.
3D Technologies for Medical Applications
Study Course Description
Course Description Statuss:Approved
Course Description Version:5.00
Study Course Accepted:15.10.2024 11:40:44
| Study Course Information | |||||||||
| Course Code: | FK_077 | LQF level: | Level 7 | ||||||
| Credit Points: | 2.00 | ECTS: | 3.00 | ||||||
| Branch of Science: | Physics | Target Audience: | Dentistry; Rehabilitation; Medical Technologies; Medicine | ||||||
| Study Course Supervisor | |||||||||
| Course Supervisor: | Jevgenijs Proskurins | ||||||||
| Study Course Implementer | |||||||||
| Structural Unit: | Department of Physics | ||||||||
| The Head of Structural Unit: | |||||||||
| Contacts: | Riga, 26a Anninmuizas boulevard, Floor No.1, Rooms 147 a and b, fizika rsu[pnkts]lv, +371 67061539 | ||||||||
| Study Course Planning | |||||||||
| Full-Time - Semester No.1 | |||||||||
| Lectures (count) | 1 | Lecture Length (academic hours) | 2 | Total Contact Hours of Lectures | 2 | ||||
| Classes (count) | 10 | Class Length (academic hours) | 3 | Total Contact Hours of Classes | 30 | ||||
| Total Contact Hours | 32 | ||||||||
| Study course description | |||||||||
| Preliminary Knowledge: | Knowledge of informatics at the level of the secondary school programme. | ||||||||
| Objective: | To train students in spatial modelling, the creation, acquisition, improvement and preparation of spatial anatomical models for 3D printing. To familiarise students with different spatial modelling capabilities and software, to provide the possibility for students to create and print digital spatial models of different complexities. It is expected that students who have completed the study course will be able to independently develop and prepare spatial models for 3D printing using data from radiology examinations, will be able to apply the acquired knowledge in their professional activities. | ||||||||
| Topic Layout (Full-Time) | |||||||||
| No. | Topic | Type of Implementation | Number | Venue | |||||
| 1 | Introduction to the 3D technology course: Importance of 3D technologies in different industries, short history and development. Introduction to 3D printing technology: benefits and applications, types, challenges and limitations of 3D printing processes and materials. Introduction to 3D modelling: Fundamentals of 3D modelling techniques and software tools, research of various industries using 3D modelling, such as architecture, product design and medicine. | Lectures | 1.00 | computer room | |||||
| 2 | Introduction to image segmentation. Image segmentation role in radiology. Role in diagnostics, treatment planning and research. Foundations of medical imaging. Overview of medical imaging methods (CT, MRI, US). 3D image segmentation process. Pre-processing. Acquisition of features. Segmentation methods. Challenges. Application of 3D image segmentation in radiology. Ethical and legal considerations. Advantages of 3D image segmentation in radiology. Future directions. | Classes | 1.00 | computer room | |||||
| 3 | Medical imaging and 3D modelling, 3D printing for use in medicine, advanced applications of 3D modelling and 3D printing in medicine. Methods for converting medical images into 3D models. Considerations about accuracy and resolution in medical 3D models. Examples of 3D modelling in medical research and clinical practice. Practical tasks. | Classes | 1.00 | computer room | |||||
| 4 | Application of machine learning (ML) in medical planning, imaging/3D model based diagnostics and imaging, medical simulations. Overview of ML algorithms for classification and regression. Types of radiological examination images and their properties. Feature acquisition and selection methods for med. images. ML applications in radiology, including image segmentation and classification. Application of programming language Python to import, process, and visualise radiological examination files. | Classes | 1.00 | computer room | |||||
| 5 | Automatic segmentation, segmentation principles and algorithms, generation of spatial models from segmentation result, artificial intelligence (AI) concept and its role in 3D technologies. Segmentation of radiological examinations using pre-trained neural networks. Working with Jupyter Notebook, connecting to a supercomputer, importing and processing data on a supercomputer. | Classes | 1.00 | computer room | |||||
| 6 | Basic parametric and direct modelling of 3D models, 3D modelling from 2D sketches/drawings or surface scan images, recognition of spatial object, basic functions in 3D modelling using OnShape, reverse engineering. | Classes | 1.00 | computer room | |||||
