Comparison of Vision Transformers and Convolutional Neural Networks in Medical Image Analysis: A Systematic Review.

In the rapidly evolving field of medical image analysis utilizing artificial intelligence (AI), the selection of appropriate computational models is critical for accurate diagnosis and patient care. This literature review provides a comprehensive comparison of vision transformers (ViTs) and convolutional neural networks (CNNs), the two leading techniques in the field of deep learning in medical imaging. We conducted a survey systematically. Particular attention was given to the robustness, computational efficiency, scalability, and accuracy of these models in handling complex medical datasets. The review incorporates findings from 36 studies and indicates a collective trend that transformer-based models, particularly ViTs, exhibit significant potential in diverse medical imaging tasks, showcasing superior performance when contrasted with conventional CNN models. Additionally, it is evident that pre-training is important for transformer applications. We expect this work to help researchers and practitioners select the most appropriate model for specific medical image analysis tasks, accounting for the current state of the art and future trends in the field.

Sensorimotor priors are effector dependent.

During sensorimotor tasks, subjects use sensory feedback but also prior information. It is often assumed that the sensorimotor prior is just given by the experiment and that the details for acquiring this prior (e.g., the effector) are irrelevant. However, recent research has suggested that the construction of priors is nontrivial. To test if the sensorimotor details matter for the construction of a prior, we designed two tasks that differ only in the effectors that subjects use to indicate their estimate. For both a typical reaching setting and an atypical wrist rotation setting, prior and feedback uncertainty matter as quantitatively predicted by Bayesian statistics. However, in violation of simple Bayesian models, the importance of the prior differs across effectors. Subjects overly rely on their prior in the typical reaching case compared with the wrist case. The brain is not naively Bayesian with a single and veridical prior. NEW & NOTEWORTHY Traditional Bayesian models often assume that we learn statistics of movements and use the information as a prior to guide subsequent movements. The effector is merely a reporting modality for information processing. We asked subjects to perform a visuomotor learning task with different effectors (finger or wrist). Surprisingly, we found that prior information is used differently between the effectors, suggesting that learning of the prior is related to the movement context such as the effector involved or that naive models of Bayesian behavior need to be extended.

Joint Prior Learning for Visual Sensor Network Noisy Image Super-Resolution.

The visual sensor network (VSN), a new type of wireless sensor network composed of low-cost wireless camera nodes, is being applied for numerous complex visual analyses in wild environments, such as visual surveillance, object recognition, etc. However, the captured images/videos are often low resolution with noise. Such visual data cannot be directly delivered to the advanced visual analysis. In this paper, we propose a joint-prior image super-resolution (JPISR) method using expectation maximization (EM) algorithm to improve VSN image quality. Unlike conventional methods that only focus on upscaling images, JPISR alternatively solves upscaling mapping and denoising in the E-step and M-step. To meet the requirement of the M-step, we introduce a novel non-local group-sparsity image filtering method to learn the explicit prior and induce the geometric duality between images to learn the implicit prior. The EM algorithm inherently combines the explicit prior and implicit prior by joint learning. Moreover, JPISR does not rely on large external datasets for training, which is much more practical in a VSN. Extensive experiments show that JPISR outperforms five state-of-the-art methods in terms of both PSNR, SSIM and visual perception.

From vocational to graduation: A mixed methods study of support needs for vocational learners pursuing post-graduate education in South Africa.

Introduction: Vocational learning has been critical in shaping South Africa's workforce, especially for paramedicine. The introduction of the National Qualification Framework (NQF) in 1995 phased out previous short course learning systems and redesigned qualifications within the framework. While recognition of prior learning is well advocated in the NQF, the predominant focus is undergraduate studies. The leap from vocational to Higher Education can be significant, especially for non-seasoned learners, and additional support may be required to ensure a successful transition. This study describes the support needs of vocational paramedics transitioning to post-graduate education. Methods: The study used a two-phase sequential design to achieve the aims. The first phase was conducted in 2021 and involved an analysis of grades followed by semi-structured interviews to obtain qualitative insights. The second phase, conducted in 2022, focused exclusively on collecting quantitative data to validate and expand upon the initial findings from phase one. Results: Analysis of the academic results over two years between Recognition of Prior Learning (RPL) and non-RPL candidates showed a difference of 4 % in the aggregated mark. This indicates that the RPL candidates have the academic acumen to succeed in a post-graduate diploma education program. Interview analysis revealed the support requirements were not academic but rather technological and institutional, with navigation of the university's learning management system being a common challenge. Hesitancy to access formal support services was noted as a university barrier. Conclusion: This study highlights the academic ability of students from vocational backgrounds to succeed in post-graduate programs. These learners demonstrated strong academic performance despite entering higher education through a non-traditional pathway. Whilst advocating for consideration and refinement of the role of RPL within the NQF, this research suggests a re-evaluation of current support systems for vocational learners transitioning to post-graduate studies.

Experiences of students who gained entry to a nursing college through recognition of prior learning: A phenomenological study.

Background Recognition of prior learning broadens employees' access to higher education and career progress. In South Africa, the process provides previously disadvantaged nurses a fair and equitable opportunity to further their education. It is necessary to understand the support needs of these nurses. OBJECTIVE: To describe the lived experiences of students who gained entry through recognition of prior learning to a three- or four-year nursing training programme at a nursing college in South Africa. DESIGN: A qualitative descriptive phenomenological approach was used to explore and describe the meanings students attached to their educational experiences. SETTING: A public nursing college in South Africa. PARTICIPANTS: Ten nursing students who gained entry through recognition of prior learning were purposefully selected. METHODS: Data were collected over a period of three months, using in-depth individual interviews, and analysed using Giorgi's descriptive phenomenological method. RESULTS: Nursing students who furthered their studies through recognition of prior learning experienced various academic, clinical practice and personal challenges that instilled in them a fear of failure and self-doubt. They used social support from various sources as a way of coping. Previously disadvantaged nursing students require institutional interventions and support to improve their chances of success. CONCLUSIONS: Nurses given the opportunity to advance their careers through recognition of prior learning should have access to person-centred support, academic orientation and resources to attain language and technological competency.

Developing accreditation for community based surgery: the Irish experience.

Purpose Carrying out minor surgery procedures in the primary care setting is popular with patients, cost effective and delivers at least as good outcomes as those performed in the hospital setting. This paper aims to describe the central role of clinical leadership in developing an accreditation system for general practitioners (GPs) undertaking community-based surgery in the Irish national setting where no mandatory accreditation process currently exists. Design/methodology/approach In all, 24 GPs were recruited to the GP network. Ten pilot standards were developed addressing GPs' experience and training, clinical activity and practice supporting infrastructure and tested, using information and document review, prospective collection of clinical data and a practice inspection visit. Two additional components were incorporated into the project (patient satisfaction survey and self-audit). A multi-modal evaluation was undertaken. A majority of GPs was included at all stages of the project, in line with the principles of action learning. The steering group had a majority of GPs with relevant expertise and representation of all other actors in the minor surgery arena. The GP research network contributed to each stage of the project. The project lead was a GP with minor surgery experience. Quantitative data collected were analysed using Predictive Analytic SoftWare. Krueger's framework analysis approach was used to analyse the qualitative data. Findings A total of 9 GPs achieved all standards at initial review, 14 successfully completed corrective actions and 1 GP did not achieve the required standard. Standards were then amended to reflect findings and a supporting framework was developed. Originality/value The flexibility of the action-learning approach and the clinical leadership design allowed for the development of robust quality standards in a short timeframe.