• Director Alexandru FLOARES, PhD, MD
    • University of Medicine and Pharmacy Iuliu Hatieganu Cluj Napoca
    • INCDO-INOE 2000, Research Institute for Analytical Instrumentation, ICIA Subsidiary

Intelligent Systems for Recurrence and Progression Prediction in Superficial Bladder Cancer based on Artificial Intelligence and Microarray Data: tumor mRNA and plasma microRNA – IntelUro

PCCA 2011/2012 –  Biotechnologies –  PN-II-PT-PCCA-2011-3.1-1221

Objective – IntelUro will develop and implement the most accurate (95%-100%) intelligent predictive systems for superficial bladder cancer recurrence and progression, and the bioinformatics methodology and workflow to reach such results. For a new patient, these systems will take as inputs the level of plasma microRNA (non-invasive) or tumor mRNA biomarkers discovered by us in IntelUro, and will predict if the patient will evolve toward recurrence/progression or not. The non-invasive systems are to be preferred except for clinical situations where the invasive surgical procedure cannot be avoided. Thus, the therapy could be personalized for the benefit of the patient with a dramatic decrease of the management costs.

Bladder cancer- Bladder cancer  is the fifth most common neoplasm accounting for about 5-7% of all new diagnosed malignancies in men, and about 2-2.5% in women. In addition to male gender, other risk factors include high age, tobacco smoking and occupational exposure to carcinogens.
From a clinical perspective, bladder cancer has been traditionally subdivided into either superficial (Ta or T1) or invasive (T2, T3, and T4) subtypes. The two types are quite different in their overall characteristics, with superficial disease having long-recurrence free episodes in most cases, while invasive disease often requires multimodal therapies combining surgery as well as chemotherapeutic approaches.

Biomarkers: tools for predicting disease evolution – The fact that bladder cancer is still an exceptionally lethal disease with an annual mortality almost equivalent to its annual incidence has stimulated intense research efforts directed at understanding the underlying molecular mechanisms. Important goals are the detection of cancer at an early stage, determining prognosis and monitoring disease progression and therapeutic response.
Recent experimental results suggest that patients with the same type of cancer often have dissimilar genetic defects in their tumors. These findings explain why patients with the same type of cancer have a different evolution and respond differently to the treatments applied. In consequence, cancer therapy is slowly shifting towards a more personalized approach in which each patient is treated according to the specific defects in the tumor (Veer and Bernards, 2008). Personalized medicine is the ultimate goal of modern cancer treatment and its success depends on the availability of cancer biomarkers (biological indicators) that can be used to guide treatment. Molecular biomarkers represent alterations in gene sequences, expression levels, protein structure or function which can be used as to detect cancers at an early stage, determine prognosis, and monitor disease progression or therapeutic response.
Biomarkers which can predict the evolution of the disease and can help physicians decide which therapy is most likely to be effective for a given patient are invaluable tools for bothcancer research and clinical practice, yet few biomarkers are in clinical use despite decades ofintense effort (Tuma, 2008). Identification of appropriate biomarkers will enable evidence-baseddecision support for different treatment options considering risks, expected benefits and medicalcosts. Furthermore, clinical management of patients can greatly be improved, for example, for some tumors surgical removal is curative and adjuvant therapy is not necessarily, while for more malignant tumors aggressive systemic therapy, often chemotherapy, is required after tumor resection. The distinction between the more mild and the more aggressive BCa is not clear by usual clinico-pathological investigations, therefore decision support systems that can accurately predict the likelihood of recurrence and progression are urgently needed in the clinic.

