ICT for Health

Accelerator-based HPC for Genomic computational building blocks

ABSTRACT

Over the past two decades, genomic has paved the way for new breakthroughs in biology and medicine. The ability to effectively handle and process genomic information, e.g. for activities like analysing and aligning DNA and protein sequences as well as generating 3D models of protein structures, is by all means crucial. The activity is focused on understanding the computational implications of next-generation sequencing approaches as well as investigating developments at the algorithm and implementation level matching the opportunities of emerging high-performance computing (HPC) accelerator-based technologies.

Available

Can be assigned to one doctoral student of cycle XXXVI 

OBJECTIVE

The main objectives of the activity will include:

• studying the computational building blocks in current genomic applications;
• investigating efficient implementation approaches based on emerging accelerator-based architectures, including GPU and FPGA devices;
• demonstrating the proposed approaches on next-generation HPC platforms, including large scale HPC facilities and/or small-scale innovative prototypes.

AI-supported modeling for retrospective and prospective health-related studies (e.g. infectious diseases due to COVID-19).

ABSTRACT

Health-related analyses generate huge amounts of heterogeneous data. Obtaining knowledge from these “big data” is both challenging and promising for data-driven medicine, that can benefit from AI tools to infer models for such complex problems. The PhD research activities will include model design, optimization, and validation, applied to prospective and retrospective studies, with the support of the MS partner (including data sanitization operations, and resulting analysis and validation). The PhD student will spend at least six months abroad working under the guidance of one or both our foreign partners, University of Warwick (UK) and University of Saint Louis (US).

Available

Can be assigned to one doctoral student of cycle XXXVI 

OBJECTIVES

Main goals include the development and application of innovative approaches to prospective and retrospective studies, aimed at modeling the complexity of infectious diseases. The approaches will be supported by AI and Big Data technologies.

Delivery Manager of Cognitive Computing for Neuroncology 

No More Available

Already assigned to a PhD student of cycle XXXV

From Metanalysis to the Cognitive Computing approach in Brain Tumors / Rare Tumors

ABSTRACT

Starting from structured and structured medical data, cognitive computing approaches has the aim to derive results and correlations that can be used later with widely validated statistical strategies such as standard and network meta-analysis.  The Standard Metanalysis and the most advanced Network Metanalysis, was used in an original research conducted at the Operative Unit of Neuroncology / Rare Tumor Regional Center of the AOU Federico II

Available

Can be assigned to one doctoral student of cycle XXXVI 

OBJECTIVE

Acquire structured and unstructured data, and implement flows and components shown in the architecture above

ABSTRACT

Multidisciplinary Prostate Cancer Units are designed to facilitate cross consultation and joint decision-making based upon diagnostic evidence to patients. At present, substantial gaps exist in their ability to accurately predict outcome and to counsel patients on short-mid and long-term treatment options. We propose to derive a Quality of Life factor through artificial intelligence and Big Data analytics, collecting, and analyzing data from 3 National Institutions, to understand how a patient’s quality of life changes over time according to type of treatment received and disease progression, also taking into account comorbidities and their own progression.

Available

Can be assigned to one doctoral student of cycle XXXVI

OBJECTIVES

Derive a Quality of Life factor through artificial intelligence and big data analytics, to create a comprehensive patient profile that will ultimately save time, consolidate knowledge, give emotional support, provide measurement of physical and mental health, and personalized treatment.

ABSTRACT

Nowadays electronic medical records, billing, clinical systems data from wearables and various pieces of research provide huge amount of healthcare information. Careful analysis of these data can lead to smarter decisions, better patient care and cost savings. In this context the development and usage of analytics and data science techniques represent a valuable decision support tool for the improvement of the clinical care activities and prevention of disease or health incidents.

Available

Can be assigned to one doctoral student of cycle XXXVI

OBJECTIVES

Main objectives are the processing and development of data science techniques for: i) drug discovery and quick/precise diagnosis by the processing of clinical and laboratory reports; ii) healthcare cost reduction and resource exploitation optimization (room usage, personnel scheduling, device maintenance, etc.).

Giovanni Poggi

Development of a Remote Ecosystem for implanted Neuromodulator to realize real-time Adaptive Therapy for Neurological Diseases.

