BackgroundChest radiograph interpretation is critical for the detection of thoracic diseases, including tuberculosis and lung cancer, which affect millions of people worldwide each year. This time-consuming task typically requires expert radiologists to read the images, leading to fatigue-based diagnostic error and lack of diagnostic expertise in areas of the world where radiologists are not available. Recently, deep learning approaches have been able to achieve expert-level performance in medical image interpretation tasks, powered by large network architectures and fueled by the emergence of large labeled datasets. The purpose of this study is to investigate the performance of a deep learning algorithm on the detection of pathologies in chest radiographs compared with practicing radiologists.Methods and findingsWe developed CheXNeXt, a convolutional neural network to concurrently detect the presence of 14 different pathologies, including pneumonia, pleural effusion, pulmonary masses, and nodules in frontal-view chest radiographs. CheXNeXt was trained and internally validated on the ChestX-ray8 dataset, with a held-out validation set consisting of 420 images, sampled to contain at least 50 cases of each of the original pathology labels. On this validation set, the majority vote of a panel of 3 board-certified cardiothoracic specialist radiologists served as reference standard. We compared CheXNeXt’s discriminative performance on the validation set to the performance of 9 radiologists using the area under the receiver operating characteristic curve (AUC). The radiologists included 6 board-certified radiologists (average experience 12 years, range 4–28 years) and 3 senior radiology residents, from 3 academic institutions. We found that CheXNeXt achieved radiologist-level performance on 11 pathologies and did not achieve radiologist-level performance on 3 pathologies. The radiologists achieved statistically significantly higher AUC performance on cardiomegaly, emphysema, and hiatal hernia, with AUCs of 0.888 (95% confidence interval [CI] 0.863–0.910), 0.911 (95% CI 0.866–0.947), and 0.985 (95% CI 0.974–0.991), respectively, whereas CheXNeXt’s AUCs were 0.831 (95% CI 0.790–0.870), 0.704 (95% CI 0.567–0.833), and 0.851 (95% CI 0.785–0.909), respectively. CheXNeXt performed better than radiologists in detecting atelectasis, with an AUC of 0.862 (95% CI 0.825–0.895), statistically significantly higher than radiologists' AUC of 0.808 (95% CI 0.777–0.838); there were no statistically significant differences in AUCs for the other 10 pathologies. The average time to interpret the 420 images in the validation set was substantially longer for the radiologists (240 minutes) than for CheXNeXt (1.5 minutes). The main limitations of our study are that neither CheXNeXt nor the radiologists were permitted to use patient history or review prior examinations and that evaluation was limited to a dataset from a single institution.ConclusionsIn this study, we developed and validated a deep learning algorithm that classified clinically ...
Background/Aims: In this study, a subpopulation of stem-like cells in human high grade serous ovarian carcinomas (ovarian cancer stem cells; OCSCs) were isolated and characterized. Methods: Primary high-grade serous ovarian carcinoma (HGSC) fresh biopsies were cultured under serum-free conditions to produce floating spheres. Sphere formation assay, including self-renewal, differentiation potential, chemo-resistance, and tumorigenicity were determined in vitro or in vivo. Results: OCSCs overexpressed stem cell genes (Oct-4, Nanog, Sox-2, Bmi-1, Nestin, CD133, CD44, CD24, ALDH1, CD117, and ABCG2). Immunostaining of spheres showed overexpressed Oct-4, Nanog, and Sox-2. These isolated tumor cells expanded as spheroid colonies for more than 30 passages. In contrast, adherent cells expressed high levels of CA125 and CK7. Flow cytometry analysis showed increased CSC markers (CD44, CD24, CD117, CD133, ABCG2, and ALDH1) in the spheroid cell population. OCSCs displayed higher chemoresistance to cisplatin or paclitaxel compared to adherent cells. Moreover, subcutaneous injection of 1 × 104 sphere-forming cells into NOD/SCID mice gave rise to new tumors similar to the original human tumors and could be passaged in mice. Conclusion: These results revealed that HGSCs are created and propagated by a small number of undifferentiated tumorigenic cells, and therapeutic targeting of these cells could be beneficial for treatment of HGSCs.
