Education in focus: Significant improvements in student learning and satisfaction with ophthalmology teaching delivered using a blended learning approach.

PURPOSE: This study aimed to measure student satisfaction with a revised ophthalmology delivery format, which due to the pandemic had previously relied on a remote online flipped classroom (OFC) format compared to a blended learning format. This educational strategy combined online learning with in-person seminars and practical patient centred sessions. Our previous investigations demonstrated a significant lack of student satisfaction with a curriculum solely reliant on a remote OFC, as such we hypothesised that a blended learning approach would result in improved levels of student satisfaction and knowledge gain. METHODS: Non-randomised intervention study of two groups; group 1 = OFC group and group 2 = BL group, compared perspectives of 4th year ophthalmology students using a validated course evaluation questionnaire (CEQ). RESULTS: A total of 59 students from the BL group (n = 257; response rate = 23.0%) and 28 from the OFC group agreed to participate in the study (n = 114; response rate = 24.6%). Participants in the BL group felt it was easier to determine the standard of work that was expected (77.42% v 60.71%) and demonstrated significantly increased satisfaction with staff motivation of students (95.16% v 64.29%, p <0.001) and provision of feedback (74.19% v 46.43%, p = 0.004), compared to the OFC group. Furthermore, students in the BL group also felt the course significantly improved their analytical skills (64.52% v 42.85%, p = 0.023) and ability to work as part of team (69.36% v 25%, p <0.001) as well as reporting reduced dissatisfaction with the level of choice afforded in terms of how they would learn (33.88% v 60.71%, p = 0.31) and the how they were assessed (59.68% v 89.28%, p = 0.004). No evidence of a statistical difference in exam score was observed. CONCLUSIONS: The COVID-19 pandemic necessitated an unavoidable pivot to online and distance learning, to meet the challenges presented by government mandates and social distancing requirements. Since many of these directives have been reversed, it is important to evaluate the effectiveness and learner perceptions' of the online and distance learning interventions. In this study we demonstrated a significant student preference for BL compared to the OFC approach, with comparable student performances determined by MCQ examinations. Our findings suggest a preference for reintroducing in-person and patient engagement activities in post-pandemic health professions education.

Processo de ensino e aprendizagem no período de suspensão das aulas presenciais em virtude da pandemia de COVID-19: estudo com professores / Teaching and learning process in the suspension period of classes in virtue of the COVID-19 pandemy: study with teachers / Proceso de enseñanza y aprendizaje durante el período de suspensión de clases presencial por la pandemia del COVID-19: estudio con docentes

Introdução: Sabe-se que durante o período da pandemia do COVID-19, escolas e professores precisaram adaptar-se com alternativas para dar continuidade às aulas. Objetivo: Investigar estratégias e recursos pedagógicos de aprendizagem adotados por professores da rede pública e/ou privada de ensino, do interior de um estado brasileiro, durante o período de suspensão das aulas presenciais, em virtude da Pandemia de Covid-19 e seus efeitos para estudantes com e sem dificuldades de aprendizagem. Método: Aplicação de questionário on-line utilizando a ferramenta Google Forms para 37 professores atuantes do 1° ao 5° ano da rede pública e/ou privada no interior do estado, que tenham trabalhado remotamente durante a Pandemia no período de suspensão das aulas presenciais. Esse material continha questões de múltipla escolha e dissertativas e averiguava a forma de trabalho durante este período, as estratégias e os recursos adotados. Resultados: Os resultados mostraram que as estratégias mais utilizadas pelos professores foram uso de materiais impressos. Os professores relataram as dificuldades e os desafios em adotar o ensino remoto, referentes à desigualdade social dos alunos, a dificuldade de adaptação dos professores a esta forma de ensino e ao empenho restrito das famílias no processo de aprendizagem. Conclusão: foi possível verificar como ocorreu o processo de adaptação ao ensino remoto pelos professores. Verifica-se a necessidade de explorar o trabalho conjunto com a Fonoaudiologia, visando minimizar as dificuldades apresentadas pelos estudantes, o que auxiliaria no processo de ensino e aprendizagem dos alunos que, posteriormente, poderiam vir a ser futuros pacientes do setor de Fonoaudiologia. (AU)

