Imperial College London
Portrait Picture

DrAntonioSimoes Monteiro de Marvao

Faculty of Medicine, Institute of Clinical Sciences

Honorary Clinical Senior Lecturer
 
 
 
//

Contact

 

+44 (0)20 3313 1510antonio.de-marvao

 
 
//

Location

 

Robert Steiner MRI UnitHammersmith HospitalHammersmith Campus

//

Summary

 

Publications

Citation

BibTex format

@unpublished{Biffi:2020,
author = {Biffi, C and Doumou, G and Duan, J and Prasad, SK and Cook, SA and O, Regan DP and Rueckert, D and Cerrolaza, JJ and Tarroni, G and Bai, W and De, Marvao A and Oktay, O and Ledig, C and Le, Folgoc L and Kamnitsas, K},
publisher = {arXiv},
title = {Explainable anatomical shape analysis through deep hierarchical generative models.},
url = {https://arxiv.org/abs/1907.00058v2},
year = {2020}
}
Download

RIS format (EndNote, RefMan)

TY  - UNPB
AB  - Quantification of anatomical shape changes currently relies on scalar global indexes which are largely insensitive to regional or asymmetric modifications. Accurate assessment of pathology-driven anatomical remodeling is a crucial step for the diagnosis and treatment of many conditions. Deep learning approaches have recently achieved wide success in the analysis of medical images, but they lack interpretability in the feature extraction and decision processes. In this work, we propose a new interpretable deep learning model for shape analysis. In particular, we exploit deep generative networks to model a population of anatomical segmentations through a hierarchy of conditional latent variables. At the highest level of this hierarchy, a two-dimensional latent space is simultaneously optimised to discriminate distinct clinical conditions, enabling the direct visualisation of the classification space. Moreover, the anatomical variability encoded by this discriminative latent space can be visualised in the segmentation space thanks to the generative properties of the model, making the classification task transparent. This approach yielded high accuracy in the categorisation of healthy and remodelled left ventricles when tested on unseen segmentations from our own multi-centre dataset as well as in an external validation set, and on hippocampi from healthy controls and patients with Alzheimer's disease when tested on ADNI data. More importantly, it enabled the visualisation in three-dimensions of both global and regional anatomical features which better discriminate between the conditions under exam. The proposed approach scales effectively to large populations, facilitating highthroughput analysis of normal anatomy and pathology in largescale studies of volumetric imaging.
AU  - Biffi,C
AU  - Doumou,G
AU  - Duan,J
AU  - Prasad,SK
AU  - Cook,SA
AU  - O,Regan DP
AU  - Rueckert,D
AU  - Cerrolaza,JJ
AU  - Tarroni,G
AU  - Bai,W
AU  - De,Marvao A
AU  - Oktay,O
AU  - Ledig,C
AU  - Le,Folgoc L
AU  - Kamnitsas,K
PB  - arXiv
PY  - 2020///
TI  - Explainable anatomical shape analysis through deep hierarchical generative models.
UR  - https://arxiv.org/abs/1907.00058v2
UR  - http://hdl.handle.net/10044/1/77445
ER  -
Download