Stefano Marrone
Napoli, Campania, Italia
475 follower
433 collegamenti
Informazioni
Since I can remember, passionate about welding, repair, assembly (and mostly disassembly) of electronic and mechanical components to discover and understand how them works. Nowadays I use gained skills and experiences to discover and understand newest technologies, third party source codes, dynamic model building, motors and robotics. My quick learning and understanding ability, coupled with the innate passion for public disclosures gave me the opportunity to work on many project in a wide range of fields.
I have earned a Master's Degree magna cum laude in Computer Engineering at University of Naples 'Federico II' (Italy), with a thesis on machine learning in biomedical image processing application. I am currently a scholarship holder and collaborate with the machine learning and pattern recognition research group at the same university.
Deep mastery of MatLab software suite, with a wide knowledge of different framework and suite for machine learning, patter recognition and computer vision, including OpenCV, Matlab Computer Vision and Machine Learning Toolbox, Weka, KNIME. Good skills in Software Design and programming (mostly C# and .NET, C++, Java) under different OS and IDE. Good knowledge of embedded systems design and programming (FGPA prototyping by HDL/VHDL, PCB composition, Arduino, Raspberry, STM products), with good familiarity on different communication protocols (UART/USART, SPI, I2C, CAN bus, USB, Ethernet, IEEE 802.11, GPRS). Good knowledge of LaTex and Office Suites.
Attività
-
I'm always more than happy to share this resource (made by Erasmo Purificato) when I'm asked to deliver a lecture on the crucial role education has…
I'm always more than happy to share this resource (made by Erasmo Purificato) when I'm asked to deliver a lecture on the crucial role education has…
Condiviso da Stefano Marrone
-
Human-Centred Artificial Intelligence (#HCAI) is currently one of the hottest topics in Computer Science. In the last few years, HCAI-related degree…
Human-Centred Artificial Intelligence (#HCAI) is currently one of the hottest topics in Computer Science. In the last few years, HCAI-related degree…
Consigliato da Stefano Marrone
-
IFOSS presented by prof. Sebastiano Battiato at American Academy of Forensic Sciences
IFOSS presented by prof. Sebastiano Battiato at American Academy of Forensic Sciences
Consigliato da Stefano Marrone
Esperienza
Formazione
-
-
-
Attività e associazioni:Fellowship from CINI ITEM National Laboratory
▪ Artificial Intelligence and Pattern Recognition Theory and Applications
▫ Adversarial and Evolutionary Learning
▫ Shallow and Deep Neural Network Architecture
▫ Convolutional, Residual, Recurrent, LSTMs and GAN Models
▫ Explainable AI
▪ Business and Swarm Intelligence for Big Data processing
▪ Deep Learning for Signal Processing (i.e. images, video, sound)
▫ Image Super-Resolution
▫ Remote Sensing
▪ Biomedical and…▪ Artificial Intelligence and Pattern Recognition Theory and Applications
▫ Adversarial and Evolutionary Learning
▫ Shallow and Deep Neural Network Architecture
▫ Convolutional, Residual, Recurrent, LSTMs and GAN Models
▫ Explainable AI
▪ Business and Swarm Intelligence for Big Data processing
▪ Deep Learning for Signal Processing (i.e. images, video, sound)
▫ Image Super-Resolution
▫ Remote Sensing
▪ Biomedical and Natural Image Processing
▪ Natural Language Processing
▫ Neural Machine Translation
▫ Text Generation and Authors Identification
▪ ChatBot for human-like Interactions
▪ Embedded and General Purpose Architecture for Deep Learning
▫ Power Efficiency and Performance Analysis
▫ Reproducibility across different Hardware configurations
▪ Ethical and Privacy related aspects of Deep Learning applications
▫ Model Inversion and Membership Inference
▫ Defense methods against racist and unethical AI -
▪ Thesis: "A Novel Model-Based Approach for Quantitative Evaluation of Motion Correction Techniques in Breast DCE-MRI" (https://goo.gl/18NEXB)
▪ Coordinators: Prof. Carlo Sansone, Prof. Mario Sansone
▪ Advisor: Ing. Gabriele Piantadosi
▪ Acquired Skills: General purposes and embedded system design and development; Design and analysis of algorithms for distributed systems and HPC facilities; Security and dependability of computer and embedded systems; Multimedial signal processing;…▪ Thesis: "A Novel Model-Based Approach for Quantitative Evaluation of Motion Correction Techniques in Breast DCE-MRI" (https://goo.gl/18NEXB)
▪ Coordinators: Prof. Carlo Sansone, Prof. Mario Sansone
▪ Advisor: Ing. Gabriele Piantadosi
▪ Acquired Skills: General purposes and embedded system design and development; Design and analysis of algorithms for distributed systems and HPC facilities; Security and dependability of computer and embedded systems; Multimedial signal processing; Software engineering; Formal Methods; Operational research -
