Related papers: A Conditional Flow Variational Autoencoder for Controllable Synthesis of Virtual Populations of Anatomy

A Conditional Flow Variational Autoencoder for Controllable Synthesis of Virtual Populations of Anatomy

URL: http://arxiv.org/abs/2306.14680v2
Date: Fri, 28 Jul 2023 10:11:19 GMT
Title: A Conditional Flow Variational Autoencoder for Controllable Synthesis of Virtual Populations of Anatomy
Authors: Haoran Dou, Nishant Ravikumar and Alejandro F. Frangi
Abstract summary: We propose a conditional variational autoencoder (cVAE) with normalising flows to boost the flexibility and complexity of the approximate posterior learnt. We demonstrate the performance of our conditional flow VAE using a data set of cardiac left ventricles acquired from 2360 patients.
Score: 76.20367415712867
License: http://creativecommons.org/licenses/by/4.0/
Abstract: The generation of virtual populations (VPs) of anatomy is essential for conducting in silico trials of medical devices. Typically, the generated VP should capture sufficient variability while remaining plausible and should reflect the specific characteristics and demographics of the patients observed in real populations. In several applications, it is desirable to synthesise virtual populations in a \textit{controlled} manner, where relevant covariates are used to conditionally synthesise virtual populations that fit a specific target population/characteristics. We propose to equip a conditional variational autoencoder (cVAE) with normalising flows to boost the flexibility and complexity of the approximate posterior learnt, leading to enhanced flexibility for controllable synthesis of VPs of anatomical structures. We demonstrate the performance of our conditional flow VAE using a data set of cardiac left ventricles acquired from 2360 patients, with associated demographic information and clinical measurements (used as covariates/conditional information). The results obtained indicate the superiority of the proposed method for conditional synthesis of virtual populations of cardiac left ventricles relative to a cVAE. Conditional synthesis performance was evaluated in terms of generalisation and specificity errors and in terms of the ability to preserve clinically relevant biomarkers in synthesised VPs, that is, the left ventricular blood pool and myocardial volume, relative to the real observed population.

Related papers

Deep vectorised operators for pulsatile hemodynamics estimation in coronary arteries from a steady-state prior [2.3971720731010766]
We propose a time-efficient surrogate model, powered by machine learning, for the estimation of pulsatile hemodynamics. We show that our model produces accurate estimates of the pulsatile velocity and pressure while being agnostic to re-sampling of the source domain.
arXiv Detail & Related papers (2024-10-15T12:24:50Z)
SeqRisk: Transformer-augmented latent variable model for improved survival prediction with longitudinal data [4.1476925904032464]
We propose SeqRisk, a method that combines variational autoencoder (VAE) or longitudinal VAE (LVAE) with a transformer encoder and Cox proportional hazards module for risk prediction. We demonstrate that SeqRisk performs competitively compared to existing approaches on both simulated and real-world datasets.
arXiv Detail & Related papers (2024-09-19T12:35:25Z)
Meta Flow Matching: Integrating Vector Fields on the Wasserstein Manifold [83.18058549195855]
We argue that multiple processes in natural sciences have to be represented as vector fields on the Wasserstein manifold of probability densities. In particular, this is crucial for personalized medicine where the development of diseases and their respective treatment response depends on the microenvironment of cells specific to each patient. We propose Meta Flow Matching (MFM), a practical approach to integrating along these vector fields on the Wasserstein manifold by amortizing the flow model over the initial populations.
arXiv Detail & Related papers (2024-08-26T20:05:31Z)
Synthetic location trajectory generation using categorical diffusion models [50.809683239937584]
Diffusion models (DPMs) have rapidly evolved to be one of the predominant generative models for the simulation of synthetic data. We propose using DPMs for the generation of synthetic individual location trajectories (ILTs) which are sequences of variables representing physical locations visited by individuals.
arXiv Detail & Related papers (2024-02-19T15:57:39Z)
Fusing Echocardiography Images and Medical Records for Continuous Patient Stratification [16.93115087698284]
We propose a method to learn the representation of a cardiovascular pathology with a difficult-to-characterize continuum, namely hypertension. Our method first projects each variable into its own representation space using modality-specific approaches. These standardized representations of multimodal data are then fed to a transformer encoder, which learns to merge them into a comprehensive representation of the patient through the task of predicting a clinical rating. We observe the major trends along this continuum on a cohort of 239 hypertensive patients, providing unprecedented details in the description of hypertension's impact on various cardiac function descriptors.
arXiv Detail & Related papers (2024-01-15T16:04:46Z)
Simulation-based Inference for Cardiovascular Models [57.92535897767929]
We use simulation-based inference to solve the inverse problem of mapping waveforms back to plausible physiological parameters. We perform an in-silico uncertainty analysis of five biomarkers of clinical interest. We study the gap between in-vivo and in-silico with the MIMIC-III waveform database.
arXiv Detail & Related papers (2023-07-26T02:34:57Z)
TREEMENT: Interpretable Patient-Trial Matching via Personalized Dynamic Tree-Based Memory Network [54.332862955411656]
Clinical trials are critical for drug development but often suffer from expensive and inefficient patient recruitment. In recent years, machine learning models have been proposed for speeding up patient recruitment via automatically matching patients with clinical trials. We introduce a dynamic tree-based memory network model named TREEMENT to provide accurate and interpretable patient trial matching.
arXiv Detail & Related papers (2023-07-19T12:35:09Z)
A Generative Shape Compositional Framework to Synthesise Populations of Virtual Chimaeras [52.33206865588584]
We introduce a generative shape model for complex anatomical structures, learnable from datasets of unpaired datasets. We build virtual chimaeras from databases of whole-heart shape assemblies that each contribute samples for heart substructures. Our approach significantly outperforms a PCA-based shape model (trained with complete data) in terms of generalisability and specificity.
arXiv Detail & Related papers (2022-10-04T13:36:52Z)
Cancer Subtyping by Improved Transcriptomic Features Using Vector Quantized Variational Autoencoder [10.835673227875615]
We propose Vector Quantized Variational AutoEncoder (VQ-VAE) to tackle the data issues and extract informative latent features that are crucial to the quality of subsequent clustering. VQ-VAE does not impose strict assumptions and hence its latent features are better representations of the input, capable of yielding superior clustering performance with any mainstream clustering method.
arXiv Detail & Related papers (2022-07-20T09:47:53Z)
Equitable modelling of brain imaging by counterfactual augmentation with morphologically constrained 3D deep generative models [0.5695579108997391]
The model is intended to synthesise counterfactual training data augmentations for downstream discriminative modelling tasks. We evaluate the quality of synthesized counterfactuals with voxel-based morphometry, classification and regression of the conditioning attributes, and the Fr'echet distance. We achieve state-of-the-art improvements, both in overall fidelity and equity.
arXiv Detail & Related papers (2021-11-29T19:55:31Z)

This list is automatically generated from the titles and abstracts of the papers in this site.