Back to Search
Start Over
Explainable Anatomical Shape Analysis Through Deep Hierarchical Generative Models
Explainable Anatomical Shape Analysis Through Deep Hierarchical Generative Models
- Source :
- IEEE Trans Med Imaging
- Publication Year :
- 2020
- Publisher :
- Institute of Electrical and Electronics Engineers (IEEE), 2020.
-
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 high-throughput analysis of normal anatomy and pathology in large-scale studies of volumetric imaging.<br />Comment: Accepted for publication in IEEE Transactions on Medical Imaging (TMI)
- Subjects :
- QA75
FOS: Computer and information sciences
Computer Science - Machine Learning
Computer science
Computer Vision and Pattern Recognition (cs.CV)
Feature extraction
Population
Computer Science - Computer Vision and Pattern Recognition
Latent variable
Hippocampus
09 Engineering
Article
Machine Learning (cs.LG)
030218 nuclear medicine & medical imaging
03 medical and health sciences
0302 clinical medicine
Discriminative model
Alzheimer Disease
FOS: Electrical engineering, electronic engineering, information engineering
Humans
Segmentation
Electrical and Electronic Engineering
education
Interpretability
education.field_of_study
Radiological and Ultrasound Technology
business.industry
Deep learning
Image and Video Processing (eess.IV)
Pattern recognition
Electrical Engineering and Systems Science - Image and Video Processing
QP
Magnetic Resonance Imaging
Computer Science Applications
Nuclear Medicine & Medical Imaging
08 Information and Computing Sciences
Artificial intelligence
business
Software
Shape analysis (digital geometry)
Subjects
Details
- ISSN :
- 1558254X and 02780062
- Volume :
- 39
- Database :
- OpenAIRE
- Journal :
- IEEE Transactions on Medical Imaging
- Accession number :
- edsair.doi.dedup.....02973443d271b95838de124c07cdf769
- Full Text :
- https://doi.org/10.1109/tmi.2020.2964499