Enhancing medical imaging education: integrating computing technologies, digital image processing and artificial intelligence DOI Creative Commons
Sibusiso Mdletshe, Alan Wang

Journal of Medical Radiation Sciences, Journal Year: 2024, Volume and Issue: unknown

Published: Nov. 7, 2024

The rapid advancement of technology has brought significant changes to various fields, including medical imaging (MI). This discussion paper explores the integration computing technologies (e.g. Python and MATLAB), digital image processing enhancement, segmentation three-dimensional reconstruction) artificial intelligence (AI) into undergraduate MI curriculum. By examining current educational practices, gaps limitations that hinder development future-ready professionals are identified. A comprehensive curriculum framework is proposed, incorporating essential computational skills, advanced techniques state-of-the-art AI tools, such as large language models like ChatGPT. proposed aims improve quality education significantly better equip students for future professional practice challenges while enhancing diagnostic accuracy, improving workflow efficiency preparing evolving demands field.

Language: Английский

Designing experiential learning activities with generative artificial intelligence tools for authentic assessment DOI
David Ernesto Salinas-Navarro, Eliseo Luis Vilalta-perdomo, Rosario Michel‐Villarreal

et al.

Interactive Technology and Smart Education, Journal Year: 2024, Volume and Issue: 21(4), P. 708 - 734

Published: May 2, 2024

Purpose This article investigates the application of generative artificial intelligence (GenAI) in experiential learning for authentic assessment higher education. Recognized its human-like content generation, GenAI has garnered widespread interest, raising concerns regarding reliability, ethical considerations and overall impact. The purpose this study is to explore transformative capabilities limitations learning. Design/methodology/approach uses “thing ethnography” “incremental prompting” delve into perspectives ChatGPT 3.5, a prominent model. Through semi-structured interviews, research prompts 3.5 on critical aspects such as conceptual clarity, integration educational settings practical applications within context assessment. design examines GenAI’s potential contributions reflective thinking, hands-on genuine assessments, emphasizing importance responsible use. Findings findings underscore enhance Specifically, highlights capacity contribute experiences facilitation assessments. Notably, emphasizes significance use harnessing purposes. Originality/value showcases operations management education, specifically lean health care. offers insights by exploring implications specific domain through thing ethnography incremental prompting. Additionally, proposes future directions, contributing originality work opening avenues further exploration

Language: Английский

Citations

15
The American Society of Radiologic Technologists (ASRT) AI educator survey: A cross-sectional study to explore knowledge, experience, and use of AI within education DOI Creative Commons
Nikolaos Stogiannos, Michael Jennings,

Craig St George

et al.

Journal of medical imaging and radiation sciences, Journal Year: 2024, Volume and Issue: 55(4), P. 101449 - 101449

Published: July 13, 2024

Artificial Intelligence (AI) is revolutionizing medical imaging and radiation therapy. AI-powered applications are being deployed to aid Medical Radiation Technologists (MRTs) in clinical workflows, decision-making, dose optimisation, a wide range of other tasks. Exploring the levels AI education provided across United States crucial prepare future graduates deliver digital future. This study aims assess educators' knowledge, current state educational provisions, perceived challenges around education, important factors for advancements.

Language: Английский

Citations

6
Transformative learning with ChatGPT: analyzing adoption trends and implications for business management students in India DOI
Tapas Sudan,

Arjun Hans,

Rashi Taggar

et al.

Interactive Technology and Smart Education, Journal Year: 2024, Volume and Issue: 21(4), P. 735 - 772

Published: July 13, 2024

Purpose The intricate dynamics of ChatGPT adoption among Indian students are discussed while exploring the factors outlined by Unified Theory Acceptance and Use Technology 2 (UTAUT2). By assessing these factors, this study aims to unravel their impact on behavioral intention use ChatGPT. Design/methodology/approach While evaluating ChatGPT's dynamics, analyses UTAUT2 core perceived benefits. Real-time data from 638 business management in India were collected through purposive sampling a cross-sectional survey. An in-depth examination using IBM SPSS AMOS revealed patterns that regulate reception educational settings. Findings Habit emerges as powerful predictor, which aligns with Loop Theory's cues, routine rewards. Perceived benefits significantly influence adoption, traditional like performance expectancy social exert no influence. insignificance effort challenges conventional understanding, unveiling novel aspects student tech adoption. Social implications There is need for guidelines ensure fair responsible students. presents advantages task automation personalized learning, integrating it into existing education system requires careful planning harness its effectively. Originality/value With recent introduction Generative-AI tools, understanding acceptance application essential. This research sheds light emerging technology, emphasizing importance analyzing technology successful

