no code implementations • 24 Feb 2025 • Boris Shirokikh, Anvar Kurmukov, Mariia Donskova, Valentin Samokhin, Mikhail Belyaev, Ivan Oseledets
Domain shift presents a significant challenge in applying Deep Learning to the segmentation of 3D medical images from sources like Magnetic Resonance Imaging (MRI) and Computed Tomography (CT).
no code implementations • 31 Jan 2025 • David Li, Anvar Kurmukov, Mikhail Goncharov, Roman Sokolov, Mikhail Belyaev
We introduce an auxiliary diffusion process to pretrain a model that produce generalizable feature representations, useful for a variety of downstream segmentation tasks.
no code implementations • 25 Sep 2024 • Anvar Kurmukov, Bogdan Zavolovich, Aleksandra Dalechina, Vladislav Proskurov, Boris Shirokikh
Image compression is a critical tool in decreasing the cost of storage and improving the speed of transmission over the internet.
1 code implementation • 16 Sep 2024 • Mikhail Goncharov, Valentin Samokhin, Eugenia Soboleva, Roman Sokolov, Boris Shirokikh, Mikhail Belyaev, Anvar Kurmukov, Ivan Oseledets
We train our APE model on 8400 publicly available CT images of abdomen and chest regions.
no code implementations • 12 Jun 2024 • Anvar Kurmukov, Valeria Chernina, Regina Gareeva, Maria Dugova, Ekaterina Petrash, Olga Aleshina, Maxim Pisov, Boris Shirokikh, Valentin Samokhin, Vladislav Proskurov, Stanislav Shimovolos, Maria Basova, Mikhail Goncahrov, Eugenia Soboleva, Maria Donskova, Farukh Yaushev, Alexey Shevtsov, Alexey Zakharov, Talgat Saparov, Victor Gombolevskiy, Mikhail Belyaev
Previous studies have measured the time-saving effect of using a deep-learning-based aid (DLA) for CT interpretation.
no code implementations • 24 May 2024 • Aleksei Leonov, Aleksei Zakharov, Sergey Koshelev, Maxim Pisov, Anvar Kurmukov, Mikhail Belyaev
Automatic ribs segmentation and numeration can increase computed tomography assessment speed and reduce radiologists mistakes.
1 code implementation • 27 Jul 2023 • Mikhail Goncharov, Vera Soboleva, Anvar Kurmukov, Maxim Pisov, Mikhail Belyaev
This paper introduces vox2vec - a contrastive method for self-supervised learning (SSL) of voxel-level representations.
1 code implementation • 11 Apr 2022 • Ekaterina Kondrateva, Polina Druzhinina, Alexandra Dalechina, Svetlana Zolotova, Andrey Golanov, Boris Shirokikh, Mikhail Belyaev, Anvar Kurmukov
Magnetic resonance imaging (MRI) data is heterogeneous due to differences in device manufacturers, scanning protocols, and inter-subject variability.
1 code implementation • 18 Jul 2021 • Talgat Saparov, Anvar Kurmukov, Boris Shirokikh, Mikhail Belyaev
We analyze a dataset of paired CT images, where smooth and sharp images were reconstructed from the same sinograms with different kernels, thus providing identical anatomy but different style.
1 code implementation • 20 Jul 2020 • Boris Shirokikh, Alexey Shevtsov, Anvar Kurmukov, Alexandra Dalechina, Egor Krivov, Valery Kostjuchenko, Andrey Golanov, Mikhail Belyaev
We propose a loss reweighting approach to increase the ability of the network to detect small lesions.
no code implementations • 2 Jun 2020 • Mikhail Goncharov, Maxim Pisov, Alexey Shevtsov, Boris Shirokikh, Anvar Kurmukov, Ivan Blokhin, Valeria Chernina, Alexander Solovev, Victor Gombolevskiy, Sergey Morozov, Mikhail Belyaev
We train our model on approximately 2000 publicly available CT studies and test it with a carefully designed set consisting of 32 COVID-19 studies, 30 cases with bacterial pneumonia, 31 healthy patients, and 30 patients with other lung pathologies to emulate a typical patient flow in an out-patient hospital.
no code implementations • 10 Aug 2018 • Anvar Kurmukov, Ayagoz Mussabayeva, Yulia Denisova, Daniel Moyer, Boris Gutman
We present two related methods for deriving connectivity-based brain atlases from individual connectomes.
no code implementations • 10 Aug 2018 • Ayagoz Mussabayeva, Alexey Kroshnin, Anvar Kurmukov, Yulia Dodonova, Li Shen, Shan Cong, Lei Wang, Boris A. Gutman
We present a method for metric optimization in the Large Deformation Diffeomorphic Metric Mapping (LDDMM) framework, by treating the induced Riemannian metric on the space of diffeomorphisms as a kernel in a machine learning context.