New ultrasound features in diagnosing fetal anal atresia: a multicenter prospective cohort study.

This research aimed to assess the validity of ultrasound scans with new features in detecting fetal anal atresia and verify the effectiveness of these new features. Additionally, we aimed at investigating the perinatal incidence of anal atresia. This multicenter prospective study recruited 94,617 normal gravidas and 84 gravidas with anal atresia fetuses. The gold standard for diagnosing perinatal anal atresia is routine neonatal anus examinations. The incidence calculation was based on the results of the gold standard. The validity of our new approach was evaluated via a diagnostic test involving all 94,701 subjects. The effectiveness of our new features was assessed through an ablation study in a randomly established new dataset, with the ratio of anal atresia to non-anal atresia cases of 1:4. The annual perinatal incidence of anal atresia between 2019 and 2023 ranges from 0.57‰ to 1.29‰. Our new method performed great regarding the Youden index, diagnostic odds ratio (DOR), area under the curve (AUC) of the receiver operating characteristic curve (ROCC), AUC of the precision-recall curve (PRC), F1-score, and Cramer's V. In the ablation study, our new approach surpassed its competitors concerning Youden index, DOR, AUC of the ROCC, and AUC of the PRC. Ultrasound scans show high validity and clinical value in detecting fetal anal atresia. Our new ultrasound features significantly promote the detection of fetal anal atresia.

High-level feature-guided attention optimized neural network for neonatal lateral ventricular dilatation prediction.

BACKGROUND: Periventricular-intraventricular hemorrhage can lead to posthemorrhagic ventricular dilatation or even posthemorrhagic hydrocephalus if not detected promptly. Sequential cranial ultrasound scans are typically used for their diagnoses. Nonetheless, manual image audit has numerous disadvantages. PURPOSE: This study aimed to develop a predictive model utilizing modified inception (MI) and high-level feature-guided attention (HFA) modules for predicting neonatal lateral ventricular dilation via ultrasound images. METHODS: The MI modules reduced input data sizes and dimensions, while the HFA modules effectively delved into semantic information through supervision from high-level feature images to low-level feature images. The process facilitated the accurate identification of dilated lateral ventricles. A total of 710 neonates, corresponding to 1420 lateral ventricles, were recruited in this study. Each lateral ventricle was captured in two images, one on the parasagittal plane and the other on the coronal plane. The combination of anterior horn width, ventricular index, thalamo-occipital distance, and ventricular height served as the gold standard. A lateral ventricle would be considered dilatated if any of these four indices exceeded its upper reference value. These lateral ventricles were randomly split into training and testing sets at a 7:3 ratio. We evaluated the validity of our proposed approach and its competitors across the coronal plane, parasagittal plane, and overall performance. We also determined the impact of subjects' baseline characteristics on the overall performance of the proposed approach. Additionally, ablation analyses were conducted to ensure the efficacy of the proposed approach. RESULTS: Our proposed approach achieved the largest Youden index (0.65, 95% CI: 0.58-0.72), DOR (27.11, 95% CI: 15.89-46.26), area under curves (AUC) of receiver operating characteristic curve (ROC) (0.84, 95% CI: 0.80-0.88), and AUC of precision-recall curve (PRC) (0.81, 95% CI: 0.74-0.86) in the overall performance assessment and ablation analyses. Moreover, it boasted the biggest Cramer's V values on the coronal (Cramer's V = 0.488, p < 0.001) and parasagittal (Cramer's V = 0.713, p < 0.001) planes individually. Factors such as left side, male sex, singleton birth, and vaginal delivery were positively correlated with higher performance regarding the proposed algorithm, except for the gestational age. CONCLUSION: This work provides a novel attention optimized algorithm for rapid and accurate ventricular dilatation predictions. It surpasses the traditional algorithms in terms of validity whether concerning the coronal plane, parasagittal plane, or overall performance. The overall performance of algorithms will be influenced by the baseline characteristics of populations.

Unlocking the potential: T1-weighed MRI as a powerful predictor of levodopa response in Parkinson's disease.

