Artificial Intelligence (AI) in Imaging

Study Course Description

Course Description Statuss:Approved

Course Description Version:6.00

Study Course Accepted:02.01.2024 10:17:09

Study Course Information
Course Code:		RAK_027		LQF level:		Level 7
Credit Points:		2.00		ECTS:		3.00
Branch of Science:		Clinical Medicine; Roentgenology and Radiology		Target Audience:		Medicine; Medical Technologies; Dentistry; Rehabilitation; Public Health
Study Course Supervisor
Course Supervisor:		Maija Radziņa
Study Course Implementer
Structural Unit:		Department of Radiology
The Head of Structural Unit:
Contacts:		Riga, 2 Hipokrata Street, RSU Study Centre, Administration, rakrsu[pnkts]lv, +371 67547139
Study Course Planning
Full-Time - Semester No.1
Lectures (count)		0	Lecture Length (academic hours)		0	Total Contact Hours of Lectures		0
Classes (count)		0	Class Length (academic hours)		0	Total Contact Hours of Classes		0
Total Contact Hours								0
Full-Time - Semester No.2
Lectures (count)		8	Lecture Length (academic hours)		2	Total Contact Hours of Lectures		16
Classes (count)		8	Class Length (academic hours)		2	Total Contact Hours of Classes		16
Total Contact Hours								32
Study course description
Preliminary Knowledge:
Informatics, Anatomy.
Objective:
The study course "Artificial intelligence in imaging" is intended for in-depth understanding of the versatile application of radiology data in clinical medicine using digitization tools. With the development of technology, the volume of radiology images and data has grown rapidly, increasing the workload of radiologists and requiring more detailed solutions and innovative approaches to solutions for various clinical needs, including the speed of data circulation. In this context, artificial intelligence (AI), which is increasingly integrated into daily practice in today's radiology, offers ample opportunities to improve the diagnostic process of radiology. AI can help prioritize patients with more severe and acute pathologies for faster diagnosis, choose appropriate image acquisition protocols, automate various measurements, image analysis and interpretation, compare current and previous examination images, automate examination description with voice-to-text conversion programs and optimize conclusion standardization, thereby reducing the consumption of resources and the time until the diagnosis is obtained and, therefore, the timely initiation of therapy through a multifaceted approach. This allows radiologists to pay attention to the most complex cases earlier and to facilitate and speed up the diagnostic process, thus improving the quality of patient care. Visual information modeling for individual needs is also needed in stomatology, rehabilitation and traumatology-orthopedics, as well as in other sectors, and AI solutions are becoming more relevant in the evaluation of implants and biomechanics.
Topic Layout (Full-Time)
No.	Topic			Type of Implementation		Number	Venue
1	What is artificial intelligence? Structural elements, metrics and terminology of artificial intelligence			Lectures		1.00	E-Studies platform
2	Data processing			Lectures		1.00	E-Studies platform
3	Practical seminar on data processing and artificial intelligence training I			Classes		1.00	computer room
4	Practical seminar on data processing and artificial intelligence training II			Classes		1.00	computer room
5	Intro into Technology, Radioanatomy and Pathology			Lectures		1.00	E-Studies platform
6	Application of artificial intelligence in work organization, image acquisition and analysis			Lectures		1.00	E-Studies platform
7	Ethical aspects of AI			Lectures		1.00	E-Studies platform
8	AI in medical imaging screening			Lectures		1.00	E-Studies platform
9	Structured descriptions in medicine, radiology and their importance for artificial intelligence			Lectures		1.00	E-Studies platform
10	Welcoming AI			Lectures		1.00	E-Studies platform
11	Clinical cases, AI application I			Classes		1.00	clinical base
12	Clinical cases, AI application II			Classes		1.00	clinical base
13	Clinical cases, AI application III			Classes		1.00	clinical base
14	Clinical cases, AI application IV			Classes		1.00	clinical base
