Search Results for author:
Found 38 papers, 11 papers with code
Hyperparameter-Free Medical Image Synthesis for Sharing Data and Improving Site-Specific Segmentation
Sharing synthetic medical images is a promising alternative to sharing real images that can improve patient privacy and data security.
Stitching for Neuroevolution: Recombining Deep Neural Networks without Breaking Them
To correct for differing feature representations between these layers we employ stitching, which merges the networks by introducing new layers at crossover points.
Multi-Objective Learning for Deformable Image Registration
The experiments also show that the proposed MO DIR approach provides a better spread of DIR outputs across the entire trade-off front than simply training multiple neural networks with weights for each objective sampled from a grid of possible values.
Learning Discretized Bayesian Networks with GOMEA
The optimal discretization, however, depends on the relations modelled between the variables.
MultiFIX: An XAI-friendly feature inducing approach to building models from multimodal data
Furthermore, it is important to understand how each modality impacts the final prediction, especially in high-stake domains, so that these models can be used in a trustworthy and responsible manner.
Fitness-based Linkage Learning and Maximum-Clique Conditional Linkage Modelling for Gray-box Optimization with RV-GOMEA
In addition, we propose a new way to model overlapping dependencies in conditional linkage models to maximize the joint sampling of fully interdependent groups of variables.
Improving the efficiency of GP-GOMEA for higher-arity operators
Experimental results show that both proposed search enhancements have a generally positive impact on the performance of GP-GOMEA, especially when the set of operators to choose from is large and contains higher-arity operators.
A Tournament of Transformation Models: B-Spline-based vs. Mesh-based Multi-Objective Deformable Image Registration
Although both models have been investigated in detail, a direct comparison has not yet been made, since the models are optimized using very different optimization methods in practice.
Shrink-Perturb Improves Architecture Mixing during Population Based Training for Neural Architecture Search
In this work, we show that simultaneously training and mixing neural networks is a promising way to conduct Neural Architecture Search (NAS).
Multi-Objective Population Based Training
Population Based Training (PBT) is an efficient hyperparameter optimization algorithm.
A Joint Python/C++ Library for Efficient yet Accessible Black-Box and Gray-Box Optimization with GOMEA
Especially in a Gray-Box Optimization (GBO) setting that allows for partial evaluations, i. e., the relatively efficient evaluation of a partial modification of a solution, GOMEA is known to excel.
The Impact of Asynchrony on Parallel Model-Based EAs
Thus, if an asynchronous parallel MBEA is also affected by an evaluation time bias, this could result in learned models to be less suited to solving the problem, reducing performance.
Convolutions, Transformers, and their Ensembles for the Segmentation of Organs at Risk in Radiation Treatment of Cervical Cancer
The results show that small improvements in metrics can be achieved by advancing and merging architectures, but the predictions of the models are quite similar (most models achieve on average more than 0. 8 Dice Coefficient when compared to the outputs of other models).
MOREA: a GPU-accelerated Evolutionary Algorithm for Multi-Objective Deformable Registration of 3D Medical Images
A recent multi-objective approach that uses the Multi-Objective Real-Valued Gene-pool Optimal Mixing Evolutionary Algorithm (MO-RV-GOMEA) and a dual-dynamic mesh transformation model has shown promise, exposing the trade-offs inherent to image registration problems and modeling large deformations in 2D.
Clinically Acceptable Segmentation of Organs at Risk in Cervical Cancer Radiation Treatment from Clinically Available Annotations
Following this motivation, we present an approach to learn a deep learning model for the automatic segmentation of Organs at Risk (OARs) in cervical cancer radiation treatment from a large clinically available dataset of Computed Tomography (CT) scans containing data inhomogeneity, label noise, and missing annotations.
Coefficient Mutation in the Gene-pool Optimal Mixing Evolutionary Algorithm for Symbolic Regression
We find that coefficient mutation can help re-discovering the underlying equation by a substantial amount, but only when no noise is added to the target variable.
Less is More: A Call to Focus on Simpler Models in Genetic Programming for Interpretable Machine Learning
Interpretability can be critical for the safe and responsible use of machine learning models in high-stakes applications.
Obtaining Smoothly Navigable Approximation Sets in Bi-Objective Multi-Modal Optimization
Even if a Multi-modal Multi-Objective Evolutionary Algorithm (MMOEA) is designed to find solutions well spread over all locally optimal approximation sets of a Multi-modal Multi-objective Optimization Problem (MMOP), there is a risk that the found set of solutions is not smoothly navigable because the solutions belong to various niches, reducing the insight for decision makers.