BACKGROUND: The efficacy of levodopa, the most crucial metric for Parkinson's disease diagnosis and treatment, is traditionally gauged through the levodopa challenge test, which lacks a predictive model. This study aims to probe the predictive power of T1-weighted MRI, the most accessible modality for levodopa response. METHODS: This retrospective study used two datasets: from the Parkinson's Progression Markers Initiative (219 records) and the external clinical dataset from Ruijin Hospital (217 records). A novel feature extraction method using MedicalNet, a pre-trained deep learning network, along with three previous approaches was applied. Three machine learning models were trained and tested on the PPMI dataset and included clinical features, imaging features, and their union set, using the area under the curve (AUC) as the metric. The most significant brain regions were visualized. The external clinical dataset was further evaluated using trained models. A paired one-tailed t-test was performed between the two sets; statistical significance was set at p < 0.001. RESULTS: For 46 test set records (mean age, 62 ± 9 years, 28 men), MedicalNet-extracted features demonstrated a consistent improvement in all three machine learning models (SVM 0.83 ± 0.01 versus 0.73 ± 0.01, XgBoost 0.80 ± 0.04 versus 0.74 ± 0.02, MLP 0.80 ± 0.03 versus 0.70 ± 0.07, p < 0.001). Both feature sets were validated on the clinical dataset using SVM, where MedicalNet features alone achieved an AUC of 0.64 ± 0.03. Key responsible brain regions were visualized. CONCLUSION: The T1-weighed MRI features were more robust and generalizable than the clinical features in prediction; their combination provided the best results. T1-weighed MRI provided insights on specific regions responsible for levodopa response prediction. CRITICAL RELEVANCE STATEMENT: This study demonstrated that T1w MRI features extracted by a deep learning model have the potential to predict the levodopa response of PD patients and are more robust than widely used clinical information, which might help in determining treatment strategy. KEY POINTS: This study investigated the predictive value of T1w features for levodopa response. MedicalNet extractor outperformed all other previously published methods with key region visualization. T1w features are more effective than clinical information in levodopa response prediction.

A Rad50-null mutation in mouse germ cells causes reduced DSB formation, abnormal DSB end resection and complete loss of germ cells.

The conserved MRE11-RAD50-NBS1/Xrs2 complex is crucial for DNA break metabolism and genome maintenance. Although hypomorphic Rad50 mutation mice showed normal meiosis, both null and hypomorphic rad50 mutation yeast displayed impaired meiosis recombination. However, the in vivo function of Rad50 in mammalian germ cells, particularly its in vivo role in the resection of meiotic double strand break (DSB) ends at the molecular level remains elusive. Here, we have established germ cell-specific Rad50 knockout mouse models to determine the role of Rad50 in mitosis and meiosis of mammalian germ cells. We find that Rad50-deficient spermatocytes exhibit defective meiotic recombination and abnormal synapsis. Mechanistically, using END-seq, we demonstrate reduced DSB formation and abnormal DSB end resection occurs in mutant spermatocytes. We further identify that deletion of Rad50 in gonocytes leads to complete loss of spermatogonial stem cells due to genotoxic stress. Taken together, our results reveal the essential role of Rad50 in mammalian germ cell meiosis and mitosis, and provide in vivo views of RAD50 function in meiotic DSB formation and end resection at the molecular level.

Automatic measurement of fetal anterior neck lower jaw angle in nuchal translucency scans.

This study aims at suggesting an end-to-end algorithm based on a U-net-optimized generative adversarial network to predict anterior neck lower jaw angles (ANLJA), which are employed to define fetal head posture (FHP) during nuchal translucency (NT) measurement. We prospectively collected 720 FHP images (half hyperextension and half normal posture) and regarded manual measurement as the gold standard. Seventy percent of the FHP images (half hyperextension and half normal posture) were used to fit models, and the rest to evaluate them in the hyperextension group, normal posture group (NPG), and total group. The root mean square error, explained variation, and mean absolute percentage error (MAPE) were utilized for the validity assessment; the two-sample t test, Mann-Whitney U test, Wilcoxon signed-rank test, Bland-Altman plot, and intraclass correlation coefficient (ICC) for the reliability evaluation. Our suggested algorithm outperformed all the competitors in all groups and indices regarding validity, except for the MAPE, where the Inception-v3 surpassed ours in the NPG. The two-sample t test and Mann-Whitney U test indicated no significant difference between the suggested method and the gold standard in group-level comparison. The Wilcoxon signed-rank test revealed significant differences between our new approach and the gold standard in personal-level comparison. All points in Bland-Altman plots fell between the upper and lower limits of agreement. The inter-ICCs of ultrasonographers, our proposed algorithm, and its opponents were graded good reliability, good or moderate reliability, and moderate or poor reliability, respectively. Our proposed approach surpasses the competition and is as reliable as manual measurement.

