BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//Talks.cam//talks.cam.ac.uk//
X-WR-CALNAME:Talks.cam
BEGIN:VEVENT
SUMMARY:Deep Learning Approaches for Label-Free Tumour Image Segmentation 
 Spectroscopy in Cancer Diagnosis - Thomas Hartigan
DTSTART:20250520T160000Z
DTEND:20250520T164500Z
UID:TALK231166@talks.cam.ac.uk
CONTACT:Pietro Lio
DESCRIPTION:In this talk\, I will present results showing the performance 
 of MSE\, PCA->LDA\, PCA->XGBoost\, XGBoost and novel Ensemble Scale-Invari
 ant CNN models in the context of tissue classification for cancer diagnosi
 s using Fourier Transform Infrared Spectroscopy biopsy images. I will then
  discuss the explainability of those models using LIME [1] to reveal waven
 umber ranges of particular importance for this classification task\, befor
 e extending the CRIME framework [2] using custom semi-supervised VAE model
 s to identify clustered explanation patterns. Finally\, I will show how th
 ese clustered explanation patterns can be used to produce a model-agnostic
 \, fully explainable linear predictive model for classification purposes.\
 n\n[1] Ribeiro\, Marco Tulio\, Sameer Singh\, and Carlos Guestrin. ‘“W
 hy Should I Trust You?”: Explaining the Predictions of Any Classifier’
 . arXiv\, 9 August 2016. https://doi.org/10.48550/arXiv.1602.04938.\n\n[2]
  Zaki\, Jihan K.\, Jakub Tomasik\, Jade A. McCune\, Sabine Bahn\, Pietro L
 iò\, and Oren A. Scherman. ‘Explainable Deep Learning Framework for SER
 S Bio-Quantification’. arXiv\, 12 November 2024. https://doi.org/10.4855
 0/arXiv.2411.08082.\n
LOCATION:Lecture Theatre 2\, Computer Laboratory\, William Gates Building
END:VEVENT
END:VCALENDAR