MicroRNA as noninvasive biomarkers – MicroRNAs (miRNAs) are small, 19- to 23-nucleotidelong, single-stranded RNA molecules. It has been shown that miRNAs can affect the stability of messenger RNA (mRNA) and in some cases influence protein synthesis through partial sequence complementation with their interacting mRNA targets.. The specific regulation and biological function of miRNAs is largely unknown. The network of interactions is probablyas complicated as other biomolecular networks in the body. Unlike most classes of biomolecules, however there are far fewer known miRNA species. Like mRNAs, some miRNAs also show restricted tissue distribution; for example, miR-122 is highly enriched in liver, whereas miR-124 is preferentially expressed in neurological tissues. It has been shown that changes in the spectrum of cellular miRNAs correlate with various physiopathological conditions, including differentiation, inflammation, diabetes, and several types of cancers.
Currently, there are more than 1000 known miRNAs for humans (miRBase release 13.0), and they do not have known postprocessing modifications, which makes their composition much less complex than that of other biomolecules. Recently, some of the miRNAs previously identified in cells and tissues have also been found in extracellular fluids such as plasma, serum, saliva, and urine. The level and composition of these extracellular miRNAs again show changes that correlate well with diseases or injurious conditions. These observations suggest that extracellular miRNAs can be used as informative biomarkers to assess and monitor the body’s physiopathological status The ideal biomarker must be accessible using noninvasive protocols, inexpensive to quantify, specific to the disease of interest, translatable from model systems to humans, and a reliable early indication of disease before clinical symptoms appear.
Lower complexity, no known postprocessing modifications, simple detection and amplification methods, tissue-restricted expression profiles, and sequence conservation between humans and model organisms make extracellular miRNAs ideal candidates for noninvasive biomarkers to reflect and study various physiopathological conditions in the body.Therefore, miRNA profiles in serum and plasma samples from cancer patients have been screened to identify novel biomarkers for the diagnosis and evolution of tumors.

Modeling workflow – The main strategy of IntelUro consists in combining advanced artificial intelligence methods, in a knowledge discovery in data approach, with both mature genomics techniques like mRNA microarray and novel and promising methods like microRNA (miRNA) array. In order to attain its objective, the project uses an interdisciplinary approach, which requires a complex team including clinicians, pathologists, imaging doctor, molecular biologists and bioinformaticians. The IntelUro framework consists of an integrated solution for the following electronic medical recording software modules: clinical, imagining, pathological, and molecular biology catalyzed by a bioinformatics module.
The pathological, clinical, imaging and molecular module provide data that will be used by IntelUro to build classifiers for predicting progression and recurrence of bladder cancer. The performance of these classifiers strongly depends on the quality of data.

Bioinformatics module – High-throughput experiments investigate thousands of molecules in parallel. Bioinformatics tools must be used to select and rank a subset of molecules, hundreds or preferably tens, capable to discriminate between two or more medical situations. A challenging biomedical informatics problem is to use artificial intelligence to transform, interesting but not very useful, lists of ranked molecules into Intelligent Clinical Decision Support Systems. These should take as inputs the most relevant subset of molecules, and predict with the highest possible accuracy important clinical outcomes. In the following we enumerate and briefly describe the workflow associated with the bioinformatics module. It is based on the following steps.

– Data Collection and Integration.
– Data preprocessing
– Identifying differentially expressed genes.
– Clustering of genes and sample
– Annotation and placing differentially expressed genes on pathways/networks.
– Developing classifiers and intelligent clinical decision support systems


Goal: The INTELCOR project will develop the best non-invasive colorectal cancer (CRC) diagnosis, early detection, differential diagnosis (with benign adenoma), and progression prediction tests. The last two tests will be developed for the first time. To be considered the best, the tests should be the most accurate (95%-100%), robust, and transparent. The tests are based on circulating microRNA (non-invasive) and advanced artificial intelligence methods (the highest robust accuracy). They will be also white-box or transparent models, discovered from microarray data, and their relationship with the hallmarks of cancer will be revealed, using knowledge mining in various knowledge bases.

These tests will take as inputs the levels of circulating microRNA biomarkers discovered by us, and will output a diagnosis – normal, CRC, or adenoma – or a prognosis – progressive or non-progressive CRC. To transform these molecular and cellular models into real clinical decision support (intelligent) systems, they will be embedded in an automated CRC clinical workflow, created for the first time. The tests will be also implemented as Software as a Service (SaaS) and in hardware (via FPGA), to further increase their commercial potential. This will be done for the first time for a medical test.

