ABAlexander Bernstein

Alexander Bernstein

*This is an algorithmically generated author record based on publicly available information.

Current Organizations / Institutes

The organizations/institutes from the scholar's latest article


Alexander Bernstein has a total of 65 co-authors. Here are the top co-authors by number of shared publications:


Latest Publications

  • Open Access

    Review of computer vision algorithms in histopathology to decipher complex features in cancer

    by Svetlana Illarionova, Anastasiia Studenikina, Joaquim Carreras, Margarita Zapevalina, Alexander V. Bernstein, Rifat Hamoudi, Maxim Sharaev

  • BioGuide: Biomedically-Guided Segmentation for Medical Tasks

    by Nadezhda Alsahanova, Yauhen Statsenko, Alexander Bernstein, Rifat Hamoudi, Maxim Sharaev

  • From Spectral Indices to Foundation Models: A Review of The AI Revolution in Satellite-based Environmental Hazard Monitoring

    by Svetlana Illarionova, Usman Tasuev, Polina Tregubova, Ivan Rubin, Dmitrii Shadrin, Aleksey Zaytsev, Dmitrii Katalevsky, Alexander Marusov, Alexander V. Bernstein, Evgeny Burnaev


  • A hierarchical algorithm with randomized learning for robust tissue segmentation and classification in digital pathology

    by S. Illarionova, R. Hamoudi, M. Zapevalina, I. Fedin, N. Alsahanova, A. Bernstein, E. Burnaev, V. Alferova, E. Khrameeva, D. Shadrin, et al.


  • Knowledge-informed randomized machine learning and data fusion for anomaly areas detection in multimodal 3D images

    by N. Alsahanova, V. Yarkin, E. Spodarev, O. Bronov, V. Bychenko, A. Marinets, E. Syrkashev, O. Karpov, E. Burnaev, A. Bernstein, et al.


  • Open Access

    Multivariate Wasserstein Functional Connectivity for Autism Screening

    by Oleg Kachan, Alexander Bernstein

    Most approaches to the estimation of brain functional connectivity from the functional magnetic resonance imaging (fMRI) data rely on computing some measure of statistical dependence, or more generally, a distance between univariate representative time series of regions of interest (ROIs) consisting of multiple voxels. However, summarizing a ROI's multiple time series with its mean or the first principal component (1PC) may result to the loss of information as, for example, 1PC explains only a small fraction of variance of the multivariate signal of the neuronal activity. We propose to compare ROIs directly, without the use of representative time series, defining a new measure of multivariate connectivity between ROIs, not necessarily consisting of the same number of voxels, based on the Wasserstein distance. We assess the proposed Wasserstein functional connectivity measure on the autism screening task, demonstrating its superiority over commonly used univariate and multivariate functional connectivity measures.

  • Machine learning for resting state fMRI-based preoperative mapping: comparison with task-based fMRI and direct cortical stimulation

    by I.N. Pronin, M.G. Sharaev, T.V. Melnikova-Pitskhelauri, A.S. Smirnov, A.V. Bernshtein, V.E. Yarkin, V.Yu. Zhukov, S.B. Buklina, E.L. Pogosbekyan, R.M. Afandiev, et al.

    ЦЕЛЬ ИССЛЕДОВАНИЯ На основе данных функциональных магнитно-резонансных томографических (фМРТ) исследований — покоя (фМРТп) и стимул-зависимой (фМРТс), а также интраоперационного картирования методом прямой электростимуляции коры (ЭСК) головного мозга разработать с использованием методов машинного обучения систему предсказаний индивидуальной активации моторной и речевой областей для предоперационного планирования у пациентов с глиомами головного мозга. МАТЕРИАЛ И МЕТОДЫ Удаление опухоли с применением ЭСК выполнено 33 пациентам (19 женщин, 14 мужчин в возрасте 19—54 лет) с глиомами больших полушарий (19 — с локализацией в моторной области, 14 — в речевой). Краниотомия с пробуждением выполнена 14 пациентам. Дооперационное картирование осуществлялось по результатам МРТ (3T) и выполнено всем пациентам по разработанному протоколу (T1, фМРТс, фМРТп). Для построения предсказательной системы с машинным обучением использованы данные открытых источников Human Connectome Project (HCP). Из этой базы данные 200 здоровых испытуемых получены для предобучения системы; далее система «дообучалась» на данных пациентов с глиомами. РЕЗУЛЬТАТЫ При ЭСК выполнены 332 стимуляции корковых зон, из них 173 с положительным ответом. По результатам сопоставлений зон активации фМРТп с фМРТс положительных ответов при ЭСК оказалось больше в зонах, предсказанных фМРТп (132 по сравнению с 112); точки стимуляции без ответа (отрицательные точки) преобладали в зонах активации фМРТс (69 и 44 соответственно). ЗАКЛЮЧЕНИЕ Разработанный метод предсказания сетевых активаций при функциональной магнитно-резонансной томографии состояния покоя с применением машинного обучения показал большую чувствительность по сравнению с классической функциональной стимул-зависимой магнитно-резонансной томографией при верификации методом электрической стимуляции коры головного мозга: при идентификации речевых зон 0,72 по сравнению с 0,66 (pp<0,05).