Introduction: it is known that during the period of the COVID-19 pandemic, schools and teachers needed to adapt with alternatives to continue classes. Purpose: Investigate pedagogical learning strategies and resources adopted by teachers from public and/or private schools in the interior of a Brazilian state during the period of suspension of face-to-face classes, due to the Covid-19 Pandemic and its effects on students with and without learning difficulties. Method: This research included the application of an online questionnaire through Google Forms to 37 active teachers from the 1st to the 5th year of the public and/or private network at Brasilian state who have worked remotely during the Pandemic during the suspension period of in-person classes. This material contained multiple choice questions and essays, referring to the way of working during this period, strategies and resources adopted. Results: The results showed that the most used strategies by teachers were the use of printed materials. Teachers reported the difficulties and challenges in adopting remote teaching, referring to the social inequality of students, the limited commitment of families in the learning process and the difficulty of teachers to adapt to this form of teaching. Conclusion: Among 37 teachers who joined the study, it was possible to verify how the process of adaptation to remote teaching took place. There is a need to explore the joint work with Speech Therapy, aiming to minimize the difficulties presented by students. Such clarifications would help in the teaching and learning process of students who could later become future patients in the Speech Therapy sector. (AU)

Introducción: se sabe que durante el período de la pandemia del COVID-19, las escuelas y los docentes requirieron adaptarse con alternativas para continuar las clases. Objetivos: Investigar estrategias y recursos pedagógicos de aprendizaje adoptados por profesores de escuelas públicas y/o privadas del interior de un estado brasileño durante el período de suspensión de clases presenciales, debido a la Pandemia Covid-19 y sus efectos en estudiantes con y sin dificultades de aprendizaje. Método: Esta investigación implicó la aplicación de un cuestionario en línea a través de Formularios de Google a 37 docentes que laboran del 1° al 5° año de la red pública y/o privada del interior del estado, que habían trabajado de manera remota durante la Pandemia en el período de suspensión de clases presenciales. Este material contenía preguntas de selección múltiple y desarrollo, referentes a la forma de trabajar durante este período, las estrategias y los recursos adoptados. Resultados: Los resultados mostraron que las estrategias más utilizadas por los docentes fue el uso de materiales impresos. Los docentes relataron las dificultades y desafíos en la adopción de la enseñanza a distancia, refiriéndose a la desigualdad social de los estudiantes, el compromiso restringido de las familias en el proceso de aprendizaje y la dificultad de adaptación de los docentes a esta forma de enseñanza. Conclusión: Entre 37 docentes que se sumaron al estudio, fue posible verificar cómo ocurrió el proceso de adaptación a la enseñanza a distancia. Existe la necesidad de explorar el trabajo conjunto con la Logopedia, con el objetivo de minimizar las dificultades presentadas por los estudiantes. Tales aclaraciones ayudarían en el proceso de enseñanza y aprendizaje de los estudiantes que luego podrían convertirse en futuros pacientes del sector de Logopedia. (AU)

Perception of enhanced learning in medicine through integrating of virtual patients: an exploratory study on knowledge acquisition and transfer.

