Search

Large-scale multi-building and multi-floor indoor localization has recently been the focus of intense research in indoor localization based on Wi-Fi fingerprinting. Although significant progress has been made in developing indoor localization algorithms, few studies are dedicated to the critical issues of using existing and constructing new Wi-Fi fingerprint databases, especially for large-scale multi-building and multi-floor indoor localization. In this paper, we first identify the challenges in using and constructing Wi-Fi fingerprint databases for large-scale multi-building and multi-floor indoor localization and then provide our recommendations for those challenges based on a case study of the UJIIndoorLoc database, which is the most popular publicly available Wi-Fi fingerprint multi-building and multi-floor database. Through the case study, we investigate its statistical characteristics with a focus on the three aspects of (1) the properties of detected wireless access points, (2) the number, distribution and quality of labels, and (3) the composition of the database records. We then identify potential issues and ways to address them using the UJIIndoorLoc database. Based on the results from the case study, we not only provide valuable insights on the use of existing databases but also give important directions for the design and construction of new databases for large-scale multi-building and multi-floor indoor localization in the future.

ROS1 rearrangement is found in 0.9%–2.6% of people with non-small-cell lung cancers (NSCLCs). Tyrosine kinase inhibitors (TKIs) target ROS1 and can block tumor growth and provide clinical benefits to patients. This review summarizes the current knowledge on ROS1 rearrangements in NSCLCs, including the mechanisms of ROS1 oncogenicity, epidemiology of ROS1-positive tumors, methods for detecting rearrangements, molecular characteristics, therapeutic agents, and mechanisms of drug resistance.

Purpose: To determine whether microRNA could be a therapy target of erectile dysfunction (ED) and the underlying mechanisms. Materials and Methods: Eight-week-old fasting male SD rats were intraperitoneally injected with streptozotocin to construct diabetic rat models. Diabetic ED rats were treated with miRNA-92a inhibitor. The cavernous nerves were electrically stimulated to measure the intracavernous pressure and mean arterial pressure of rats in each group. After the detection, the penile cavernous tissues are properly stored for subsequent experiments. Rat aortic endothelial cells were used in in vitro studies. Results:The expression of miR-92a was significantly increased in the corpus cavernosum of Streptozocin (STZ)-induced diabetic rats and injection of miR-92a antagomir into the corpus cavernosum of diabetic rats significantly increased eNOS/NO/ cGMP signaling pathway activities, cavernous endothelial cell proliferation, endothelial cell-cell junction protein expression and decreased the levels of oxidative stress. These changes restored erectile function in STZ-induced diabetic rats. Moreover, in vitro study demonstrated that the miR-92a expression increased significantly in endothelial cells treated with high glucose, inhibiting AMPK/eNOS and AMPK/Nrf2/HO-1 signaling pathways in rat aortic endothelial cells via targeting Prkaa2, causing endothelial dysfunction and overactive oxidative stress, miR-92a inhibitor can improve the above parameters. Conclusions: miRNA-92a inhibitor could exert an inhibition role on oxidative stress and endothelial dysfunction to improve diabetic ED effectively.

