Search

Abstract This study aims to develop a super-resolution (SR) algorithm tailored specifically for enhancing the image quality and resolution of early cervical cancer (CC) magnetic resonance imaging (MRI) images. The proposed method is subjected to both qualitative and quantitative analyses, thoroughly investigating its performance across various upscaling factors and assessing its impact on medical image segmentation tasks. The innovative SR algorithm employed for reconstructing early CC MRI images integrates complex architectures and deep convolutional kernels. Training is conducted on matched pairs of input images through a multi-input model. The research findings highlight the significant advantages of the proposed SR method on two distinct datasets at different upscaling factors. Specifically, at a 2× upscaling factor, the sagittal test set outperforms the state-of-the-art methods in the PSNR index evaluation, second only to the hybrid attention transformer, while the axial test set outperforms the state-of-the-art methods in both PSNR and SSIM index evaluation. At a 4× upscaling factor, both the sagittal test set and the axial test set achieve the best results in the evaluation of PNSR and SSIM indicators. This method not only effectively enhances image quality, but also exhibits superior performance in medical segmentation tasks, thereby providing a more reliable foundation for clinical diagnosis and image analysis.

Abstract Backgrounds Mycoplasma pneumoniae (M. pneumoniae) is a common pathogen causing respiratory diseases in children. This study aimed to characterize epidemiological and disease severity shifts of M. pneumoniae: infections in Guangzhou, China during and after the coronavirus disease 2019 (COVID-19) pandemic. Methods Throat swab samples were obtained from 5405 hospitalized patients with symptoms of acute respiratory infections to detect M. pneumoniae. Differences in epidemiological and clinical characteristics of M. pneumoniae: infections were investigated during 2020–2022 and after COVID-19 pandemic (2023). Results M. pneumoniae were detected in 849 (15.6%, 849/5405) patients. The highest annual positive rate was 29.4% (754/2570) in 2023, followed by 5.3% (72/1367) in 2022, 1.2% (12/1015) in 2021, and 2.0% (11/553) in 2020, with significantly increasing annual prevalence from 2020 to 2023. M. pneumoniae incidence peaked between July and December post-COVID-19 pandemic in 2023, with the highest monthly positive rate (56.4%, 165/293). Clinical characteristics and outcomes of patients with M. pneumoniae did not vary between periods during and after COVID-19 pandemic except that patients with M. pneumoniae post-COVID-19 pandemic were more likely to develop fever. Patients with severe M. pneumoniae pneumonia (SMPP) were more likely to develop respiratory complications, myocardial damage, and gastrointestinal dysfunction than those with non-SMPP. Patients with SMPP had lower lymphocytes, CD3+ T cells, CD4+ T cells, CD8+ T cells, B cells, and higher IL-4, IL-6, IL-10 levels than those with non-SMPP. Bronchoalveolar lavage fluid specimens from infected patients were obtained to identify macrolide resistance mutations. Macrolide-resistant M. pneumoniae (MRMP) proportion in 2023 was 91.1% (215/236). Conclusion Outbreaks of M. pneumoniae: occurred in Guangzhou, China in 2023 upon Non-pharmaceutical interventions easing. Despite the increasing incidence of M. pneumoniae, the disease severity remained similar during and after the COVID-19 pandemic.

Abstract Background Chest computed tomography (CT) image quality impacts radiologists’ diagnoses. Pre-diagnostic image quality assessment is essential but labor-intensive and may have human limitations (fatigue, perceptual biases, and cognitive biases). This study aims to develop and validate a deep learning (DL)-driven multi-view multi-task image quality assessment (M $$^2$$ 2 IQA) method for assessing the quality of chest CT images in patients, to determine if they are suitable for assessing the patient’s physical condition. Methods This retrospective study utilizes and analyzes chest CT images from 327 patients. Among them, 1613 images from 286 patients are used for model training and validation, while the remaining 41 patients are reserved as an additional test set for conducting ablation studies, comparative studies, and observer studies. The M $$^2$$ 2 IQA method is driven by DL technology and employs a multi-view fusion strategy, which incorporates three scanning planes (coronal, axial, and sagittal). It assesses image quality for multiple tasks, including inspiration evaluation, position evaluation, radiation protection evaluation, and artifact evaluation. Four algorithms (pixel threshold, neural statistics, region measurement, and distance measurement) have been proposed, each tailored for specific evaluation tasks, with the aim of optimizing the evaluation performance of the M $$^2$$ 2 IQA method. Results In the additional test set, the M $$^2$$ 2 IQA method achieved 87% precision, 93% sensitivity, 69% specificity, and a 0.90 F1-score. Extensive ablation and comparative studies have demonstrated the effectiveness of the proposed algorithms and the generalization performance of the proposed method across various assessment tasks. Conclusion This study develops and validates a DL-driven M $$^2$$ 2 IQA method, complemented by four proposed algorithms. It holds great promise in automating the assessment of chest CT image quality. The performance of this method, as well as the effectiveness of the four algorithms, is demonstrated on an additional test set.