Marco Lops

ABSTRACT

The usage of adaptive neuromodulation devices with simultaneous sensing and stimulation is the most recent advance in clinical neurological therapy. Sensing and stimulating specific areas in the nervous system will lead to maximize global knowledge about disease model, minimize time delays for therapy actuation and investigate the instantaneous response to a stimulation, enabling thus the deployment of a medical artificial intelligence as real-time therapy controller. The capability to grant a viable, low-energy communication layer between Implanted devices and computing resources is essential to allow the flourishing of neuromodulation as a continuous bioelectronic medicine

Available

Can be assigned to one doctoral student of cycle XXXVI 

OBJECTIVES

Develop a remote controller system that could enable a use case involving end-to-end adaptive-loop neuromodulation, in order to:

• minimize energy expenditure in the implanted pulse generator;
• fulfil therapeutic task (e.g. damping oscillating behaviour in neurological disease like Parkinson, essential tremor, bypass damaged nervous areas, forecast seizures) while minimizing potential side-effects;
• providing data exposure to third-parties in order to provide data for analytics and AI system;
• enable a reliable and non-invasive patient-centric monitoring system for chronical disease.
• allow interoperability with other medical use-cases related to tele-health system

Paolo Bifulco

ABSTRACT

The research aims to improve knowledge on the electrical potential generated by neurons in the brain in physiological condition and in some diseases such as epilepsy. Acquisition of biopotentials by means of electrode matrices placed directly on the brain cortex combined with anatomical information obtained by CT and MRI can provide more accurate information about the functioning of various brain areas. This can enrich our knowledge about neuroscience issues, support more specific diagnoses and treatments of pathologies and design new brain computer interfaces.

Available

Can be assigned to one doctoral student of cycle XXXVI

OBJECTIVES

To obtain accurate anatomical localization of neuronal population that generate specific EEG waves by means of biomedical signals and images processing. Interpretation of some brain functions in healthy and pathological subjects. Development of diagnosis and therapy support tools.

ABSTRACT

Our lives depend more and more on the correct functioning of computer-based medical devices, ranging from wearable appliances to surgical robots. Nevertheless, as also witnessed by recent studies, software malfunctions and cyber attacks targeting such devices may harm patient health or cause sensitive data leakages.  With the collaboration of Italian and foreign partners, the aim of the research is to analyse the potential threats in current and future medical applications and define/experiment actionable countermeasures.

Available

Can be assigned to one doctoral student of cycle XXXVI

OBJECTIVES

- Analyze the current practice for patient data treatment and data collection from real equipment
- leverage real-time data analytics solutions for on-line fault or attack detection
- experiment with real-time software containerization to isolate critical components

Francesco Amato

ABSTRACT

Cardiovascular diseases represent, to date, the major cause of mortality worldwide. Diagnosis of the most frequent of such disease, Acute Myocardial Infarction (AMI), requires the evaluation of time-series measurements of specific cardiac biomarkers. The project will develop novel dynamical models, which synthetically describes the basic mechanisms underlying cardiac troponin release into the plasma, after the onset of AMI. The aim of the project is to provide the clinicians with a quantitative tool to analyze such timeseries, to enhance the diagnostic procedures 

OBJECTIVES

An experimental campaign will be performed versus a dataset of AMI patients treated at the Interventional Cardiology unit of the Catanzaro University Hospital, to show the potentially relevant implications on both the quality and cost of diagnosis and prognosis of the AMI pathology.

ABSTRACT

The goal of this research activity is the development of computational tools and algorithms for diagnostics at the single cell level by using holographic imaging in opto-fluidic environments. Recently, optical imaging and microfluidics was used synergistically to synthesize novel functionalities for biological samples characterization. Among optical imaging modalities, the label-free quantitative phase imaging by digital holography has been demonstrated as one of the most powerful method to investigate biological samples for diagnostic purposes. The digital holography research unit at the Istituto di Scienze Applicate e Sistemi Intelligenti “E. Caianiello”, Consiglio Nazionale delle Ricerche (ISASI-CNR), has been recognized as worldwide leader in the aforementioned fields, especially for applications in blood diseases diagnostics.

