GO-MAE: Self-supervised pre-training via masked autoencoder for OCT image classification of gynecology.

Genitourinary syndrome of menopause (GSM) is a physiological disorder caused by reduced levels of oestrogen in menopausal women. Gradually, its symptoms worsen with age and prolonged menopausal status, which gravely impacts the quality of life as well as the physical and mental health of the patients. In this regard, optical coherence tomography (OCT) system effectively reduces the patient's burden in clinical diagnosis with its noncontact, noninvasive tomographic imaging process. Consequently, supervised computer vision models applied on OCT images have yielded excellent results for disease diagnosis. However, manual labeling on an extensive number of medical images is expensive and time-consuming. To this end, this paper proposes GO-MAE, a pretraining framework for self-supervised learning of GSM OCT images based on Masked Autoencoder (MAE). To the best of our knowledge, this is the first study that applies self-supervised learning methods on the field of GSM disease screening. Focusing on the semantic complexity and feature sparsity of GSM OCT images, the objective of this study is two-pronged: first, a dynamic masking strategy is introduced for OCT characteristics in downstream tasks. This method can reduce the interference of invalid features on the model and shorten the training time. In the encoder design of MAE, we propose a convolutional neural network and transformer parallel network architecture (C&T), which aims to fuse the local and global representations of the relevant lesions in an interactive manner such that the model can still learn the richer differences between the feature information without labels. Thereafter, a series of experimental results on the acquired GSM-OCT dataset revealed that GO-MAE yields significant improvements over existing state-of-the-art techniques. Furthermore, the superiority of the model in terms of robustness and interpretability was verified through a series of comparative experiments and visualization operations, which consequently demonstrated its great potential for screening GSM symptoms.

Decoding the origins, spread, and global risks of mcr-9 gene.

BACKGROUND: The global spread of the plasmid-mediated mcr (mobilized colistin resistance) gene family presents a significant threat to the efficacy of colistin, a last-line defense against numerous Gram-negative pathogens. The mcr-9 is the second most prevalent variant after mcr-1. METHODS: A dataset of 698 mcr-9-positive isolates from 44 countries is compiled. The historical trajectory of the mcr-9 gene is reconstructed using Bayesian analysis. The effective reproduction number is used innovatively to study the transmission dynamics of this mobile-drug-resistant gene. FINDINGS: Our investigation traces the origins of mcr-9 back to the 1960s, revealing a subsequent expansion from Western Europe to the America and East Asia in the late 20th century. Currently, its transmissibility remains high in Western Europe. Intriguingly, mcr-9 likely emerged from human-associated Salmonella and exhibits a unique propensity for transmission within the Enterobacter. Our research provides a new perspective that this host preference may be driven by codon usage biases in plasmids. Specifically, mcr-9-carrying plasmids prefer the nucleotide C over T compared to mcr-1-carrying plasmids among synonymous codons. The same bias is seen in Enterobacter compared to Escherichia (respectively as their most dominant genus). Furthermore, we uncovered fascinating patterns of coexistence between different mcr-9 subtypes and other resistance genes. Characterized by its low colistin resistance, mcr-9 has used this seemingly benign feature to silently circumnavigate the globe, evading conventional detection methods. However, colistin-resistant Enterobacter strains with high mcr-9 expression have emerged clinically, implying a strong risk of mcr-9 evolving into a global "true-resistance-gene". INTERPRETATION: This study explores the mcr-9 gene, emphasizing its origin, adaptability, and dissemination potential. Given the high mcr-9 expression colistin-resistant strains was observed in clinically the prevalence of mcr-9 poses a significant challenge to drug resistance prevention and control within the One Health framework. FUNDING: This work was partially supported by the National Natural Science Foundation of China (Grant No. 32141001 and 81991533).

Tracking intra-species and inter-genus transmission of KPC through global plasmids mining.

Klebsiella pneumoniae carbapenemase (KPC) poses a major public health risk. Understanding its transmission dynamics requires examining the epidemiological features of related plasmids. Our study compiled 15,660 blaKPC-positive isolates globally over the past two decades. We found extensive diversity in the genetic background of KPC, with 23 Tn4401-related and 341 non-Tn4401 variants across 163 plasmid types in 14 genera. Intra-K. pneumoniae and cross-genus KPC transmission patterns varied across four distinct periods. In the initial periods, plasmids with narrow host ranges gradually established a survival advantage. In later periods, broad-host-range plasmids became crucial for cross-genera transmission. In total, 61 intra-K. pneumoniae and 66 cross-genus transmission units have been detected. Furthermore, phylogenetic reconstruction dated the origin of KPC transmission back to 1991 and revealed frequent exchanges across countries. Our research highlights the frequent and transient spread events of KPC mediated by plasmids across multiple genera and offers theoretical support for high-risk plasmid monitoring.