INTRODUCTION: Virtual Patients (VPs) have been shown to improve various aspects of medical learning, however, research has scarcely delved into the specific factors that facilitate the knowledge gain and transfer of knowledge from the classroom to real-world applications. This exploratory study aims to understand the impact of integrating VPs into classroom learning on students' perceptions of knowledge acquisition and transfer. METHODS: The study was integrated into an elective course on "Personalized Medicine in Cancer Treatment and Care," employing a qualitative and quantitative approach. Twenty-two second-year medical undergraduates engaged in a VP session, which included role modeling, practice with various authentic cases, group discussion on feedback, and a plenary session. Student perceptions of their learning were measured through surveys and focus group interviews and analyzed using descriptive statistics and thematic analysis. RESULTS: Quantitative data shows that students highly valued the role modeling introduction, scoring it 4.42 out of 5, and acknowledged the practice with VPs in enhancing their subject matter understanding, with an average score of 4.0 out of 5. However, students' reflections on peer dialogue on feedback received mixed reviews, averaging a score of 3.24 out of 5. Qualitative analysis (of focus-group interviews) unearthed the following four themes: 'Which steps to take in clinical reasoning', 'Challenging their reasoning to enhance deeper understanding', 'Transfer of knowledge ', and ' Enhance Reasoning through Reflections'. Quantitative and qualitative data are cohered. CONCLUSION: The study demonstrates evidence for the improvement of learning by incorporating VPs with learning activities. This integration enhances students' perceptions of knowledge acquisition and transfer, thereby potentially elevating students' preparedness for real-world clinical settings. Key facets like expert role modeling and various authentic case exposures were valued for fostering a deeper understanding and active engagement, though with some mixed responses towards peer feedback discussions. While the preliminary findings are encouraging, the necessity for further research to refine feedback mechanisms and explore a broader spectrum of medical disciplines with larger sample sizes is underscored. This exploration lays a groundwork for future endeavors aimed at optimizing VP-based learning experiences in medical education.

Organizational learning in surgery in Tanzania's health system: a descriptive cross-sectional study.

Organizational learning is critical for delivering safe, high-quality surgical care, especially in low- and middle-income countries (LMICs) where perioperative outcomes remain poor. While current investments in LMICs prioritize physical infrastructure, equipment, and staffing, investments in organizational learning are equally important to support innovation, creativity, and continuous improvement of surgical quality. This study aims to assess the extent to which health facilities in Tanzania's Lake Zone perform as learning organizations from the perspectives of surgical providers. The insights gained from this study can motivate future quality improvement initiatives and investments to improve surgical outcomes. We conducted a cross-sectional analysis using data from an adapted survey to explore the key components of organizational learning, including a supportive learning environment, effective learning processes, and encouraging leadership. Our sample included surgical team members and leaders at 20 facilities (health centers, district hospitals, and regional hospitals). We calculated the average of the responses at individual facilities. Responses that were 5+ on a 7-point scale or 4+ on a 5-point scale were considered positive. We examined the variation in responses by facility characteristics using a one-way ANOVA or Student's t-test. We used univariate and multiple regression to assess relationships between facility characteristics and perceptions of organizational learning. Ninety-eight surgical providers and leaders participated in the survey. The mean facility positive response rate was 95.1% (SD 6.1%). Time for reflection was the least favorable domain with a score of 62.5% (SD 35.8%). There was variation by facility characteristics including differences in time for reflection when comparing by level of care (P = .02) and location (P = .01), and differences in trying new approaches (P = .008), capacity building (P = .008), and information transfer (P = .01) when comparing public versus faith-based facilities. In multivariable analysis, suburban centers had less time for reflection than urban facilities (adjusted difference = -0.48; 95% CI: -0.95, -0.01; P = .046). Surgical team members reported more positive responses compared to surgical team leaders. We found a high overall positive response rate in characterizing organizational learning in surgery in 20 health facilities in Tanzania's Lake Zone. Our findings identify areas for improvement and provide a baseline for assessing the effectiveness of change initiatives. Future research should focus on validating the adapted survey and exploring the impact of strong learning environments on surgical outcomes in LMICs. Organizational learning is crucial in surgery and further research, funding, and policy work should be dedicated to improving learning cultures in health facilities.

The effectiveness of interprofessional peer-led teaching and learning for therapeutic radiography students and Speech and Language Therapy students.

