Development and Validation of a Diagnostic Model for Identifying Clear Cell Renal Cell Carcinoma in Small Renal Masses Based on CT Radiological Features: A Multicenter Study.

RATIONALE AND OBJECTIVES: This study aimed to develop a diagnostic model based on clinical and CT features for identifying clear cell renal cell carcinoma (ccRCC) in small renal masses (SRMs). MATERIAL AND METHODS: This retrospective multi-centre study enroled patients with pathologically confirmed SRMs. Data from three centres were used as training set (n = 229), with data from one centre serving as an independent test set (n = 81). Univariate and multivariate logistic regression analyses were utilised to screen independent risk factors for ccRCC and build the classification and regression tree (CART) diagnostic model. The area under the curve (AUC) was used to evaluate the performance of the model. To demonstrate the clinical utility of the model, three radiologists were asked to diagnose the SRMs in the test set based on professional experience and re-evaluated with the aid of the CART model. RESULTS: There were 310 SRMs in 309 patients and 71% (220/310) were ccRCC. In the testing cohort, the AUC of the CART model was 0.90 (95% CI: 0.81, 0.97). For the radiologists' assessment, the AUC of the three radiologists based on the clinical experience were 0.78 (95% CI:0.66,0.89), 0.65 (95% CI:0.53,0.76), and 0.68 (95% CI:0.57,0.79). With the CART model support, the AUC of the three radiologists were 0.93 (95% CI:0.86,0.97), 0.87 (95% CI:0.78,0.95) and 0.87 (95% CI:0.78,0.95). Interobserver agreement was improved with the CART model aids (0.323 vs 0.654, P < 0.001). CONCLUSION: The CART model can identify ccRCC with better diagnostic efficacy than that of experienced radiologists and improve diagnostic performance, potentially reducing the number of unnecessary biopsies.

Synergistic effect of dual phase cocatalysts: MoC-Mo2C quantum dots anchored on g-C3N4 for high-stability photocatalytic hydrogen evolution.

The extensive examination of hexagonal molybdenum carbide (ß-Mo2C) as a non-noble cocatalyst in the realm of photocatalytic H2 evolution is predominantly motivated by its exceptional capacity to adsorb H+ ions akin to Pt and its advantageous conductivity characteristics. However, the H2 evolution rate of photocatalysts modified with ß-Mo2C is limited as a result of their comparatively low ability to release H through desorption. Therefore, a facile method was employed to synthesize carbon intercalated dual phase molybdenum carbide (MC@C) quantum dots (ca. 3.13 nm) containing both α-MoC and ß-Mo2C decorated on g-C3N4 (gCN). The synthesis process involved a simple and efficient combination of sonication-assisted self-assembly and calcination techniques. 3-MC@C/gCN exhibited the highest efficiency in generating H2, with a rate of 4078 µmol g-1h-1 under 4 h simulated sunlight irradiation, which is 13 times higher than pristine gCN. Furthermore, from the cycle test, 3-MC@C/gCN showcased exceptional photochemical stability of 65 h, as it maintained a H2 evolution rate of 40 mmol g-1h-1. The heightened level of activity observed in the 3-MC@C/gCN system can be ascribed to the synergistic effects of MoC-Mo2C that arise due to the existence of a carbon layer. The presence of a carbon layer enhanced the transmission of photoinduced electrons, while the MoC-Mo2C@C composite served as active sites, thereby facilitating the H2 production reaction of gCN. The present study introduces a potentially paradigm-shifting concept pertaining to the exploration of novel Mo-based cocatalysts with the aim of augmenting the efficacy of photocatalytic H2 production.

Virtual Classification: Modulating Domain-Specific Knowledge for Multidomain Crowd Counting.