An explainable unsupervised risk early warning framework based on the empirical cumulative distribution function: Application to dairy safety.

Efficient food safety risk assessment significantly affects food safety supervision. However, food detection data of different types and batches show different feature distributions, resulting in unstable detection results of most risk assessment models, lack of interpretability of risk classification, and insufficient risk traceability. This study aims to explore an efficient food safety risk assessment model that takes into account robustness, interpretability and traceability. Therefore, the Explainable unsupervised risk Warning Framework based on the Empirical cumulative Distribution function (EWFED) was proposed. Firstly, the detection data's underlying distribution is estimated as non-parametric by calculating each testing indicator's empirical cumulative distribution. Next, the tail probabilities of each testing indicator are estimated based on these distributions and summarized to obtain the sample risk value. Finally, the "3σ Rule" is used to achieve explainable risk classification of qualified samples, and the reasons for unqualified samples are tracked according to the risk score of each testing indicator. The experiments of the EWFED model on two types of dairy product detection data in actual application scenarios have verified its effectiveness, achieving interpretable risk division and risk tracing of unqualified samples. Therefore, this study provides a more robust and systematic food safety risk assessment method to promote precise management and control of food safety risks effectively.

Evaluation of the changes in cardiac morphology of fetuses with congenital heart disease using fetalHQ.

Objective: To evaluate the changes in cardiac morphology of fetuses with congenital heart disease (CHD) using the fetal heart quantitative technique (fetalHQ).Methods: A total of 20 normal pregnant women (control group) and 20 pregnant women suspected of fetal CHD (case group) were included in this study. The dynamic images of the four-chamber view of the fetal heart were recorded and analyzed using fetalHQ. The global sphericity index (GSI) and 24-segment SI of the two groups were compared. The differences in the left and right ventricular 24-segment SI for each group were investigated.Results: There was no statistically significant difference in the GSI between the two groups (p > 0.05). The difference in the SI values of left ventricular segments 1-2 between the case group and control group was statistically significant (all p < 0.05), while the intergroup difference in SI of left ventricular segments 3-24 was not significant (all p > 0.05). The SI of the 24 segments of the right ventricle showed no significant intergroup difference (all p > 0.05). The difference in the left and right ventricular 24-segment SI in the case group did not reach statistical significance (all p > 0.05). In the control group, the SI values between the left and right ventricles were significantly different in segments 18-24 (all p < 0.05), and no significant difference was found in segments 1-17 (all p > 0.05). There was a statistically significant intergroup difference in the percentage of unusual left ventricular SI, determined based on Z-score (p < 0.05), and the percentage of outliers for the right ventricle between the two groups showed no significant difference (p > 0.05).Conclusion: The fetalHQ is regarded as a straightforward and reliable approach for assessing the cardiac GSI and 24-segment SI of left and right ventricles in fetuses diagnosed with CHD. While CHD may not significantly impact the overall shape of the fetal heart or the geometric shape of the right ventricle, in this study, a notable increase in SI values for the left ventricular 1-2 segments was observed, indicating a more flattened ventricular chamber. Additionally, the morphological distinctions between the left and right ventricles in fetuses with CHD are no longer discernible.

CSGNN: Contamination Warning and Control of Food Quality via Contrastive Self-Supervised Learning-Based Graph Neural Network.

Effective contamination warning and control of food quality can significantly reduce the likelihood of food quality safety incidents. Existing food contamination warning models for food quality rely on supervised learning, do not model the complex feature associations between detection samples, and do not consider the unevenness of detection data categories. In this paper, To overcome these limitations, we propose a Contrastive Self-supervised learning-based Graph Neural Network framework (CSGNN) for contamination warning of food quality. Specifically, we structure the graph for detecting correlations between samples and then define the positive and negative instance pairs for contrastive learning based on attribute networks. Further, we use a self-supervised approach to capture the complex relationships between detection samples. Finally, we assessed each sample's contamination level based on the absolute value of the subtraction of the prediction scores from multiple rounds of positive and negative instances obtained by the CSGNN. Moreover, we conducted a sample study on a batch of dairy product detection data in a Chinese province. The experimental results show that CSGNN outperforms other baseline models in contamination assessment of food quality, with AUC and recall of unqualified samples reaching 0.9188 and 1.0000, respectively. Meanwhile, our framework provides interpretable contamination classification for food detection. This study provides an efficient early warning method with precise and hierarchical contamination classification for contamination warning of food quality work.

