Search Results for author: Tommy Löfstedt

Found 15 papers, 4 papers with code

Beyond a Single Mode: GAN Ensembles for Diverse Medical Data Generation

1 code implementation31 Mar 2025 Lorenzo Tronchin, Tommy Löfstedt, Paolo Soda, Valerio Guarrasi

The advancement of generative AI, particularly in medical imaging, confronts the trilemma of ensuring high fidelity, diversity, and efficiency in synthetic data generation.

Diagnostic Diversity +1

A Cost-Aware Approach to Adversarial Robustness in Neural Networks

no code implementations11 Sep 2024 Charles Meyers, Mohammad Reza Saleh Sedghpour, Tommy Löfstedt, Erik Elmroth

Considering the growing prominence of production-level AI and the threat of adversarial attacks that can evade a model at run-time, evaluating the robustness of models to these evasion attacks is of critical importance.

Adversarial Robustness GPU +1

A Correlation- and Mean-Aware Loss Function and Benchmarking Framework to Improve GAN-based Tabular Data Synthesis

no code implementations27 May 2024 Minh H. Vu, Daniel Edler, Carl Wibom, Tommy Löfstedt, Beatrice Melin, Martin Rosvall

The proposed loss function demonstrates statistically significant improvements over existing methods in capturing the true data distribution, significantly enhancing the quality of synthetic data generated with GANs.

Benchmarking

A Training Rate and Survival Heuristic for Inference and Robustness Evaluation (TRASHFIRE)

1 code implementation24 Jan 2024 Charles Meyers, Mohammad Reza Saleh Sedghpour, Tommy Löfstedt, Erik Elmroth

The proposed approach uses survival models, worst-case examples, and a cost-aware analysis to precisely and accurately reject a particular model change during routine model training procedures rather than relying on real-world deployment, expensive formal verification methods, or accurate simulations of very complicated systems (\textit{e. g.}, digitally recreating every part of a car or a plane).

Adversarial Robustness

LatentAugment: Data Augmentation via Guided Manipulation of GAN's Latent Space

1 code implementation21 Jul 2023 Lorenzo Tronchin, Minh H. Vu, Paolo Soda, Tommy Löfstedt

Data Augmentation (DA) is a technique to increase the quantity and diversity of the training data, and by that alleviate overfitting and improve generalisation.

Data Augmentation Diversity

Reproducibility of the Methods in Medical Imaging with Deep Learning

no code implementations20 Oct 2022 Attila Simko, Anders Garpebring, Joakim Jonsson, Tufve Nyholm, Tommy Löfstedt

We have evaluated all accepted full paper submissions to MIDL between 2018 and 2022 using established, but slightly adjusted guidelines on reproducibility and the quality of the public repositories.

Deep Learning

A Data-Adaptive Loss Function for Incomplete Data and Incremental Learning in Semantic Image Segmentation

no code implementations22 Apr 2021 Minh H. Vu, Gabriella Norman, Tufve Nyholm, Tommy Löfstedt

Among different types of deep learning models, convolutional neural networks have been among the most successful and they have been used in many applications in medical imaging.

Image Segmentation Incremental Learning +2

Multi-Decoder Networks with Multi-Denoising Inputs for Tumor Segmentation

no code implementations16 Nov 2020 Minh H. Vu, Tufve Nyholm, Tommy Löfstedt

Automatic segmentation of brain glioma from multimodal MRI scans plays a key role in clinical trials and practice.

Decoder Denoising +2

Evaluation of Multi-Slice Inputs to Convolutional Neural Networks for Medical Image Segmentation

no code implementations19 Dec 2019 Minh H. Vu, Guus Grimbergen, Tufve Nyholm, Tommy Löfstedt

In this study, we systematically evaluate the segmentation performance and computational costs of this pseudo-3D approach as a function of the number of input slices, and compare the results to conventional end-to-end 2D and 3D CNNs.

Image Segmentation Medical Image Segmentation +2

TuNet: End-to-end Hierarchical Brain Tumor Segmentation using Cascaded Networks

no code implementations11 Oct 2019 Minh H. Vu, Tufve Nyholm, Tommy Löfstedt

Glioma is one of the most common types of brain tumors; it arises in the glial cells in the human brain and in the spinal cord.

Brain Tumor Segmentation Segmentation +1

A general multiblock method for structured variable selection

no code implementations29 Oct 2016 Tommy Löfstedt, Fouad Hadj-Selem, Vincent Guillemot, Cathy Philippe, Nicolas Raymond, Edouard Duchesney, Vincent Frouin, Arthur Tenenhaus

However, for technical reasons, the variable selection offered by SGCCA was restricted to a covariance link between the blocks (i. e., with $\tau=1$).

Variable Selection

Structured Sparse Principal Components Analysis with the TV-Elastic Net penalty

no code implementations6 Sep 2016 Amicie de Pierrefeu, Tommy Löfstedt, Fouad Hadj-Selem, Mathieu Dubois, Philippe Ciuciu, Vincent Frouin, Edouard Duchesnay

However, in neuroimaging, it is essential to uncover clinically interpretable phenotypic markers that would account for the main variability in the brain images of a population.

Cannot find the paper you are looking for? You can Submit a new open access paper.