| 7 | Modelling of personalised medical devices, medical use of implants and prostheses, including their historical development, types, materials used and comparison of traditional and personalised solutions. Modelling of implant prostheses. Hip implant. Patient anatomy for precise suitability and functioning. Biomechanical factors for stability and durability. Selection of materials for biocompatibility and durability. Integration with existing anatomical structures. | Classes | 1.00 | computer room | |||||
| 8 | Modelling of surgical templates for precision surgery, use of surgical templates, types and benefits thereof. | Classes | 2.00 | computer room | |||||
| 9 | Work on the graduation project. Practical experience with 3D modelling software. Individual project demonstrating the medical use of 3D modelling and printing. | Classes | 2.00 | computer room | |||||
| Assessment | |||||||||
| Unaided Work: | Practical tasks on segmenting radiological examinations and processing 3D models. To assess the overall quality of the study course, the student must complete the course evaluation questionnaire on the Student Portal. | ||||||||
| Assessment Criteria: | Active participation in the practical classes. Independent learning 50%. Successfully passed examination in the form of text in the e-learning environment accounting for 50% of the final assessment. | ||||||||
| Final Examination (Full-Time): | Exam | ||||||||
| Final Examination (Part-Time): | |||||||||
| Learning Outcomes | |||||||||
| Knowledge: | To provide students with insight and practical knowledge in 3D scanning and modelling, which students could potentially encounter in the future in their professional environment, thereby increasing their competitiveness. | ||||||||
| Skills: | As a result of the study course, students will be able to use the acquired knowledge of 3D scanning and modelling in order to be able to work practically with various 3D modelling programmes, as well as to be able to apply these technologies in practice. It is expected that students who have completed the study course will be able to independently develop and prepare spatial models for printing using data from radiology examinations, will be able to apply the acquired knowledge in their professional activities. As a result of completing the study course, students will be able to use the available 3D scanning and modelling technologies, will be able to assess the current situation in 3D technologies, predict its development directions. | ||||||||
| Competencies: | 1. Independently develops new – individually suitable for patients – unique digital models of implants and prostheses and prepares these models for production (uses and adapts technologies for manufacturing implants/prostheses). (3.1. Creation of digital content; 3.2. Integration and redevelopment of digital content; 5.2. Identification of needs and technological solutions; 5.3. Creative use of digital technologies; DigComp 7) 2. Segments CT, CBCT and MRI examinations and creates personalised 3D models of anatomical structures, which can be used in planning the individual therapy of patients. (3.1. Creation of digital content; 3.2. Integration and redevelopment of digital content; 5.3. Creative use of digital technologies; DigComp 7) 3. Uses and adapts scripts of various programming languages, e.g. Python for automated segmentation of anatomical structures adapted to each patient’s individual medical history and available radiological examinations. (3.1. Creation of digital content; 3.2. Integration and redevelopment of digital content; 3.4. Programming; 4.2. Protection of personal data and privacy; 5.3. Creative use of digital technologies) 4. Creates unique and specially adapted therapy solutions for patients (3D surgical planning, creation of implant models), develops these solutions in cases of limited data volume (limitations of radiological examinations) by combining various segmentation and 3D modelling software, e.g. Fusion 360, Blender, Meshmixer and 3-Matic Mimics Innovation Suite. (3.1. Creation of digital content; 3.2. Integration and redevelopment of digital content; 5.2. Collaboration using digital technologies; DigComp 7). | ||||||||
| Bibliography | |||||||||
| No. | Reference | ||||||||
| Required Reading | |||||||||
| 1 | Introduction to Machine Learning with Python. by Andreas C. Müller, Sarah Guido. Released September 2016. Publisher(s): O'Reilly Media, Inc. | ||||||||
| 2 | 3D Deep Learning with Python. by Xudong Ma, Vishakh Hegde, Lilit Yolyan. Released October 2022. Publisher(s): Packt Publishing | ||||||||
| Additional Reading | |||||||||
| 1 | Richard Szeliski. Computer Vision: Algorithms and Applications. 2nd ed. The University of Washington, Springer, 2022 | ||||||||
| 2 | Geoff Dougherty. Digital Image Processing for Medical Applications. California State University, Channel Islands, April 2009. | ||||||||
