BrainMap

Mr. Bogdan Belean

PhD

- INSTITUTUL NATIONAL DE CERCETARE DEZVOLTARE PENTRU TEHNOLOGII IZOTOPICE SI MOLECULARE I N C D T I M

Other affiliations

Researcher - GRAPHIT INNOVATION FACTORY S.R.L. (Romania)

Researcher

Curriculum Vitae (31/01/2024)

Expertise & keywords

Development of an Integrative tool for Comprehensive Profiling of the Migratory Phenotype of Tumor Cells based on Microfluidic Platforms and Machine Learning Algorithms Call name: PNCDI IV, SP 5.7.1 - Proiect experimental demonstrativ
PN-IV-P7-7.1-PED-2024-2349 2025 - 2026

Role in this project: Partner team leader

Coordinating institution: INSTITUTUL ONCOLOGIC PROF.DR.I.CHIRICUTA CLUJ-NAPOCA

Project partners: INSTITUTUL ONCOLOGIC PROF.DR.I.CHIRICUTA CLUJ-NAPOCA (RO); GRAPHIT INNOVATION FACTORY S.R.L. (RO)

Affiliation: INSTITUTUL ONCOLOGIC PROF.DR.I.CHIRICUTA CLUJ-NAPOCA (RO)

Project website: http://Site proiect IOCN: mlcellm.iocn.ro si aplicatia MCELLML: https://mlcellm.graphit.ro

Abstract:

The proposed project addresses a research topic in the field of breast cancer, the evaluation and invasion of tumor cells. To be able to analyze the single cluster migration of tumor cells, the project proposes an integrative tool, MCELLML, for the comprehensive analysis of the migratory phenotype of tumor cells, based on microfluidic platforms, together with image processing and machine learning algorithms. This approach aims to obtain a tool that can be used to predict the metastatic potential of any given tumor, based on direct phenotypic data. The research project is carried out in a public-private partnership, putting together the know-how from the medical area with the applicability of computational algorithms with automatic learning. In terms of informatics approaches, the project proposes algorithms used for the automatic tracking of cell clusters migrating through microfluidic channels and for the calculation of essential characteristics of single cells and cell clusters integrated into a software application. The novelty of the proposed application is represented by the development of two different neural networks, used for the automatic identification of cell cluster events and for the migration phenotype identification, as mesenchymal or amoeboid. The software application uses the experience of medical doctors in labeling the phenotype of migrating cells, for training and validation procedures for the machine learning algorithm.

Adaptive Design and Assembly of Polymer-based nanoplaTforms for smart gene and drug delivery Call name: P 5.2 - SP 5.2.1 - Proiecte de cercetare pentru stimularea tinerelor echipe independente - Competiția 2023
PN-IV-P2-2.1-TE-2023-0300 2025 - 2026

Role in this project:

Coordinating institution: INSTITUTUL NATIONAL DE CERCETARE DEZVOLTARE PENTRU TEHNOLOGII IZOTOPICE SI MOLECULARE I N C D T I M

Project partners: INSTITUTUL NATIONAL DE CERCETARE DEZVOLTARE PENTRU TEHNOLOGII IZOTOPICE SI MOLECULARE I N C D T I M (RO)

Affiliation:

Project website: https://www.itim-cj.ro/PNCDI/adapt4dlvry/

Abstract:

Recent breakthroughs in gene therapy have cleared the way for a larger second wave of medicines and established the groundwork for next-generation technologies. An effective gene delivery system is essential for gene therapy to be successful. As some of the most adaptable building blocks in soft nanotechnology, natural and synthetic macromolecules are the main focus in the development of delivery vectors with specialized compositions and functions. In this project, we propose a novel computational approach to smart tune polymers and/or nanocomposite architectures as efficient building blocks for polymer-based nanoplatforms (PBNs). We will (i) create delivery vectors depending on the gene or drug that needs to be delivered while reducing the socio-economic burden of various diseases. We will also (ii) develop a novel protocol to find drug-excipient combinations that produce stable, self-assembled polymer-based nanoplatforms as smart delivery vectors. These will represent the scaffold that is needed to shift from the traditional drug/gene delivery to personalized medicine. Cutting-edge developments in artificial intelligence and state-of-the art modeling approaches will be all combined in the adaptive design of the polymer-based nanoplatforms in a synergistic fashion and show how computational modeling can lead to the discovery of novel delivery vectors with technological applications.

