no code implementations • 1 Nov 2022 • Elvira Zainulina, Alexey Chernyavskiy, Dmitry V. Dylov
Computed Tomography (CT) imposes risk on the patients due to its inherent X-ray radiation, stimulating the development of low-dose CT (LDCT) imaging methods.
no code implementations • 6 Aug 2021 • Ekaterina Redekop, Alexey Chernyavskiy
While current weakly-supervised approaches that use 2D bounding boxes as weak labels can be applied to medical image segmentation, we show that their success is limited in cases when the assumption about the tightness of the bounding boxes breaks.
1 code implementation • 10 Jul 2021 • Ivan Zakazov, Boris Shirokikh, Alexey Chernyavskiy, Mikhail Belyaev
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.
no code implementations • 16 Feb 2021 • Ekaterina Redekop, Alexey Chernyavskiy
The success of modern deep learning algorithms for image segmentation heavily depends on the availability of large datasets with clean pixel-level annotations (masks), where the objects of interest are accurately delineated.
no code implementations • 3 Feb 2021 • Elvira Zainulina, Alexey Chernyavskiy, Dmitry V. Dylov
Low-dose computed tomography (LDCT) became a clear trend in radiology with an aspiration to refrain from delivering excessive X-ray radiation to the patients.
1 code implementation • 17 Aug 2020 • Boris Shirokikh, Ivan Zakazov, Alexey Chernyavskiy, Irina Fedulova, Mikhail Belyaev
Our results demonstrate that 1) domain-shift may deteriorate the quality even for a simple brain extraction segmentation task (surface Dice Score drops from 0. 85-0. 89 even to 0. 09); 2) fine-tuning of the first layers significantly outperforms fine-tuning of the last layers in almost all supervised domain adaptation setups.