INTELCOR is a highly interdisciplinary project. Thus, UMF Cluj (P1) will enroll and investigate the CRC patients clinically, pathologically, imagistic, and will produce the corresponding microarray data. SAIA will develop a bioinformatics data analysis workflow and use it to develop the tests, which will be functionally analyzed together with P1. Rivel Market (P2) will develop and implement a top level CRC Electronic Medical Records for data integration, and the first automated CRC clinical workflow for tests integration into clinical practice. They will also implement the tests as software packages, as SaaS, and in hardware, for commercial reasons.

As validation on large cohort of patients is known to improve the credibility and the marketability of omics tests, more data will be acquired from specialized companies. All available data will be integrated by CO in a multicenter database and a meta-analysis will be performed. As in any project combining high throughput data with artificial intelligence, the number of microarray samples and the computational power are important, but costly. INTELCOR is carefully designed to satisfy the financial and time constraints and reach not only the best published results, but also the best CRC omics tests on the market, by properly combining the human resources and facilities of the 3 partners with the project budget.



  • University of Medicine and Pharmacy Iuliu Hatieganu Cluj Napoca
  • Babes-Bolyai University
  • The“ Ion Chiricuta” Cancer Institute -Comprehensive Cancer Center
  • “Raluca Ripan” Institute For Research in Chemistry, Babes-Bolyai University

Improving diagnosis and therapy of bladder cancer in the context of the emergence of new urinary tumor markers, and cytogenetic characterization of minimally invasive therapeutic methods

From the informational website about Vezuvium research project .


Theme design fits into the overall goal of the program CEEX Medicine and innovative technology platform is fully compliant with the specific objectives of the thematic area.

Measurable objectives:

  • study on bladder cancer early detection, diagnosis and appropriate therapy for each patient diagnosed in order to decrease mortality from this pathology
  • Increase accuracy paraclinical diagnosis of bladder cancer by entering the diagnostic arsenal of new items: urinary tumor markers
  • Analysis of concordance between prediction methods known diagnosis – urinary cytology, abdominal ultrasound, urethrorectal-cystoscopy and urinary tumor markers, results were assessed after histological results
  • increasing the proportion of cases of bladder cancer diagnosed in the early stages of disease
  • Translational research in major diseases by assessing genetic changes in patients with bladder cancer specimens studied histopathological
  • the methods curative in patients diagnosed in early stages of disease (transuretrorezectia bladder – TUR-V)
  • the methods curative in patients diagnosed in local stages infiltrative disease – classical radical laparoscopic cystectomy, external radiation or dam curieterapia
  • the methods palliative surgery in patients in advanced stages of disease – internal and external urinary drainage
  • monitoring patients
  • Increase the total number of cases of bladder cancer detected
  • Introduction to diagnostic protocol methods to increase detection sensitivity disease – urinary tumor markers such as NMP 22, BTA, fibrin degradation products and evaluating engagement risk factors for responsiveness to neoadjuvant therapy / adjuvant by immunohistochemical criteria designed to define genotypic bladder tumors to develop patient oriented strategies from prevention to diagnosis and treatment
  • the results obtained in specialized works.
  • Promote multidisciplinary research project to understand and correlate medical results in current modern context. Based on the results and partnership achieved to a depth multidisciplinary basic research, clinical research and create the opportunity to continue in future studies proposed in this project thus ensuring internally:
  • Developing a network of institutions that can become internal sources of scientific and technical competence in the field of innovative medicine
  • Increasing the uptake, implementation and development of knowledge, services and advanced technologies to handle evolution and international competition.


  • Applied Research Phase I. Critical analysis of data from the literature, techniques and equipment used. Preliminary research.
  • Stage II. Applied research. Selecting and characterizing groups of patients.
  • Stage III. Applied research. Monitoring groups of patients and integration of new patients in the study. Preliminary Statistical evaluation of the data obtained.
  • Stage IV. Applied research. Reassessment tracking standards oncology patients and correlate data obtained additional information from the study. Investigation of new patients using diagnostic algorithm obtained in previous steps. Statistical evaluation of the data results.
  • Stage V. Applied Research. Support activities. Transferring important study results based on the new biological marker introduced in medical practice. Dissemination of results.


