1 code implementation • 27 Sep 2022 • Juan Miguel Valverde, Artem Shatillo, Jussi Tohka
We present Sauron, a filter pruning method that eliminates redundant feature maps by discarding the corresponding filters with automatically-adjusted layer-specific thresholds.
1 code implementation • 4 Aug 2021 • Juan Miguel Valverde, Artem Shatillo, Riccardo de Feo, Jussi Tohka
We present MedicDeepLabv3+, a convolutional neural network that is the first completely automatic method to segment cerebral hemispheres in magnetic resonance (MR) volumes of rats with lesions.
1 code implementation • 3 Aug 2021 • Juan Miguel Valverde, Jussi Tohka
We show that, under the proposed RW loss framework, certain loss functions, such as Active Contour and Boundary loss, can be reformulated similarly with appropriate RW maps, thus revealing their underlying similarities and a new perspective to understand these loss functions.
no code implementations • 2 Feb 2021 • Juan Miguel Valverde, Vandad Imani, Ali Abdollahzadeh, Riccardo de Feo, Mithilesh Prakash, Robert Ciszek, Jussi Tohka
We found 129 articles that applied transfer learning to brain MRI tasks.
1 code implementation • 24 Jan 2020 • Juan Miguel Valverde, Artem Shatillo, Riccardo de Feo, Olli Gröhn, Alejandra Sierra, Jussi Tohka
RatLesNetv2 obtained similar to higher Dice coefficient values than the other ConvNets and it produced much more realistic and compact segmentations with notably fewer holes and lower Hausdorff distance.
no code implementations • 9 Sep 2019 • Juan Miguel Valverde, Vandad Imani, John D. Lewis, Jussi Tohka
These last two measurements were derived from the T1-weighted MR images using cortical surfaces produced by the CIVET pipeline.
no code implementations • 23 Aug 2019 • Juan Miguel Valverde, Artem Shatillo, Riccardo de Feo, Olli Gröhn, Alejandra Sierra, Jussi Tohka
Several automatic methods have been developed for different human brain MRI segmentation, but little research has targeted automatic rodent lesion segmentation.