Intelligent water perimeter security event recognition based on NAM-MAE and distributed optic fiber acoustic sensing system.

Distributed optical acoustic sensing (DAS) based on phase-sensitive optical time-domain reflectometry can realize the distributed monitoring of multi-point disturbances along an optical fiber, thus making it suitable for water perimeter security applications. However, owing to the complex environment and the production of various noises by the system, continuous and effective recognition of disturbance signals becomes difficult. In this study, we propose a Noise Adaptive Mask-Masked Autoencoders (NAM-MAE) algorithm based on the novel mask mode of a Masked Autoencoders (MAE) and applies it to the intelligent event recognition in DAS. In this method, fewer but more accurate features are fed into the deep learning model for recognition by directly shielding the noise. Taking the fading noise generated by the system as an example, data on water perimeter security events collected in DAS underwater acoustic experiments are used. The NAM-MAE is compared with other models. The results indicate higher training accuracy and higher convergence speed of NAM-MAE than other models. Further, the final test accuracy reaches 96.6134%. It can be demonstrated that the proposed method has feasibility and superiority.

A multilayer perceptron-based model applied to histopathology image classification of lung adenocarcinoma subtypes.

Objective: Lung cancer is one of the most common malignant tumors in humans. Adenocarcinoma of the lung is another of the most common types of lung cancer. In clinical medicine, physicians rely on the information provided by pathology tests as an important reference for the fifinal diagnosis of many diseases. Thus, pathological diagnosis is known as the gold standard for disease diagnosis. However, the complexity of the information contained in pathology images and the increase in the number of patients far exceeds the number of pathologists, especially in the treatment of lung cancer in less-developed countries. Methods: This paper proposes a multilayer perceptron model for lung cancer histopathology image detection, which enables the automatic detection of the degree of lung adenocarcinoma infifiltration. For the large amount of local information present in lung cancer histopathology images, MLP IN MLP (MIM) uses a dual data stream input method to achieve a modeling approach that combines global and local information to improve the classifification performance of the model. In our experiments, we collected 780 lung cancer histopathological images and prepared a lung histopathology image dataset to verify the effectiveness of MIM. Results: The MIM achieves a diagnostic accuracy of 95.31% and has a precision, sensitivity, specificity and F1-score of 95.31%, 93.09%, 93.10%, 96.43% and 93.10% respectively, outperforming the diagnostic results of the common network model. In addition, a number of series of extension experiments demonstrated the scalability and stability of the MIM. Conclusions: In summary, MIM has high classifification performance and substantial potential in lung cancer detection tasks.

RVM-GSM: Classification of OCT Images of Genitourinary Syndrome of Menopause Based on Integrated Model of Local-Global Information Pattern.

Genitourinary syndrome of menopause (GSM) is a group of syndromes, including atrophy of the reproductive tract and urinary tract, and sexual dysfunction, caused by decreased levels of hormones, such as estrogen, in women during the transition to, or late stage of, menopause. GSM symptoms can gradually become severe with age and menopausal time, seriously affecting the safety, and physical and mental health, of patients. Optical coherence tomography (OCT) systems can obtain images similar to "optical slices" in a non-destructive manner. This paper presents a neural network, called RVM-GSM, to implement automatic classification tasks for different types of GSM-OCT images. The RVM-GSM module uses a convolutional neural network (CNN) and a vision transformer (ViT) to capture local and global features of the GSM-OCT images, respectively, and, then, fuses the two features in a multi-layer perception module to classify the image. In accordance with the practical needs of clinical work, lightweight post-processing is added to the final surface of the RVM-GSM module to compress the module. Experimental results showed that the accuracy rate of RVM-GSM in the GSM-OCT image classification task was 98.2%. This result is better than those of the CNN and Vit models, demonstrating the promise and potential of the application of RVM-GSM in the physical health and hygiene fields for women.

CTS-Net: A Segmentation Network for Glaucoma Optical Coherence Tomography Retinal Layer Images.

Optical Coherence Tomography (OCT) technology is essential to obtain glaucoma diagnostic data non-invasively and rapidly. Early diagnosis of glaucoma can be achieved by analyzing the thickness and shape of retinal layers. Accurate retinal layer segmentation assists ophthalmologists in improving the efficiency of disease diagnosis. Deep learning technology is one of the most effective methods for processing OCT retinal layer images, which can segment different retinal layers and effectively obtain the topological structure of the boundary. This paper proposes a neural network method for retinal layer segmentation based on the CSWin Transformer (CTS-Net), which can achieve pixel-level segmentation and obtain smooth boundaries. A Dice loss function based on boundary areas (BADice Loss) is proposed to make CTS-Net learn more features of edge regions and improve the accuracy of boundary segmentation. We applied the model to the publicly available dataset of glaucoma retina, and the test results showed that mean absolute distance (MAD), root mean square error (RMSE), and dice-similarity coefficient (DSC) metrics were 1.79 pixels, 2.15 pixels, and 92.79%, respectively, which are better than those of the compared model. In the cross-validation experiment, the ranges of MAD, RMSE, and DSC are 0.05 pixels, 0.03 pixels, and 0.33%, respectively, with a slight difference, which further verifies the generalization ability of CTS-Net.