▪ Thesis (english translatad): "Artificial Intelligence Classification Techniques for Breast Lesions Detection in Medical Images"
▪ Coordinator: Prof. Carlo Sansone
▪ Advisor: Prof. Mario Sansone
▪ Acquired Skills: Artificial Intelligence; Software and databases engineering, algorithms and data structures, programming and operating systems; Electronic computers, logical networks, computer networks; Digital circuits, automation systems; Signal Theory and digital transmission; Physics…▪ Thesis (english translatad): "Artificial Intelligence Classification Techniques for Breast Lesions Detection in Medical Images"
▪ Coordinator: Prof. Carlo Sansone
▪ Advisor: Prof. Mario Sansone
▪ Acquired Skills: Artificial Intelligence; Software and databases engineering, algorithms and data structures, programming and operating systems; Electronic computers, logical networks, computer networks; Digital circuits, automation systems; Signal Theory and digital transmission; Physics and electronic (analog/digital); Analysis and mathematic's methods for engineering, numerical calculus, geometry and algebra; Economics and Business Administration -
▪ Acquired Skills: Informatics; Chemistry (general and organic) and Biology; Physics and Mathematics; Technical Drawing; English
Licenze e certificazioni
Pubblicazioni
-
Breast segmentation using Fuzzy C-Means and anatomical priors in DCE-MRI
Pattern Recognition (ICPR), 2016 23rd International Conference on
Dynamic Contrast Enhanced-Magnetic Resonance Imaging (DCE-MRI) has demonstrated in recent years a great potential in screening of high-risk women for breast cancer, in staging newly diagnosed patients and in assessing therapy effects. The aim of this work is to propose an automated system for suspicious lesion detection in DCE-MRI to support radiologists during patient image analysis. The proposed method is based on a Support Vector Machine trained with dynamic features, extracted, after a…
Dynamic Contrast Enhanced-Magnetic Resonance Imaging (DCE-MRI) has demonstrated in recent years a great potential in screening of high-risk women for breast cancer, in staging newly diagnosed patients and in assessing therapy effects. The aim of this work is to propose an automated system for suspicious lesion detection in DCE-MRI to support radiologists during patient image analysis. The proposed method is based on a Support Vector Machine trained with dynamic features, extracted, after a suitable pre-processing of the image, from an area pre-selected by using a pixel-based approach. The performance were evaluated by using a leave-one-patient-out approach and compared to manual segmentation made up by an experienced radiologist. Our results were also compared to other automatic segmentation methodologies: the proposed method maximises the area of correctly detected lesions while minimizing the number of false alarms (with an accuracy of 98.70%).
Altri autoriVedi pubblicazione -
A secure, scalable and versatile multi-layer client–server architecture for remote intelligent data processing
Springer International Publishing
In recent years, the need for data collection and analysis is growing in many scientific disciplines. This is consequently causing an increase of research in automated data management and data mining to create reliable methods for data analysis. To deal with the need for smart environments and big computational resources, some previous works proposed to address the problem by moving on remote processing, with the aim of sharing supercomputer resources, algorithms and costs. Following this…
In recent years, the need for data collection and analysis is growing in many scientific disciplines. This is consequently causing an increase of research in automated data management and data mining to create reliable methods for data analysis. To deal with the need for smart environments and big computational resources, some previous works proposed to address the problem by moving on remote processing, with the aim of sharing supercomputer resources, algorithms and costs. Following this trend, in this work we propose an architecture for advanced remote data processing in a secure, smart and versatile client–server environment that is capable of integrating pre-existing local software. In order to assess the feasibility of our proposal, we developed a case study in the context of an image-based medical diagnostic environment. Our tests demonstrated that the proposed architecture has several benefits: increase of the system throughput, easy upgradability, maintainability and scalability. Moreover, for the scenario we have considered, the system showed a very low transmission overhead which settles on about 2.5 % for the widespread 10/100 mbps. Security has been achieved using client–server certificates and up-to-date standards.
