- Department: Electronic Engineering
- Module co-ordinator: Dr. Manish Chauhan
- Credit value: 20 credits
- Credit level: M
- Academic year of delivery: 2023-24
The module aims to equip students with practical knowledge of pattern recognition and signal analysis in medical imaging (via different modalities like radiography, fluoroscopy, mammography, nuclear medical imaging, nuclear medicine planar imaging, and ultrasound imaging etc.). Introduce students with concepts of computer-aided diagnosis (CAD), which comprise of four general schemes for image analysis: (i) Preprocessing, (ii) Segmentation, (iii) Feature extraction, and (iv) Feature classification. Further, the module will provide students with image analysis via artificial intelligence modelling and deep learning based algorithms. Finally, the benefits of CAD will be appreciated by students, like (i) improving the time efficiency for image diagnosis, (ii) ameliorating subjectivity of traditional histopathology image analysis, (iii) mathematical and consistent approach for recording images, (iv) reduce the workload for a highly experienced radiologist as CAD can help improve the accuracy and interpretation time for less experienced physicians. The results of this study will enable students to apply their knowledge to develop future healthcare technologies and equipment. Learning will be achieved through case studies, exercises, models, and laboratory exercises.
|A||Semester 1 2023-24|
Subject content aims:
Introducing practical knowledge of pattern recognition and signal analysis in medical imaging (via different modalities like radiography, fluoroscopy, mammography, nuclear medical imaging, nuclear medicine planar imaging, and ultrasound imaging etc.).
Develop understanding for methods of diagnosis by CAD applications in Breast (Ultrasound, MR, FFDM), Chest (CT Thorax, PA/Lateral Xray), GI (Virtual colonoscopy, liver metastases), whole body imaging (PET/CT), Neuro.
Introduce and practice the CAD algorithm for image analysis, Part-1: (i) Preprocessing, (ii) Segmentation, (iii) Feature extraction, and (iv) Feature classification. Part -2: Classify (using AI neural network, semantic pattern recognition, rule based classifier methods) obtained images in lesions and false-positive categories.
Graduate skills aims:
Learn basic image pre-processing; where filters are applied to enhance the target in question and suppress everything else.
Learn segmentation of body regions; like separating lung from muscle, fat, bone, mediastinum and external body. Focusing on specific regions for CAD through slice-by-slice evaluation.
Learn initial lesion identification through candidate generation (identifying unhealthy candidate regions of interest) by understanding water density of image nodules, surface normal vectors, morphology, clustered segments, Bayesian model selections.
Learn feature extraction through AI and deep learning algorithms for CAD (like AI neural network, semantic pattern recognition, rule based classifier methods). Finally, classifying regions of interest into lesions and false-positive categories for efficient diagnosis.
Develop image processing methods with subject knowledge from AI/machine learning, MATLAB programming, Python programming etc.
After successful completion of this module, students will:
Understand and be able to apply Computer-Aided Design (CAD) algorithms
Have developed an integrated understanding of basic anatomy and bioimaging modalities.
Be able to critically evaluate biomedical images, their production, characteristics, and process them through machine learning algorithms (collect, process, store, and transfer data).
Understand and be able to apply the methodology of understanding radiology images and utilise a standard CAD algorithm for its analysis.
Be able to discuss physiological changes from interaction of radiation and the human tissues.
Be able to demonstrate good laboratory practice.
Be familiar with health and safety in the wider context including relevant legislation as it affects product development.
Laboratory practice: Students will be expected to follow good laboratory practice procedures.
Health and safety: Students will be introduced to health and safety in the wider context including relevant legislation as it affects product development.
Teamwork: Students will be introduced to the need to establish communications, coordination and control mechanisms within their group to help deliver efficiently and effectively. The groups will be guided in the establishment of these by their academic supervisor. They will be expected to describe their approach and any problems they encountered in their individual report.
Research: Students will determine the research needs for their project and seek out appropriate resources. They will be expected to maintain accurate and professional records of their research and report it through accurate and full referencing.
Communication: Students will be expected to document the work undertaken in their project to a professional standard, producing appropriate information for technical and non-technical audiences. Examples of technical information include specifications, test reports, etc. Examples of non-technical information include user manuals, etc.
Ethics: Groups will be expected to decide, in conjunction with their group academic supervisor, what ethical approval is required and then produce and gain appropriate approval for it.
Project management: Students will be introduced to formal project management tools and required to produce a planned and managed project plan.
Meetings & meetings management: Students will be expected to record their weekly meetings and track actions allocated. They will be introduced to the concept of Design Reviews and be expected to hold them as part of the project.
Risk management: Students will be introduced to risk management as a manageable activity, including how to quantify risks and use a risk register as a tool to manage risks. They will produce a risk register for their project.
|Task||Length||% of module mark|
Essay : Individual Report
Group work : Group Project Demonstration
Students will be graded based on their individual performance. Each student will be tasked with a specific role on the imaging modality.
|Task||Length||% of module mark|
Essay : Individual Report Reassessment
'Feedback’ at a university level can be understood as any part of the learning process which is designed to guide your progress through your degree programme. We aim to help you reflect on your own learning and help you feel more clear about your progress through clarifying what is expected of you in both formative and summative assessments. A comprehensive guide to feedback and to forms of feedback is available in the Guide to Assessment Standards, Marking and Feedback.
The School of PET aims to provide some form of feedback on all formative and summative assessments that are carried out during the degree programme. In general, feedback on any written work/assignments undertaken will be sufficient so as to indicate the nature of the changes needed in order to improve the work. The School will endeavour to return all exam feedback within the timescale set out in the University's Policy on Assessment Feedback Turnaround Time. The School would normally expect to adhere to the times given, however, it is possible that exceptional circumstances may delay feedback. The School will endeavour to keep such delays to a minimum. Please note that any marks released are subject to ratification by the Board of Examiners and Senate. Meetings at the start/end of each term provide you with an opportunity to discuss and reflect with your supervisor on your overall performance to date.
Regular lectures, workshop and lab sessions will help students to engage with concepts of biomedical engineering. Project reports and associated presentations will help students to develop problem solving, critical analysis and public speaking skills.
Opportunities for obtaining formative feedback include lab work with spoken feedback and problem-solving, help during lab demonstrations, speaking about assignment plans with academics, revision sessions and workshops, and pre-presentation briefing sessions.
Coursework: Weekly lectures followed by individual/group project demonstrations will help students to gain feedback on understanding the key module material covered in the lectures. Emails to the Module Coordinator with Questions / Comments will be answered as soon as possible.
Suzuki, K., 2013. Machine learning in computer-aided diagnosis of the thorax and colon in CT: a survey. IEICE transactions on information and systems, 96(4), pp.772-783.
De Azevedo-Marques, P.M., Mencattini, A., Salmeri, M. and Rangayyan, R.M. eds., 2017. Medical image analysis and informatics: computer-aided diagnosis and therapy. CRC Press.
Li, Q., & Nishikawa, R.M. (Eds.). (2015). Computer-Aided Detection and Diagnosis in Medical Imaging (1st ed.). CRC Press. https://doi.org/10.1201/b18191
Spratt, J.D., Salkowski, L.R., Loukas, M., Turmezei, T., Weir, J. and Abrahams, P.H., 2020. Weir & abrahams' imaging atlas of human anatomy E-book. Elsevier Health Sciences.