MEDISURE: Towards Assuring Machine Learning-based Medical Image Classifiers using Mixup Boundary Analysis

Byfield, Adam and Poulett, William and Jose, Anusha and Tyagi, Shatakshi and Shembekar, Smita and Qayyum, Adnan and Qadir, Adnan and Bilal, Muhammad (2024) MEDISURE: Towards Assuring Machine Learning-based Medical Image Classifiers using Mixup Boundary Analysis. In: ISBI 2024, 27th - 31th May 2024, Athens, Greece.

[thumbnail of _Camera_Ready__Medical_Image_Classification_Assurance__ISBI2024.pdf]
Preview
Text
_Camera_Ready__Medical_Image_Classification_Assurance__ISBI2024.pdf - Accepted Version

Download (1MB)

Abstract

Machine learning (ML) models are becoming integral in healthcare technologies, necessitating formal assurance methods to ensure their safety, fairness, robustness, and trustworthiness. However, these models are inherently error-prone, posing risks to patient health and potentially causing irreparable harm when deployed in clinics. Traditional software assurance techniques, designed for fixed code, are not directly applicable to ML models, which adapt and learn from curated datasets during training. Thus, there is an urgent need to adapt established software assurance principles such as boundary testing with synthetic data. To bridge this gap and enable objective assessment of ML models in real-world clinical settings, we propose Mix-Up Boundary Analysis (MUBA), a novel technique facilitating the evaluation of image classifiers in terms of prediction fairness. We evaluated MUBA using brain tumour and breast cancer classification tasks and achieved promising results. This research underscores the importance of adapting traditional assurance principles to assess ML models, ultimately enhancing the safety and reliability of healthcare technologies. Our code is available at \url{https://github.com/willpoulett/MUBA_pipeline}.

Item Type: Conference or Workshop Item (Paper)
Identification Number: 10.1109/ISBI56570.2024.10635870
Dates:
Date
Event
29 February 2024
Accepted
22 August 2024
Published Online
Subjects: CAH11 - computing > CAH11-01 - computing > CAH11-01-05 - artificial intelligence
Divisions: Faculty of Business, Law and Social Sciences > College of Accountancy, Finance and Economics
Faculty of Business, Law and Social Sciences > College of Business, Digital Transformation & Entrepreneurship
Depositing User: Muhammad Bilal
Date Deposited: 21 Jun 2024 13:54
Last Modified: 08 Nov 2024 14:12
URI: https://www.open-access.bcu.ac.uk/id/eprint/15560

Actions (login required)

View Item View Item

Research

In this section...