Artificial-intelligence-based end-to-end prediction of cancer immunotherapy response Call name: P 3 - SP 3.2 - Proiecte ERA.NET - COFUND
ERANET-TRANSCAN-3-TANGERINE 2022 - 2024

Role in this project:

Coordinating institution: INSTITUTUL ONCOLOGIC PROF.DR.I.CHIRICUTA CLUJ-NAPOCA

Project partners: INSTITUTUL ONCOLOGIC PROF.DR.I.CHIRICUTA CLUJ-NAPOCA (RO)

Affiliation:

Project website: http://tangerine.iocn.ro/

Abstract:

Cancer immunotherapy with immune checkpoint inhibitors (ICIs) is widely used in multiple cancer types, with proven benefits. However, response is not guaranteed, difficult to predict, and serious toxicity may occur. Predictive biomarkers for ICIs response exist, but only few of them are clinically used because they require tissue samples, are costly and increase turnaround time. Thus, there is an urgent clinical need to predict response to ICIs at patient’s

level.

Aims

TANGERINE partners have developed artificial intelligence (AI)-based histology image analysis and computed tomography (CT)-based radiomics for predicting immune features related to ICIs response. We propose to a) expand and combine them to develop and validate an end-to-end open AI tool to predict response and toxicity to ICIs; and b) identify cellular structures and image patterns associated with ICIs response that explain model predictions.

Methods

Digital images of tumour histopathology slides and CT scans will be retrieved, linked to clinical outcomes data and anonymized for analysis. An initial retrospective (2017-21) data retrieval from 1800 patients at 6 centres will continue with a prospective recruitment of 600 more to validate models. Patients that received ICls as first line for any tumour will be included and response recorded according to iRECIST. Radiomics and deep convolutional neural networks will be used. Model explainability will use spatial transcriptomics data on a subset of 30 patients. At analysis, homogenous subgroups will be considered, as gender and ethnicity.

Expected results and potential impact

TANGERINE will provide a public-available, non-invasive, low-cost tool based on routinely available images and clinical data to accurately predict ICI response and toxicity. The explanatory module might identify new patients on which ICI may be beneficial. The transnational collaboration will provide patients with enough variability to build generalizable

models.

Collaboration module CERN-RO, Atlas Tiles Calorimeter Phase II Upgrade Call name:
2015 - 2024

Role in this project: Key expert

Coordinating institution: INSTITUTUL NATIONAL DE CERCETARE DEZVOLTARE PENTRU TEHNOLOGII IZOTOPICE SI MOLECULARE I N C D T I M

Project partners: INSTITUTUL NATIONAL DE CERCETARE DEZVOLTARE PENTRU TEHNOLOGII IZOTOPICE SI MOLECULARE I N C D T I M (RO)

Affiliation: INSTITUTUL NATIONAL DE CERCETARE DEZVOLTARE PENTRU TEHNOLOGII IZOTOPICE SI MOLECULARE I N C D T I M (RO)

Project website:

Abstract:

The project is part of the CERN Atlas Tile Calorimeter Phase II Upgrade program and proposes the FPGA based firmware implementation for high voltage and temperature control of the PMT blocks using the HVOpto boards included in the Front-End electronics. This approach for high voltage regulation of the PMTs is known as the HV internal option of the Tile Calorimeter phase-II upgrade. The firmware is developed at the level of both Front-End and Back-End electronics. The Back-End electronics firmware continuously sends monitoring commands and also forwards the commands initiated by the DCS to the Front-End electronics. The aforementioned set of commands are used to set parameters for each PMT channel and also to read back PMT parameter values into the Back-End electronics. The proposed firmware description includes the data format, the VHDL wrappers with input-output ports and also the finite state machine used for the implementation of the desired functionalities.

Automated fault detection and non-contact diagnostic tools for aircraft industry Call name: P 4 - Proiecte de Cercetare Exploratorie, 2020
PN-III-P4-ID-PCE-2020-0368 2021 - 2022

Role in this project:

Coordinating institution: INSTITUTUL NATIONAL DE CERCETARE DEZVOLTARE PENTRU TEHNOLOGII IZOTOPICE SI MOLECULARE I N C D T I M

Project partners: INSTITUTUL NATIONAL DE CERCETARE DEZVOLTARE PENTRU TEHNOLOGII IZOTOPICE SI MOLECULARE I N C D T I M (RO)

Affiliation:

Project website: https://www.itim-cj.ro/PNCDI/pce368/

Abstract:

In this project, a new active infrared (IR) methodology for product testing and quality control (e.g. breathing crack detection) in airspace inspection will be developed. The method is based on IR lock-in thermography technique coupled with laser scanning of the surface to be investigated. Crack depth prediction using finite element simulations and experimental approach will also be carried out. A proof-of-concept setup including mini-PC with embedded visualization toolbox that ensures the localization and the characterization of the defect on the examined sample in real time will be implemented. The method will be validated on real samples from aircraft industry (IAR Brasov, Romania).

