X-ray system simulation software tools for radiology and radiography education

Radiographers' perceptions of first year diagnostic radiography students' performance following implementation of a simulation-based education model

INTRODUCTION

Simulation-based education (SBE) partially replaced the clinical placement learning for a cohort of first year students on a BSc (Hons) Diagnostic Radiography programme. This was in response to the pressures on hospital-based training caused by increasing student numbers and following increased capability and positive outcomes for student learning in delivering SBE as a result of the COVID-19 pandemic.

METHODS

A survey was distributed to diagnostic radiographers, across five NHS Trusts, involved in the clinical education of first year diagnostic radiography students at one UK university. The survey sought radiographers' perception of student performance in undertaking radiographic examinations, safety procedures, knowledge of anatomy, professionalism, and the impact of embedding simulation-based education through multichoice and free text questions. Descriptive and thematic analysis of the survey data was undertaken.

RESULTS

Twelve survey responses from radiographers across four Trusts were collated. Responses indicated the majority of radiographers perceived students to require the expected level of assistance in undertaking appendicular examinations, applying infection control and radiation safety measures, and had the expected level of radiographic anatomy knowledge. Students also interacted appropriately with service users, demonstrated increased confidence in coming into the clinical environment and were receptive to feedback. Some variation was noted, particularly in professionalism and engagement, though not always attributed to SBE.

CONCLUSION

Replacement of clinical placement with SBE was perceived to have provided appropriate learning opportunities and some additional benefits, however it was felt by some radiographers that SBE could not replace the experience of the real imaging environment.

IMPLICATIONS FOR PRACTICE

Embedding simulated-based education requires a holistic approach and close collaboration with placement partners to ensure complimentary learning experiences in the clinical placement setting, and support achievement of the learning outcomes.

Convolutional Encoder-Decoder Networks for Volumetric Computed Tomography Surviews from Single- and Dual-View Topograms

Computed tomography (CT) is an extensively used imaging modality capable of generating detailed images of a patient's internal anatomy for diagnostic and interventional procedures. High-resolution volumes are created by measuring and combining information along many radiographic projection angles. In current medical practice, single and dual-view two-dimensional (2D) topograms are utilized for planning the proceeding diagnostic scans and for selecting favorable acquisition parameters, either manually or automatically, as well as for dose modulation calculations. In this study, we develop modified 2D to three-dimensional (3D) encoder-decoder neural network architectures to generate CT-like volumes from single and dual-view topograms. We validate the developed neural networks on synthesized topograms from publicly available thoracic CT datasets. Finally, we assess the viability of the proposed transformational encoder-decoder architecture on both common image similarity metrics and quantitative clinical use case metrics, a first for 2D-to-3D CT reconstruction research. According to our findings, both single-input and dual-input neural networks are able to provide accurate volumetric anatomical estimates. The proposed technology will allow for improved (i) planning of diagnostic CT acquisitions, (ii) input for various dose modulation techniques, and (iii) recommendations for acquisition parameters and/or automatic parameter selection. It may also provide for an accurate attenuation correction map for positron emission tomography (PET) with only a small fraction of the radiation dose utilized.

Augmented Reality in Radiology for Education and Training—A Design Study

Education is an important component of every healthcare system. Patients need to be educated about their planned procedures; healthcare professionals need to be trained in their respective profession. Both patient education and the training of healthcare professionals are often completed in person, which requires resources and is bound to certain times and places. Virtual educational environments can potentially save human and monetary resources, increase learner engagement, and enable users to learn according to their own schedules. This design study describes proofs of concept for two augmented reality-enabled (AR) educational tools, utilizing a Microsoft HoloLens head-mounted display. In the first use case, we demonstrate an AR application which could be used to educate cancer patients about their radiotherapy treatment and potentially reduce patient anxiety. The second use case demonstrates an AR training environment, which could complement the practical training of undergraduate radiography students. Two prototypes—VIPER, for patient education, and ARTUR for the training of radiography students—were developed and tested for viability and usability, both based on individual user tests. Both patient and student education were evaluated as viable and usable additions to conventional educational methods, despite being limited in terms of accessibility, usability, and fidelity. Suitable hardware is becoming more accessible and capable, and higher-fidelity holograms, better utilization of real-world objects, and more intuitive input methods could increase user immersion and acceptance of the technology.

