of prestige, sycophancy, and coterie. Critiques of capitalism allege that it is exploitative, alienating, unstable, unsustainable, and inefficient. In turn, critical theory inspired philosophers such as Michel Foucault to conceptualize how we form identities through social interaction. When the patient's body entered the field of medicine, it also entered the field of power where the patient can be manipulated by professional authority. Without forcibly being a proponent of political theory, as an academic, one is inevitably confronted with Marxism in terms of philosophy. As a discipline at the interface of medicine, lifestyle, and cosmetics, trichology is particularly susceptible to the primary aims of profit, consumption, and prestige that characterize the capitalistic bourgeoisie. The trichological sciences, particularly trichoscopy, have discovered a profitable market for itself. The practice of trichology is not immune to malpractice. It has created an industry that dwells on the autistic thinking of patients and doctors, and because it is prosperous, makes propaganda among lay people and doctors that necessarily leads to abuses.

A Radiomics Approach on Chest CT Distinguishes Primary Lung Cancer from Solitary Lung Metastasis in Colorectal Cancer Patients.

PURPOSE: This study utilized a radiomics approach combined with a machine learning algorithm to distinguish primary lung cancer (LC) from solitary lung metastasis (LM) in colorectal cancer (CRC) patients with a solitary pulmonary nodule (SPN). MATERIALS AND METHODS: In a retrospective study, 239 patients who underwent chest computerized tomography (CT) at three different institutions between 2011 and 2019 and were diagnosed as primary LC or solitary LM were included. The data from the first institution were divided into training and internal testing datasets. The data from the second and third institutions were used as an external testing dataset. Radiomic features were extracted from the intra and perinodular regions of interest (ROI). After a feature selection process, Support vector machine (SVM) was used to train models for classifying between LC and LM. The performances of the SVM classifiers were evaluated with both the internal and external testing datasets. The performances of the model were compared to those of two radiologists who reviewed the CT images of the testing datasets for the binary prediction of LC versus LM. RESULTS: The SVM classifier trained with the radiomic features from the intranodular ROI and achieved the sensitivity/specificity of 0.545/0.828 in the internal test dataset, and 0.833/0.964 in the external test dataset, respectively. The SVM classifier trained with the combined radiomic features from the intra- and perinodular ROIs achieved the sensitivity/specificity of 0.545/0.966 in the internal test dataset, and 0.833/1.000 in the external test data set, respectively. Two radiologists demonstrated the sensitivity/specificity of 0.545/0.966 and 0.636/0.828 in the internal test dataset, and 0.917/0.929 and 0.833/0.929 in the external test dataset, which were comparable to the performance of the model trained with the combined radiomics features. CONCLUSION: Our results suggested that the machine learning classifiers trained using radiomics features of SPN in CRC patients can be used to distinguish the primary LC and the solitary LM with a similar level of performance to radiologists.

Utilizing artificial intelligence to solving time - cost - quality trade-off problem.

This study presents the Slime Mold Algorithm (SMA) to solve the time-cost-quality trade-off problem in a construction project. The proposed SMA is a flexible and efficient algorithm in exploration and exploitation to reach the best optimal solution to process the input model's data. This paper aims to discuss and solve the optimization problem and compare the evaluation with other algorithms such as Opposition-based Multiple Objective Differential Evolution, Non-dominated sorting genetic algorithm, Multiple objective particle swarm optimization, Multiple objective differential evolution and Chaotic initialized multiple objective differential evolution (CAMODE) to verify the efficiency and potential of the proposed algorithm. According to the analysis results, the SMA model generated a diversification measure for case studies, producing superior outcomes to those of previous algorithms.

Prediction of the histologic upgrade of ductal carcinoma in situ using a combined radiomics and machine learning approach based on breast dynamic contrast-enhanced magnetic resonance imaging.

Objective: To investigate whether support vector machine (SVM) trained with radiomics features based on breast magnetic resonance imaging (MRI) could predict the upgrade of ductal carcinoma in situ (DCIS) diagnosed by core needle biopsy (CNB) after surgical excision. Materials and methods: This retrospective study included a total of 349 lesions from 346 female patients (mean age, 54 years) diagnosed with DCIS by CNB between January 2011 and December 2017. Based on histological confirmation after surgery, the patients were divided into pure (n = 198, 56.7%) and upgraded DCIS (n = 151, 43.3%). The entire dataset was randomly split to training (80%) and test sets (20%). Radiomics features were extracted from the intratumor region-of-interest, which was semi-automatically drawn by two radiologists, based on the first subtraction images from dynamic contrast-enhanced T1-weighted MRI. A least absolute shrinkage and selection operator (LASSO) was used for feature selection. A 4-fold cross validation was applied to the training set to determine the combination of features used to train SVM for classification between pure and upgraded DCIS. Sensitivity, specificity, accuracy, and area under the receiver-operating characteristic curve (AUC) were calculated to evaluate the model performance using the hold-out test set. Results: The model trained with 9 features (Energy, Skewness, Surface Area to Volume ratio, Gray Level Non Uniformity, Kurtosis, Dependence Variance, Maximum 2D diameter Column, Sphericity, and Large Area Emphasis) demonstrated the highest 4-fold mean validation accuracy and AUC of 0.724 (95% CI, 0.619-0.829) and 0.742 (0.623-0.860), respectively. Sensitivity, specificity, accuracy, and AUC using the test set were 0.733 (0.575-0.892) and 0.7 (0.558-0.842), 0.714 (0.608-0.820) and 0.767 (0.651-0.882), respectively. Conclusion: Our study suggested that the combined radiomics and machine learning approach based on preoperative breast MRI may provide an assisting tool to predict the histologic upgrade of DCIS.