BACKGROUND: Therapeutic Radiographers (RT) and Speech and Language Therapists (SLT) work closely together in caring for people with head and neck cancer and need a strong understanding of each others' roles. Peer teaching has been shown to be one of the most effective methods of teaching; however, no studies to date, have involved RT and SLT students. This research aims to establish the effectiveness and perceptions of peer-led teaching between undergraduate RT and SLT students in Ulster University. METHODS: Twenty SLT students and 14 RT students participated. Knowledge tests were taken online before the peer-led teaching session (T1), after the session (T2) and 3 months later (T3). Students' perceptions of the experience were collected at the end of the session. Wilcoxon signed-rank tests were used to analyse the impact of the intervention on knowledge scores. Qualitative content analysis was used for open text response data. RESULTS: RT students' own professional knowledge score at T2 was statistically significantly higher than the score at T1; the score at T3 was not deemed to be statistically significantly higher. RT students' SLT knowledge score at T2 and T3 was found to be statistically significantly higher than the score at T1. SLT students' own professional knowledge score was not statistically significantly higher at T2 or T3 than T1. They did have a statistically significantly higher score at T2 on the RT test, but score at T3 was not deemed to be statistically significantly higher. The majority of students across both professions agreed or strongly agreed that the peer-led teaching experience had a positive impact on their learning. CONCLUSION: This investigation highlights the benefits of an interprofessional peer-led teaching intervention for RT and SLT students and the findings add to the evidence of more objective study of knowledge gain as a result of interprofessional peer teaching.

Roseburia intestinalis Supplementation Could Reverse the Learning and Memory Impairment and m6A Methylation Modification Decrease Caused by 27-Hydroxycholesterol in Mice.

The abnormality in N6-methyladenosine (m6A) methylation is involved in the course of Alzheimer's disease (AD), while the intervention of 27-Hydroxycholesterol (27-OHC) can affect the m6A methylation modification in the brain cortex. Disordered gut microbiota is a key link in 27-OHC leading to cognitive impairment, and further studies have found that the abundance of Roseburia intestinalis in the gut is significantly reduced under the intervention of 27-OHC. This study aims to investigate the association of 27-OHC, Roseburia intestinalis in the gut, and brain m6A modification in the learning and memory ability injury. In this study, 9-month-old male C57BL/6J mice were treated with antibiotic cocktails for 6 weeks to sweep the intestinal flora, followed by 27-OHC or normal saline subcutaneous injection, and then Roseburia intestinalis or normal saline gavage were applied to the mouse. The 27-OHC level in the brain, the gut barrier function, the m6A modification in the brain, and the memory ability were measured. From the results, we observed that 27-OHC impairs the gut barrier function, causing a disturbance in the expression of m6A methylation-related enzymes and reducing the m6A methylation modification level in the brain cortex, and finally leads to learning and memory impairment. However, Roseburia intestinalis supplementation could reverse the negative effects mentioned above. This study suggests that 27-OHC-induced learning and memory impairment might be linked to brain m6A methylation modification disturbance, while Roseburia intestinalis, as a probiotic with great potential, could reverse the damage caused by 27-OHC. This research could help reveal the mechanism of 27-OHC-induced neural damage and provide important scientific evidence for the future use of Roseburia intestinalis in neuroprotection.

What is the effectiveness of reporting systems in promoting learning in healthcare?

Patient safety in healthcare remains a top priority. Learning from safety events is vital to move towards safer systems. As a result, reporting systems are recognised as the cornerstone of safety, especially in high-risk industries. However, in healthcare, the benefits of reporting systems in promoting learning remain contentious. Though the strengths of these systems, such as promoting a safety culture and providing information from near misses are noted, there are problems that mean learning is missed. Understanding the factors that both enable and act as barriers to learning from reporting is also important to consider. This review, considers the effectiveness of reporting systems in contributing to learning in healthcare.

The role of cerebellum in learned vocal communication in adult songbirds.

Injury, tumors, ischemia, and lesions in the cerebellum show the involvement of this region in human speech. The association of the cerebellum with learned birdsong has only been identified recently. Cerebellar dysfunction in young songbirds causes learning disabilities, but its role in adult songbirds has not been established. The aim of this study was to investigate the role of the deep cerebellar nuclei (DCN) in adult birdsong. We created bilateral excitotoxic lesions in the DCN of adult male zebra finches (Taeniopygia guttata) and recorded their songs for up to 4 months. Using magnetic resonance imaging (MRI) and immunohistochemistry, we validated the lesion efficacy. We found that the song duration significantly increased from 14 weeks post-op; the increase in duration was caused by a greater number of introductory notes as well as a greater number of syllables sung after the introductory notes. On the other hand, the motif duration decreased from 8 weeks after DCN lesions were induced, which was due to faster singing of syllables, not changes in inter-syllable interval length. DCN lesions also caused a decrease in the fundamental frequency of syllables. In summary, we showed that DCN lesions influence the temporal and acoustic features of birdsong. These results suggest that the cerebellum influences singing in adult songbirds.

