Explainable anatomical shape analysis through deep hierarchical generative models
File(s)
Accepted version
Author(s)
Biffi, carlo
Cerrolaza Martinez, Juan Jose
Tarroni, Giacomo
Bai, wenjia
Simoes Monteiro de Marvao, antonio
Type
Journal Article
Abstract
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.
Date Issued
2020-06-01
Date Acceptance
2019-12-21
Citation
IEEE Transactions on Medical Imaging, 2020, 39 (6), pp.2088-2099
ISSN
0278-0062
Publisher
Institute of Electrical and Electronics Engineers
Start Page
2088
End Page
2099
Journal / Book Title
IEEE Transactions on Medical Imaging
Volume
39
Issue
6
Copyright Statement
© 2020 IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other uses, in any current or future media, including reprinting/republishing this material for advertising or promotional purposes, creating new collective works, for resale or redistribution to servers or lists, or reuse of any copyrighted component of this work in other works.
Sponsor
British Heart Foundation
The Academy of Medical Sciences
Imperial College Healthcare NHS Trust- BRC Funding
British Heart Foundation
Imperial College Healthcare NHS Trust- BRC Funding
Grant Number
RE/08/002/23906
nil
RDC04
NH/17/1/32725
RDB02
Subjects
08 Information and Computing Sciences
09 Engineering
Nuclear Medicine & Medical Imaging
Publication Status
Published
Date Publish Online
2020-01-06