Serum Raman spectroscopy combined with convolutional neural network for rapid diagnosis of HER2-positive and triple-negative breast cancer.

Breast cancer is common in women, and its number of patients ranks first among female malignant tumors. Breast cancer is highly heterogeneous, and different types of breast cancer have different biological behaviors and prognoses. Therefore, identifying the different types of breast cancer is of great help in formulating individualized treatment plans. Based on serum Raman spectroscopy and deep learning algorithms, we propose a fast and low-cost diagnosis method for screening triple-negative breast cancer, human epidermal growth factor receptor 2 (HER2)-positive breast cancer, and healthy controls. We collected 75 serum samples in this study, including 23 triple-negative breast cancers, 22 HER2-positive breast cancers, and 30 healthy controls. Using the preprocessed Raman spectra as the input of deep learning, three deep learning models, neural network language model (NNLM), bidirectional long-short-term memory network (BiLSTM), and convolutional neural network (CNN), were established, and the accuracy rates of the three models were 87.78%, 90.37%, and 91.11%, respectively. The experimental results demonstrate the feasibility of serum Raman spectroscopy combined with deep learning algorithms to diagnose breast cancer, which can be used as an effective auxiliary diagnosis method for breast cancer.

Rapidly detecting fennel origin of the near-infrared spectroscopy based on extreme learning machine.

Fennel contains many antioxidant and antibacterial substances, and it has very important applications in food flavoring and other fields. The kinds and contents of chemical substances in fennel vary from region to region, which can affect the taste and efficacy of the fennel and its derivatives. Therefore, it is of great significance to accurately classify the origin of the fennel. Recently, origin detection methods based on deep networks have shown promising results. However, the existing methods spend a relatively large time cost, a drawback that is fatal for large amounts of data in practical application scenarios. To overcome this limitation, we explore an origin detection method that guarantees faster detection with classification accuracy. This research is the first to use the machine learning algorithm combined with the Fourier transform-near infrared (FT-NIR) spectroscopy to realize the classification and identification of the origin of the fennel. In this experiment, we used Rubberband baseline correction on the FT-NIR spectral data of fennel (Yumen, Gansu and Turpan, Xinjiang), using principal component analysis (PCA) for data dimensionality reduction, and selecting extreme learning machine (ELM), Convolutional Neural Network (CNN), recurrent neural network (RNN), Transformer, generative adversarial networks (GAN) and back propagation neural network (BPNN) classification model of the company realizes the classification of the sample origin. The experimental results show that the classification accuracy of ELM, RNN, Transformer, GAN and BPNN models are above 96%, and the ELM model using the hardlim as the activation function has the best classification effect, with an average accuracy of 100% and a fast classification speed. The average time of 30 experiments is 0.05 s. This research shows the potential of the machine learning algorithm combined with the FT-NIR spectra in the field of food production area classification, and provides an effective means for realizing rapid detection of the food production area, so as to merchants from selling shoddy products as good ones and seeking illegal profits.

Tunable delay line based on balanced coupled resonators cladded with VO2 films.

A delay line consisting of a balanced side-coupled integrated spaced sequence of resonators and phase change material VO2 films is employed to realize continuously tunable delays with ultrafast response and low distortion. Simulation results show that a tunable delay of up to 80 ps with a 10% broadening, 150 GHz bandwidth, and 0.087 dB/ps delay loss is achieved from this structure. Taking advantage of photoinduced phase transition of VO2 films, this device obtains a switching time of less than 0.6 ps and effective compensation for group delay dispersion. This delay line shows advantages in the high-bit-rate all-optical processing systems.

Effect of the mitochondrial unfolded protein response on hypoxic death and mitochondrial protein aggregation.