Multidomain crowd counting aims to learn a general model for multiple diverse datasets. However, deep networks prefer modeling distributions of the dominant domains instead of all domains, which is known as domain bias. In this study, we propose a simple-yet-effective modulating domain-specific knowledge network (MDKNet) to handle the domain bias issue in multidomain crowd counting. MDKNet is achieved by employing the idea of "modulating", enabling deep network balancing and modeling different distributions of diverse datasets with little bias. Specifically, we propose an instance-specific batch normalization (IsBN) module, which serves as a base modulator to refine the information flow to be adaptive to domain distributions. To precisely modulating the domain-specific information, the domain-guided virtual classifier (DVC) is then introduced to learn a domain-separable latent space. This space is employed as an input guidance for the IsBN modulator, such that the mixture distributions of multiple datasets can be well treated. Extensive experiments performed on popular benchmarks, including Shanghai-tech A/B, QNRF, and NWPU validate the superiority of MDKNet in tackling multidomain crowd counting and the effectiveness for multidomain learning. Code is available at https://github.com/csguomy/MDKNet.

Evaluating AI rib fracture detections using follow-up CT scans.

PURPOSE: This study compares the results of Artificial Intelligence (AI) diagnosis of rib fractures using initial CT and follow-up CT as the final diagnostic criteria, and studies AI-assisted diagnosis in improving the detection rate of rib fractures. METHODS: A retrospective study was conducted on 113 patients who underwent initial and follow-up CT scans due to trauma. The initial and follow-up CT were used as diagnostic criteria, respectively. All images were transmitted to the AI software (V2.1.0, Huiying Medical Technology Co., Beijing, China) for rib fracture detection. The radiologist group (Group 1), AI group (Group 2), and Radiologist with AI group (Group 3) reviewed CT images at an interval of one month, recorded and compared the differences in the sensitivity and specificity for diagnosing rib fractures. RESULTS: 589 and 712 rib fractures were diagnosed by the initial and follow-up CT, respectively. The initial CT diagnosis failed to detect 127 rib fractures, resulting in a missed rate of 17.84%. In addition, four normal ribs were mistakenly identified as being fractured. The follow-up CT was regarded as the diagnostic standard for rib fractures. The sensitivity and specificity were 82.16% and 99.80% for Group 1, 79.35% and 84.90% for Group 2, and 91.57% and 99.70% for Group 3. The sensitivity of Group 3 was higher than that of Group 1 and Group 2 (p < 0.05). The specificity was lower for Group 2 compared with Group 1 and Group 3 (p < 0.05). CONCLUSION: AI-assisted diagnosis improved the detection rate of rib fractures, the follow-up CT should be used for the diagnosis standard of rib fractures, and AI misdiagnoses can be greatly reduced when a radiologist reviews the diagnosis.

Artificial Intelligence in Coronary CT Angiography: Current Status and Future Prospects.

Coronary heart disease (CHD) is the leading cause of mortality in the world. Early detection and treatment of CHD are crucial. Currently, coronary CT angiography (CCTA) has been the prior choice for CHD screening and diagnosis, but it cannot meet the clinical needs in terms of examination quality, the accuracy of reporting, and the accuracy of prognosis analysis. In recent years, artificial intelligence (AI) has developed rapidly in the field of medicine; it played a key role in auxiliary diagnosis, disease mechanism analysis, and prognosis assessment, including a series of studies related to CHD. In this article, the application and research status of AI in CCTA were summarized and the prospects of this field were also described.

Confusion-Based Metric Learning for Regularizing Zero-Shot Image Retrieval and Clustering.

Deep metric learning turns to be attractive in zero-shot image retrieval and clustering (ZSRC) task in which a good embedding/metric is requested such that the unseen classes can be distinguished well. Most existing works deem this "good" embedding just to be the discriminative one and race to devise the powerful metric objectives or the hard-sample mining strategies for learning discriminative deep metrics. However, in this article, we first emphasize that the generalization ability is also a core ingredient of this "good" metric and it largely affects the metric performance in zero-shot settings as a matter of fact. Then, we propose the confusion-based metric learning (CML) framework to explicitly optimize a robust metric. It is mainly achieved by introducing two interesting regularization terms, i.e., the energy confusion (EC) and diversity confusion (DC) terms. These terms daringly break away from the traditional deep metric learning idea of designing discriminative objectives and instead seek to "confuse" the learned model. These two confusion terms focus on local and global feature distribution confusions, respectively. We train these confusion terms together with the conventional deep metric objective in an adversarial manner. Although it seems weird to "confuse" the model learning, we show that our CML indeed serves as an efficient regularization framework for deep metric learning and it is applicable to various conventional metric methods. This article empirically and experimentally demonstrates the importance of learning an embedding/metric with good generalization, achieving the state-of-the-art performances on the popular CUB, CARS, Stanford Online Products, and In-Shop datasets for ZSRC tasks.

