BMET5933: Biomedical Image Analysis (2021 - Semester 1)

Download UoS Outline

Unit: BMET5933: Biomedical Image Analysis (6 CP)
Mode: Normal-Day
On Offer: Yes
Level: Postgraduate
Faculty/School: School of Biomedical Engineering
Unit Coordinator/s: Dr Kumar, Ashnil
Session options: Semester 1
Versions for this Unit:
Campus: Camperdown/Darlington
Pre-Requisites: None.
Brief Handbook Description: Biomedical imaging technology is a fundamental element of both clinical practice and biomedical research, enabling the visualisation of biological characteristics and function often in a non-invasive fashion. The advancement of digital scanning technologies alongside the development of computational tools has driven significant progress in medical image analysis tools that support clinical decisions and the analysis of data from biological experiments. The focus of this unit will be the development of fundamental computational skills and knowledge in biomedical imaging, including data acquisition, formats, visualisation, segmentation, feature extraction, and machine learning based image analysis.

On completion of this unit, students will be able to engineer and develop solutions for different biomedical imaging tasks encountered across a variety of use cases: clinical practice (e.g., computerised disease detection and diagnosis), research (e.g., cell video analysis), and industry (e.g., fabrication of customised implants from patient image data).
Assumed Knowledge: An understanding of biology (1000-level), experience with programming (ENGG1801, ENGG1810, BMET2922 or BMET9922).
Timetable: BMET5933 Timetable
Time Commitment:
# Activity Name Hours per Week Sessions per Week Weeks per Semester
1 Lecture 2.00 1 13
2 Tutorial 1.00 1 13
3 Laboratory 2.00 1 13
4 Independent Study 4.00 13
T&L Activities: Lectures will focus on examining different aspects of biomedical image analysis.

Tutorials will provide an opportunity to consolidate theoretical knowledge from lectures through exercises.

Laboratories (in computer labs) will provide an opportunity to translate theoretical knowledge into practice through the implementation of biomedical image analysis techniques. Most labs will have a challenge-driven structure: students will be given a set of problems and will have to creatively apply the knowledge of image analysis that have gained to address those problems.

Independent study will be necessary to review and consolidate weekly lecture material, complete tutorial or laboratory exercises, and to complete assessment tasks.

Attributes listed here represent the key course goals (see Course Map tab) designated for this unit. The list below describes how these attributes are developed through practice in the unit. See Learning Outcomes and Assessment tabs for details of how these attributes are assessed.

Attribute Development Method Attribute Developed
Students are required to understand and explain the mathematical theories behind image analysis algorithms, both in laboratory exercises and in practical assessments. Based on these theories, students will have to rationally select the appropriate algorithms for the specific problem. (1) Maths/ Science Methods and Tools (Level 3)
Students are given scenario(s) that require them to use various components and tools to create a pipeline to process a set of medical imaging data. Students have to implement and construct appropriate methods & tools given the requirements and constraints in the given setting. (2) Engineering/ IT Specialisation (Level 4)
Students design and implement a pipeline of image analysis processes. They will describe the integration of these processes to encompass a software framework for specific application scenarios, identifying both strengths and limitations, and how these can be addressed through new inventions in research literature. (3) Problem Solving and Inventiveness (Level 3)
Students are required to perform requirements analysis through the practical assessment. They have to identify implicit & explicit requirements in a given project brief, and how they translate to different software functions.

Students are required to practice their written and oral communication skills through the assessments. They need to articulate the technical means through which their software addresses a given problem, and the justification for their design decisions. They should be able to discuss and draw insights from the experimental results gathered from the performance analysis of their implemented software.
(6) Communication and Inquiry/ Research (Level 4)

For explanation of attributes and levels see Engineering & IT Graduate Outcomes Table 2018.

Learning outcomes are the key abilities and knowledge that will be assessed in this unit. They are listed according to the course goal supported by each. See Assessment Tab for details how each outcome is assessed.

(6) Communication and Inquiry/ Research (Level 4)
1. Identify and assess the strengths and limitations of biomedical image analysis algorithms from research literature
2. Describe and document the process used to design and develop a biomedical image analysis pipeline, in oral and written form
3. Interpret and communicate experimental metrics to explain the performance of biomedical image analysis algorithms
(3) Problem Solving and Inventiveness (Level 3)
4. Analyse end-user and task-based requirements to define the functional and performance requirements of biomedical imaging software tools
5. Combine biomedical imaging analysis algorithms to address image processing and image-based prediction tasks
(2) Engineering/ IT Specialisation (Level 4)
6. Understand and apply a variety of image processing techniques (segmentation, registration, fusion, feature extraction) across a variety of biomedical imaging contexts.
7. Implement software solutions for medical image processing tasks using existing software packages and libraries.
(1) Maths/ Science Methods and Tools (Level 3)
8. Explain the mathematical underpinnings of medical image processing algorithms in the context of different tasks.
9. Appraise the effectiveness of different medical image analysis algorithms and tools using standard performance metrics.
Assessment Methods:
# Name Group Weight Due Week Outcomes
1 Assignment: Image Processing No 20.00 Week 6 2, 3, 4, 5, 6, 7, 9,
2 Quiz No 20.00 Week 7 1, 3, 4, 8, 9,
3 Assignment: Classification No 20.00 Week 12 2, 3, 4, 5, 6, 7, 9,
4 Exam No 40.00 Exam Period 1, 3, 4, 8, 9,
Assessment Description: • Assignment: Image Processing – students will implement a software tool for processing medical image data (e.g., performing segmentation), preparing a brief report on its performance. The software functionality and the associated analysis in the report will be assessed.

• Quiz – a paper-based mid-semester quiz covering materials from lectures, tutorials, and laboratories.