CroReLU: Cross-Crossing Space-Based Visual Activation Function for Lung Cancer Pathology Image Recognition.

Lung cancer is one of the most common malignant tumors in human beings. It is highly fatal, as its early symptoms are not obvious. In clinical medicine, physicians rely on the information provided by pathology tests as an important reference for the final diagnosis of many diseases. Therefore, pathology diagnosis is known as the gold standard for disease diagnosis. However, the complexity of the information contained in pathology images and the increase in the number of patients far outpace the number of pathologists, especially for the treatment of lung cancer in less developed countries. To address this problem, we propose a plug-and-play visual activation function (AF), CroReLU, based on a priori knowledge of pathology, which makes it possible to use deep learning models for precision medicine. To the best of our knowledge, this work is the first to optimize deep learning models for pathology image diagnosis from the perspective of AFs. By adopting a unique crossover window design for the activation layer of the neural network, CroReLU is equipped with the ability to model spatial information and capture histological morphological features of lung cancer such as papillary, micropapillary, and tubular alveoli. To test the effectiveness of this design, 776 lung cancer pathology images were collected as experimental data. When CroReLU was inserted into the SeNet network (SeNet_CroReLU), the diagnostic accuracy reached 98.33%, which was significantly better than that of common neural network models at this stage. The generalization ability of the proposed method was validated on the LC25000 dataset with completely different data distribution and recognition tasks in the face of practical clinical needs. The experimental results show that CroReLU has the ability to recognize inter- and intra-class differences in cancer pathology images, and that the recognition accuracy exceeds the extant research work on the complex design of network layers.

Predictors of strain for Canadian caregivers seeking service navigation for their youth with mental health and/or addictions issues.

Caring for youth with mental health and/or addictions (MHA) concerns is associated with caregiver strain, which may lead to negative consequences for youth and their caregivers. These consequences may be mitigated by caregivers and/or youth receiving assistance in navigating the healthcare system. Understanding what factors are associated with caregiver strain may be important in developing and implementing navigation services for such families; nonetheless, limited evidence currently exists regarding the predictors of strain in caregivers seeking navigation support. This study aimed to determine whether (a) the mental health profile of youth and (b) the home and family situation for youth with MHA concerns contribute significantly to strain in caregivers engaged in navigation. Data were collected from 66 adults caring for at least one youth with MHA issues accessing navigation service in Toronto, Ontario, between March and August 2018. Multiple linear regressions were conducted to determine which factors were associated with caregiver strain. The first regression model exploring youth-specific independent variables (adjusted r2  = .478, F6,47  = 9.086, p < .001) demonstrated that lower levels of caregiver-rated youth health (ß = -0.577, p = .001) and higher levels of youth mental health symptom severity (ß = 0.077, p < .001) significantly predicted higher levels of strain. The second regression model (adjusted r2  = .348, F5,54  = 7.287, p < .001) showed that lower levels of family functioning (ß = -0.089, p < .001) significantly predicted higher levels of strain. Higher levels of caregiver strain in caregivers of youth with MHA concerns who are accessing navigation services are associated with lower levels of caregiver-rated youth health, higher levels of youth mental health symptom severity, and lower levels of family functioning. These predictors may be potential targets for providers aiming to reduce caregiver strain, as part of navigation or other healthcare services.

Study on timing sequence control fracture blasting excavation of deep rock masses with filled joints.

During the blasting excavation of deep underground caverns, the effects of the structural surface on crack propagation are usually considered in addition to the clamping effects of high in situ stress. Based on the notched borehole and timing sequence control (TSC) fracture blasting method, this paper studies the effects of different borehole shapes on the degree of damage of the surrounding rock and profile flatness of the rock anchor beams and the effects of different filled joint characteristics on the blasting crack propagation rules. The results show that the damage depth of the surrounding rocks by round hole smooth blasting is approximately twice that by notched hole smooth blasting, by which the profile formed is flatter. The notched primary borehole (PBH) remains a strong guidance for crack propagation in a rock mass with filled joints, while the stress concentration effects of the round target borehole (TBH) cannot fully guide the cracks until they fall within a certain distance between the PBH and TBH. It is favourable for cracks to propagate along the lines between boreholes with larger filled joint strengths and larger angles between boreholes.