  • Translating research into clinical practice by implementing the algorithm for the diagnosis of urinary bladder cancer tumor markers
  • Create a unique database for evaluating screening strategies in improving early diagnosis of bladder tumors
  • scientific communication in the country and abroad, publishing articles in professional journals presenting clinical trial design and highlighting the country’s scientific potential
  • contribution to the international recognition of the state of scientific, technical and technological Romania
  • publication of results will allow the increase of international cooperation
  • attract and support young people through their involvement in this research project


  • exploitation of the project results
  • reducing medication and health care costs that raising the quality of life
  • diversifying the areas of applied research through interdisciplinary scientific collaborations
  • increasing the involvement of researchers in areas of great
  • use scientific capacity of members of research teams
  • new opportunities for participation in research programs representative for the European area.
  • Dissemination of results will be made by communication and publishing results in articles in professional journals Romanian and foreign participation in national and international congresses specialized Web page, CD-ROM presentations, brochures, books, conference virtual roundtable common.



  • Technical University Cluj Napoca
  • The“ Ion Chiricuta” Cancer Institute -Comprehensive Cancer Center   
  • University of Medicine and Pharmacy Iuliu Hatieganu Cluj Napoca
  • Software Itc Cluj S.A.

Intelligent System for the Noninvasive Detection and Evaluation of Liver Fibrosis, Restructuration and Dysplastic Nodules, Using 2D/3D Ultrasound and Molecular Markers – SIDEF.

From the informational website about a CEEX research project  SIDEF

The S.I.D.E.F. project wants to create a model for the prediction of the degree of liver damage, based on an intelligent system of noninvasive evaluation and detection of fibrosis, regeneration and dysplastic nodules of the liver with the use of 2D and 3D ultrasonography and molecular markers. In order to do this one would have to perform an experimental research, the result of which will be a prototype able to analyze the ecographic 2D and 3D image and discern between normal and other different pathologic stages (fibrosis, liver cirrhosis or dysplastic nodules). In the second stage, of applicative research, the product will be developed and optimized through clinical correlation studies, through the integration of the information provided by different molecular markers, so in the end one could homologate and validate a noninvasive diagnosis computer system of liver diseases. The automatic analysis system of the ecographic images is desired to also have a knowledge communication and managing role, helping the doctor to take optimal diagnosis decisions (C.A.S. – Computer Aided Solution).

The consortium– made of five institutions with tradition in research and with experience in excellence research – wants the long term results of the project to allow a better understanding of the pathogenetic mechanisms that cause the ecographic perceptible changes. The creation of some recommendations of treatment based on complex, but noninvasive, evaluation in liver disease will constitute the crowning of all efforts made by researchers. Another important aspect is that of the possible advantage offered by the “export” model to other fields where it could be applied.

The degree of innovation and originality of the project is based on the integration in medical practice of a diagnosis computer aided system, which will realize the integrated processing of complex medical data, allowing the noninvasive hi-fi diagnosis of liver disease. We consider that this model is a “virtual liver biopsy”. This could help the original research contribution, in a field of high interest in the European research circuit, permitting the connection between the scientific and academic community in Romania and the international idea flow in the field of hepatology. The complexity of this project is the result of the great work volume, condensed with the help of modern computer techniques, of the information processing speed and of the significant decrease of diagnosis costs. By abandoning the invasive diagnosis, as much as it is possible, one could achieve a substantial saving of founds and a shifting of financial resources from the diagnostic needs to the therapy.



  • Technical University Cluj Napoca
  • The“ Ion Chiricuta” Cancer Institute -Comprehensive Cancer Center
  • University of Medicine and Pharmacy Iuliu Hatieganu Cluj Napoca
  • Software Itc Cluj S.A.