Objective: To investigate the frailty, as estimated by accumulated health deficits, in association with the symptomatic carotid atherosclerosis and in relation to five-year cardiovascular (CVD) outcomes. Methods: This is a five-year prospective cohort study. Secondary analysis of data from the Beijing Longitudinal Study on Aging. Community-dwelling people aged 55+ years (n = 1257) have been followed between 2009 and 2014, and having carotid ultrasonography examinations with no CVD events at baseline. Frailty was quantified using the deficit accumulation-based frailty index (FI), constructed from 37 health deficits assessed at baseline. The association between the degree of frailty and carotid atherosclerosis was examined using odds ratios (OR) with multivariate logistic regression analyses. Effects of frailty on the probability of five-year cardiovascular events and mortality were evaluated using Cox proportional hazard ratios (HR). The analyses were adjusted for demographics, baseline carotid atherosclerosis status, and CVD risk factors. Results: The FI showed characteristic properties and was independently associated with the major carotid atherosclerosis symptoms, including carotid artery intima-media thickening (the most frail vs. the least frail: OR = 4.39: 1.98–7.82), carotid plaque (OR = 3.41: 1.28–6.54), and carotid plaque stability (OR = 1.19, 95 % CI: 1.01–3.59). Compared with the least frail, the most frail individuals were more likely to develop a cardiovascular event in five years, including myocardial infarction (HR = 3.38, 95 % CI = 1.84–6.19), stroke (HR = 1.26, 95 % CI = 1.00–5.87), CVD death (HR = 6.33, 95 % CI = 1.69–11.02), and all-cause death (HR = 5.95, 95 % CI = 2.74–8.95). Conclusion: Deficit accumulation was closely associated with carotid atherosclerosis risks and strongly predicted five-year CVD events. The frailty index can be used to help identify older adults at high risks of CVD for improved preventive healthcare.

Location fingerprinting using Received Signal Strength Indicators (RSSIs) has become a popular technique for indoor localization due to its use of existing Wi-Fi infrastructure and Wi-Fi-enabled devices. Artificial intelligence/machine learning techniques such as Deep Neural Networks (DNNs) have been adopted to make location fingerprinting more accurate and reliable for large-scale indoor localization applications. However, the success of DNNs for indoor localization depends on the availability of a large amount of pre-processed and labeled data for training, the collection of which could be time-consuming in large-scale indoor environments and even challenging during a pandemic situation like COVID-19. To address these issues in data collection, we investigate multi-dimensional RSSI data augmentation based on the Multi-Output Gaussian Process (MOGP), which, unlike the Single-Output Gaussian Process (SOGP), can exploit the correlation among the RSSIs from multiple access points in a single floor, neighboring floors, or a single building by collectively processing them. The feasibility of MOGP-based multi-dimensional RSSI data augmentation is demonstrated through experiments using the hierarchical indoor localization model based on a Recurrent Neural Network (RNN)—i.e., one of the state-of-the-art multi-building and multi-floor localization models—and the publicly available UJIIndoorLoc multi-building and multi-floor indoor localization database. The RNN model trained with the UJIIndoorLoc database augmented with the augmentation mode of “by a single building”, where an MOGP model is fitted based on the entire RSSI data of a building, outperforms the other two augmentation modes and results in the three-dimensional localization error of 8.42 m.

Abstract Background Castration-resistant prostate cancer (CRPC) is a major cause of recurrence and mortality among prostate cancer (PCa) patients. Myeloid-derived suppressor cells (MDSCs) regulate castration resistance in PCa. Previously, it was shown that intercellular communication was efficiently mediated by exosomes (Exos), but the role and the mechanism of MDSC-derived Exos in CRPC progression was unclear. Methods In this study, the circRNA expression profiles in PC3 cells treated with MDSC-Exo and control cells were investigated using a circRNA microarray. Results The data showed that circMID1 (hsa_circ_0007718) expression was elevated in PC3 cells treated with MDSC-Exo. Moreover, high circMID1 expression was found in PCa compared with benign prostatic hyperplasia (BPH) tissues and in CRPC patients compared with hormone sensitive prostate cancer (HSPC) patients. Further studies showed that MDSC-Exo accelerated PCa cell proliferation, migration, and invasion, while circMID1 deficiency inhibited MDSC-Exo-regulated CRPC progression in vitro and in vivo. Mechanistically, MDSC-derived exosomal S100A9 increased circMID1 expression to sponge miR-506-3p, leading to increased MID1 expression and accelerated tumor progression. Conclusion Together, our results showed that a S100A9/circMID1/miR-506-3p/MID1 axis existed in MDSC-Exo-regulated CRPC progression, which provided novel insights into MDSC-Exo regulatory mechanisms in CRPC progression.

