Medical Imaging Courses Research Articles

Integrating AI in College Education: Positive yet Mixed Experiences with ChatGPT

The integration of artificial intelligence (AI) chatbots into higher education marks a shift towards a new generation of pedagogical tools, mirroring the arrival of milestones like the internet. With the launch of ChatGPT-4 Turbo in November 2023, we developed a ChatGPT-based teaching application (https://chat.openai.com/g/g-1imx1py4K-chatge-medical-imaging) and integrated it into our undergraduate medical imaging course in the Spring 2024 semester. This study investigates the use of ChatGPT throughout a semester-long trial, providing insights into students’ engagement, perception, and the overall educational effectiveness of the technology. We systematically collected and analyzed data concerning students’ interaction with ChatGPT, focusing on their attitudes, concerns, and usage patterns. The findings indicate that ChatGPT offers significant advantages such as improved information access and increased interactivity, but its adoption is accompanied by concerns about the accuracy of the information provided and the necessity for well-defined guidelines to optimize its use.

Application of artificial intelligence-assisted image diagnosis software based on volume data reconstruction technique in medical imaging practice teaching

BackgroundIn medical imaging courses, due to the complexity of anatomical relationships, limited number of practical course hours and instructors, how to improve the teaching quality of practical skills and self-directed learning ability has always been a challenge for higher medical education. Artificial intelligence-assisted diagnostic (AISD) software based on volume data reconstruction (VDR) technique is gradually entering radiology. It converts two-dimensional images into three-dimensional images, and AI can assist in image diagnosis. However, the application of artificial intelligence in medical education is still in its early stages. The purpose of this study is to explore the application value of AISD software based on VDR technique in medical imaging practical teaching, and to provide a basis for improving medical imaging practical teaching.MethodsTotally 41 students majoring in clinical medicine in 2017 were enrolled as the experiment group. AISD software based on VDR was used in practical teaching of medical imaging to display 3D images and mark lesions with AISD. Then annotations were provided and diagnostic suggestions were given. Also 43 students majoring in clinical medicine from 2016 were chosen as the control group, who were taught with the conventional film and multimedia teaching methods. The exam results and evaluation scales were compared statistically between groups.ResultsThe total skill scores of the test group were significantly higher compared with the control group (84.51 ± 3.81 vs. 80.67 ± 5.43). The scores of computed tomography (CT) diagnosis (49.93 ± 3.59 vs. 46.60 ± 4.89) and magnetic resonance (MR) diagnosis (17.41 ± 1.00 vs. 16.93 ± 1.14) of the experiment group were both significantly higher. The scores of academic self-efficacy (82.17 ± 4.67) and self-directed learning ability (235.56 ± 13.50) of the group were significantly higher compared with the control group (78.93 ± 6.29, 226.35 ± 13.90).ConclusionsApplying AISD software based on VDR to medical imaging practice teaching can enable students to timely obtain AI annotated lesion information and 3D images, which may help improve their image reading skills and enhance their academic self-efficacy and self-directed learning abilities.

A four-prong approach for engaging biomedical engineering students

My involvement in a large medical imaging company for nearly 20 years shaped my approach to teaching biomedical engineering. These experiences are described in Medical Physics International Journal, 6,602–620, May 2021. At Boston University, I taught undergraduates using a four pronged approach. The first part included a “lessons learned” career overview lecture and discussion to incoming freshman. This talk emphasized shifting paradigms in medical device development and changing trends in research and development and how to best prepare for a biomedical engineering career by prudent course selection, practical experience and life-long networking. Second, I designed two ultrasound lab modules which were part of the mandatory physiology lab all juniors took. These laboratories provided condensed theory with hands-on experiments on imaging and Doppler processing/imaging and data analysis. Third, I taught ultrasound and medical imaging courses which included rigorous theory, applications and examples. My book, Diagnostic Ultrasound Imaging: Inside Out, second edition, is being used in ultrasound courses throughout the world. A new book and curriculum, coauthored with Peter Kaczkowski, and sponsored by Verasonics, is underway. Finally, for 15 years, I taught a usually two semester course in entrepreneurship, innovation and engineering design which culminated in a team-based senior project.

Application of Improved CNN Technology in Medical Imaging Course

The role of artificial intelligence technology in the medical field has become more and more important. As an important part of artificial intelligence technology, the CNN model in deep learning has become more and more widely used in the field of CT image recognition. In the process of recognizing CT images, the previous CNN model will have the consequences of low recognition accuracy and over fitting, resulting in less obvious recognition effect.This paper proposes an improved CT image recognition method based on 3-D CNN, a convolutional neural network for image classification mainly used to solve the correlation information between images and add new dimension information on human cancer tissue. The method saves valuable education resources on Chinese medicine, reduces the repetitive mechanical workload of medical college lecturers, and improves the efficiency of medical students' knowledge acquisition. Experimental results show that the accuracy of medical CT images can be improved by using 3D-CNN method, thus improving the prediction of the location of cancer areas during CT scans. Keywords: 3-D CNN model; CT image; depth Learning; medicine Education

