MIDL_Submission.pdf (2.38 MB)
Cell anomaly localisation using structured uncertainty prediction networks
conference contribution
posted on 2023-06-10, 04:19 authored by Boyko Vodenicharski, Samuel McDermott, Katherine Webber, Viola Introini, Pietro Cicuta, Richard Bowman, Ivor SimpsonIvor Simpson, Neill D F CampbellThis paper proposes an unsupervised approach to anomaly detection in bright-field or fluorescence cell microscopy, where our goal is to localise malaria parasites. This is achieved by building a generative model (a variational autoencoder) that describes healthy cell images, where we additionally model the structure of the predicted image uncertainty, rather than assuming pixelwise independence in the likelihood function. This provides a “whitened” residual representation, where the anticipated structured mistakes by the generative model are reduced, but distinctive structures that did not occur in the training distribution, e.g. parasites are highlighted. We employ the recently published Structured Uncertainty Prediction Networks approach to enable tractable learning of the uncertainty structure. Here, the residual covariance matrix is efficiently approximated using a sparse Cholesky parameterisation. We demonstrate that our proposed approach is more effective for detecting real and synthetic structured image perturbations compared to diagonal Gaussian likelihoods.
History
Publication status
- Published
File Version
- Accepted version
Journal
Proceedings of Machine Learning ResearchISSN
2640-3498Publisher
PMLRPage range
1285-1300Event name
Medical Imaging with Deep Learning (MIDL 2022)Event location
Zürich, SwitzerlandEvent type
conferenceEvent date
6-8 July 2022Department affiliated with
- Informatics Publications
Full text available
- Yes
Peer reviewed?
- Yes
Legacy Posted Date
2022-07-26First Open Access (FOA) Date
2022-07-27First Compliant Deposit (FCD) Date
2022-07-26Usage metrics
Categories
No categories selectedKeywords
Licence
Exports
RefWorks
BibTeX
Ref. manager
Endnote
DataCite
NLM
DC