Abstract To classify early endometrial cancer (EC) on sagittal T2-weighted images (T2WI) by determining the depth of myometrial infiltration (MI) using a computer-aided diagnosis (CAD) method based on a multi-stage deep learning (DL) model. This study retrospectively investigated 154 patients with pathologically proven early EC at the institution between January 1, 2018, and December 31, 2020. Of these patients, 75 were in the International Federation of Gynecology and Obstetrics (FIGO) stage IA and 79 were in FIGO stage IB. An SSD-based detection model and an Attention U-net-based segmentation model were trained to select, crop, and segment magnetic resonance imaging (MRl) images. Then, an ellipse fitting algorithm was used to generate a uterine cavity line (UCL) to obtain MI depth for classification. In the independent test datasets, the uterus and tumor detection model achieves an average precision rate of 98.70% and 87.93%, respectively. Selecting the optimal MRI slices method yields an accuracy of 97.83%. The uterus and tumor segmentation model with mean IOU of 0.738 and 0.655, mean PA of 0.867 and 0.749, and mean DSC of 0.845 and 0.779, respectively. Finally, the CAD method based on the calculated MI depth reaches an accuracy of 86.9%, a sensitivity of 81.8%, and a specificity of 91.7% for early EC classification. In this study, the CAD method implements an end-to-end early EC classification and is found to be on par with radiologists in terms of performance. It is more intuitive and interpretable than previous DL-based CAD methods.

Abstract Objective The current paper aims to discuss the development of a virtual simulation experiment teaching system and review its effectiveness in improving the teaching of clinical skills to college medical students. Methods Collaborators used 3D Studio Max, Unity 3D and Visual Studio to develop four modules: laboratory thinking training, biosafety training, gene testing and experimental assessment. Teaching was conducted and a virtual software program was used for evaluation of the students. Results The laboratory safety training system, virtual gene experiment system and experimental assessment system were developed. The results of the questionnaire survey show that the software provides good interactivity and guidance. The interest of medical students in study is improved and they received training in clinical experimental thinking. Student evaluation assists their scientific research practice, and can improve the awareness of biosafety. Conclusion The virtual simulation experiment teaching system, when applied in the teaching of undergraduate and postgraduate experiment courses, can bring about rapid improvements in the following areas: biosafety awareness, interest in learning about experiments and experimental skills, clinical experimental thinking, and comprehensive experimental ability.

Abstract Background Fluoroquinolone-resistant Haemophilus influenzae (FRHI) has been reported worldwide but remain unclear in China. Methods A total of 402 H. influenzae isolates collected from 2016 to 2017 were included. Antimicrobial susceptibility on 10 antibiotics was performed, and minimum inhibitory concentration of ciprofloxacin- and nalidixic acid-resistant strains were further determined by E-test strips, with risk factors also evaluated. Strains with resistance or reduced susceptibility to ciprofloxacin were subjected to sequencing of the quinolone resistance-determining regions (QRDR) and plasmid-mediated quinolone resistance genes by sequencing, with multi-locus sequence typing. Results 2.2% of H. influenzae strains were non-susceptible (7/402, 1.7%) or susceptible (2/402, 0.5%) to ciprofloxacin but NAL-resistant by E-test, and multidrug resistance was more common in fluoroquinolones non-susceptible H. influenzae group (p = 0.000). Infection risk factors included invasive procedure (p = 0.011), catching cold/previous contact with someone who had a cold (p = 0.019), fluoroquinolones use during previous 3 months (p = 0.003). With none of mutations obtained in gyrB, parE and other plasmid-mediated quinolone resistance genes, 7 and 4 strains were found for Ser-84-Leu substitutions in gyrA and one amino acid substitution in the QRDR of gyrA linked with one amino acid substitution in the QRDR of parC, respectively. In addition, five sequence types (ST) were identified, with ST1719 firstly found. Conclusions For the first time, this study has reported the incidence, risk factors, molecular determinants on fluoroquinolones resistance and ST of FRHI strains in mainland China, representing the first evidence of mutation of gyrA and parC in China and the new ST1719 worldwide.