Selected works

TopoMortar: A dataset to evaluate image segmentation methods focused on topology accuracy

J.M. Valverde, M. Koga,, N. Otsuka, A.B. Dahl

in Arxiv, 2025.

#Segmentation #Topology #Dataset

TopoMortar is the first dataset specifically designed to evaluate whether topology-enhancing methods do actually improve topology accuracy. TopoMortar allows to portray different challenging scenarios where, unlike in existing datasets, an increase in topology accuracy can be attributed to the incorporation of prior topology knowledge.

[ArXiv], [Code]

Disconnect to Connect: A Data Augmentation Method for Improving Topology Accuracy in Image Segmentation

J.M. Valverde, M. Østergaard, A. Rodriguez-Palomo, P.A.S. Vibe, N.K. Wittig, H. Birkedal, A.B. Dahl

in Arxiv, 2025.

#Segmentation #Topology #DataAugmentation

CoLeTra is the first data augmentation method specifically developed to increase topology accuracy. It encourages the models to learn that visually-disconnected structures may be connected.

[ArXiv], [Code]

Sauron U-Net: Simple automated redundancy elimination in medical image segmentation via filter pruning

J.M. Valverde, A. Shatillo, J. Tohka

in NeuroComputing, 2024.

#Segmentation #MRI #CT #FilterPruning

SauronUNet is a filter pruning method for UNet-like architectures that, first, increases the redundancy among feature maps to, later, eliminate them.

[ArXiv], [Code], [ Publication]

Region-wise Loss for Biomedical Image Segmentation

J.M. Valverde, J. Tohka

in Pattern Recognition, 2023.

#Segmentation #MRI #CT #Loss

Region-wise loss is a loss function that allows you to penalize pixels based on the distances to the structures' boundary.

[ArXiv], [Code], [ Publication]

Transfer Learning in Magnetic Resonance Brain Imaging: A Systematic Review

J.M. Valverde, V. Imani, A. Abdollahzadeh, R. De Feo, M. Prakash, R. Ciszek, J. Tohka

in Journal of Imaging, 2021.

#TransferLearning #MRI

In this review, we identify research directions, gaps in knowledge, applications, and widely used strategies among the transfer learning approaches applied in MR brain imaging.

[ArXiv], [ Publication]

RatLesNetv2: A Fully ConvNet for Rodent Brain Lesion Segmentation

J.M. Valverde, A. Shatillo, R. de Feo, A. Sierra, O. Gröhn, J. Tohka

in Frontiers in Neuroscience, 2020.

#Segmentation #MRI #Lesion #Rodents

RatLesNetv2 is a convolutional neural network to segment rodent brain lesions in MR images that we validated on an exceptionally large dataset of 916 T2-weighted rat brain MRI scans.

[ArXiv], [Code], [ Publication], [Cake]