Conditioning and pseudoconditioning differently change intrinsic excitability of inhibitory interneurons in the neocortex.

Many studies indicate a broad role of various classes of GABAergic interneurons in the processes related to learning. However, little is known about how the learning process affects intrinsic excitability of specific classes of interneurons in the neocortex. To determine this, we employed a simple model of conditional learning in mice where vibrissae stimulation was used as a conditioned stimulus and a tail shock as an unconditioned one. In vitro whole-cell patch-clamp recordings showed an increase in intrinsic excitability of low-threshold spiking somatostatin-expressing interneurons (SST-INs) in layer 4 (L4) of the somatosensory (barrel) cortex after the conditioning paradigm. In contrast, pseudoconditioning reduced intrinsic excitability of SST-LTS, parvalbumin-expressing interneurons (PV-INs), and vasoactive intestinal polypeptide-expressing interneurons (VIP-INs) with accommodating pattern in L4 of the barrel cortex. In general, increased intrinsic excitability was accompanied by narrowing of action potentials (APs), whereas decreased intrinsic excitability coincided with AP broadening. Altogether, these results show that both conditioning and pseudoconditioning lead to plastic changes in intrinsic excitability of GABAergic interneurons in a cell-specific manner. In this way, changes in intrinsic excitability can be perceived as a common mechanism of learning-induced plasticity in the GABAergic system.

The Contribution of Willingness to Communicate to L2 Learners' Depth of Vocabulary Knowledge: An Empirical Study.

The issues of depth vocabulary knowledge and Willingness to Communicate (henceforth, WTC) are among the most important issues in second language learning. The present study set out to empirically look into the contribution of WTC to depth of vocabulary knowledge in L2 learning. To this end, 88 English L2 learners, divided into two groups in terms of their WTC, were given two depth vocabulary tests. The Word Association Test (WAT) was first administered to make a comparison between the depth vocabulary knowledge of the two WTC groups. Then, to triangulate the results, the Word Part Levels Test (WPLT) was administered to check whether the obtained results confirmed those of WAT. Analyzing data through independent t-test and MANOVA indicated that learners with higher levels of WTC had deeper vocabulary knowledge than those with lower levels of WTC on the WAT. Further, the triangulation results evinced that although the two groups did not differ significantly on the form-section and meaning-section of the WPLT, they significantly differed on the use-section of the test. The relevant pedagogical implications of the study are discussed.

Glucosamine Enhancement of Learning and Memory Functions by Promoting Fibroblast Growth Factor 21 Production.

Fibroblast growth factor 21 (FGF21) plays a crucial role in metabolism and brain function. Glucosamine (GLN) has been recognized for its diverse beneficial effects. This study aimed to elucidate the modulation of FGF21 production by GLN and its impact on learning and memory functions. Using both in vivo and in vitro models, we investigated the effects of GLN on mice fed with a normal diet or high-fat diet and on mouse HT22 hippocampal cells, STHdhQ7/Q7 striatal cells, and rat primary cortical neurons challenged with GLN. Our results indicated that GLN promotes learning and memory functions in mice and upregulates FGF21 expression in the hippocampus, cortex, and striatum, as well as in HT22 cells, STHdhQ7/Q7 cells, and cortical neurons. In animals receiving GLN together with an FGF21 receptor FGFR1 inhibitor (PD173074), the GLN-enhanced learning and memory functions and induction of FGF21 production in the hippocampus were significantly attenuated. While exploring the underlying molecular mechanisms, the potential involvement of NF-κB, Akt, p38, JNK, PKA, and PPARα in HT22 and NF-κB, Akt, p38, and PPARα in STHdhQ7/Q7 were noted; GLN was able to mediate the activation of p65, Akt, p38, and CREB in HT22 and p65, Akt, and p38 in STHdhQ7/Q7 cells. Our accumulated findings suggest that GLN may increase learning and memory functions by inducing FGF21 production in the brain. This induction appears to be mediated, at least in part, through GLN's activation of the NF-κB, Akt, p38, and PKA/CREB pathways.