  • Comparison of resting state and task-based functional MRI in preoperative mapping in patients with brain gliomas

    by A.S. Smirnov, T.V. Melnikova-Pitskhelauri, M.G. Sharaev, V.E. Yarkin, A.M. Turkin, R.M. Afandiev, L.M. Khasieva, A.V. Bernshtein, D.I. Pitskhelauri, I.N. Pronin

    To analyze and compare the results of cerebral cortex mapping with task-based (tb-fMRI) and resting-state functional MRI in patients with glioma of eloquent cortical areas. There were 55 patients (24 men and 31 women aged 24 - 74 years, median 39) with glial tumors. In 26 patients, the tumor was located in motor areas. Twenty-nine patients had lesions of Broca and Wernicke's areas. All patients underwent preoperative tb-fMRI and rs-fMRI. Then, resection of tumor was carried out in all cases. Comparison of fMRI and rs-fMRI activation maps was assessed by calculating the Dice coefficient for inclusive speech and motor cortex masks and exclusive masks without brainstem, cerebellum, subcortical nuclei. Inclusive Dice coefficient for motor cortex ranged from 0.11 to 0.50, for speech cortex - from 0.006 to 0.240 (pp<0.05). When comparing the results of cortical mapping in patients with glial tumors, the use of hemispheric exclusive and inclusive masks did not significantly increase activation maps matching. Probably, low degree of correspondence was associated with different genesis of activations, as well as with high variability of speech cortex.


  • Open Access

    Absence of enterotypes in the human gut microbiomes reanalyzed with non-linear dimensionality reduction methods

    by Ivan Bulygin, Vladislav Shatov, Anton Rykachevsky, Arseny Rayko, Alexander Bernstein, Evgeny Burnaev, Mikhail S. Gelfand

    Enterotypes of the human gut microbiome have been proposed to be a powerful prognostic tool to evaluate the correlation between lifestyle, nutrition, and disease. However, the number of enterotypes suggested in the literature ranged from two to four. The growth of available metagenome data and the use of exact, non-linear methods of data analysis challenges the very concept of clusters in the multidimensional space of bacterial microbiomes. Using several published human gut microbiome datasets, we demonstrate the presence of a lower-dimensional structure in the microbiome space, with high-dimensional data concentrated near a low-dimensional non-linear submanifold, but the absence of distinct and stable clusters that could represent enterotypes. This observation is robust with regard to diverse combinations of dimensionality reduction techniques and clustering algorithms.

  • Manifold Modeling in Machine Learning

    by E. V. Burnaev, A. V. Bernstein

    Predictive Modeling problems deal with high-dimensional data; however, the curse of dimensionality presents an obstacle to the use of many methods for their solutions. In many applications, real-world data occupy only a very small part of high-dimensional observation space whose intrinsic dimension is essentially lower than that of the space. A popular model for such data is the manifold model, according to which the data lie on an unknown low-dimensional manifold (Data Manifold) embedded in the ambient high-dimensional space. Predictive modeling problems, which are studied under this assumption, are called manifold estimation problems. The general goal of such problems is to identify the low-dimensional structure of multidimensional data from a given dataset. If dataset points are sampled according to an unknown probability measure on the data manifold, there is a need to model manifolds when solving various machine learning problems. We provide a short survey of such problems and outline some approaches to their solution.