Abstract Background Frailty can be operationalized based on the accumulation of deficits using a frailty index (FI) and is associated with an increased risk of adverse health outcomes. Here, we aim to compare validity of a FI from laboratory data with that of the common clinical FI for prediction of mortality in adults aged 55 + years, also examine whether combined FI could improve identification of adults aged 55 + years at increased risk of death. Methods Data for this analysis were obtained from the Beijing Longitudinal Study of Aging that involved 1,257 community-dwelling Chinese people, aged 55 + years at baseline. The main outcome measure was 5-year mortality. An FI-self-report based on 30 self-reported health-related data was constructed. An FI-lab was developed using laboratory data, in addition to pulse, systolic and diastolic blood pressure, pulse pressure, body mass index (BMI) and waist. A combined FI comprised all items from each FI. Kaplan–Meier survival curve and Cox proportional hazards models were performed to evaluate the risk of each FI on death. The area under receiver operating characteristic(ROC) curves were used to compare the discriminative performance of each FI. Results Of 1257 participants, 155 died and 156 lost at the end of the 5-year follow-up. The mean FI-self-report score was 0.11 ± 0.10, the FI-lab score was 0.33 ± 0.14 and FI-combined score was 0.19 ± 0.09. Higher frailty level defined by each FI was associated with higher risk of death. After adjustment for age and sex, Cox proportional hazards models showed that the higher scores of frailty were associated with a higher risk of mortality for each FI, the hazard ratios for the FI-self-report and FI-lab and FI-combined were 1.04 (1.03 to 1.05) and 1.02 (1.01 to 1.03) and 1.05 (1.04 to 1.07), respectively. The areas under the ROC curve were 0.79 (0.77–0.82) for the FI-self-report, 0.77(0.75–0.80) for the FI-lab and 0.81(0.78–0.82) for FI-combined. Conclusions A FI from laboratory data can stratify older adults at increased risk of death alone and in combination with FI based on self-report data. Assessment in clinical settings of creating an FI using routine collected laboratory data needs to be further developed.

Abstract The associations of blood pressure components with cardiovascular risks and death remain unclear, and the definition of wide pulse pressure (PP) is still controversial. Using data from 1257 participants without a history of cardiovascular disease, who were followed for 4.84 years, we performed multivariable Cox regression analyses to assess how systolic blood pressure (SBP), diastolic blood pressure (DBP), and PP contribute to risks of cardiovascular events and all‐cause death. Among all participants, SBP and PP were significantly associated with the risks of cardiovascular events and all‐cause death (all p < .05). DBP was not significantly associated with the risk of all‐cause death; rather, it was only associated with a marginally significant 1% increased risk for cardiovascular events (p = 0.051). In participants aged

Cognitive impairment is a major global disease, manifests as a decline in cognitive functioning and endangers the health of the population worldwide. The incidence of cognitive impairment has increased rapidly with an increasingly aging population. Although the mechanisms of cognitive impairment have partly been elucidated with the development of molecular biological technology, treatment methods are very limited. As a unique form of programmed cell death, pyroptosis is highly pro-inflammatory and is closely associated with the incidence and progression of cognitive impairment. In this review, we discuss the molecular mechanisms of pyroptosis briefly and the research progress on the relationship between pyroptosis and cognitive impairment and its potential therapeutic values, to provide a reference for research in the field of cognitive impairment.