Genomic and microfluidic approaches in blocking breast cancer invasion and metastasis Call name:
POC 103557 2014 - 2020

Role in this project: Key expert

Coordinating institution: INSTITUTUL ONCOLOGIC PROF.DR.I.CHIRICUTA CLUJ-NAPOCA

Project partners: INSTITUTUL ONCOLOGIC PROF.DR.I.CHIRICUTA CLUJ-NAPOCA (RO)

Affiliation: INSTITUTUL ONCOLOGIC PROF.DR.I.CHIRICUTA CLUJ-NAPOCA (RO)

Project website:

Abstract:

Proiectul urmareste evaluarea fenotipului tumoral in cancerul mamar prin abordari de microfluidica si genomica functionala. Astfel, in cadrul acestei cercetari vor fi identificati noi markeri predictivi, de invazie si metastazare, respectiv markeri de evaluare a rezistentei la terapie, atat a componentei intrinseci cat si a celei dobandite in timpul tratamentului administrat. Daca scopul proiectului va fi atins, suntem increzatori ca datele noi legate de caracterizarea fenotipului tumoral, a capacitatii de invazie si metastazare a celuelor tumorale, respectiv a rezistentei lor la terapie vor juca in viitor un rol important în managementul tratamentului și stabilirea unei terapii personalizate. In acest fel, rezultatele obținute in cadrul acestui proiect ar putea duce la imbunatatirea tratamentului administrat pacienților cu cancer de sân.

Improving "eco-friendly" ceramic blocks fabrication technology Call name: P 2 - SP 2.1 - Transfer de cunoaștere la agentul economic „Bridge Grant”
PN-III-P2-2.1-BG-2016-0203 2016 - 2018

Role in this project:

Coordinating institution: UNIVERSITATEA TEHNICA DIN CLUJ - NAPOCA

Project partners: UNIVERSITATEA TEHNICA DIN CLUJ - NAPOCA (RO); INSTITUTUL NATIONAL DE CERCETARE DEZVOLTARE PENTRU TEHNOLOGII IZOTOPICE SI MOLECULARE I N C D T I M (RO); CEMACON - S.A. (RO)

Affiliation: INSTITUTUL NATIONAL DE CERCETARE DEZVOLTARE PENTRU TEHNOLOGII IZOTOPICE SI MOLECULARE I N C D T I M (RO)

Project website: https://constructii.utcluj.ro/files/2016-2017/bridge_grant/

Abstract:

The project is set to improve the ceramic material produced by CEMACON Zalau Company, by optimizing the existing technology of fabrication in order to reduce the energy demand in operation and implicitly the embodied energy in nZEBs.

The target is to improve both, the thermal characteristics and cost, by adding recycled materials and pore generating additives into the fabrication recipes. In the first stage, the basic raw materials that compose the ceramic masonry blocks will be analyzed from microstructural point of view. In the second stage, the microstructural, thermal and mechanical characteristics of some reference samples produced by CEMACON Company following the existing fabrication recipes will be defined. In the third stage the existing recipes will be optimized and the newly obtained products will be analyzed from thermal and physical-mechanical point of view. The improvement of quality control will be targeted by developing a methodology able to identify the structural deficiencies of the ceramic blocks through synchronous thermography detection. In the last stage, cost-benefit and environmental impact analyses will be performed, following the anti-seismic design regulations and the nZEB standards.

Development of active thermal-wave methodologies for non-destructive evaluation and thermophotonic imaging of teeth Call name: Projects for Young Research Teams - RUTE -2014 call
PN-II-RU-TE-2014-4-1507 2015 - 2017

Role in this project:

Coordinating institution: INSTITUTUL NATIONAL DE CERCETARE DEZVOLTARE PENTRU TEHNOLOGII IZOTOPICE SI MOLECULARE I N C D T I M

Project partners: INSTITUTUL NATIONAL DE CERCETARE DEZVOLTARE PENTRU TEHNOLOGII IZOTOPICE SI MOLECULARE I N C D T I M (RO)

Affiliation: INSTITUTUL NATIONAL DE CERCETARE DEZVOLTARE PENTRU TEHNOLOGII IZOTOPICE SI MOLECULARE I N C D T I M (RO)

Project website: http://www.itim-cj.ro/PNCDI/ru136/index.htm

Abstract:

The main objective of the project is to improve the performance in dental diagnosis and to show that using different types of modulation sources (lasers, LEDs), modulation schemes, and complex image processing algorithms, one can construct high resolution images of defective zones of teeth.