Classification of Microcalcification Clusters Using Bilateral Features Based on Graph Convolutional Network.

Breast cancer is one of the diseases with the highest incidence and mortality among women in the world, which has posed a serious threat to women's health. The appearance of clustered calcifications is one of the important signs of breast cancer, and thus how to classify clustered calcifications comes to be a key breakthrough in controlling breast cancer. In this study, the discriminant model based on image convolution is used to learn the image features related to the classification of clustered microcalcifications, and the graph convolutional network (GCN) based on topological graph is used to learn the spatial distribution characteristics of clustered microcalcifications. These two models are fused to obtain a complementary model of image information and spatial information. The results show that the performance of the fusion model proposed in this paper is obviously superior to that of the two classification models in the classification of clustered microcalcification.

Enhancing electronic metal support interaction (EMSI) over Pt/TiO2 for efficient catalytic wet air oxidation of phenol in wastewater.

Phenol is one of the major hazardous organic compounds in industrial wastewater. In this work, a highly active Pt/TiO2 catalyst for catalytic wet air oxidation (CWAO) of phenol was obtained by supporting pre-synthesized Pt on TiO2. During the followed hydrogen reduction, strong hydrogen spillover occurred without the migration of TiO2 onto Pt. The reduced support then enhanced the electron transfer from TiO2 to Pt, increasing the percentage of partially negative Pt (Ptδ-), which has been confirmed by XPS. The strong EMSI made the obtained catalyst far more active than Pt/TiO2 prepared by impregnation method. The electron-enriched Pt/TiO2 achieved total organic carbon (TOC) conversion of 88.8% and TOF 149 h-1 at 100 °C and 2 MPa O2, while conventional Pt/TiO2 gave TOC conversion of 39.5% and TOF 41 h-1 for CWAO of phenol. Our work indicates that the enhancement of EMSI between metal and support can be an effective approach to develop highly active catalysts for phenol treatment.

Survival Outcomes of Lobectomy Versus Segmentectomy in Clinical Stage I Non-Small Cell Lung Cancer: A Meta-Analysis.

INTRODUCTION: The gold standard surgical therapy for patients with clinical stage I non-small cell lung cancer (NSCLC) is lobectomy with mediastinal lymph node dissection. Meanwhile, segmentectomy has emerged as an alternative choice with the advantage of fewer postoperative complications. The acceptance of this procedure remains controversial, and conflicting results exist in the retrospective trials. OBJECTIVES: The aim of this meta-analysis was to analyze the survival outcomes of lobectomy versus segmentectomy in clinical stage I NSCLC. METHODS: A computerized literature search was done on published trials in PubMed, Embase, and the Cochrane Library to June 2019 to identify clinical trials. Lung cancer-specific survival (LCSS) and overall survival (OS) were measured as outcomes. Statistical analysis was performed in the Meta-analysis Revman 5.3 software. RESULTS: A systematic literature search was conducted including seven studies. In this meta-analysis, the LCSS and OS in the lobectomy group were linked to a markedly lower trend in comparison to the segmentectomy group without significant statistical difference (P > 0.05), indicating that lobectomy confers an equivalent survival outcome compared with segmentectomy. CONCLUSION: No significant differences were found in survival outcomes between lobectomy and segmentectomy. Further large-scale, prospective, randomized trials are needed to explore reasonable surgical treatments for early-stage lung cancer.