The global burden of cancer is increasing rapidly, and nanomedicine offers promising prospects for enhancing the life expectancy of cancer patients. Janus nanoparticles (JNPs) have garnered considerable attention due to their asymmetric geometry, enabling multifunctionality in drug delivery and theranostics. However, achieving precise control over the self-assembly of JNPs in solution at the nanoscale level poses significant challenges. Herein, a low-temperature reversed-phase microemulsion system was used to obtain homogenous Mn3O4-Ag2S JNPs, which showed significant potential in cancer theranostics. Structural characterization revealed that the Ag2S (5–10 nm) part was uniformly deposited on a specific surface of Mn3O4 to form a Mn3O4-Ag2S Janus morphology. Compared to the single-component Mn3O4 and Ag2S particles, the fabricated Mn3O4-Ag2S JNPs exhibited satisfactory biocompatibility and therapeutic performance. Novel diagnostic and therapeutic nanoplatforms can be guided using the magnetic component in JNPs, which is revealed as an excellent T1 contrast enhancement agent in magnetic resonance imaging (MRI) with multiple functions, such as photo-induced regulation of the tumor microenvironment via producing reactive oxygen species and second near-infrared region (NIR-II) photothermal excitation for in vitro tumor-killing effects. The prime antibacterial and promising theranostics results demonstrate the extensive potential of the designed photo-responsive Mn3O4-Ag2S JNPs for biomedical applications.

Abstract Background ApoE gene polymorphism and serum total homocysteine (tHcy) has been reportedly associated with cognition. In this study, we assessed the association of combined ApoE gene polymorphism and tHcy with cognition in Chinese elder adults. Methods A cross- sectional study was carried out by recruiting 1458 community-dwelling people aged 55+ and above in Beijing in 2009. All participants were interviewed using a standard questionnaire and underwent a physical examination. The mini-mental scale examination (MMSE) score was used in assessing cognitive function. Fasting venous blood samples were taken for ApoE rs429358, rs7412 genotyping, tHcy and other serum lipid measurements. Results Participants with high serum tHcy level showed a relatively lower orientation, attention abilities as well as the total MMSE score than the group with normal tHcy after adjusting confounding factors. ApoE rs429358 and rs7412 variants were observed to have the highest serum TC and TG level in the subjects with high serum tHcy level (p

Abstract Background Radial artery (RA) atherosclerosis in acute coronary syndrome (ACS) patients has not been systematically observed in vivo. The study aims to characterize plaque morphology and intimal hyperplasia of the RA in patients with ACS, using optical coherence tomography (OCT). Methods In this retrospective study involving 239 ACS patients underwent RA OCT without guidewire shadow, 3 groups were divided according to the following criteria: radial artery plaque (RAP) group included patients with fibrous, lipid or calcified plaque; patients without RAP were further classified into radial intimal hyperplasia (RIH) group (intima media thickness ratio [IMR] ≥ 1) or normal group (IMR

ABSTRACT: Lung cancer has the highest incidence and mortality rate worldwide. Immunotherapy is a universal treatment for lung cancer, but its overall treatment remains a challenge. Tumor immunoediting is a process in which the immune system restricts or promotes tumor development through elimination, equilibrium, and escape to change tumor immunogenicity and obtain an immunosuppressive mechanism to promote disease progression. An increasing number of immunotherapy drugs, including monoclonal antibody-targeting drugs and chimeric antigen (Ag) receptor-modified T cells (CAR-T cells), have been used in clinical therapy. Additionally, cancer vaccine development and new clustered regularly spaced short palindromes (CRISPR)- based combination therapies against cancer open up new avenues for immunotherapy. However, these immunotherapies cause autoimmune induction and non-specific inflammation, with many limitations. The development and study of nanoparticle systems have shown the possibility of localization, pharmacokinetic programming, and immunomodulator co-delivery. Rapid advances in nanotechnology over the past decade have provided a strategic impetus for cancer immunotherapy improvements. Nanotechnology advancements in various aspects, such as virus-like size, high surface-volume ratio, and surface modifications to precisely target specific cell types, can be investigated through cancer vaccine and immunomodulator delivery system development. This review presents the current immunotherapy approaches for lung cancer and emphasizes the current process and prospects of the fusion of cancer immunotherapy, nanotechnology, bioengineering, and drug delivery.

