Vladimir Groza

Novosibirsk State University

Author Statistics

Papers

Citation

H-Index

i-10 index

Research Trends

Author Order

Document Type

Co-Authors

M. E. Amelin

Federal Neurosurgical Center Novosibirsk

Bair Tuchinov

Novosibirsk State University

ЕЛ

Е. Л. Амелина

Novosibirsk State University

Sergey Golushko

Novosibirsk State University

Evgeniy Pavlovskiy

Novosibirsk State University

A. Yu. Letyagin

Institute of Cytology and Genetics

Nikolay Tolstokulakov

Novosibirsk State University

Didier Auroux

Institut national de recherche en informatique et en automatique

Charles Voyton

Clemson University

Benoît Huet

Median (Czechia)

Cooperative Institutions

Centre National de la Recherche Scientifique

Inserm

Novosibirsk State University

Assistance Publique – Hôpitaux de Paris

Institut national de recherche en informatique et en automatique

Federal Neurosurgical Center Novosibirsk

Sorbonne Université

Université Paris Cité

Dokuz Eylül University

University of Duisburg-Essen

Author Statistics

Papers

Citation

H-Index

i-10 index

Research Field

Pneumothorax Segmentation with Effective Conditioned Post-Processing in Chest X-Ray

Vladimir Groza A. A. Kuzin

The automatic detection of abnormal elements in chest Xrays (CXR), such as pneumothorax, is important and challenging problem. Screening for unexpected findings or any surveys in the complicated conditions are the common scenarios for the radiologists in their clinical workflow, where the automated solutions are required. The pneumothorax can be caused by a blunt chest injury, damage from underlying lung disease or it may occur for no obvious reason at all [1]. This is one of the complex problems for the experts manual detection, which can be solved automatically and simplify the clinical workflow. Proposed method presents new segmentation pipeline for the CXR images with the multi step conditi oned post-processing. This approach leads to the significant improvement compare with any "baseline" by the reduction of the totally missed and false positive detections of the pneumothorax collapse regions. Obtained results demonstrate very high accuracy and strong robustness due to very similar performance on the double-stage test dataset. Final Dice scores are 0.8821 and 0.8614 for "stage 1" and "stage 2" test datasets respectively, what is resulted in top 0.01% standing of the private leaderboard on the Kaggle competition platform. Code is available at https://github.com/n01z3/kaggle-pneumothoraxsegmentation.

Robustness

10.1109/isbiworkshops50223.2020.9153444

Cite

Citations (16)

Identification de paramètres et analyses de sensibilité pour un modèle d'usinage par jet d'eau abrasif

Vladimir Groza

Ce travail fait partie du projet Marie-Curie ITN STEEP, dans le domaine des faisceaux energetiques. Nous etudions ici l'identification de parametres pour un modele generique d'usinage par jet d'eau abrasif. L'etude de ce probleme trouve son origine dans les applications industrielles d'usinage, ou la necessite de modeliser et predire la surface finale avec une tres grande precision est essentielle en l'absence de connaissance des parametres du modele Nous proposons ici une methode d'identification des parametres du modele basee sur la minimisation d'une fonction cout, mesurant la difference entre la solution numerique et les observations experimentales. L'approche variationnelle, basee sur le Lagrangien, permet de considerer l'adjoint, et l'utilisation d'un logiciel de differentiation automatique (TAPENADE) conduit a une identification rapide et precise des parametres, quelles que soient la complexite et la taille du probleme etudie. La qualite de l'identification peut etre fortement instable et dependre largement des donnees experimentales en cas de bruit. Nous introduisons alors des termes de regularisation permettant de gerer la presence d'erreurs de mesure. Plusieurs cas d'usinage par jet abrasif sont consideres: probleme stationnaire, jet qui se deplace a vitesse constante, ou en accelerant, utilisation synthetiques ou reelles L'etude de sensibilite montre la robustesse de l'approche, qui permet d'obtenir de tres bons resultats acceptables d'un point de vue industriel

Source

Cite

Citations (0)

Data Preprocessing Via Compositions Multi-Channel MRI Images to Improve Brain Tumor Segmentation

Nikolay Tolstokulakov Evgeniy Pavlovskiy Bair Tuchinov Е. Л. Амелина M. E. Amelin

Magnetic resonance imaging (MRI) stays one of the most essential noninvasive methods for brain diagnostics. It allows obtaining the detailed 3D image of the brain, including various types of soft tissues. In this paper, we compare the influence of the multichannel data composition approach on the model's performance. We consider the binary brain tumor segmentation problem evaluating the Dice, Recall and Precision metrics. One common way to process the medical images with the use of neural networks is to use 2D slices as the input. In contrast to the RGB images, there are plenty of methods of how to combine the multi-channel MRI data structure into the common format for ML-based algorithms. After evaluating several possible combinations we demonstrate the most performance improvement by 6–7% in Dice & Recall metrics using the pseudo-RGB approach.