Adaptive Objective Configuration in Bi-Objective Evolutionary Optimization for Cervical Cancer Brachytherapy Treatment Planning
For this reason, we propose a novel adaptive objective configuration method to use with MO-RV-GOMEA so that we can accommodate additional aims of this nature.
GPU-Accelerated Parallel Gene-pool Optimal Mixing in a Gray-Box Optimization Setting
However, unless population sizes are large, this offers limited gains.
Solving Multi-Structured Problems by Introducing Linkage Kernels into GOMEA
This cannot be modelled sufficiently well when using linkage models that aim at capturing a single type of linkage structure, deteriorating the advantages brought by MBEAs.
Evolutionary Neural Cascade Search across Supernetworks
A recent method called Neural Architecture Transfer (NAT) further improves the efficiency of NAS for computer vision tasks by using a multi-objective evolutionary algorithm to find high-quality subnetworks of a supernetwork pretrained on ImageNet.
Data variation-aware medical image segmentation
In experiments with a real clinical dataset of CT scans with prostate segmentations, our approach provides an improvement of several percentage points in terms of Dice and surface Dice coefficients compared to when all network paths are trained on all training data.
Mixed-Block Neural Architecture Search for Medical Image Segmentation
The design of the best possible medical image segmentation DNNs, however, is task-specific.
Multi-Objective Dual Simplex-Mesh Based Deformable Image Registration for 3D Medical Images -- Proof of Concept
Concordantly, this work introduces the first method for multi-objective 3D deformable image registration, using a 3D dual-dynamic grid transformation model based on simplex meshes while still supporting the incorporation of annotated guidance information and multi-resolution schemes.
Evolvability Degeneration in Multi-Objective Genetic Programming for Symbolic Regression
Genetic programming (GP) is one of the best approaches today to discover symbolic regression models.
Adults as Augmentations for Children in Facial Emotion Recognition with Contrastive Learning
Our results indicate that adult data can be considered to be a meaningful augmentation of pediatric data for the recognition of emotional facial expression in children, and open up the possibility for other applications of contrastive learning to improve pediatric care by complementing data of children with that of adults.
Heed the Noise in Performance Evaluations in Neural Architecture Search
Due to stochastic factors in neural network initialization, training, and the chosen train/validation dataset split, the performance evaluation of a neural network architecture, which is often based on a single learning run, is also stochastic.
Parameterless Gene-pool Optimal Mixing Evolutionary Algorithms
When it comes to solving optimization problems with evolutionary algorithms (EAs) in a reliable and scalable manner, detecting and exploiting linkage information, i. e., dependencies between variables, can be key.
Automatic Landmarks Correspondence Detection in Medical Images with an Application to Deformable Image Registration
Conclusions: DCNN-Match learns to predict landmark correspondences in 3D medical images in a self-supervised manner, which can improve DIR performance.
A Novel Surrogate-assisted Evolutionary Algorithm Applied to Partition-based Ensemble Learning
We propose a novel surrogate-assisted Evolutionary Algorithm for solving expensive combinatorial optimization problems.
Multi-Objective Learning to Predict Pareto Fronts Using Hypervolume Maximization
We discuss and illustrate why training processes to approximate Pareto fronts need to optimize on fronts of individual training samples instead of on only the front of average losses.
Multi-objective Optimization by Uncrowded Hypervolume Gradient Ascent
On several bi-objective benchmarks, we find that gradient-based algorithms outperform the tested EAs by obtaining a better hypervolume with fewer evaluations whenever exact gradients of the multiple objective functions are available and in case of small evaluation budgets.
Optimization and Control
Observer variation-aware medical image segmentation by combining deep learning and surrogate-assisted genetic algorithms
There has recently been great progress in automatic segmentation of medical images with deep learning algorithms.
An End-to-end Deep Learning Approach for Landmark Detection and Matching in Medical Images
We tested the approach on 22, 206 pairs of 2D slices with varying levels of intensity, affine, and elastic transformations.
Machine learning for automatic construction of pseudo-realistic pediatric abdominal phantoms
To assess the effects of radiation therapy, treatment plans are typically simulated on phantoms, i. e., virtual surrogates of patient anatomy.
On Explaining Machine Learning Models by Evolving Crucial and Compact Features
In this article, we assess to what extent GP still performs favorably at feature construction when constructing features that are (1) Of small-enough number, to enable visualization of the behavior of the ML model; (2) Of small-enough size, to enable interpretability of the features themselves; (3) Of sufficient informative power, to retain or even improve the performance of the ML algorithm.
Improving Model-based Genetic Programming for Symbolic Regression of Small Expressions
We show that the non-uniformity in the distribution of the genotype in GP populations negatively biases LL, and propose a method to correct for this.