Altri autoriVedi pubblicazione -
Data-driven selection of motion correction techniques in breast DCE-MRI
IEEE
It is well known that some sort of motion correction technique (MCT) should be performed before DCE-MRI data analysis in order to reduce movement artefacts. However, it is not clear if a single MCT can produce optimum results for every single examination, since for example different movements can occur. In this paper we investigated the possibility of choosing the best MCT per each specific patient, before performing further data analysis (e.g. tumour segmentation). In particular, our aim is…
It is well known that some sort of motion correction technique (MCT) should be performed before DCE-MRI data analysis in order to reduce movement artefacts. However, it is not clear if a single MCT can produce optimum results for every single examination, since for example different movements can occur. In this paper we investigated the possibility of choosing the best MCT per each specific patient, before performing further data analysis (e.g. tumour segmentation). In particular, our aim is the proposal of some physiological model-based quality indexes (QIs) for ranking different MCT on a patient basis. Moreover, for practical feasibility, we investigated the performance of our proposal when only a small fraction of the available data was used. We performed tests on a dataset of patients with breast tumour. Specifically, for each patient we compared the “reference ranking” of different MCT obtained by using the results of tumour segmentation with the rankings produced with each QI. Our results indicate that the ranking obtained by using the QI based on the Extended Tofts-Kermode model (with the Parker arterial input function) are in accordance with the “reference ranking”. Moreover, computational load can be significantly reduced without affecting the overall performance by using only 5% of the available data.
Altri autoriVedi pubblicazione -
A Novel Model-based Measure for Quality Evaluation of Image Registration Techniques in DCE-MRI
IEEE Computer Society
Dynamic Contrast Enhanced-Magnetic Resonance Imaging (DCE-MRI) has demonstrated in the last decades a great potential in screening of high-risk women for breast cancer, in staging newly diagnosed patients and in assessing therapy effects. The aim of this work is to propose a novel model-based measure for quality evaluation of image registration techniques in DCE-MRI. The proposed measure is based on a compartmental model of blood plasma and of the extra vascular extra cellular space (EES) for…
Dynamic Contrast Enhanced-Magnetic Resonance Imaging (DCE-MRI) has demonstrated in the last decades a great potential in screening of high-risk women for breast cancer, in staging newly diagnosed patients and in assessing therapy effects. The aim of this work is to propose a novel model-based measure for quality evaluation of image registration techniques in DCE-MRI. The proposed measure is based on a compartmental model of blood plasma and of the extra vascular extra cellular space (EES) for tumour tissue. Its suitability for evaluating image registration techniques has been indirectly verified by considering the results obtained, after each image registration technique, by a CAD segmentation system, developed in our previous work. In particular, it has been shown that the ranking obtained by means of the proposed quality assessment measure is in agreement with the ranking of the CAD segmentation systems, proving that our measure can correctly evaluate image registration techniques in the DCE-MRI context.
Altri autoriVedi pubblicazione -
A secure OsiriX plug-in for detecting suspicious lesions in breast DCE-MRI
Springer International Publishing
Up-to-date medical image processing is currently based on very sophisticated algorithms that often require a large computational load not always available on conventional workstations. Moreover, algorithms are in continuous evolution and hence clinicians are typically required to update their workstation periodically. The main objective of this paper is to propose a secure and versatile client-server architecture for providing these services at a low cost. In particular, we developed a plug-in…
Up-to-date medical image processing is currently based on very sophisticated algorithms that often require a large computational load not always available on conventional workstations. Moreover, algorithms are in continuous evolution and hence clinicians are typically required to update their workstation periodically. The main objective of this paper is to propose a secure and versatile client-server architecture for providing these services at a low cost. In particular, we developed a plug-in allowing OsiriX - a widespread medical image processing application dedicated to DICOM images coming from several equipments - to interact with a system for automatic detection of suspicious lesions in breast DCE-MRI. The large amount of data and the privacy of the information flowing through the network requires a flexible but comprehensive security approach. According to NIST guidelines, in our proposal data are transmitted over SSL/TLS channel after an authentication and authorization procedure based on X.509 standard digital certificate associated with a 3072bit RSA Key Pair. Authentication and authorization procedure is achieved through the services offered by Java JAAS classes.
Altri autoriVedi pubblicazione -
Automatic lesion detection in breast DCE-MRI
Springer Berlin Heidelberg
Dynamic Contrast Enhanced-Magnetic Resonance Imaging (DCE-MRI) has demonstrated in recent years a great potential in screening of high-risk women for breast cancer, in staging newly diagnosed patients and in assessing therapy effects. The aim of this work is to propose an automated system for suspicious lesion detection in DCE-MRI to support radiologists during patient image analysis. The proposed method is based on a Support Vector Machine trained with dynamic features, extracted, after a…
Dynamic Contrast Enhanced-Magnetic Resonance Imaging (DCE-MRI) has demonstrated in recent years a great potential in screening of high-risk women for breast cancer, in staging newly diagnosed patients and in assessing therapy effects. The aim of this work is to propose an automated system for suspicious lesion detection in DCE-MRI to support radiologists during patient image analysis. The proposed method is based on a Support Vector Machine trained with dynamic features, extracted, after a suitable pre-processing of the image, from an area pre-selected by using a pixel-based approach. The performance were evaluated by using a leave-one-patient-out approach and compared to manual segmentation made up by an experienced radiologist. Our results were also compared to other automatic segmentation methodologies: the proposed method maximises the area of correctly detected lesions while minimizing the number of false alarms (with an accuracy of 98.70%).