BackgroundLymph node (LN) metastasis is strongly associated with distant metastasis of renal cell carcinoma (RCC) and indicates an adverse prognosis. Accurate LN-status prediction is essential for individualized treatment of patients with RCC and to help physicians make appropriate surgical decisions. Thus, a prediction model to assess the hazard index of LN metastasis in patients with RCC is needed.MethodsPartial data were extracted from the Surveillance, Epidemiology, and End Results (SEER) database. Data of 492 individuals with RCC, collected from the Southwest Hospital in Chongqing, China, were used for external validation. Eight indicators of risk of LN metastasis were screened out. Six machine learning (ML) classifiers were established and tuned, focused on predicting LN metastasis in patients with RCC. The models were integrated with big data analytics and ML algorithms. Based on the optimal model, we developed an online risk calculator and plotted overall survival using Kaplan–Meier analysis.ResultsThe extreme gradient-boosting (XGB) model was superior to the other models in both internal and external trials. The area under the curve, accuracy, sensitivity, and specificity were 0.930, 0.857, 0.856, and 0.873, respectively, in the internal test and 0.958, 0.935, 0.769, and 0.944, respectively, in the external test. These parameters show that XGB has an excellent ability for clinical application. The survival analysis showed that patients with predicted N1 tumors had significantly shorter survival (p

BackgroundPrimary tracheal or bronchial tumors are relatively uncommon, whether benign or malignant. Sleeve resection is an excellent surgical technique for most primary tracheal or bronchial tumors. However, depending on the size and location of the tumor, thoracoscopic wedge resection of trachea or bronchus can be performed with the assistance of a fiberoptic bronchoscope for some malignant and benign tumors.Case DescriptionWe performed a single incision video-assisted bronchial wedge resection in a patient with a left main bronchial hamartoma with a size of 7 × 5 × 5 mm. The patient was discharged from the hospital six days after the surgery with no postoperative complications. There was no obvious discomfort during the 6-month postoperative follow-up, and the reexamination of fiberoptic bronchoscopy revealed no evident stenosis of the incision.ConclusionsThrough the detailed case study and literature review, we believe that tracheal or bronchial wedge resection is a significantly superior technique under the appropriate conditions. Video-assisted thoracoscopic wedge resection of trachea or bronchus should be a new and excellent development direction of minimally invasive bronchial surgery.

Pyogenic liver abscess and keratitis are aggressive bacterial infections and the treatment has failed to eradicate bacteria in infectious sites completely owing to the currently severe drug resistance to existing antibiotics. Here, we report a simple and efficient one-step development of ultrasmall non-antibiotic nanoparticles (ICG-Ga NPs) containing clinically approved gallium (III) (Ga3+) and liver targeting indocyanine green (ICG) molecules to eradicate multi-drug resistant (MDR) bacteria thought the synergetic effect of photodynamic therapy and iron metabolism blocking. The ICG-Ga NPs induced photodynamic effect could destroy the bacterial membrane, further boost the endocytosis of Ga3+, then replace iron in bacteria cells to disrupt bacterial iron metabolism, and demonstrate the synergetic bacterial killing and biofilm disrupting effects. The ICG-Ga NPs show an excellent therapeutic effect against extended spectrum β-lactamases Escherichia coli (ESBL E. coli) and significantly improve treatment outcomes in infected liver abscess and keratitis. Meanwhile, the ultrasmall size of ICG-Ga NPs could be cleared rapid via renal clearance route, guaranteeing the biocompatibility. The protective effect and good biocompatibility of ICG-Ga NPs will facilitate clinical treatment of bacteria infected diseases and enable the development of next-generation non-antibiotic antibacterial agents.