Children's cognition and attitudes during long-term cancer treatment: an ethnographic study.

BACKGROUND: Cancer treatment for children is typically long-term and difficult, and the experience is unique for each child. When designing child-centred care, individuals' values and preferences are considered equally important as the clinical evidence; therefore, understanding children's thoughts and attitudes while they receive long-term treatment could offer valuable insights for better clinical practice. METHODS: We conducted long-term consecutive participatory observations and interviews with seven children, who were hospitalised and receiving cancer treatment for the first time. The daily observational data on those children's discourses, behaviours and interactions with health professionals were systematically collected and thematically examined. The analysis was expanded to explore significant narratives for each child to capture their narrative sequence over time. RESULTS: The initial analysis identified 685 narrative indexes for all observation data, which were categorised into 21 sub-codes. Those sub-codes were assembled into five main themes by thematic analysis: making promises with health professionals, learning about the treatment procedures through participation, taking care of oneself, increasing the range of activities one can perform and living an ordinary life. CONCLUSION: We observed a forward-looking attitude toward understanding cancer, accepting treatment and looking forward to the future among children undergoing in-hospital cancer treatment. In addition, the children developed cognitively, affectively and relationally throughout cancer treatment processes. These findings have implications for better clinical practice in child-centred care, including children's participation in shared decision-making in paediatric oncology.

Development of Web-Based Education Modules to Improve Carer Engagement in Cancer Care: Design and User Experience Evaluation of the e-Triadic Oncology (eTRIO) Modules for Clinicians, Patients, and Carers.

BACKGROUND: Carers often assume key roles in cancer care. However, many carers report feeling disempowered and ill-equipped to support patients. Our group published evidence-based guidelines (the Triadic Oncology [TRIO] Guidelines) to improve oncology clinician engagement with carers and the management of challenging situations involving carers. OBJECTIVE: To facilitate implementation of the TRIO Guidelines in clinical practice, we aimed to develop, iteratively refine, and conduct user testing of a suite of evidence-based and interactive web-based education modules for oncology clinicians (e-Triadic Oncology [eTRIO]), patients with cancer, and carers (eTRIO for Patients and Carers [eTRIO-pc]). These were designed to improve carer involvement, communication, and shared decision-making in the cancer management setting. METHODS: The eTRIO education modules were based on extensive research, including systematic reviews, qualitative interviews, and consultation analyses. Guided by the person-based approach, module content and design were reviewed by an expert advisory group comprising academic and clinical experts (n=13) and consumers (n=5); content and design were continuously and iteratively refined. User experience testing (including "think-aloud" interviews and administration of the System Usability Scale [SUS]) of the modules was completed by additional clinicians (n=5), patients (n=3), and carers (n=3). RESULTS: The final clinician module comprises 14 sections, requires approximately 1.5 to 2 hours to complete, and covers topics such as carer-inclusive communication and practices; supporting carer needs; and managing carer dominance, anger, and conflicting patient-carer wishes. The usability of the module was rated by 5 clinicians, with a mean SUS score of 75 (SD 5.3), which is interpreted as good. Clinicians often desired information in a concise format, divided into small "snackable" sections that could be easily recommenced if they were interrupted. The carer module features 11 sections; requires approximately 1.5 hours to complete; and includes topics such as the importance of carers, carer roles during consultations, and advocating for the patient. The patient module is an adaptation of the relevant carer module sections, comprising 7 sections and requiring 1 hour to complete. The average SUS score as rated by 6 patients and carers was 78 (SD 16.2), which is interpreted as good. Interactive activities, clinical vignette videos, and reflective learning exercises are incorporated into all modules. Patient and carer consumer advisers advocated for empathetic content and tone throughout their modules, with an easy-to-read and navigable module interface. CONCLUSIONS: The eTRIO suite of modules were rigorously developed using a person-based design methodology to meet the unique information needs and learning requirements of clinicians, patients, and carers, with the goal of improving effective and supportive carer involvement in cancer consultations and cancer care.

