9 papers
Adaptation to CT Reconstruction Kernels by Enforcing Cross-domain Feature Maps Consistency
Stanislav Shimovolos, Andrey Shushko, Mikhail Belyaev +1
Deep learning methods provide significant assistance in analyzing coronavirus disease (COVID-19) in chest computed tomography (CT) images, including identification, severity assess…
Systematic Clinical Evaluation of A Deep Learning Method for Medical Image Segmentation: Radiosurgery Application
Boris Shirokikh, Alexandra Dalechina, Alexey Shevtsov +6
We systematically evaluate a Deep Learning (DL) method in a 3D medical image segmentation task. Our segmentation method is integrated into the radiosurgery treatment process and di…
Anatomy of Domain Shift Impact on U-Net Layers in MRI Segmentation
Ivan Zakazov, Boris Shirokikh, Alexey Chernyavskiy +1
Domain Adaptation (DA) methods are widely used in medical image segmentation tasks to tackle the problem of differently distributed train (source) and test (target) data. We consid…
First U-Net Layers Contain More Domain Specific Information Than The Last Ones
Boris Shirokikh, Ivan Zakazov, Alexey Chernyavskiy +2
MRI scans appearance significantly depends on scanning protocols and, consequently, the data-collection institution. These variations between clinical sites result in dramatic drop…
Universal Loss Reweighting to Balance Lesion Size Inequality in 3D Medical Image Segmentation
Boris Shirokikh, Alexey Shevtsov, Anvar Kurmukov +5
Target imbalance affects the performance of recent deep learning methods in many medical image segmentation tasks. It is a twofold problem: class imbalance - positive class (lesion…
CT-based COVID-19 Triage: Deep Multitask Learning Improves Joint Identification and Severity Quantification
Mikhail Goncharov, Maxim Pisov, Alexey Shevtsov +8
The current COVID-19 pandemic overloads healthcare systems, including radiology departments. Though several deep learning approaches were developed to assist in CT analysis, nobody…