Hello, if you have any need, please feel free to consult us, this is my wechat: wx91due

DTS306TC Security, Privacy and Ethics

Coursework 2

Submission deadline: 5 pm China Time (UTC+8 Beijing) on Sat. 14th Dec 2024

Percentage in final mark: 70%

Maximum score: 100 marks

Learning outcomes assessed:

B: Evaluating the potential risks and benefits of AI technologies on privacy and personal data

C: Understanding the importance of fairness in AI systems and its implications

Late policy: 5% of the total marks available for the assessment shall be deducted from the assessment mark for each working day after the submission date, up to a maximum of five working days.

Risks:

•     Please  read  the   coursework  instructions  and  requirements  carefully.  Not  following  these instructions and requirements may result in loss of marks.

•     Plagiarism results in award of ZERO mark.

•    The formal procedure for submitting coursework at XJTLU is strictly followed. Submission link on Learning Mall will be provided in due course. The submission timestamp on Learning Mall will be used to check late submission.

Overview

Artificial intelligence has great effect on modern lives. In this coursework, the theme on framework design of new medical image-based bias-mitigated and fair computer-aided diagnosis system will be investigated and explored. The coursework consists of two parts. In Part 1, you need to complete a report based given theme. In Part 2, you need to explain your design via video presentation.

Part 1 (Individual Report: 70 marks)

Healthcare industry is rich of electronic (digital) medical data from different modalities. Deep learning has revolutionized the use of machine learning in healthcare industry by leveraging on the model’s automatic feature extraction and learning. To date, deep models have been applied for numerous computer-aided diagnosis tasks such as prediction, detection and classification. Despite its promising outlook, deep learning- based computer-aided diagnosis models still fail to earn the trust of medical doctors. In fact, there are reports of inaccurate missed diagnoses due to bias error, lack of understanding about the underlying mechanism of deep learning, and miscalibration in real practice.

Therefore, there is an open call for fair and transparent computer-aided diagnosis model for trustworthy smart healthcare.

The aim of this task is to empirically assess the current status of computer-aided diagnosis, technologies, challenges and solutions in smart healthcare, and research questions in AI fairness to design a towards innovative bias-mitigated and  fair deep   learning medical image-based computer-aided diagnosis model framework design with predefined traits. Hence, you are required to equip yourselves with the understanding about the specific domain of medical imaging. Besides, you need to apply the knowledge acquired from the lectures and tutorials to complete this coursework. You also need to do literature review to identify further relevant information that is helpful to develop your report content.

Part 2 (Individual Presentation: 30 marks) Task Instructions:

(1) Prepare and record a short individual presentation video of 5 minutes+/-5%. Your presentation should be clear, should be in no more than 10 Powerpoint slides and should not take beyond 5 minutes+/-5%. The presentation should address the followings:

i.  To introduce and explain the significance of your proposed towards innovative bias- mitigated  and fair  deep learning medical image-based   computer-aided diagnosis model framework design.

ii. To  explain how your proposed  model design can effectively  become General Data Protection Regulation (GDPR) and IEEE “Human Standards” with Implications for AI compliance in order to promote your design to overseas  healthcare  market successfully.

Report Format:

Cover Page: This should include the Assessment Number, Assessment Title, Student Name, Student ID and Student Email

Body of the report: This should include all the relevant section headings to address each section as indicated above and marking rubrics.

References: Both your in-text and the references included in the “References” section at the end of the report should adhere strictly to the IEEE reference style.

Formatting requirement:

• Use multiple spacing : 1.08 and spacing after: 8pt;

• Use a standard 12-point font, font type: Tahoma

• Use “Justify” body text

• Put your page numbers at the top right (except the cover page)

• Most importantly, always run a spelling and grammar check; however, remember, such checks may not pick up all errors. You should still edit your work manually and carefully.

Referencing:

It is compulsory to use IEEE reference style for citing and referencing research. Reference list is excluded from the imposed word limit.

Presentation Format:

Students are not requested to submit their presentation slides to the submission system. However, they must  present  their Powerpoint presentation slides clearly throughout the video presentation period. Otherwise, the presentation will not be evaluated and ZERO marks will be given.

All video presentation must be uploaded to the Mediasite and attach the video presentation link at the last page of report. It is student responsibility to attach the link properly and apply the right accessibility setting in Mediasite to ensure examiners can access to the video presentation link in their computers during marking.