Prediction evolution and estimation of treatment response of malignant tumors by morphologic and hemodynamic modeling, using imaging techniques, mathematical and artificial intelligence – ANGIOTUMOR

Project funded by the Ministry of Education and Research Excellence programs CEEX 2006, Program VIASAN – no. 138/2006

ANGIOTUMOR is a fundamental research project applied clinical character who pursue complex mathematical models and imaging of
tumor neovascularization using information extracted from clinical practice by ultrasonography (U.S.) for high performance. Research for
this purpose include the latest developments in medical imaging, information and communication technology (ICT), image processing and
data analysis and processing using artificial intelligence systems.

The importance of this project is that it will have immediate application in clinical imaging services and oncology wards and can be used for research and therapeutic efficacy in clinical trials following the various chemotherapeutics.

To fulfill their intended purpose ANGIOTUMOR project has set the following objectives:
Assessment of malignant tumor neovascularization using high performance ultrasound techniques, immunohistochemistry, cell culture,
mathematical modeling, imaging and evolving.
– Analysis of angiogenesis as a method for predicting the development of malignant tumors.
– Development of quantitative models for describing and predicting therapeutic response dynamics of malignant tumors
– The ultimate goal is to generate abstract simulation systems spatial and temporal development of tumor angiogenesis process for:
– Accurate noninvasive diagnosis of disease
– Assess the potential evolutionary and cancer prognosis
– Estimation of treatment response.

Stage I – tumor nodules study and data traffic in experimental angiogenesis, VEGF, current therapies: circulation changes in tumor nodules
treated (anti-VEGF, chemo, radiation).
Step 2 – Set group of patients, 2D/3D cross examination protocols, eco Doppler Angiopower, histogram, morphometry, serology, histology,
immunohistochemistry, tumor cell cultures
Step 3 – modeling and design system components
Step 4 – Improving imaging model year angiotumor genesis. The development of mode improvement of angiogenesis in vitro. Realization
and verification of software components medical deck assisting the research component. Evaluation and optimization of experimental
models (in vitro and imaging) of tumor angiogenesis.



  • The“ Ion Chiricuta” Cancer Institute -Comprehensive Cancer Center
  • University of Medicine and Pharmacy Iuliu Hatieganu Cluj Napoca
  • The Institute of Public Health “Iuliu Moldovan„ Cluj-Napoca  

Implementing mini invasive therapy in colorectal cancer improving diagnosis and prognosis correlated to the plasmatic level of angiogenesis molecules in relation to VEGF. CELIOMARK

From the informational website about a research project  CELIOMARK.

General and specific objectives, estimated results:

Measurable aims:

  • a study of early diagnosis of colorectal cancer
  • evaluating risk factors, associated pathologies with high risk of developing colorectal cancer
  • introducing new methods of diagnosis that will increase sensitivity in detecting the disease and the prognosis – angiogenesis markers in the attempt to establish a proper treatement
  • to determine the level of angiogenic markers and VEGF in the resected tumours and establishing a relationship with their plasmatic levels with the purpose of including the results of the research in the colorectal cancer treatement strategy (monoclonal antibodies)
  • to evaluate the correlation between the level of angiogenic markers, VEGF and the surgical technique (open vs. mini invasive)
  • staging by intraoperative liver ultrasound
  • the use of various therapy methods in relation to the stage of the disease
  • monitoring the patients
  • to evaluate the complications of colorectal cancer (haemorrhage, perforation, occlusion)
  • to increase the number of case diagnosed in early stages
  • to evaluate treatement costs
  • to evaluate the opportunity of screening by increasing the compliance of the population concerning the disease
  • creating a unique database
  • processing the data
  • presenting the results in journals, medical convention
  • developing teaching and training programs.

The project includes 3 activities regarding colorectal cancer: screening, molecular evaluation of genes involved in tumour angiogenesis and mini invasive surgical treatment, the consequent data processing being accomplished by systems involving artificial intelligence, systems with higer objectivity and prediction capacity.

