A new e-learning platform for radiology education (RadEd)

One of the key elements of e-learning platforms is the content provided to the students. Content creation is a time demanding task that requires teachers to prepare material taking into account that it will be accessed on-line. Moreover, the teacher is restricted by the functionalities provided by the e-learning platforms. In contexts such as radiology where images have a key role, the required functionalities are still more specific and difficult to be provided by these platforms. Our purpose is to create a framework to make teacher's tasks easier, specially when he has to deal with contents where images have a main role. In this paper, we present RadEd, a new web-based teaching framework that integrates a smart editor to create case-based exercises that support image interaction such as changing the window width and the grey scale used to render the image, taking measurements on the image, attaching labels to images and selecting parts of the images, amongst others. It also provides functionalities to prepare courses with different topics, exercises and theory material, and also functionalities to control students' work. Different experts have used RadEd and all of them have considered it a very useful and valuable tool to prepare courses where radiological images are the main component. RadEd provides teachers functionalities to prepare more realistic cases and students the ability to make a more specific diagnosis.

The role of Artificial intelligence in the assessment of the spine and spinal cord

Artificial intelligence (AI) application development is underway in all areas of radiology where many promising tools are focused on the spine and spinal cord. In the past decade, multiple spine AI algorithms have been created based on radiographs, computed tomography, and magnetic resonance imaging. These algorithms have wide-ranging purposes including automatic labeling of vertebral levels, automated description of disc degenerative changes, detection and classification of spine trauma, identification of osseous lesions, and the assessment of cord pathology. The overarching goals for these algorithms include improved patient throughput, reducing radiologist workload burden, and improving diagnostic accuracy. There are several pre-requisite tasks required in order to achieve these goals, such as automatic image segmentation, facilitating image acquisition and postprocessing. In this narrative review, we discuss some of the important imaging AI solutions that have been developed for the assessment of the spine and spinal cord. We focus on their practical applications and briefly discuss some key requirements for the successful integration of these tools into practice. The potential impact of AI in the imaging assessment of the spine and cord is vast and promises to provide broad reaching improvements for clinicians, radiologists, and patients alike.

IVET, an Interactive Veterinary Education Tool

The use of e-learning tools for medical teaching is a common practice, but similar tools do not exist for veterinary teaching. In this article, we present a fully web-based e-learning platform, denoted Interactive Veterinary Education Tool (IVET), which is designed to support teaching and learning in veterinary science. To make content creation easier, it provides theory, exercise, and image editors with functionalities to prepare exercises and theoretical content including 2-dimensional (2D) images, 3-dimensional (3D) models, and Digital Imaging and Communications in Medicine (DICOM) files, which can be manipulated by the users. It supports different types of exercises such as quizzes, 2D and 3D location exercises, and exercises based on multiplanar reconstructions from a set of animal scans (DICOM files). In addition, a correction strategy is defined for each type of exercise to automatically correct them and avoid the teacher to perform this process manually. All data are stored in a central repository, including the material prepared by the teacher and the solutions sent by the students, from which the system is able to compute some statistics, such as the evolution of the students and the final score of a course. By this way, teachers can use this information to carry out continuous assessment. All the resources such as 2D images, 3D models, and DICOM files are stored in the multimedia repository, included in the central one. To obtain real 3D models from animal scans, a manual segmentation process is also described. The platform has been reviewed by a group of teachers through an experimental test, and its functionalities have been compared with other veterinary e-learning tools from the literature.

Introducing Online Continuing Education in Radiology for General Practitioners

The aim of this study was to determine whether e-learning as a new teaching methodology was acceptable for general practitioners in continuous education courses of radiology. Generally, these courses are face-to-face with the corresponding time and place limitations. To overcome these limitations, we transformed one of these courses to an online one evaluating its acceptance. The course was about thorax radiology and it was delivered to 249 participants. The experiment was carried out in two phases: Phase 1, as a pilot testing with 12 general practitioners (G1), and Phase 2, with 149 general practitioners (G2), 12 radiologists (G3) and 76 medical residents (G4). All participants evaluated the course design, the delivering e-learning platform, and the course contents using a five-point Likert scale (satisfaction level from 1 to 5). Collected data was analysed using t, Mann-Whitney U and Kruskal-Wallis tests. In Phase 1, the rounded scores of all questions except one surpassed 3.5. In Phase 2, all the rounded scores surpassed 4.0 indicating that a total agreement on all items was achieved. All collected impressions indicate the high acceptance of the proposed methodology.

