Rostislav Epifanov

Mr. Rostislav Epifanov


Research Focus & Metrics

Academic Career Length

3Years (2024-Present)

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

Representative Publications

View All Publications
26 June 2025 in Journal of Imaging
Verified
Journal Article
Open access
PDF file
RERostislav Epifanov
Rostislav Epifanov
--- -
- -
SDSavely Evgenievich Dyachuk
Savely Evgenievich Dyachuk
AGAlexander Gostev
Alexander Gostev
AKAndrey Karpenko
Andrey Karpenko
Rustam MullyadzhanovRustam Mullyadzhanov
Rustam Mullyadzhanov
The accurate segmentation of blood vessels and centerline extraction are critical in vascular imaging applications, ranging from preoperative planning to hemodynamic modeling. This study introduces a novel one-stage method for simultaneous vessel segmentation and centerline extraction using a multitask neural network. We designed a hybrid architecture that integrates convolutional and graph layers, along with a task-specific loss function, to effectively capture the topological relationships between segmentation and centerline extraction, leveraging their complementary features. The proposed end-to-end framework directly predicts the centerline as a polyline with real-valued coordinates, thereby eliminating the need for post-processing steps commonly required by previous methods that infer centerlines either implicitly or without ensuring point connectivity. We evaluated our approach on a combined dataset of 142 computed tomography angiography images of the thoracic and abdominal regions from LIDC-IDRI and AMOS datasets. The results demonstrate that our method achieves superior centerline extraction performance (Surface Dice with threshold of 3 mm: 97.65%±2.07%) compared to state-of-the-art techniques, and attains the highest subvoxel resolution (Surface Dice with threshold of 1 mm: 72.52%±8.96%). In addition, we conducted a robustness analysis to evaluate the model stability under small rigid and deformable transformations of the input data, and benchmarked its robustness against the widely used VMTK toolkit.

1 June 2024 in Computer Optics
Verified
Journal Article
Closed access
NUNovosibirsk State University
Novosibirsk State University
RERostislav Epifanov
Rostislav Epifanov
NNNikita Nikitin
Nikita Nikitin
MCMeshalkin National Medical Research Center
Meshalkin National Medical Research Center
ARA.A. Rabtsun
A.A. Rabtsun
IRInstitute of Thermophysics SB RAS
Institute of Thermophysics SB RAS
In this paper, we address the issue of developing of a convolutional neural network for the problem of aneurysm segmentation into three classes and of exploring ways for improving the quality of final segmentation masks. As a result of our study, macro dice score for classes of interest reaches 83.12% ± 4.27%. We explored different augmentation styles and showed the importance of applying intensity augmentation style to improve segmentation algorithm robustness in conditions of clinical data diversity. Augmentation with spatial and insensitive styles increase macro dice score up to 3%. The comparison of various inference mode indicate that combination of overlapping inference and segmentation window enlargement ameliorate macro dice up to 1.4%. Overall improvement of the quality of segmentation masks by macro dice score amounted up to 6% using combination of data-based augmentation style and advanced inference technique.

1 December 2025 in Doklady Mathematics
Verified
Journal Article
Open access
PDF file
RERostislav Epifanov
Rostislav Epifanov
YFYa. V. Fedotova
Ya. V. Fedotova
DPD. R. Popov
D. R. Popov
RMR. I. Mulliyazhanov
R. I. Mulliyazhanov
An Erratum to this paper has been published: https://doi.org/10.1134/S1064562425330026

2 July 2024 in Digital Diagnostics
Verified
Journal Article
Open access
PDF file
RERostislav Epifanov
Rostislav Epifanov
Rustam MullyadzhanovRustam Mullyadzhanov
Rustam Mullyadzhanov
AKAndrey Karpenko
Andrey Karpenko
BACKGROUND: The majority of current algorithms for blood flow surface extraction in the context of hemomodeling of abdominal aortic aneurysms are derived through a segmentation step, rather than directly from CT scans [1]. This approach introduces a degree of complexity, as the segmentation neural network is trained without consideration of the fact that the blood flow is a simply-connected region. Consequently, post-processing may be required to fulfill the simple connectivity criterion. In addition, the blood flow surface obtained from the segmentation mask using marching cubes is too coarse and requires smoothing. To provide one-stage surface extraction, Voxel2Mesh [2] was the first to be proposed. Voxel2Mesh shows good performance in extracting relatively simple geometries, while for more complex ones, its modifications have been proposed in the literature [3, 4]. AIM: The study aimed to develop an algorithm for single-stage extraction of the lumen surface of an abdominal aortic aneurysm. MATERIALS AND METHODS: A total of 90 contrast-enhanced CT images and segmentation masks with blood flow region labeling were prepared and divided into three groups: 40, 20, and 30 images for training, validation, and testing, respectively. Affine and non-linear augmentations were applied to increase the effective training sample size. A hybrid neural network consisting of a voxel encoder, a voxel decoder, and a grid decoder was proposed for single-stage surface extraction. The architectural design of the encoder is based on the Atto-sized ConvNeXtV2 architecture. The voxel decoder is comprised of five blocks, beginning with an interpolation layer and concluding with two super-precision words with packet normalization layers and ReLU. The voxel decoder and encoder are linked by means of analogous connections to those observed in the Unet architecture. The grid decoder comprises four GraphSAGE convolutions, with GeLU intervening between each pair. It is connected to the voxel decoder. The input to the encoder is a computed tomography image, while the input to the grid decoder is an initial approximation of the surface in the form of a ball. The output of the voxel decorrelation is a segmentation mask, while the output of the mesh decorrelation is the extracted surface. A combination of voxel and mesh loss functions was employed for the purposes of training. The surface generated from the segmentation mask by the Marching Cubes algorithm was employed as the reference surface. The mesh loss function was regularized to set the necessary parameters for the generated mesh. The quality of the generated mesh was evaluated using the Dice coefficient, which compares the true segmentation mask with the rasterized generated surface. RESULTS: We proposed the first hybrid neural network with an encoder based on the state-of-the-art ConvNeXtV2 architecture for the direct generation of abdominal aortic aneurysm blood flow meshes. A 14.01% improvement in generation was achieved by the Dice metric, with a score of 85.32%, in comparison to Voxel2Mesh. The results demonstrate the potential for accurate lumen geometry generation, with metrics approaching those of the segmentation task. This eliminates the necessity for post-processing steps typically required for the latter. CONCLUSION: Shows promising results for accurately generating lumen geometry with performance similar to the segmentation task, eliminating the need for post-processing steps required for the latter.