Europe following Galen.

Unlike previous chapters, this is not about the teachings of a specific individual. Rather, it traces the slow changes in milieu and practice in the centuries following the death of Galen. They were to be profound. The Roman Empire fell in the middle of the 5th century. The Christian religion became increasingly dominant in the west, not only in spiritual matters but also in every activity related to culture and learning. The Byzantine Empire became increasingly important in the east. Islam was founded and began to spread in competition with Christianity. Academic advances develop best in stable societies so that it is not surprising that this was not a period of new ideas. Galen had gained overwhelming authority. The most valuable work on surgery to be written during these times was Book VI of Paul of Ægina's encyclopedia.

PMFFNet: A hybrid network based on feature pyramid for ovarian tumor segmentation.

Ovarian cancer is a highly lethal malignancy in the field of oncology. Generally speaking, the segmentation of ovarian medical images is a necessary prerequisite for the diagnosis and treatment planning. Therefore, accurately segmenting ovarian tumors is of utmost importance. In this work, we propose a hybrid network called PMFFNet to improve the segmentation accuracy of ovarian tumors. The PMFFNet utilizes an encoder-decoder architecture. Specifically, the encoder incorporates the ViTAEv2 model to extract inter-layer multi-scale features from the feature pyramid. To address the limitation of fixed window size that hinders sufficient interaction of information, we introduce Varied-Size Window Attention (VSA) to the ViTAEv2 model to capture rich contextual information. Additionally, recognizing the significance of multi-scale features, we introduce the Multi-scale Feature Fusion Block (MFB) module. The MFB module enhances the network's capacity to learn intricate features by capturing both local and multi-scale information, thereby enabling more precise segmentation of ovarian tumors. Finally, in conjunction with our designed decoder, our model achieves outstanding performance on the MMOTU dataset. The results are highly promising, with the model achieving scores of 97.24%, 91.15%, and 87.25% in mACC, mIoU, and mDice metrics, respectively. When compared to several Unet-based and advanced models, our approach demonstrates the best segmentation performance.

Development and validation of metrics for a new RAPN training model.

Robot-assisted partial nephrectomy (RAPN) is a complex and index procedure that urologists need to learn how to perform safely. No validated performance metrics specifically developed for a RAPN training model (TM) exist. A Core Metrics Group specifically adapted human RAPN metrics to be used in a newly developed RAPN TM, explicitly defining phases, steps, errors, and critical errors. A modified Delphi meeting concurred on the face and content validation of the new metrics. One hundred percent consensus was achieved by the Delphi panel on 8 Phases, 32 Steps, 136 Errors and 64 Critical Errors. Two trained assessors evaluated recorded video performances of novice and expert RAPN surgeons executing an emulated RAPN in the newly developed TM. There were no differences in procedure Steps completed by the two groups. Experienced RAPN surgeons made 34% fewer Total Errors than the Novice group. Performance score for both groups was divided at the median score using Total Error scores, into HiError and LoError subgroups. The LowErrs Expert RAPN surgeons group made 118% fewer Total Errors than the Novice HiErrs group. Furthermore, the LowErrs Expert RAPN surgeons made 77% fewer Total Errors than the HiErrs Expert RAPN surgeons. These results established construct and discriminative validity of the metrics. The authors described a novel RAPN TM and its associated performance metrics with evidence supporting their face, content, construct, and discriminative validation. This report and evidence support the implementation of a simulation-based proficiency-based progression (PBP) training program for RAPN.

CT Perfusion Map Synthesis from CTP Dynamic Images Using a Learned LSTM Generative Adversarial Network for Acute Ischemic Stroke Assessment.

