In this article, glioma segmentation in the glioma grading computer-aided diagnosis (CAD) system requires manual delineation from radiologists, adding substantially to their workload. Although automatic segmentation is powerful, it cannot fully delegate power to artificial intelligence. We propose an AI-powered radiomics algorithm based on slice pooling (AI-RASP). AI-RASP generated compress images by compressing the gray value of each magnetic resonance imaging slice for radiologists to segment manually. In addition, AI-RASP integrated radiomics models to verify the glioma grading effect and the availability of compressed images. AI-RASP significantly reduce the time of manual segmentation. Results reported on multicenter datasets reveal that our architecture is better than the traditional manual segmentation while being over five times faster. The radiomics model with slice pooling mechanism achieves an area under the curve values of 0.86, 086, and 0.83 in the validation cohorts. Radiologists and patients can benefit from a CAD system integrated with AI-RASP.

Background Aspiration pneumonia (AP) is a common complication in the intensive care unit (ICU), which is associated with significantly increased morbidity and mortality and has a significant impact on patient prognosis. Antibiotics are commonly used in the clinical treatment of AP. However, the prognostic impact of antibiotics on patients with AP has not been adequately characterized. The purpose of this study is to illustrate the relationship between the use of antibiotics and in-hospital mortality of AP patients, as well as to analyze the effects of different antibiotic treatment regimens on the prognosis of the patients, and to further understand the distribution of pathogens and drug resistance in AP patients, so as to provide guidance information for the rational use of medication for patients in the clinic. Methods Clinical data of AP patients were extracted from the MIMIC-IV database. Statistical methods included multivariate logistic regression, propensity score matching (PSM), and inverse probability weighting (IPW) based on propensity scores to ensure the robustness of the findings. In addition, the characteristics of the medications used by patients with AP were described using statistical graphs and tables. Results A total of 4132 patients with AP were included. In-hospital mortality was significantly lower in the group using antibiotics compared to the group not using antibiotics (odds ratio [OR] = 0.44, 95% confidence interval [CI] 0.27- 0.71, P = 0.001). Furthermore, in the group using mechanical ventilation (MV), antibiotics use significantly reduced in-hospital mortality (OR = 0.30, 95% CI 0.15-0.57, P < 0.001). Vancomycin and cephalosporins are the most commonly used antibiotics to treat AP. Specifically, vancomycin in combination with piperacillin-tazobactam was used most frequently with 396 cases. The highest survival rate (97.6\%) was observed in patients treated with levofloxacin combined with metronidazole. Additionally, vancomycin combined with piperacillin-tazobactam had many inflammation related features that differed significantly from those in patients who did not receive medication. Conclusions Antibiotics use is closely associated with lower in-hospital mortality in ICU patients with AP. Moreover, understanding antibiotics use, the composition of pathogenic bacteria, and the rates of drug resistance in patients with AP can aid in disease prevention and prompt infection control.

Generalized zero-shot learning (GZSL) aims to classify classes that do not appear during training. Recent state-of-the-art approaches rely on generative models, which use correlating semantic embeddings to synthesize unseen classes visual features; however, these approaches ignore the semantic and visual relevance, and visual features synthesized by generative models do not represent their semantics well. Although existing GZSL methods based on generative model disentanglement consider consistency between visual and semantic models, these methods consider semantic consistency only in the training phase and ignore semantic consistency in the feature synthesis and classification phases. The absence of such constraints may lead to an unrepresentative synthesized visual model with respect to semantics, and the visual and semantic features are not modally well aligned, thus causing the bias between visual and semantic features. Therefore, an approach for GZSL is proposed to enhance semantic-consistent features and discriminative features transformation (ESTD-GZSL). The proposed method can enhance semantic-consistent features at all stages of GZSL. A semantic decoder module is first added to the VAE to map synthetic and real features to the corresponding semantic embeddings. This regularization method allows synthesizing unseen classes for a more representative visual representation, and synthetic features can better represent their semantics. Then, the semantic-consistent features decomposed by the disentanglement module and the features output by the semantic decoder are transformed into enhanced semantic-consistent discriminative features and used in classification to reduce the ambiguity between categories. The experimental results show that our proposed method achieves more competitive results on four benchmark datasets (AWA2, CUB, FLO, and APY) of GZSL.

The access to and sharing of medical image data is essential to accelerate the research progress of complex diseases and sudden disease outbreaks. Multicenter image data is collected from different medical institutions, and the contrast and brightness of the images are significantly different, making it difficult to use the images directly. Herein, we introduce a standardized method based on magnetic resonance imaging, referred to as Histogram specification–grid search (HS–GS), which is mainly used to eliminate differences in image contrast and brightness. A Gaussian probability density function with adjustable parameters is used to generate the cumulative distribution function, and the transfer function required for the HS mapping is constructed to obtain standardized image sets based on the controllable parameters. The image sets are used to perform the GS task of radiomics classification to find the optimal controllable parameter combination and classification results, and then obtain the optimal standardized image sets. We used HS–GS to test and verify the predictive ability of the standardized mixed image sets for glioma grading, and compared it with existing methods. The experiments indicate that the standardized image sets generated by the HS–GS algorithm retain excellent stability after mixing and also show excellent classification performance. This novel image set standardization technique has proven to be a promising solution for integration into medical expert systems.