First year medical student experiences with a clinical skills seminar emphasizing sexual and gender minority population complexity.

PURPOSE: Patients identifying as sexual and gender minorities (SGMs) face healthcare barriers. This problem is partly due to medical training.1 We evaluated first year medical student experiences during a novel four-hour seminar, in which students answered discussion questions, participated in peer role-plays, and interviewed two standardized patients. METHOD: A constructivist qualitative design employed audio-recorded and transcribed student focus groups. Using generic content analysis, transcripts were iteratively coded, emergent categories identified, sensitizing concepts applied, and a thematic framework created. RESULTS: Thirty-five students (71% female) participated in five focus groups. Two themes were developed: SGM bias (faculty, standardized patients [SPs], students, curriculum), and Adaptive Expertise in Clinical Skills (case complexity, learner support, skill development). SPs identifying as SGM brought authenticity and lived experience to their roles. Preceptor variability impacted student learning. Students were concerned when a lack of faculty SGM knowledge accompanied negative biases. Complex SP cases promoted cognitive integration and preparation for clinical work. CONCLUSIONS: These students placed importance on the lived experiences of SGM community members. Persistent prejudices amongst faculty negatively influenced student learning. Complex SP cases can promote student adaptive expertise, but risk unproductive learning failures. The lessons learned have implications for clinical skills teaching, learning about minority populations, and medical and health professions education in general.

OBJECTIF: Les patients qui s'identifient comme faisant partie de minorités sexuelles et de genre (MSG) se heurtent à des obstacles en matière de soins de santé.1 Ce problème est en partie attribuable à la formation des médecins. Nous avons évalué l'expérience des étudiants en première année de médecine dans un séminaire inédit de quatre heures, au cours duquel les étudiants ont répondu à des questions dans le cadre d'une discussion, ont participé à des jeux de rôle entre pairs et ont interrogé deux patients standardisés. MÉTHODE: Cette recherche à devis qualitatif constructiviste a employé des groupes de discussion d'étudiants, qui ont été enregistrés sur bande audio et transcrits. Par le biais d'une analyse de contenu générique, nous avons codé les transcriptions de manière itérative, identifié des catégories émergentes, appliqué des concepts sensibilisateurs et créé un cadre thématique. RÉSULTATS: Trente-cinq étudiants (71 % de femmes) ont participé à cinq groupes de discussion. Deux thèmes ont été développés : biais MSG (corps professoral, patients standardisés [PS], étudiants, cursus) et expertise adaptative en habiletés cliniques (complexité des cas, soutien aux apprenants, développement des habiletés). Les PS qui se sont identifiés comme faisant partie de MSG ont amené de l'authenticité et une expérience vécue à leurs rôles. Les différences entre superviseurs ont eu un impact sur l'apprentissage des étudiants. Le manque de connaissances en matière de MSG chez certains membres du corps professoral inquiétait les étudiants lorsqu'il était accompagné de préjugés négatifs. Les cas complexes de PS ont favorisé l'échec productif, l'intégration cognitive et la préparation au travail clinique. CONCLUSIONS: Les étudiants ont accordé de l'importance aux expériences vécues par les membres de la communauté MSG. Les préjugés inconscients au sein du corps professoral ont eu une influence négative sur l'apprentissage des étudiants. Les cas complexes de PS peuvent favoriser l'expertise adaptative des étudiants, mais risquent d'entraîner des lacunes concernant les apprentissages. Les leçons apprises ont des implications pour l'enseignement des habiletés cliniques, la familiarisation avec les populations minoritaires et l'éducation des professionnels de la santé et l'éducation médicale en général.

An Ontology-Independent Representation Learning for Similar Disease Detection Based on Multi-Layer Similarity Network.

To identify similar diseases has significant implications for revealing the etiology and pathogenesis of diseases and further research in the domain of biomedicine. Currently, most methods for the measurement of disease similarity utilize either associations of ontological disease concepts or functional interactions between disease-related genes. These methods are heavily dependent on the ontology, which are not always available, and the selection of datasets. Moreover, many methods suffer from a drawback that they only use a single metric to evaluate disease similarity from an individual data source, which may result in biased conclusions without consideration of other aspects. In this study, we proposed a novel ontology-independent framework, namely RADAR, for learning representations for diseases to deduce their similarities from an integrative perspective. By leveraging the associations between diseases and disease-related biomedical entities, a disease similarity network was built under various metrics. Then, a multi-layer disease similarity network was constructed by integrating multiple disease similarity networks derived from multiple data sources, where the representation learning was derived to provide a comprehensive evaluation of disease similarities. The performance of RADAR was assessed by a benchmark disease set and 100 random disease sets. Experimental results demonstrated that RADAR can detect similar diseases effectively.