Mitochondria are the main oxygen consumers in cells and as such are the primary organelle affected by hypoxia. All hypoxia pathology presumably derives from the initial mitochondrial dysfunction. An early event in hypoxic pathology in C. elegans is disruption of mitochondrial proteostasis with induction of the mitochondrial unfolded protein response (UPRmt) and mitochondrial protein aggregation. Here in C. elegans, we screen through RNAis and mutants that confer either strong resistance to hypoxic cell death or strong induction of the UPRmt to determine the relationship between hypoxic cell death, UPRmt activation, and hypoxia-induced mitochondrial protein aggregation (HIMPA). We find that resistance to hypoxic cell death invariantly mitigated HIMPA. We also find that UPRmt activation invariantly mitigated HIMPA. However, UPRmt activation was neither necessary nor sufficient for resistance to hypoxic death and vice versa. We conclude that UPRmt is not necessarily hypoxia protective against cell death but does protect from mitochondrial protein aggregation, one of the early hypoxic pathologies in C. elegans.

Expression of autophagy and apoptosis-related factors in the periodontal tissue of experimental diabetic rats: a histomorphometric, microtomographic and immunohistochemical study.

OBJECTIVE: This study aimed to investigate the expression of autophagy-related factors microtubule-associated protein l light chain 3 (LC3) and the apoptosis-related factors BCL2-associated X protein (Bax) and B cell lymphoma-2 (Bcl-2) in the periodontal tissue of experimental diabetic rats. These data were used to explore the potential mechanism in diabetes-induced periodontal tissue lesions. METHODS: A total of 32 Sprague Dawley (SD) rats were randomly assigned into diabetes (group D, n = 16) and control groups (group N, n = 16). The diabetic group was induced by intraperitoneal injection of 1% streptozotocin (STZ, 60 mg/kg) and the control group was injected with citrate buffer (0.1mol/L). Rats were sacrificed after 4 and 8 weeks of feeding and collected as D1, N1 groups and D2, N2 groups, and the maxilla were retained for analysis. The changes in periodontal tissue structure were observed by hematoxylin-eosin (HE) staining. The expression and distribution of LC3, Bax and Bcl-2 in the periodontium of the rats was detected by immunohistochemical (SP) staining. RESULTS: Diabetic rats showed several changes compared to control animals including sparse alveolar bone trabecular structure, loss of the lamina dura and absorption of the local alveolar bone. The positive expression level of LC3 in the gingival epithelial, periodontal ligament and alveolar bone of group D1 was significantly higher than in the N1, N2 and D2 groups (P < 0.05). The level of Bax expression in the group D2 rats was significantly higher than those in the N1, N2 and D1 groups (P < 0.05), while the positive degree of Bcl-2 was significantly lower than those of other groups (P < 0.001). LC3 was negatively correlated with Bax and was irrelevant with Bcl-2; Bcl-2 was not correlated with Bax. CONCLUSIONS: The expression of LC3, Bax and Bcl-2 changes in the periodontal tissue of diabetic rats may indicate that autophagy and apoptotic are involved in the process of periodontal tissue damage in diabetic rats. These changes may be one of the mechanisms of periodontal tissue lesions.

The regulatory role of smooth muscle 22 on the proliferation of aortic smooth muscle cells participates in the development of aortic dissection.

OBJECTIVE: The aim of this study was to determine the role of smooth muscle 22 (SM22) in aortic dissection (AD) vascular remodeling and its regulatory mechanism on vascular smooth muscle cell function. METHODS: Seven patients who underwent surgery for AD with no genetic predisposition and seven organ donors who died from nonvascular diseases were selected. In each aorta sample, the levels of SM22 were detected using immunohistochemistry and Western blot analysis. We inhibited the expression of SM22 with the application of RNA interference in human aortic smooth muscle cells (HASMCs). Cell-counting Kit-8 (Dojindo, Kumamoto, Japan) analyses were used to detect HASMC proliferation. Furthermore, the intracellular calcium concentration was detected using Rhod-2/AM (Dojindo) staining. RESULTS: SM22 was significantly downregulated in the media of AD samples compared with controls (P < .05). In an in vitro study, downregulation of SM22 can significantly promote HASMC proliferation. Our research further revealed that cells treated with nifedipine can inhibit the promoter activity of SM22 downregulation on HASMC proliferation. Intracellular calcium concentration was a significantly varied during the process. CONCLUSIONS: SM22 regulates HASMC function activity through intracellular calcium. It presents a downregulation in AD, which might play a potential role in vascular remodeling of AD.