Numerous epidemiological and laboratory studies on essential trace elements have reported protective associations in developing various cancer types, including esophagus cancer (EC). However, the results are not always consistent. Some essential trace elements could play a vital role in preventing esophagus cancer. Some showed no association with esophageal cancer risk, while others harmed individuals. This article reviews the association between the intake or supplementation of essential trace elements (especially zinc, copper, iron, and selenium) and the risk of esophageal cancer. Generally, zinc intake may decrease the risk of esophageal cancer (EC), especially in high esophageal squamous cell carcinoma (ESCC) prevalence regions. The association between copper supplementation and EC remains uncertain. Total iron consumption is thought to be associated with lower EC risk, while heme iron intake may be associated with higher EC risk. Selenium intake showed a protective effect against EC, especially for those individuals with a low baseline selenium level. This review also prospects the research direction of the association between EC and essential trace elements.

Abstract Background Some previous studies on different populations have yielded inconsistent findings with respect to the relationship between levels of high-density lipoprotein cholesterol (HDL-C) and future type 2 diabetes mellitus (T2DM) incidence. This study was designed to gain further insight into this relationship through a cohort study with a 25-year follow-up duration. Methods In total, 1462 individuals that were 55 years of age or older and were free of T2DM at baseline were enrolled in the present study. T2DM incidence among this study population was detected through self-reported diagnoses or the concentration of fasting plasma glucose. The data were derived from nine surveys conducted from 1992 to 2017. The correlation between HDL-C levels and the T2DM risk was assessed through Cox proportional-hazards model and proportional hazards model for the sub-distribution with time-dependent variables. Results Over the follow-up period, 120 participants were newly diagnosed with new-onset T2DM. When research participants were separated into four groups on the basis for quartiles of their levels of HDL-C measured at baseline, and incidence of diabetes declined with higher baseline HDL-C levels at 12.60, 9.70, 5.38, and 5.22 per 1000 person-years, respectively. Adjusted hazard ratios (HRs) were 0.98 (95% confidence interval [CI]: 0.62–1.55), 0.48 (95% CI: 0.27–0.85) and 0.44 (95% CI: 0.25–0.80) for individuals with HDL-C levels within the 1.15–1.39, 1.40–1.69, and ≥ 1.70 mmol/L ranges relative to participants with HDL-C levels

Lung adenocarcinoma (LUAD) usually contains heterogeneous histological subtypes, among which the micropapillary (MIP) subtype was associated with poor prognosis while the lepidic (LEP) subtype possessed the most favorable outcome. However, the genomic features of the MIP subtype responsible for its malignant behaviors are substantially unknown. In this study, eight FFPE samples from LUAD patients were micro-dissected to isolate MIP and LEP components, then sequenced by whole-exome sequencing. More comprehensive analyses involving our samples and public validation cohorts on the two subtypes were performed to better decipher the key biological and evolutionary mechanisms. As expected, the LEP and MIP subtypes exhibited the largest disease-free survival (DFS) differences in our patients. EGFR was found with the highest mutation frequency. Additionally, shared mutations were observed between paired LEP and MIP components from single patients, and recurrent mutations were verified in the Lung-Broad, Lung-OncoSG, and TCGA-LUAD cohorts. Distinct biological processes or pathways were involved in the evolution of the two components. Besides, analyses of copy number variation (CNV) and intratumor heterogeneity (ITH) further discovered the possible immunosurveillance escape, the discrepancy between mutation and CNV level, ITH, and the pervasive DNA damage response and WNT pathway gene alternations in the MIP component. Phylogenetic analysis of five pairs of LEP and MIP components further confirmed the presence of ancestral EGFR mutations. Through comprehensive analyses combining our samples and public cohorts, PTP4A3, NAPRT, and RECQL4 were identified to be co-amplified. Multi-omics data also demonstrated the immunosuppression prevalence in the MIP component. Our results uncovered the evolutionary pattern of the concomitant LEP and MIP components from the same patient that they were derived from the same initiation cells and the pathway-specific mutations acquired after EGFR clonal mutation could shape the subtype-specificity. We also confirmed the immunosuppression prevalence in the MIP subtype by multi-omics data analyses, which may have resulted in its unfavorable prognosis.

