XAILUNG tackles oncology's black‑box AI problem with transparent multimodal models that fuse imaging and metadata for explainable support.
Speaker
Joseph Atte
Agenda
12:30 - Event start with welcome and introductions
12:40 - Talk: "XAILUNG – Explainable AI as a Professional Responsibility" followed by Q&A
13:30 - Event close
Synopsis
AI in oncology is held back by the “black box” problem: high accuracy with low transparency.
XAILUNG, developed by Joseph Ayodeji Atte, is a new multi modal deep learning framework that tackles this by combining 3D imaging, 2D pathology and clinical metadata using a strict late fusion architecture, achieving 94.2% accuracy on held out tests.
Built with explainability at its core, XAILUNG integrates Grad CAM and SHAP to provide fully auditable, clinically reviewable outputs. FP16 optimisation reduces inference time to around 10 seconds, enabling real time use and offering a scalable blueprint for digital twin modelling in other high stakes sectors.
This talk explores how transparent, multi stream AI can move clinical decision support systems and wider industry digital twins from experimental to deployable.
About the speaker
Joseph Ayodeji Atte is a rising AI Systems Engineer specialising in Explainable AI and Multimodal Deep Learning. A distinction graduate of the MSc Computer Science programme at Birmingham City University and originally from Kogi State, Nigeria, he is driven by a commitment to making intelligent systems transparent, accountable and human centred.
Joseph’s work spans advanced deep learning, full stack engineering and the design of audit ready AI systems for high stakes environments. His research interests sit at the intersection of technical innovation and social impact, with a focus on building AI that people can understand and trust. Beyond his engineering practice, Joseph is a multimedia storyteller who explores how technology can surface the narratives of underrepresented places and communities.
When he is not experimenting with new AI methods or creating digital content, he can often be found on the tennis court, pursuing his love for the game.
Our events are for adults aged 16 years and over.
This meeting is conducted in accordance with the BCS Code of Conduct for Meetings.
BCS is a membership organisation. If you enjoy this event, please consider joining BCS. You’ll be very welcome. You’ll receive access to many exclusive career development tools, an introduction to a thriving professional community and also help us Make IT Good For Society. Join BCS today
Please note: if you have any accessibility needs, please let us know via groups@bcs.uk, and we’ll work with you to make suitable arrangements.
For overseas delegates who wish to attend the event, please note that BCS does not issue invitation letters.
This event is brought to you by: Data Management specialist group.