Altri autoriVedi pubblicazione
Progetti
-
BLADeS (Breast Lesion Automatic Detection System)
-
A system for automated detention of breast neoplasms in DCE-MRI, based on SVM classifier trained on dynamic feature. BLADeS is able to automatically determine the breast parenchyma, attenuate motion artefacts by means of different motion correction techniques (among which rigid and ron-rigid 2D and 3D transformation), remove improper results and detect actual neoplasm with an accuracy of about 98%
Altri creatori -
CATE (Connect Android To Embedded Systems)
-
An application for connecting embedded devices to Android terminals, in order to exploit sensors and connectivity capabilities in a simple, fast and reliable manner
Altri creatori -
-
FIP (Frame Interchange Protocol):
-
A new communication protocol for simplified communication over USB between different electronic devices (smartphones, embedded systems, FPGA, etc)
Altri creatori -
-
The Athlete's Diet
-
A game-learning application for teaching proper eating habits to children in primary and secondary schools
-
Water Saver
-
A home automation system for the automatic recovery and reuse of rainwater
Lingue
-
Italiano
-
-
Inglese
-
Organizzazioni
-
GIRPR - Gruppo Italiano Ricercatori in Pattern Recognition
Member
- Presente -
IEEE - Institute of Electrical and Electronics Engineers
Student Member
- Presente -
IEEE Young Professionals
Member
- Presente
Altre attività di Stefano
-
We're super excited to discuss our #LLM project where we are creating a European LLM leader for foundational models. With millions of GPU hours at…
We're super excited to discuss our #LLM project where we are creating a European LLM leader for foundational models. With millions of GPU hours at…
Consigliato da Stefano Marrone
-
🌟 Exciting Announcement! Join us for a thought-provoking tech talk on Human-Centered ML in Mobile and Wearable Data Ecosystems with Sofia Yfantidou…
🌟 Exciting Announcement! Join us for a thought-provoking tech talk on Human-Centered ML in Mobile and Wearable Data Ecosystems with Sofia Yfantidou…
Consigliato da Stefano Marrone
-
A very inspiring panel discussion that took place during the First Future AI Research Workshop on Resilient AI - Spoke 3 with Giovanna De Minico…
A very inspiring panel discussion that took place during the First Future AI Research Workshop on Resilient AI - Spoke 3 with Giovanna De Minico…
Consigliato da Stefano Marrone
-
Non potrete essere a #Firenze lunedì mattina? Nessun problema, potrete seguire l'evento di presentazione delle nostre cascade calls anche in…
Non potrete essere a #Firenze lunedì mattina? Nessun problema, potrete seguire l'evento di presentazione delle nostre cascade calls anche in…
Consigliato da Stefano Marrone
-
💥 Excited to share that our Special Issue "User Perspectives in Human-Centered Artificial Intelligence" on the International Journal of…
💥 Excited to share that our Special Issue "User Perspectives in Human-Centered Artificial Intelligence" on the International Journal of…
Consigliato da Stefano Marrone
-
This week, at the Congress Center in Via Partenope (Università degli Studi di Napoli Federico II), we had the privilege of hosting the HOMINIS…
This week, at the Congress Center in Via Partenope (Università degli Studi di Napoli Federico II), we had the privilege of hosting the HOMINIS…
Consigliato da Stefano Marrone
-
I’m in the beautiful city of Naples ❤️ Very excited to kickoff our awesome collaboration with University of Naples Federico II and #NVIDIA for our…
I’m in the beautiful city of Naples ❤️ Very excited to kickoff our awesome collaboration with University of Naples Federico II and #NVIDIA for our…
Consigliato da Stefano Marrone
-
🚀 Excited to announce our comprehensive survey on user modeling and user profiling! Together with my co-authors, Ludovico Boratto and Ernesto…
🚀 Excited to announce our comprehensive survey on user modeling and user profiling! Together with my co-authors, Ludovico Boratto and Ernesto…
Consigliato da Stefano Marrone
-
As Winter School 2024, organized by Motore Sanità on 8-9 February in the beautiful setting of Villa Erba in Cernobbio, draws to a close, I am…
As Winter School 2024, organized by Motore Sanità on 8-9 February in the beautiful setting of Villa Erba in Cernobbio, draws to a close, I am…
Consigliato da Stefano Marrone
Altri profili simili
Altre persone che si chiamano Stefano Marrone in Italia
Su LinkedIn ci sono altre 37 persone che si chiamano Stefano Marrone in Italia
Vedi altre persone che si chiamano Stefano Marrone