Sleep Deprivation and Study Habits Effects toward Medical Imaging Students, UiTM Puncak Alam

This study aimed to investigate the effects of sleep deprivation and study habits during online distance learning (ODL) among students. The objective of this study is to evaluate the relationship between sleep deprivation and study habits with academic performance among students during ODL. A cross-sectional survey is used through an online platform. The questionnaire was distributed to 191 students in Medical Imaging course. The data being analyzed using SPSS software version 26. Most students had poor sleep (n=130, 68.1%) and poor study habits (n=136, 71.2%). There is no significant correlation between sleep deprivation (X2=0.31, df=2, p=0.855) and study habits (X2=1.26, df=2, p=0.533) on student's academic performance.

Impact of Team-Based Learning Versus Lecture-Based Learning on Chinese Radiology Education: A Scoping Review and Meta-Analysis

This meta-analysis aimed to evaluate the effectiveness of team-based learning in radiology education. Data sources and selection criteria Databases were searched from inception up to August 2019 and included Pubmed, Medline, Embase, China National Knowledge Infrastructure (CNKI), Chinese Wanfang Database, and Chinese VIP. Randomized trials comparing teaching approaches for medical imaging of which provide the outcomes of theoretical scores and/or practical scores were included. Data were extracted independently by two authors and double-checked for accuracy. Outcomes included knowledge scores and practical scores. We pooled data using random-effects meta-analysis. Twelve trials involving 1,371 participants were included. Team-based learning teaching method had positive impacts on theoretical scores compared with the lecture-based learning or traditional teaching method (SMD = 1.07, 95% CI [0.50, 1.63]) and it positively improved skill scores (SMD = 0.68, 95% CI [0.19, 1.17]). Team-based learning could not only improve theoretical and skill scores in medical imaging courses but also encourage students to learn by themselves. Participants believed team-based learning raised their learning interest, team cooperation ability, and interpersonal communication skills. The heterogeneity of the included studies must be noticed and large well-designed and well-conducted trials are urgently needed.

Evaluation of Multimedia Courseware-Assisted Teaching Effect of Medical Images Based on the Deep Learning Algorithm.

In order to improve the dynamic evaluation ability of medical image multimedia courseware-assisted teaching effect, the evaluation of medical image multimedia courseware-assisted teaching effect based on a deep learning algorithm is proposed. The statistical data analysis model of medical image multimedia courseware-assisted teaching effect is established to estimate its utilization rate and scale parameters. Based on the prediction of spatial attribute parameters, the classification big data mining model of medical image multimedia courseware-assisted teaching is constructed by using the deep learning algorithm, mining association rules and frequent item sets that can dynamically reflect the quality of medical image multimedia courseware-assisted teaching, and extracting the statistical feature of the dataset of constraint indicators of medical image multimedia courseware-assisted teaching effect to improve the teaching quality of medical imaging course. The simulation results show that this method has a better precision delivery effect, higher dynamic matching degree of teaching evaluation parameters, more than 90% reliability, and better clustering of statistical eigenvalues.

Innovating the Medical Imaging Course

Artificial intelligence (AI) and machine learning (ML), especially deep learning, have generated tremendous impacts throughout our society, including the tomographic medical imaging field. In contrast to computer vision and image analysis, which have been major application examples of deep learning and deal with existing images, tomographic medical imaging mainly produces cross-sectional or volumetric images of internal structures from sensor measurements. Recently, deep learning has started being actively developed worldwide for medical imaging, including both tomographic reconstruction and image analysis. While medical imaging is a well-established field, in which extensive teaching experience has been accumulated over the past few decades, updating the medical imaging course to reflect AI/ML influence is a new challenge given the rapidly changing landscape of AI-based medical imaging, particularly deep tomographic imaging. In the 2019 fall semester, the medical imaging course at Rensselaer Polytechnic Institute was modified to include an AI framework with positive feedback from students. Encouragingly, many students showed a strong motivation to learn AI in classes and hands-on projects, as confirmed in their survey reports. In the 2020 fall semester, we improved this course further, incorporating new advances. This article describes our teaching philosophy, practice, and considerations with respect to integrating deep learning, tomographic imaging, and hands-on programming to redefine the medical imaging course. Furthermore, given the persistent pandemic, online teaching and examination have become an integral part of higher education. These needs will be addressed as well, with the hope of developing an open course in the future.