Language: Английский

Citations

6
Decoding Wisdom: Evaluating ChatGPT's Accuracy and Reproducibility in Analyzing Orthopantomographic Images for Third Molar Assessment DOI Creative Commons
Ana Suárez, Simone Arena,

Alberto Calzada

et al.

Computational and Structural Biotechnology Journal, Journal Year: 2025, Volume and Issue: 28, P. 141 - 147

Published: Jan. 1, 2025

Language: Английский

Citations

0
The performance of Chat GPT 4.0o in medical imaging evaluation: a preliminary investigation DOI Creative Commons
Elio Arruzza,

C. Evangelista,

Minh Chau

et al.

Journal of Educational Evaluation for Health Professions, Journal Year: 2024, Volume and Issue: 21, P. 29 - 29

Published: Oct. 30, 2024

This study investigated the performance of ChatGPT-4.0o in evaluating quality positioning radiographic images. Thirty radiographs depicting a variety knee, elbow, ankle, hand, pelvis, and shoulder projections were produced using anthropomorphic phantoms uploaded to ChatGPT-4.0o. The model was prompted provide solution identify any errors with justification offer improvements. A panel radiographers assessed solutions for based on established criteria, grading scale 1–5. In only 20% projections, correctly recognized all justifications offered correct suggestions improvement. most commonly occurring score 3 (9 cases, 30%), wherein at least 1 specific error provided mean 2.9. Overall, low accuracy demonstrated, receiving partially solutions. findings reinforce importance robust radiography education clinical experience.

Language: Английский

Citations

3
Comparing ChatGPT 4.0’s Performance in Interpreting Thyroid Nodule Ultrasound Reports Using ACR-TI-RADS 2017: Analysis Across Different Levels of Ultrasound User Experience DOI Creative Commons
Katharina Wakonig,

Simon Barisch,

Leonard Kozarzewski

et al.

Diagnostics, Journal Year: 2025, Volume and Issue: 15(5), P. 635 - 635

Published: March 6, 2025

Background/Objectives: This study evaluates ChatGPT 4.0's ability to interpret thyroid ultrasound (US) reports using ACR-TI-RADS 2017 criteria, comparing its performance with different levels of US users. Methods: A team medical experts, an inexperienced user, and 4.0 analyzed 100 fictitious reports. ChatGPT's was assessed for accuracy, consistency, diagnostic recommendations, including fine-needle aspirations (FNA) follow-ups. Results: demonstrated substantial agreement experts in assessing echogenic foci, but inconsistencies other such as composition margins, were evident both analyses. Interrater reliability between ranged from moderate almost perfect, reflecting AI's potential also limitations achieving expert-level interpretations. The user outperformed a nearly perfect the highlighting critical role traditional training standardized risk stratification tools TI-RADS. Conclusions: showed high specificity recommending FNAs lower sensitivity follow-ups compared student. These findings emphasize supportive tool rather than replacement human expertise. Enhancing AI algorithms could improve clinical utility, enabling better support clinicians managing nodules improving patient care. highlights promise current diagnostics, advocating refinement integration into workflows. However, it emphasizes that must not be compromised, is essential identifying correcting AI-driven errors.

Language: Английский

Citations

0
Structural Chain of Thoughts for Radiology Education DOI
Akash Awasthi, Beom Sun Chung, Tuan A. Vu

et al.

Published: Jan. 1, 2025

Language: Английский

Citations

0
Інноватика в професійному становленні та розвитку майбутніх вчителів DOI Creative Commons
Оксана Цюняк,

Наталія Яремчук,

Ольга Галюка

et al.