10.1109/isbiworkshops50223.2020.9153416

Cite

Citations (3)

A novel imaging biomarker for survival prediction in EGFR-mutated NSCLC patients treated with TKI

bioRxiv (Cold Spring Harbor Laboratory) (2019)

Annabelle Collin Vladimir Groza Louise Missenard François Chomy Thierry Colin

Abstract EGFR-mutated non-small cells lung carcinoma are treated with Tyrosine Kinase Inhibitors (TKI). Very often, the disease is only responding for a while before relapsing. TKI efficacy in the long run is therefore challenging to evaluate. Our objective is to derive a new imaging biomarker that could offer better insights on the disease response to treatment. This study includes 17 patients diagnosed as EGFR-mutated non-small cell lung cancer and exposed to an EGFR-targeting TKI. The early response to treatment is evaluated with 3 computed tomography (CT) scans of the primitive tumor (one before the TKI introduction and two after). Using our knowledge of the disease, an imaging biomarker based on the tumor heterogeneity evolution between the first and the third exams is defined and computed using a novel mathematical model calibrated on patient data. Defining the overall survival as the time between the introduction of the TKI treatment and the patient death, we obtain a statistically significant correlation between the overall survival and our imaging marker (p = 0.009). Using the ROC curve, the patients are separated into two populations hence the comparison of the survival curves is statistically significant (p = 0.025). Initial state of the tumor seems to have a role for the prognosis of the response to TKI treatment. More precisely, the imaging marker - defined using only the CT scan before the TKI introduction - allows us to determine a first classification of the population which is refined over time using the imaging marker as more CT scans become available. This exploratory study leads us to think that it is possible to obtain a survival assessment using only few CT scans of the primary tumor.

Imaging biomarker

10.1101/681577

Cite

Citations (0)

3D-Morphomics, Morphological Features on CT Scans for Lung Nodule Malignancy Diagnosis

Lecture notes in computer science (2022)

Elias Muñoz Pierre Baudot Van-Khoa Le Charles Voyton Benjamin Renoust

Ground truth

Nodule (geology)

10.1007/978-3-031-17979-2_1

Cite

Citations (3)

Data Preprocessing via Multi-sequences MRI Mixture to Improve Brain Tumor Segmentation

Lecture notes in computer science (2020)

Vladimir Groza Bair Tuchinov Evgeniy Pavlovskiy Е. Л. Амелина M. E. Amelin

Brain tumor

Data pre-processing

10.1007/978-3-030-45385-5_62

Cite

Citations (10)

CHAOS Challenge - combined (CT-MR) healthy abdominal organ segmentation

Medical Image Analysis (2020)

Ali Emre Kavur Naciye Sinem Gezer Mustafa Barış Sinem Aslan Pierre-Henri Conze

Dice

Modality (human–computer interaction)

Sørensen–Dice coefficient

10.1016/j.media.2020.101950

Cite

Citations (512)

Optimal parameters identification and sensitivity study for Abrasive Waterjet Milling model

arXiv (Cornell University) (2016)

Didier Auroux Vladimir Groza

In this paper we present the work related to the parameters identification for Abrasive Waterjet Milling (AWJM) model that appears as an ill-posed inverse problem. The necessity of studying this problem comes from the industrial milling applications where the possibility to predict and model the final surface with high accuracy is one of the primary tasks in the absence of any knowledge of the model parameters that should be used. The adjoint approach based on corresponding Lagrangian gives the opportunity to find out the unknowns of the AWJM model and their optimal values that could be used to reproduce the required trench profile. Due to the complexity of the nonlinear problem and the large number of the model parameters, we use an automatic differentiation (AD) software tool. This approach also gives us the ability to distribute the research on more complex cases and consider different types of model errors and 3D time dependent model with variations of the jet feed speed. This approach gives us a good opportunity to identify the optimal model parameters and predict the surface profile both with self-generated data and measurements obtained from the real production. Considering different types of model errors allows us to receive the results acceptable in manufacturing and to expect the proper identification of unknowns.

Identification

10.48550/arxiv.1605.08583

Cite

Citations (0)

Chest X-Ray Pneumothorax Segmentation with the Multistep Post-Processing

Vladimir Groza A. A. Kuzin

Source

Cite

Citations (0)

Multi-class Brain Tumor Segmentation via Multi-sequences MRI Mixture Data Preprocessing

A. Yu. Letyagin Sergey Golushko M. E. Amelin Bair Tuchinov Е. Л. Амелина

In this paper, we extend the previous work on the robust pre-processing technique which allows to consider all available information from MRI scans by composition of T1, T1C and FLAIR sequences in the unique input. Such approach enriches the input data for the automatic segmentation process and helps to improve the accuracy of the segmentation performance. Proposed method also demonstrate significant improvement on the multi-class segmentation problem with respect to Dice metrics compare to similar training / evaluation procedure based on any single sequence regardless of the chosen neural network architecture. Obtained results demonstrate significant evaluation improvement while combining three MRI sequences in the 3-channel RGB like image for considered problem of multi-class brain tumor segmentation. We also provide results of comparison of various gradient descent optimization methods and of different backbone architectures. We found that different algorithms worked best for different tumors, but no single algorithm ranked in the top for all types of tumors simultaneously. Final improvements on the test part of our dataset are in the range of 6 - 9% on the trained model according to the Dice metric with the best value of 0.949.

Dice

10.1109/csgb51356.2020.9214645

Cite

Citations (7)