Background The effect of isolated maternal hypothyroxinaemia (IMH) on pregnancy complications and neonatal outcomes in human beings is still controversial. Methods This was a retrospective cohort study based on the electronic medical register system. The records of women with a singleton pregnancy who sought antenatal examination between January 2014 and December 2015 at Shanghai First Maternity and Infant Hospital were extracted from the electronic medical records system. Thyroid-stimulating hormone (TSH), free thyroxine (fT4) and anti-thyroperoxidase autoantibody (TPO-Ab) was measured before 20 gestational weeks, and a multiple logistic regression model was used to estimate the odds ratios of pregnancy complications and neonatal outcomes between euthyroid women and those with isolated hypothyroxinaemia. Results A total of 8173 women were included in this study, of whom 342 (4.18%) were diagnosed with IMH. Regression analysis showed that IMH diagnosed in the second trimester (13–20 weeks) was associated with an increased risk of hypertensive disorders of pregnancy (OR = 2.66, 95% CI: 1.38–5.10) and placenta abruption (OR = 3.64, 95% CI: 1.07–12.41), but not with preterm delivery (OR = 1.09, 95% CI: 0.50–2.40), small or large gestational age of infant (OR = 0.91, 95% CI: 0.39–2.12; OR = 1.16, 95% CI: 0.72–1.86), macrosomia (OR = 1.71, 95% CI: 0.95–3.07), gestational diabetes mellitus (OR = 1.36, 95% CI: 0.86–2.15) and placenta previa (OR = 1.62, 95% CI: 0.39–7.37). Conclusion IMH could be a risk factor for hypertensive disorders of pregnancy.
Background-The absolute risk reduction (ARR) in cardiovascular events from therapy is generally assumed to be proportional to baseline risk-such that high-risk patients benefit most. Yet newer analyses have proposed using randomized trial data to develop models that estimate individual treatment effects. We tested two hypotheses: first, that models of individual treatment effects could reveal that patients may most benefit from intensive blood pressure therapy that are proportional to baseline risk; and second, that a machine learning approach designed to predict heterogeneous treatment effects-the X-learner meta-algorithm-is equivalent to a conventional logistic regression approach. Methods and Results-We compared conventional logistic regression to the X-learner approach for prediction of 3-year CVD event risk reduction from intensive (target systolic blood pressure <120 mmHg) versus standard (target <140 mmHg) blood pressure treatment, using individual participant data from the SPRINT (N=9361) and ACCORD-BP (N=4733) trials. Each model incorporated 17 covariates, an indicator for treatment arm, and interaction terms between covariates and treatment. Logistic regression had lower C-statistic for benefit than the X-learner (0.51 [95% CI: 0.49, 0.53] versus 0.60 [95% CI: 0.58, 0.63], respectively). Following the logistic regression's recommendation for individualized therapy produced restricted mean time until CVD event of 1065.47 days [95% CI: 1061.04, 1069.35], while following the X-learner's recommendation improved mean time until CVD event to 1068.71 days [95% CI: 1065.42, 1072.08]. Calibration was worse for logistic regression; it overestimated ARR attributable to intensive treatment (slope between predicted and observed ARR of 0.73 [95% CI: 0.30, 1.14], versus 1.06 [95% CI: 0.74, 1.32] for the X-learner, compared to the ideal of 1). Predicted ARRs using Cox were generally proportional to baseline pre-treatment cardiovascular risk, whereas the
SummaryWnt pathways play an important role in pre-implantation embryo development, blastocyst implantation, and post-implantation uterine decidualisation. However, little is known about the potential role that Wnt signaling plays in patients with unexplained recurrent spontaneous miscarriage (URSM), and no single biomarker with a high predictive value of maternally caused URSM has been identified. We aim to study the molecular mechanisms by which the Wnt pathway controls the progression of early pregnancy by investigating the expression of Dickkopf-1 (DKK1), one of the Wnt agonists, in URSM patients. Plasma and fresh decidual tissues samples were collected from 59 subjects (29 patients with URSM and 30 patients with normal, early pregnancy). Time-resolved immunofluorometric assay system and quantitative real-time RT-PCR were used to determine the serum levels of DKK1 and DKK1 mRNA in the deciduas, respectively. Western blot and immunohistochemistry were used to measure DKK1 protein levels in the deciduas. Serum DKK1 levels were significantly higher in URSM patients compared to the control group (P < 0·001); the expression of DKK1 mRNA and protein in URSM patients were higher relative to healthy controls (P = 0·013). Glandular epithelium from decidual tissues demonstrated cytoplasmic signals for DKK1 in URSM patients, and DKK1 did not stain in healthy controls. Furthermore, serum DKK1 levels significantly correlated with those in the decidual tissues. Our study suggests that DKK1 may be a valuable biomarker of URSM; it can be reliably and conveniently detected in serum, thus obviating the need for decidual tissue analysis.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.
hi@scite.ai
10624 S. Eastern Ave., Ste. A-614
Henderson, NV 89052, USA
Copyright © 2024 scite LLC. All rights reserved.
Made with 💙 for researchers
Part of the Research Solutions Family.