Available

Can be assigned to one doctoral student of cycle XXXVI

OBJECTIVES

The PhD research activity will focus on the development of new algorithms and computational tools for:

• Fast and accurate identification of rare cells in blood samples though suitable label-free biomarkers.
• Speeding up the holographic processing with the aim to implement the real-time point-of-care diagnostics paradigm.
• Design and implementation of new opto-fluidics solutions.

The possibility to employ deep learning based strategies to achieve the proposed goals will be considered

ABSTRACT

Understanding when a patient with bladder cancer is in a real progression of disease requires a great deal of interpretation of a huge amount of data that often may not be analyzed effectively by the oncologist when a decision must be taken. The aim of the research is to develop an appropriate classification of cancer that indicates, through machine learning techniques and statistical analysis of patients’ clinical variables, the status of the bladder cancer, how it is progressing and if a change of therapy is needed. The research will be in cooperation with Clinical Research Technology S.r.l. (IT), European Institute of Oncology (IT) and Klinik Sankt Moritz (CH).

Available

Can be assigned to one doctoral student of cycle XXXVI

OBJECTIVES

The aim is to help the oncologist to better understand when a change of therapy is needed through machine learning methodologies and statistical analysis of clinical variables such as the patient's medical condition, the aggressiveness of the cancer, the effectiveness of the treatments.

ABSTRACT

In subjects with autoimmunity (i.e., multiple sclerosis), an important aspect of the immune system is how T lymphocytes respond to T cell receptor (TCR) stimulation. This is a key event controlling the fate of naïve T lymphocytes impacting on activation, differentiation and regulation of the immune response, which has been shown to be impaired in subjects with autoimmunity. T cell responsiveness is inherently stochastic (i.e., it cannot be predicted a priori) due to different sources of noise that are intrinsically produced by the underlying biochemical reactions. Such a noise may influence T cell activation grade by degrading the information transmission from the TCR.

Available

Can be assigned to one doctoral student of cycle XXXVI

OBJECTIVES

The main focus of this research activity is to develop specific mathematical models to understand the kinetic and dynamic issues regulating the TCR stimulation process and its possible alterations during autoimmunity. Results from this study could help to identify the relevant molecular targets and pave the way for the development of novel therapies aimed at restoring T cell responsiveness in autoimmunity.

Oncological Pain Automatic Assessment

ABSTRACT

In oncological patients, pain is one of the most disabling symptoms. The correct approach to pain treatment has a positive impact on her prospectives to afford other therapies for recovery. Therapist defines treatment based on subjective pain scales and continuously refine drug dosages, based on the patient responses, in a loop that sometimes hardly converging. This project aims at creating an automatic pain assessment protocol, based on the collection of multimodal data generated during a patient's life. Patients will be remotely monitored, recording texts (questionnaires), video (self-report), biometric parameters (recorded via personal devices), drug timing scheduling, etcetera. This project falls in the area of big data technologies for health. Physicians will cooperate with computer scientists and data analysts to design, process, and evaluate this flux of data to be used both for real-time monitoring and training of AI systems.

Available

Can be assigned to one doctoral student of cycle XXXVI

OBJECTIVES

• the creation of a dataset for pain assessment substituting subjective scale for self-evaluation;
• the definition of an interventionist protocol in the field of refining treatments and drug dosages ;
• the design of AI-based decision making systems in the field of big data for oncological purposes.

ABSTRACT

A key challenge for the development of personalized therapies is the ability of delivering drugs in situ and avoid unwanted side effects to the patients. A promising approach is the use of synthetically engineered cell populations with advanced functionalities whose collective behavior can be carefully controlled so that they can move to the target area and release some drug. This proposal focuses on the development of multicellular control strategies to create microbial consortia in which cell populations cooperate to realize this challenging goal. The project will be supervised by the proponent together with prof Brunetti and prof Surace at the Dept. of Translational Medicine and will involve active collaboration with leading groups at ETH and Bristol and the start-up companies at TIGEM.  

No More Available

Already assigned to a PhD student of cycle XXXV

OBJECTIVES

- Develop synthetic biology approaches for drug delivery based on multicellular consortia;
- Synthesize gene regulatory networks to implement the desired functions in vivo;
- Adopt and develop methods from ICT to achieve multicellular control of bacterial and mammalian cell populations;
- Carry out in-vivo validation using optogenetics and microfluidics platforms.