Computed tomography perfusion (CTP) is a dynamic 4-dimensional imaging technique (3-dimensional volumes captured over approximately 1 min) in which cerebral blood flow is quantified by tracking the passage of a bolus of intravenous contrast with serial imaging of the brain. To diagnose and assess acute ischemic stroke, the standard method relies on summarizing acquired CTPs over the time axis to create maps that show different hemodynamic parameters, such as the timing of the bolus arrival and passage (Tmax and MTT), cerebral blood flow (CBF), and cerebral blood volume (CBV). However, producing accurate CTP maps requires the selection of an arterial input function (AIF), i.e. a time-concentration curve in one of the large feeding arteries of the brain, which is a highly error-prone procedure. Moreover, during approximately one minute of CT scanning, the brain is exposed to ionizing radiation that can alter tissue composition, and create free radicals that increase the risk of cancer. This paper proposes a novel end-to-end deep neural network that synthesizes CTP images to generate CTP maps using a learned LSTM Generative Adversarial Network (LSTM-GAN). Our proposed method can improve the precision and generalizability of CTP map extraction by eliminating the error-prone and expert-dependent AIF selection step. Further, our LSTM-GAN does not require the entire CTP time series and can produce CTP maps with a reduced number of time points. By reducing the scanning sequence from about 40 to 9 time points, the proposed method has the potential to minimize scanning time thereby reducing patient exposure to CT radiation. Our evaluations using the ISLES 2018 challenge dataset consisting of 63 patients showed that our model can generate CTP maps by using only 9 snapshots, without AIF selection, with an accuracy of 84.37 % .

MUSCLE: multi-view and multi-scale attentional feature fusion for microRNA-disease associations prediction.

MicroRNAs (miRNAs) synergize with various biomolecules in human cells resulting in diverse functions in regulating a wide range of biological processes. Predicting potential disease-associated miRNAs as valuable biomarkers contributes to the treatment of human diseases. However, few previous methods take a holistic perspective and only concentrate on isolated miRNA and disease objects, thereby ignoring that human cells are responsible for multiple relationships. In this work, we first constructed a multi-view graph based on the relationships between miRNAs and various biomolecules, and then utilized graph attention neural network to learn the graph topology features of miRNAs and diseases for each view. Next, we added an attention mechanism again, and developed a multi-scale feature fusion module, aiming to determine the optimal fusion results for the multi-view topology features of miRNAs and diseases. In addition, the prior attribute knowledge of miRNAs and diseases was simultaneously added to achieve better prediction results and solve the cold start problem. Finally, the learned miRNA and disease representations were then concatenated and fed into a multi-layer perceptron for end-to-end training and predicting potential miRNA-disease associations. To assess the efficacy of our model (called MUSCLE), we performed 5- and 10-fold cross-validation (CV), which got average the Area under ROC curves of 0.966${\pm }$0.0102 and 0.973${\pm }$0.0135, respectively, outperforming most current state-of-the-art models. We then examined the impact of crucial parameters on prediction performance and performed ablation experiments on the feature combination and model architecture. Furthermore, the case studies about colon cancer, lung cancer and breast cancer also fully demonstrate the good inductive capability of MUSCLE. Our data and code are free available at a public GitHub repository: https://github.com/zht-code/MUSCLE.git.

Smart active particles learn and transcend bacterial foraging strategies.

Throughout evolution, bacteria and other microorganisms have learned efficient foraging strategies that exploit characteristic properties of their unknown environment. While much research has been devoted to the exploration of statistical models describing the dynamics of foraging bacteria and other (micro-) organisms, little is known, regarding the question of how good the learned strategies actually are. This knowledge gap is largely caused by the absence of methods allowing to systematically develop alternative foraging strategies to compare with. In the present work, we use deep reinforcement learning to show that a smart run-and-tumble agent, which strives to find nutrients for its survival, learns motion patterns that are remarkably similar to the trajectories of chemotactic bacteria. Strikingly, despite this similarity, we also find interesting differences between the learned tumble rate distribution and the one that is commonly assumed for the run and tumble model. We find that these differences equip the agent with significant advantages regarding its foraging and survival capabilities. Our results uncover a generic route to use deep reinforcement learning for discovering search and collection strategies that exploit characteristic but initially unknown features of the environment. These results can be used, e.g., to program future microswimmers, nanorobots, and smart active particles for tasks like searching for cancer cells, micro-waste collection, or environmental remediation.