Biomedical Imaging in the Undergraduate Science Curriculum

In recent years, physics (and mathematics) have become very critical and conspicuous contributors to biology and medicine. One notable reason is the indispensable role that sophisticated imaging techniques now play in fundamental biological research and in diagnosing and treating many serious diseases. In light of this, we recently developed an undergraduate course in which imaging serves as a foundation for integrating physics with material that is engaging and relevant, especially to students majoring in physics and/or the life sciences. Our course is in some respects similar to traditional medical imaging courses that focus on the physical basis of prominent medical imaging modalities, such as ultrasonography and magnetic resonance imaging (MRI). However, in addition to these and related techniques, our imaging course also deals extensively with optical microscopy. We included this imaging modality because undergraduates in the life sciences are extensively exposed to optical microscopy in teaching and research settings and because optics is an extremely important branch of applied physics. We also use a mix of lecture- and laboratory-based pedagogical approaches. It has been gratifying to find that the course is very enthusiastically received by students at our institution majoring in biology, biochemistry, chemistry, and/or physics; thus, here we describe some of our most popular lecture topics and associated experimental activities to help pave the way for other educators who are interested in teaching a similar course.

Application of case introduced method based on PACS system in medical imaging course

Objective To evaluate the teaching effects of case introduced method based on pic- ture archiving and communication system （ PACS ） system in medical imaging course. Methods Totally 148 students （ 2009 grade ） majored in five-year clinical medicine from Xiangya Medical College were divided into 10 groups; the 10 groups were taken randomly as control group （ n=75 ） and experimental group （ n=73 ）. Control group used traditional teaching methods （ film teaching ） while experimental group used case introduced method based on PACS system. Effects of teaching between were evaluated by questionnaire and test. χ^2 test was used to compare students＇ theoretical test scores, with α level = 0.05. Results Based on results of questionnaires, more students in experimental group than in control group hold that case introduced method based on PACS system can achieve the purpose of teaching, improve interests in learning, and strengthen the mastery of knowledge. Test scores showed that the percentage of students scored 90-100 and 80-89 （ respectively 14%, 75% ） in experimental group was significantly higher than that in control group （respectively 5%, 66% ） （χ^2 =17.932, P=O.O00 ）. Conclusions Application of case introduced method based on PACS system in medical imaging course not only improve students＇ motivation to learn and their clinica~ ability-, but also allow teachers to find and correct short- comings of students timely, therefore, it is worth promoting. Key words: Picture archiving and communication system; Case introduced method; Prac-tice teaching

An active learning approach to the physics of medical imaging

This paper describes an experimentally oriented medical imaging course where the students record, process and analyse 3D data of an unknown piece of formalin fixed porcine tissue hidden in agar in order to estimate the tissue types present in a selected 2D slice. The recorded planar X-ray, CT, MRI, ultrasound and SPECT images show the tissue in very different ways. The students can only estimate the tissue type by studying the physical principles of the imaging modalities. The true answer is later revealed by anatomical photographs obtained from physical slicing. The paper describes the phantoms and methods used in the course. Sample images recorded with the different imaging modalities are provided. Challenges faced by the students are outlined. Results of the course show high increase in competencies as judged from graded reports, low course drop-out rate, high pass-rate at the exam, high student participation and large student satisfaction.

Development of Online Ultrasound Instructional Module and Comparison to Traditional Teaching Methods

AbstractA Web‐based teaching device was constructed to deliver information on fundamentals of ultrasound imaging to approximately one‐half the students in an undergraduate medical imaging course, while the remaining students were taught the same material via traditional lectures and typed notes. The students participating in this study were separated randomly but in such a manner that prior achievement was statistically equivalent for the two groups. After approximately two weeks of instruction, an ultrasound imaging exam was administered. Results indicated no statistically significant difference in scores on homework assigned during the instructional period between the traditional and online groups. Similarly, there was no statistically significant difference in the average exam scores of students in the two groups. The traditional group required significantly more time on learning activities than did the online group. These results indicated that level of understanding was not affected by use of the online device, while efficiency of learning improved dramatically. Reasons reported by the students for the improved efficiency of the online method included flexibility in time usage and ability to cater to the individual, which came with the added responsibility of self‐discipline. The traditional teaching method, meanwhile, allowed interaction with and instant feedback from a professor and other students. In this study we have demonstrated that the nature of an online device yields a higher level of efficiency than traditional lectures, despite the inherent drawbacks of the approach. The effectiveness of this device could potentially be improved by implementing enhancements to increase the level of interaction for the user and to help with discipline and time management.

MRI electromagnetic field penetration in cylindrical objects

Magnetic Resonance Imaging information depends on the knowledge of the behavior of the transverse, radio frequency (RF) electromagnetic fields inside biological objects. Here we present exact results for the RF vector potential field inside and outside a cylindrical object that minics the human body. These results are obtained by solving Maxwell Equations with appropriate boundary conditions, and take into consideration the object conductivity and dielectric constant and the presence of a cylindrical RF uniform-current-carrying coil. A computer code that evaluates RF magnetic field phase and magnitude is presented for two cases of interest: for a longitudinal and for a φ-directed current. Each of those cases is studied in free space and in the presence of a metallic shielding. The symbolic code will be of use for order-of-magnitude calculations in the clinical world and, for pedagogical uses in medical imaging courses.