ABSTRACT

The need of having advanced tools for data analysis is one of the most important trends in the current economic, technological and social scenario and, nowadays, it is mainly based on methodologies and techniques of artificial intelligence and BigData. One of the goals of modern medicine is the "precision medicine", whose purpose is to offer personalized treatments based on the specific characteristics of patients and pathologies. In this context, new analysis techniques such as Radiomics is becoming a novel research field. The analysis of the large number of data derived from medical images allows to recognize many characteristics of cancers and they can be integrated with other molecular and genomic characteristics by obtaining further correlations.

Available

Can be assigned to one doctoral student of cycle XXXVI

OBJECTIVES 

The implementation of a decision support system based on a sematic multimedia bigdata to support the analysis of medical images represented by novel radiomics descriptors and texture analysis.

ABSTRACT

Software applications for the Health care are becoming more and more widespread and complex, as they can rely on the most modern ICT technologies. To cite a few, they can be developed as event-based and context-aware mobile systems, can be integrated with distributed software architectures for data collection, use machine learning techniques to support decision-making processes, or exploit virtual or augmented reality technologies. To manage the complexity of developing this type of system and assure their quality, acceptability and dependability, it is increasingly necessary to invest in the search for new development paradigms, architectures and techniques that simplify their development and validation.

Available

Can be assigned to one doctoral student of cycle XXXVI

OBJECTIVES

- Develop innovative model driven solutions for the development, testing, validation and certification of mobile, sensor-based and context-aware solutions for health care domain;
- Carry out experimental validation of the proposed approaches by case studies in selected health care fields

ABSTRACT

Sentinel node (SLN) biopsy is used to stage patients with early-stage breast cancer with clinically negative axillary nodes, but it is invasive and with complications. To overcome such issues this research aims to predict SLNs metastasis using radiomics on T1w-MRI of the native tumor, even in combination with histological features and patients clinical data, supporting treatment decision by providing a non-invasive approach in clinical routine.

No More Available

Already assigned to a PhD student of cycle XXXV

OBJECTIVES

Development of  a radiomic platform to predict sentinel nodes metastasis in a non-invasive ways using artificial intelligence-based methods extracting information from T1w-MR scans and patient clinical data.

ABSTRACT

What we release into the environment can come back to us, often with negative effects. At high exposure levels, environmental pollution can cause adverse health effects. There are no doubts on the negative effects of environmental pollution on human health, what can still be verified is the correlation between implicated variables (lifestyle, pollutant, social context) and the appearance of many diseases (respiratory, oncological, etc.).
This project aims to integrate a huge amount of health, socio-economic and environmental data in order to determine the cause-effects relationships between environmental pollution and human health. In particular, the goal is to propose the study and the development of a forecast model related to the spread of pollutants in a given area and of a correlation model between the concentration of the very same pollutants and health data of people living in the analysed geographical area.
It’s of utmost importance to ensure the semantic interoperability between different databases, i.e. the capability of a computer system to cooperate and exchange data with other systems, in a more or less complete and error-free way, with reliability and resource efficiency. Interoperability’s purpose is to ease interaction between different systems as well as data exchange and reuse between not homogenous information systems.

Available

Can be assigned to one doctoral student of cycle XXXVI

OBJECTIVES

The increase in pollution-related diseases turned science’s attention to the correlation between man-environment to safeguard the living condition of the planet and its inhabitants. Starting from the concentration maps of the pollutants taken into consideration it will be possible to identify impact areas and/or the ones with higher pollutants concentrations. Information obtained will support the acknowledgment of a correlation with health data regarding patients suffering respiratory, oncologic, etc. The development of knowledge on the relationship between environment and human health is mandatory to develop programs useful in protecting environment and in preventing related diseases.

ABSTRACT

The project consists on the development of an innovative m-Health system based on wearable devices in e-textile technology. M-Health means the provision of healthcare services supported by "mobile" devices which the most recent studies identify as the ICT sector with the greatest future potential expansion; while for e-textile we mean the integration of electronic components directly into washable and sensorized garments, commercially available at low and decreasing costs and  suitable for home care based applications.

No More Available

Already assigned to a PhD student of cycle XXXV

OBJECTIVES

Project, development and experimental setting of e-textile based prototyping t-shirt and socks for biomedical physiological signals and movement analysis' indexes processing