Expected results:

  • an increased number of newly diagnosed colorectal cancer cases
  • an improved life quality for patients with colorectal cancer
  • the development of early diagnosis and treatment strategies in colorectal cancer
  • a decrease in hospitalisation costs
  • to present results at national medical conventions thus promoting new information
  • training specialists in the field
  • to inspire postgraduate and PhD studies in this field



  • The“ Ion Chiricuta” Cancer Institute -Comprehensive Cancer Center
  • The Institute of Public Health “Iuliu Moldovan„ Cluj-Napoca (ISPCN)
  • S.C. Biona SRL

Defining the molecular transcriptomic profile for predicting the clinical outcome of anthracycline resistant breast cancers. Defining metastases in relation with the primary tumor. – Breast-OMICS

Defining the molecular transcriptomic profile for predicting the clinical outcome of anthracycline resistant breast cancers. Defining metastases in relation with the primary tumor. From the informational website about a research project realized in the National Program of RDI.—PN II-partnership, BREAST-OMICS.

Project description: BREAST-OMICS subscribes to Health area 4.1.3. Investigation and intervention methods based on molecular and cellular medicine, genomics and proteomics.  This project is based on a highly complex partnership and seeks to develop the interdisciplinary sciences and high tech fields of genomics and proteomics in Romania, in the field of oncology. It would study tumor pathology and would use the newest technologies of genomics (microarray) and proteomics (protein-array) in breast cancer. The project will be carried on 36 months.It is estimated that 1 out of 8 (13%) women will develop breast cancer during their life and 1 out of 33 will die from it.

New concepts that resulted from the microarray technology in the discovery of biomarkers have shown that the pattern of transcription or the proteins can lead to a correct and timely diagnosis. By evaluating a single biomarker, these modern technologies (microarray, protein array) are capable of providing data about the whole transcriptome or proteome associated with cancer. They are able to evaluate thousands or tens of thousands of transcription products or proteins associated with the genes of interest. It is thus possible to study the differences between normal and tumor cells as well as the cellular mechanisms responsible for the development of cancer.

The resistance to cytostatics is one of the major problems in the treatment of cancer and the study of pharmacogenomics, which analyzes the simultaneous expression of the entire cellular transcript, is the only tool capable of clarifying the function of the cell after a treatment with cytostatics. The main aim of this project is to define of the molecular transcriptomic profile for the optimization of neoadjuvant anthracycline treatment in breast cancer. The objectives of the study are: the identification of a molecular signal through microarray, the analysis of differential gene expressions during anthracycline treatment; the validation through tissue array studies of the principal proteins associated to the studied genes; the evaluation of proangiogenic molecules in the development of the tumor and during treatment; the identification of a molecular target for angiogenesis and immune system modulators that will help define metastases and the primary tumor.


  • Partners:
    • Technical University Cluj Napoca
    • The“ Ion Chiricuta” Cancer Institute -Comprehensive Cancer Center
    • University of Medicine and Pharmacy Iuliu Hatieganu Cluj Napoca
    • IPA SA CIFATT Cluj subsidiary


From the informational website about a research project  Intel-PRO
General objectives:
• Prediction of postoperative evolution of disease in patients with localized prostate cancer without metastases, after the radical prostatectomy operations by integrating them into groups with different prognosticuri, according to PSA level
• Reduce discomfort and the degree of invasiveness of medical practice, minimizing risks and costs involved
Specific objectives:
• collection of medical data in a systematic manner appropriate for research project
• Obtaining useful information from your computer imaging methods, automated, characterization and recognition of tumor detection, localization and delimitation of its
• Extracting domain knowledge, representation, their extension and improvement, in order to optimize the process of diagnosis and prediction of disease evolution, extract inference rules

The main activities:
• Development of medical research protocols for data acquisition
• Database structure modeling, database implementation
• Data collection, preprocessing and integration
• Development of methods for processing, analysis and recognition of images.   Definition and model generation imaging prostate adenocarcinoma (ADKP)
• Development of methods for data mining (data mining)
• Developing an ontology, a knowledge base of an expert system
• Development of an experimental system that integrates modules made ​​in various fields