Aleksei Samarin

Dr. Aleksei Samarin

orcid

Research Focus & Metrics

Academic Career Length

7Years (2020-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
1 September 2022 in Pattern Recognition and Image Analysis
Verified
Journal Article
Closed access
PDF file
ASAleksei Samarin
Aleksei Samarin
ASAlexander Savelev
Alexander Savelev
ATAleksei Toropov
Aleksei Toropov
ADA. Dzestelova
A. Dzestelova
VMV. Malykh
V. Malykh
AMAlexandr Motyko
Alexandr Motyko
Computer tomography is most commonly used for diagnosing lung cancer, which is one of the deadliest cancers in the world. Online services that allow users to share their single-channel monochrome images, in particular computer tomography scans, in order to receive independent medical advice are becoming wide-spread these days. In this paper, we propose an optimization for the previously known two-staged architecture for detecting cancerous tumors in computer tomography scans that demonstrates the state-of-the-art results on Open Joint Monochrome Lungs Computer Tomography dataset. Modernized architecture allows to reduce the number of weights of the neural network based model (4 920 073 parameters vs. 26 468 315 in the original model) and its inference time (0.38 vs. 2.15 s in the original model) without loss of neoplasms recognition quality (0.996 F1 score). The proposed results were obtained using heavyweight encoder elimination, special combined loss function and watershed based method for the automated dataset markup and a consistency regularization approach adaptation that are described in the current paper.

1 June 2023 in Pattern Recognition and Image Analysis
Verified
Journal Article
Closed access
PDF file
ASAleksei Samarin
Aleksei Samarin
ASAlexander Savelev
Alexander Savelev
ATAleksei Toropov
Aleksei Toropov
ADA. Dzestelova
A. Dzestelova
VMV. Malykh
V. Malykh
AMAlexandr Motyko
Alexandr Motyko
Currently, one of the most useful methods for diagnosing lung cancer is based on computed tomography. In addition, online medical consultation services are becoming increasingly popular. The article presents two architectures based on neural networks with an attention mechanism for recognizing lung cancer from a single computed tomography image. One of the proposed approaches is an optimization of a previously presented two-stage model that has demonstrated state-of-the-art results on the Open Joint Monochrome Lungs Computer Tomography (OJMLCT) dataset first proposed by Samarin et al. [13]. Our solution allowed us to reduce the number of model parameters without significant loss of classification efficiency.

1 September 2024 in Pattern Recognition and Image Analysis
Verified
Journal Article
Closed access
PDF file
ASAleksei Samarin
Aleksei Samarin
ASAlexander Savelev
Alexander Savelev
ATAleksei Toropov
Aleksei Toropov
ANArtem Nazarenko
Artem Nazarenko
AGA. Golovatiuk
A. Golovatiuk
VMV. Malykh
V. Malykh
Tasks related to the automation of medical data processing are becoming more urgent. Particular attention is paid to systems for monitoring and analyzing human physiological parameters. Such systems often use specialized sensors to capture biomedical images, such as infrared cameras. This article describes our study of the problem of segmenting the eye pupil and iris in images obtained using an infrared camera. In our work, we propose a proprietary deep neural network architecture with a novel loss function for learning to segment human ocular structures. We also present a segmentation dataset and perform a comparative analysis of different eye structure segmentation methods. Our proposed model outperforms other considered approaches and has demonstrated state-of-the-art results in segmentation of human ocular structures.

1 June 2023 in Pattern Recognition and Image Analysis
Verified
Journal Article
Closed access
PDF file
ASAleksei Samarin
Aleksei Samarin
ASAlexander Savelev
Alexander Savelev
ATAleksei Toropov
Aleksei Toropov
ADA. Dzestelova
A. Dzestelova
VMV. Malykh
V. Malykh
AMAlexandr Motyko
Alexandr Motyko
We present a description of various custom image descriptor modifications that are used as part of an image classification pipeline with text elements. The problem under consideration is related to the classification of images of commercial facades by the type of services provided. Some of the proposed descriptor types are presented for the first time and demonstrate state-of-the-art performance on open datasets. In our study, we used a special type of descriptor for image areas with text based on traces of the movement of agents. The traces in question are generated using parameterized movement strategies, which are presented and compared in this article.

1 September 2024 in Pattern Recognition and Image Analysis
Verified
Journal Article
Closed access
PDF file
ASAleksei Samarin
Aleksei Samarin
ANArtem Nazarenko
Artem Nazarenko
ASAlexander Savelev
Alexander Savelev
ATAleksei Toropov
Aleksei Toropov
ADA. Dzestelova
A. Dzestelova
VMV. Malykh
V. Malykh
Improving image quality is becoming an increasingly popular task, especially when working with mobile devices. One common approach to image enhancement is the use of convolutional neural networks. However, to achieve good results, such networks must be large enough, otherwise there is a risk of unwanted artifacts. In addition, large convolutional neural networks require significant computational resources, which can be a problem for mobile devices. Another disadvantage of such models is their low interpretability. Another approach to improving image quality is to use predefined filters combined with predictions in which cases they should be applied. We present a solution that follows this concept and outperforms both existing convolutional neural network-based models and filter-based methods in the task of image enhancement. Our model is easily adapted for mobile devices, since it contains only 47 000 parameters. On the RANDOM250 (MIT Adobe FiveK) dataset our method achieved a best structural similarity index score of 0.919 among small models and was three times faster than existing solutions.

12 August 2020
Verified
Book Chapter
Closed access
ASAleksei Samarin
Aleksei Samarin
VMValentin Malykh
Valentin Malykh
SMSergey Muravyov
Sergey Muravyov