Asynchronous online learning as a key tool to adapt to new educational needs in radiology during the COVID-19 pandemic

The risk of contagion and the lockdown caused by the COVID-19 pandemic forced a change in teaching methodologies in radiology. New knowledge about the disease that was being acquired on a daily basis needed to be rapidly spread worldwide, but the restrictions imposed made it difficult to share this information. This paper describes the methodology applied to design and launch a practice-based course on chest X-ray suggestive of COVID-19 right after the pandemic started, and aims to determine whether asynchronous online learning tools for radiology education are useful and acceptable to general practitioners and other medical personnel during a pandemic. The study was carried out from April to October 2020 and involved 2632 participants. Pre- and post-testing was used to assess the participants' gain of knowledge in the course content (paired t-tests and chi-squared tests of independence). A five-point Likert scale questionnaire inspired by the technological acceptance model (TAM) was provided to evaluate the e-learning methodology (ANOVA tests). The results from the pre- and post-tests showed that there were significant differences in the scores before and after completing the course (sample size = 2632, response rate = 56%, p<0.001). As for the questionnaire, all questions surpassed 4.5 out of 5, including those referring to perceived ease of use and perceived usefulness, and no significant differences were found between experienced and inexperienced participants (sample size = 2535, response rate = 53%, p=0.85). The analysis suggests that the applied methodology is flexible enough to adapt to complex situations, and is useful to improve knowledge on the subject of the course. Furthermore, a wide acceptance of the teaching methodology is confirmed for all technological profiles, pushing for and endorsing a more widespread use of online platforms in the domain of radiology continuing education.

Deep learning for the quality control of thermoforming food packages

Quality control is a key process designed to ensure that only products satisfying the defined quality requirements reach the end consumer or the next step in a production line. In the food industry, in the packaging step, there are many products that are still evaluated by human operators. To automate the process and improve efficiency and effectiveness, computer vision and artificial intelligence techniques can be applied. This automation is challenging since specific strategies designed according to the application scenario are required. Focusing on the quality control of the sealing and closure of matrix-shaped thermoforming food packages, the aim of the article is to propose a deep-learning-based solution designed to automatically perform the quality control while satisfying production cadence and ensuring 100% inline inspection of the products. Particularly, the designed computer vision system and the image-based criteria defined to determine when a product has to be accepted or rejected are presented. In addition, the vision control software is described with special emphasis on the different convolutional neural network (CNN) architectures that have been considered (ResNet18, ResNet50, Vgg19 and DenseNet161, non-pre-trained and pre-trained on ImageNet) and on the specifically designed dataset. To test the solution, different experiments are carried out in the laboratory and also in a real scenario, concluding that the proposed CNN-based approach improves the efficiency and security of the quality control process. Optimal results are obtained with the pre-trained DenseNet161, achieving false positive rates that range from 0.03 to 0.30% and false negative rates that range from 0 to 0.07%, with a rejection rate between 0.64 and 5.09% of production, and being able to detect at least 99.93% of the sealing defects that occur in any production. The modular design of our solution as well as the provided description allow it to adapt to similar scenarios and to new deep-learning models to prevent the arrival of faulty products to end consumers by removing them from the automated production line.

BeST-Graft viewer, a new system to improve the bone allograft-recipient matching process

INTRODUCTION

Tissue establishments are responsible for processing, testing, preserving, storing, and distributing allografts from donors to be transplanted into recipients. In some situations, a matching process is required to determine the allograft that best fits the recipient. Allograft morphology is a key consideration for the matching process. The manual procedures applied to obtain these parameters make the process error-prone.

MATERIAL AND METHODS

A new system to manage bone allograft-recipient matching for tissue establishments is proposed. The system requires bone allografts to be digitalized and the resulting images to be stored in a DICOM file. The system provides functionalities to: (i) manage DICOM files (registered in the PACs) from both allografts and recipients; (ii) reconstruct 3D models from DICOM images; (iii) explore 3D models using 2D, 3D, and multiplanar reconstructions; (iv) take allograft and recipient measurements; and (v) visualize and interact with recipient and allograft data simultaneously. The system has been installed in the Barcelona Tissue Bank (Banc de Sang i Teixits), which has digitalized the bone allografts to test the system.

RESULTS

A use case with a femur is presented to test all the viewer functionalities. In addition, the recipient-allograft workflow is evaluated to show the steps of the procedure where the viewer can be used.

CONCLUSIONS

The bone allograft-recipient matching procedure can be optimized using software tools with functionalities to visualize, interact, and take measurements.