no code implementations • 20 Sep 2022 • Krešimir Romić, Irena Galić, Marija Habijan, Hrvoje Leventić
This paper presents an evaluation framework for computer vision-based guiding of the visually impaired persons in such critical situations.
1 code implementation • 21 Jun 2022 • Marin Benčević, Marija Habijan, Irena Galić, Danilo Babin
In this paper, we present a general approach to improving the semantic segmentation performance of neural networks in these tasks and validate our approach on the task of aorta segmentation.
1 code implementation • 1 Jun 2022 • Marin Benčević, Marija Habijan, Irena Galić, Aleksandra Pizurica
In this paper, we evaluate a method of reducing the need for labeled data in medical image object detection by using self-supervised neural network pretraining.
no code implementations • 13 May 2022 • Hrvoje Leventić, Marin Benčević, Danilo Babin, Marija Habijan, Irena Galić
Atrial fibrillation (AF) is a cardiovascular disease identified as one of the main risk factors for stroke.
no code implementations • 27 Apr 2022 • Marin Benčević, Marija Habijan, Irena Galić
Fully automatic and reliable measurements of epicardial adipose tissue from CT scans could provide better disease risk assessment and enable the processing of large CT image data sets for a systemic epicardial adipose tissue study.
1 code implementation • IEEE Access 2021 • Marin Benčević, Irena Galić, Marija Habijan, Danilo Babin
We show that our method produces state-of-the-art results for lesion, liver, and polyp segmentation and performs better than most common neural network architectures for biomedical image segmentation.
Ranked #1 on Lesion Segmentation on ISIC 2018