Insight the psychological dimensions of society, Journal Year: 2024, Volume and Issue: 11, P. 143 - 163

Published: May 1, 2024

Метою емпіричного дослідження є з’ясування та обґрунтування психологічних змістових параметрів інноватики у професійному становленні розвитку майбутніх учителів. Завданнями є: визначення кореляційних зв’язків професійної готовності здобувачів до інноваційної діяльності з незалежними змінними; статистично достовірних відмінностей між досліджуваними вибірках бакалаврів (група І) і магістрантів ІІ); порівняння досліджуваних груп високим низьким рівнями сформованості коефіцієнтів інноватики. Методи: ретроспективне аналізування, узагальнення, систематизація порівняння; авторська анкета “Професійна готовність діяльності” (ГІД) (Цюняк, 2021); методика “Діагностика мотиваційної структури особистості” (ДМСО) (Мільман, 1990); “Здібності педагога творчого саморозвитку” (ЗПТС) (Нікішина, 2009). Результати. З’ясовано, що вибірками I) ІІ) немає запропонованих параметрах. Позитивну тенденцію зафіксовано групі I в кількісному коефіцієнті KKI (М=.68; SD=.22; Me=.68) ІІ – якісному ЯKI (М=.62; SD=.23; Me=.61). Встановлено, коефіцієнти мають по чотири достовірні кореляційні зв’язки змінними: творча активність, соціальна корисність, активний саморозвиток, зупинений саморозвиток (р<.050; р<.010). Констатовано відмінності групах із кількісного коефіцієнта (ККІ) якісного (ЯКІ). Дискусія висновки. Пояснено, наявність достовірного зв’язку ЯКІ параметром “соціальна корисність” свідченням того, досліджувані готові нести соціальну відповідальність за нововведення, займати зрілу позицію працювати на довготривалу перспективу. Рекомендовано отримані емпіричні результати взяти уваги організаторам освітнього процесу гарантам профільних освітньо-наукових програм, які відповідають навчально-професійну підготовку вчителів.

Citations

3
ChatGPT performance on radiation technologist and therapist entry to practice exams DOI Creative Commons
Ryan Duggan, Kaitlyn M. Tsuruda

Journal of medical imaging and radiation sciences, Journal Year: 2024, Volume and Issue: 55(4), P. 101426 - 101426

Published: May 25, 2024

BackgroundThe aim of this study was to describe the proficiency ChatGPT (GPT-4) on certification style exams from Canadian Association Medical Radiation Technologists (CAMRT), and its performance across multiple exam attempts.MethodsChatGPT prompted with questions CAMRT practice in disciplines radiological technology, magnetic resonance (MRI), nuclear medicine radiation therapy (87-98 each). attempted each five times. Exam evaluated using descriptive statistics, stratified by discipline question type (knowledge, application, critical thinking). Light's Kappa used assess agreement answers attempts.ResultsUsing a passing grade 65 %, passed technology only once (20 %), MRI all times (100 three (60 %). ChatGPT's best knowledge except therapy. It performed worst thinking questions. Agreement responses attempts substantial within MRI, medicine, almost perfect for therapy.ConclusionChatGPT able pass technologists therapists, but varied between disciplines. The algorithm demonstrated it provided attempts. Future research evaluating standardized tests should consider repeated measures.

Language: Английский

Citations

3
Trend of Using ChatGPT in Learning Process and Character Education: A Systematic Literature Review DOI Creative Commons

Mahsun Mahsun,

Mudzakkir Ali,

Ifada Retno Ekaningrum

et al.

International Journal of Learning Teaching and Educational Research, Journal Year: 2024, Volume and Issue: 23(5), P. 387 - 402

Published: May 30, 2024

Generative pre-trained transformers (ChatGPTs) have become an increasingly interesting topic in education, particularly student character development. However, the use of ChatGPT learning and education faces significant challenges. This systematic literature review article utilized PRISMA protocol by using current from PubMed, IEEE, Xplore, Scopus 2017-2023 that presents analysis challenges, opportunities, solutions related to context education. The results showed challenges include limited context, reliance on baseline data, lack direct supervision. there were also such as creativity designing scenarios, scalability large amounts potential a personal assistant for students. Several proposed address these including developing specialized models, implementing filters or supervision mechanisms, user Understanding has been essential harness full improving

Language: Английский

Citations

1