15	Clinical cases, AI application V			Classes		1.00	clinical base
16	Clinical cases, AI application VI			Classes		1.00	clinical base
Assessment
Unaided Work:
Independent work - know how to practically apply MI types in imaging diagnostics (examples from medical imaging data). In order to evaluate the quality of the study course as a whole, the student must fill out the study course evaluation questionnaire on the Student Portal.
Assessment Criteria:
Credited if the specified types of AI are used in the imaging example; exam.
Final Examination (Full-Time):		Exam
Final Examination (Part-Time):
Learning Outcomes
Knowledge:		1. Students should be able to critically evaluate AI claims and understand the connection between models and clinical realities. 2. Students have a robust conceptual understanding of AI and the structure of clinical data science.
Skills:		1. Students have been involved in hands-on workshops with the focus - recognizing appropriate potential applications of AI to health data. 2. Understanding how to discern between different methods that can be applied to data (e.g. the distinction between prediction and causal inference approaches).
Competencies:		1. Uses and adapts algorithms for segmentation of imaging data, correction of results obtained by automated programs, choosing the most appropriate program for the task/body part (3D slicer, Lunit, Gleamer), classifies and knows how to apply data types and recommend new solutions for the basic principles of annotation. 2. Describes the most common investigation workflow problems that can be solved with artificial intelligence (list of cases, prioritization features, post-processing algorithm solutions). Offers strategies for how AI can be applied in health data processing - image diagnostics and creating standardized conclusions. 3. Analyzes pathologies and structures in DICOM format that are diagnosed with the help of AI software. 4. Apply Data Security regulations to a certain clinical situations.
Bibliography
No.	Reference
Required Reading
1	Tang X. The role of artificial intelligence in medical imaging research. BJR Open. 2019, Nov 28;2(1): 20190031.
2	Zenker S, Strech D, Ihrig K, et.al. Data protection-compliant broad consent for secondary use of health care data and human biosamples for (bio)medical research: Towards a new German national standard. Journal of Biomedical Informatics, 2022, 131:104096.
3	Merel Huisman, Elmar Kotter, Peter M. A. van Ooijen Erik R. Ranschaert. Members: Tugba Akinci D’ Antonoli, Marcio Aloisio Bezzera Cavalcanti Rockenbach, Vera Cruz e Silva, Emmanouil Koltsakis, Pinar Yilmaz. The eBook for Undergraduate Education in Radiology. Chapter- AI in Radiology
4	Hosny, A., Parmar, C., Quackenbush, J. et.al. Artificial intelligence in radiology. Nat Rev Cancer 18, 500–510. 2018
Additional Reading
1	Geis, J.R., Brady, A., Wu, C.C., et.al. Ethics of artificial intelligence in radiology: summary of the joint European and North American multisociety statement. Insights Imaging 10, 101. 2019.
2	Nobel, J.M., Kok, E.M. & Robben, S.G.F. Redefining the structure of structured reporting in radiology. Insights Imaging 11, 10. 2020.
3	Strohm L, Hehakaya C, Ranschaert ER, et.al. Implementation of artificial intelligence (AI) applications in radiology: hindering and facilitating factors. Eur Radiol, 2020, 30:5525–5532.
4	Simpson SA, Cook TS. Artificial Intelligence and the Trainee Experience in Radiology. Journal of the American College of Radiology, 2020, 17:1388–1393.
5	Gabriel Chartrand, Phillip M. Cheng, Eugene Vorontsov, et.al. Deep Learning: A Primer for Radiologists. RadioGraphics, 2017 37:7, 2113-2131.
6	Phillip M. Cheng, Emmanuel Montagnon, Rikiya Yamashita, Ian Pan, et.al. Deep Learning: An Update for Radiologists. RadioGraphics, 2021 41:5, 1427-1445.
7	Bradley J. Erickson, Panagiotis Korfiatis, Zeynettin Akkus, and Timothy L. Kline. Machine Learning for Medical Imaging. RadioGraphics, 2017 37:2, 505-515.
8	European Society of Radiology (ESR). The new EU General Data Protection Regulation: what the radiologist should know. Insights Imaging. 2017 Jun;8(3):295-299.