Purpose: This study aimed to develop a prognostic indicator based on epithelial-mesenchymal transition (EMT)-related long noncoding RNAs (lncRNAs) and explore the function of EMT-related lncRNAs in malignant progression in lung adenocarcinoma (LUAD).Materials and methods: A LUAD dataset was acquired from The Cancer Genome Atlas (TCGA) to identify prognostic EMT-related lncRNAs via differential expression analysis and univariate Cox regression analysis. Least Absolute Shrinkage and Selection Operator (LASSO) Cox regression analysis was utilized for variable selection and model construction. The EMT-related prognostic index (ERPI) was calculated according to the model and served as a classifier to divide LUAD individuals into high-ERPI and low-ERPI groups. A nomogram incorporating ERPI and clinicopathological variables was constructed. TCGA-LUAD, GSE50081, and GSE31210 were used to test the predictive capacity of the ERPI and nomogram. The characteristics of the tumor microenvironment (TME) were evaluated via the ESTIMATE, TIMER, and ssGSEA algorithms. Gene set variation analysis (GSVA) and ssGSEA were used to annotate the functions of the high-ERPI and low-ERPI groups. CCK8, transwell assay, wound-healing assay, and clone formation assay were conducted to clarify the biological functions of prognostic EMT-related lncRNAs.Results: Ninety-seven differentially expressed EMT-related lncRNAs were identified, 15 of which were related to overall survival (OS). A prognostic signature was constructed based on 14 prognostic EMT-related lncRNAs to calculate the ERPI of each patient, and the predictive ability of ERPI was verified in TCGA, GSE50081, and GSE31210. The low-ERPI group survived longer and had a lower percentage of patients in advanced stage than the high-ERPI group. The nomogram had the highest predictive accuracy, followed by ERPI and stage. Patients with low ERPI had higher infiltration degree of immune cells and stronger immune responses than those with high ERPI. A series of in vitro experiments demonstrated that knockdown of LINC01138 dampened variability, proliferation, and motility of A549 and H460 cells.Conclusion: Our study developed a prognostic classifier with robust prognostic performance and clarified the biological functions of LINC01138 in LUAD, aiding in making individual treatments for patients with LUAD and dissecting the mechanism of oncogenesis.

PurposeIn clinical work, accurately measuring the volume and the size of breast cancer is significant to develop a treatment plan. However, it is time-consuming, and inter- and intra-observer variations among radiologists exist. The purpose of this study was to assess the performance of a Res-UNet convolutional neural network based on automatic segmentation for size and volumetric measurement of mass enhancement breast cancer on magnetic resonance imaging (MRI).Materials and methodsA total of 1,000 female breast cancer patients who underwent preoperative 1.5-T dynamic contrast-enhanced MRI prior to treatment were selected from January 2015 to October 2021 and randomly divided into a training cohort (n = 800) and a testing cohort (n = 200). Compared with the masks named ground truth delineated manually by radiologists, the model performance on segmentation was evaluated with dice similarity coefficient (DSC) and intraclass correlation coefficient (ICC). The performance of tumor (T) stage classification was evaluated with accuracy, sensitivity, and specificity.ResultsIn the test cohort, the DSC of automatic segmentation reached 0.89. Excellent concordance (ICC > 0.95) of the maximal and minimal diameter and good concordance (ICC > 0.80) of volumetric measurement were shown between the model and the radiologists. The trained model took approximately 10–15 s to provide automatic segmentation and classified the T stage with an overall accuracy of 0.93, sensitivity of 0.94, 0.94, and 0.75, and specificity of 0.95, 0.92, and 0.99, respectively, in T1, T2, and T3.ConclusionsOur model demonstrated good performance and reliability for automatic segmentation for size and volumetric measurement of breast cancer, which can be time-saving and effective in clinical decision-making.