Generation of reusable learning objects from digital medical collections: An analysis based on the MASMDOA framework

Learning Objects represent a widespread approach to structuring instructional materials in a large variety of educational contexts. The main aim of this work consists of analyzing the process of generating reusable learning objects followed by Clavy, a tool that can be used to retrieve data from multiple medical knowledge sources and reconfigure such sources in diverse multimedia-based structures and organizations. From these organizations, Clavy is able to generate learning objects that can be adapted to various instructional healthcare scenarios with several types of user profiles and distinct learning requirements. Moreover, Clavy provides the capability of exporting these learning objects through standard educational specifications, which improves their reusability features. The analysis proposed is conducted following criteria defined by the MASMDOA framework for comparing and selecting learning object generation methodologies. The analysis insights highlight the importance of having a tool to transfer knowledge from the available digital medical collections to learning objects that can be easily accessed by medical students and healthcare practitioners through the most popular e-learning platforms.

Evolving Deep Learning Convolutional Neural Networks for Early COVID-19 Detection in Chest X-ray Images

This article proposes a framework that automatically designs classifiers for the early detection of COVID-19 from chest X-ray images. To do this, our approach repeatedly makes use of a heuristic for optimisation to efficiently find the best combination of the hyperparameters of a convolutional deep learning model. The framework starts with optimising a basic convolutional neural network which represents the starting point for the evolution process. Subsequently, at most two additional convolutional layers are added, at a time, to the previous convolutional structure as a result of a further optimisation phase. Each performed phase maximises the the accuracy of the system, thus requiring training and assessment of the new model, which gets gradually deeper, with relevant COVID-19 chest X-ray images. This iterative process ends when no improvement, in terms of accuracy, is recorded. Hence, the proposed method evolves the most performing network with the minimum number of convolutional layers. In this light, we simultaneously achieve high accuracy while minimising the presence of redundant layers to guarantee a fast but reliable model. Our results show that the proposed implementation of such a framework achieves accuracy up to 99.11%, thus being particularly suitable for the early detection of COVID-19.

CTSim: Changing teaching practice in radiography with simulation

INTRODUCTION

Simulation offers radiography students the possibility to experiment with Computed Tomography (CT) in a way not possible in clinical practice. The aim of this work was to test a newly developed simulator 'CTSim' for effectiveness in teaching and learning.

METHODS

The simulator was tested in two phases. The first phase used a test-retest methodology with two groups, a group that experienced a Simulation based learning intervention and one which did not. The second phase subsequently tested for changes when the same intervention was introduced as part of an existing CT training module.

RESULTS

Phase 1 demonstrated statistically significant improvement of mean scores from 58% to 68% (P < .05) for students who experienced the intervention against no change in scores for the control group. Phase 2 saw mean scores improve statistically significantly in a teaching module from 66% to 73% (P < .05) following the application of the intervention as an active learning component.

CONCLUSION

The use of the CTSim simulator had a demonstrable effect on student learning when used as an active learning component in CT teaching.

IMPLICATIONS FOR PRACTICE

Simulation tools have a place in enhancing teaching and learning in terms of effectiveness and also introduce variety in the medium by which this is done.

A VBA module simulation for finding optimal lag order in time series models and its use on teaching financial data computation

In this study, a tool has been designed and developed for learning about the concept of lag order within a dynamic model, which can be used in any teaching classes on statistics and financial data computation. To show a solution for a complex and multi-step process of finding the optimal lag order for multiple variables data series based on an information criterion a module using Visual Basic for Applications (VBA) for Microsoft Excel (MS Excel) is being developed. This module can be used for estimating a multivariate dynamic model as well as determining the optimal lag order of such a model.

Geometric validation of a computer simulator used in radiography education

Objectives

The radiographical process of projection of a complex human form onto a two-dimensional image plane gives rise to distortions and magnifications. It is important that any simulation used for educational purposes should correctly reproduce these. Images generated using a commercially available computer simulation widely used in radiography education (ProjectionVR^TM) were tested for geometric accuracy of projection in all planes.

Methods

An anthropomorphic skull phantom was imaged using standard projection radiography techniques and also scanned using axial CT acquisition. The data from the CT was then loaded into the simulator and the same projection radiography techniques simulated. Bony points were identified on both the real radiographs and the digitally reconstructed radiographs (DRRs). Measurements sensitive to rotation and magnification were chosen to check for rotation and distortion errors.

Results

The real radiographs and the DRRs were compared by four experienced observers and measurements taken between the identified bony points on each of the images obtained. Analysis of the mean observations shows that the measurement from the DRR matches the real radiograph +1.5 mm/-1.5 mm. The Bland Altman bias was 0.55 (1.26 STD), with 95% limits of agreement 3.01 to -1.91.

Conclusions

Agreement between the empirical measurements is within the reported error of cephalometric analysis in all three anatomical planes. The image appearances of both the real radiographs and DRRs compared favourably.

Advances in knowledge

The commercial computer simulator under test (ProjectionVR^TM) was able to faithfully recreate the image appearances of real radiography techniques, including magnification and distortion. Students using this simulation for training will obtain feedback likely to be useful when lessons are applied to real-world situations.