• Assignment: Classification – students will implement a software tool for making a diagnostic prediction from medical image data, preparing a brief report on its performance. The software functionality and the associated analysis in the report will be assessed.

• Written exam: Final examination covering all materials in lectures, tutorials, laboratories, and assignments.
Assessment Feedback: The teaching team will provide feedback on the assessment tasks. Assignment results will be published on Canvas. Students are required to check their results. Any errors or omissions must be reported to the unit coordinator, with appropriate evidence, within 5 working days (a week) of being published; 5 days after being published, marks are considered to have been confirmed and will not subsequently be altered.
Policies & Procedures: This course will use text-based similarity detecting software (Turnitin) for all text-based written assignments. Deadlines for assignments are set on the assumption that students may experience minor setbacks caused by sickness, computer breakdown etc. In this context, ‘minor’ means ‘causing a delay of up to three working days’. Extensions will not be granted for minor setbacks.

Late work will incur a penalty of 5% of the total marks per day (or part thereof); work that is more than 10 days late will not be marked. Students who have a genuine misadventure should make an application for Special Consideration.

Note that the "Weeks" referred to in this Schedule are those of the official university semester calendar

Week Description
Week 1 Lecture: Introduction to the unit, learning outcomes, and assessments
Tutorial: Introduction to Assignment case studies, and expectations of assignments
Lab: Introduction to software and tools to be used during the semester
Week 2 Lecture: Medical image acquisition – scanners, devices, physics
Tutorial: Imaging properties (resolution, bit-depth, partial volume effects) and formats (DICOM)
Lab: Input/output pipelines and data transformation
Week 3 Lecture: Medical image processing fundamentals – signals, contrast, windows
Tutorial: Processing fundamentals (denoising, resampling, windowing) and analysis techniques
Lab: Implementing analysis pipelines - overview
Week 4 Lecture: Medical image segmentation – thresholding, region growing, shape models, atlases, neural networks
Lab: Segmentation theory and performance analysis (Dice, Jaccard, Hausdorff)
Lab: Implementing segmentation techniques
Week 5 Lecture: Medical image visualisation – 2D and 3D
Tutorial: Visualisation theory - opacity, transfer functions
Lab: Implementing visualisation
Week 6 Lecture: Medical image registration and fusion – landmark, rigid and non-rigid, intermixing
Tutorial: Registration and fusion theory
Lab: Integrating segmentation, registration, fusion, and visualisation
Assessment Due: Assignment: Image Processing
Week 7 Lecture: Quiz
Tutorial: Seminar Discussion (Assignment: Image Processing)
Lab: Demonstration (Assignment: Image Processing)
Assessment Due: Quiz
Week 8 Lecture: Image feature extraction - semantic and agnostic, radiomics, shape, texture
Tutorial: Understanding and analysing medical imaging features
Lab: Implementation of feature extraction
Week 9 Lecture: Artificial intelligence in medical imaging
Tutorial: Supervised, unsupervised, and reinforcement learning
Lab: Implementing prediction tools
Week 10 Lecture: Convolutional neural networks and deep learning in medical imaging
Tutorial: Convolutional neural networks
Lab: Implementing a transfer-learned CNN
Week 11 Lecture: Putting it all together – designing pipelines
Lab: Pipeline design and analysis
Lab: Additional topics on CNNs
Week 12 Lecture: Putting it all together – implementing pipelines
Tutorial: Pipelines in clinical environments
Lab: Implementing a pipeline with a CNN
Assessment Due: Assignment: Classification
Week 13 Lecture: Review – exam preparation
Tutorial: Seminar Discussion (Assignment: Classification)
Lab: Demonstration (Assignment: Classification)
Exam Period Assessment Due: Exam

Course Relations

The following is a list of courses which have added this Unit to their structure.

Course Year(s) Offered
Biomedical Mid-Year 2018, 2019, 2020, 2021
Biomedical/ Project Management 2019, 2020, 2021
Biomedical 2018, 2019, 2020, 2021
Biomedical / Arts 2017, 2018, 2019, 2020, 2021
Biomedical / Commerce 2017, 2018, 2019, 2020, 2021
Biomedical / Medical Science 2017
Biomedical / Music Studies 2017
Biomedical / Project Management 2017, 2018
Biomedical /Science 2017, 2018, 2019, 2020, 2021
Biomedical/Science (Health) 2018, 2019, 2020, 2021
Biomedical / Law 2017, 2018, 2019, 2020, 2021
Biomedical/Science (Medical Science Stream) 2018, 2019, 2020, 2021
Master of Engineering 2019, 2020, 2021
Master of Professional Engineering (Accelerated) (Biomedical) 2019, 2020, 2021
Master of Professional Engineering (Biomedical) 2018, 2019, 2020, 2021

Course Goals

This unit contributes to the achievement of the following course goals:

Attribute Practiced Assessed
(6) Communication and Inquiry/ Research (Level 4) Yes 32%
(3) Problem Solving and Inventiveness (Level 3) Yes 18%
(2) Engineering/ IT Specialisation (Level 4) Yes 16%
(1) Maths/ Science Methods and Tools (Level 3) Yes 34%

These goals are selected from Engineering & IT Graduate Outcomes Table 2018 which defines overall goals for courses where this unit is primarily offered. See Engineering & IT Graduate Outcomes Table 2018 for details of the attributes and levels to be developed in the course as a whole. Percentage figures alongside each course goal provide a rough indication of their relative weighting in assessment for this unit. Note that not all goals are necessarily part of assessment. Some may be more about practice activity. See Learning outcomes for details of what is assessed in relation to each goal and Assessment for details of how the outcome is assessed. See Attributes for details of practice provided for each goal.