The main investigation technique will be infrared lock-in thermography, which is a non-contact and non-invasive tool.

In order to evaluate the adaptation between restorative materials and tooth, an automatic defect detection methodology will be implemented.The method will allow the assessment of both marginal and internal microgaps located at the interface between tooth and filling. The progression of demineralization of enamel with time, for specimens undergoing different treatment demineralization periods, will also be analyzed. 2D maps of the demineralized zones of dental tissue and of the interfaces will be obtained, highlighting the areas with defects .

The method will be validated by complementary techniques: SEM and X-ray diffraction.

Analysis of technologies for parallel processing of image data of stained HL tissue and automatic PDE based approach for CGH microarray image processing Call name:
2015 - 2015

Role in this project: Partner team leader

Coordinating institution: INSTITUTUL NATIONAL DE CERCETARE DEZVOLTARE PENTRU TEHNOLOGII IZOTOPICE SI MOLECULARE I N C D T I M

Project partners: INSTITUTUL NATIONAL DE CERCETARE DEZVOLTARE PENTRU TEHNOLOGII IZOTOPICE SI MOLECULARE I N C D T I M (RO); Johann Wolfgang Goethe University (RO)

Affiliation: INSTITUTUL NATIONAL DE CERCETARE DEZVOLTARE PENTRU TEHNOLOGII IZOTOPICE SI MOLECULARE I N C D T I M (RO)

Project website:

Abstract:

Regarding parallel processing of stained HL tissue images, considering the available resources for parallel computing and the existing Java implementations of the image processing pipeline, the selected software tools for parallel implementations of image processing algorithms were OpenCL. The stained HL tissue image pipeline together with the automatic cDNA microarray image processing pipeline are implemented using CUDA for multi-core architectures using OpenCL in order to decrease the computational time.

Low complexity algorithms for microarray image processing Call name:
POSDRU-PARTING-159-1.5-S-137516 2014 - 2015

Role in this project: Partner team leader

Coordinating institution: INSTITUTUL NATIONAL DE CERCETARE DEZVOLTARE PENTRU TEHNOLOGII IZOTOPICE SI MOLECULARE I N C D T I M

Project partners: INSTITUTUL NATIONAL DE CERCETARE DEZVOLTARE PENTRU TEHNOLOGII IZOTOPICE SI MOLECULARE I N C D T I M (RO)

Affiliation: INSTITUTUL NATIONAL DE CERCETARE DEZVOLTARE PENTRU TEHNOLOGII IZOTOPICE SI MOLECULARE I N C D T I M (RO)

Project website:

Abstract:

Automated system for cDNA microarray image acquisition and processing Call name:
PN-II-IDEI-332 2007 - 2011

Role in this project: Key expert

Coordinating institution: UNIVERSITATEA TEHNICA DIN CLUJ - NAPOCA

Project partners: UNIVERSITATEA TEHNICA DIN CLUJ - NAPOCA (RO)

Affiliation: UNIVERSITATEA TEHNICA DIN CLUJ - NAPOCA (RO)

Project website:

Abstract:

Automation is an open subject in DNA microarray image processing, aiming reliable gene expression estimation. The project presents a novel shock filter based approach for automatic microarray grid alignment. The proposed method brings up significantly reduced computational complexity compared to state of the art approaches, while similar results in terms of accuracy are achieved. Based on this approach, we also propose an FPGA based system for microarray image analysis that eliminates the shortcomings of existing software platforms: user intervention, increased computational time and cost. Our system includes application-specific architectures which involve algorithm parallelization, aiming fast and automated cDNA microarray image processing. The proposed automated image processing chain is implemented both on a general purpose processor and using the developed hardware architectures as co-processors in a FPGA based system. The comparative results included in the last section show that an important gain in terms of computational time is obtained using hardware based implementations.

FILE DESCRIPTION	DOCUMENT
List of research grants as project coordinator or partner team leader
Significant R&D projects for enterprises, as project manager
R&D activities in enterprises
Peer-review activity for international programs/projects