Matteo Roffilli

Matteo Roffilli
Bioretics

Ph.D. in Computer Science

About

49
Publications
9,212
Reads
How we measure 'reads'
A 'read' is counted each time someone views a publication summary (such as the title, abstract, and list of authors), clicks on a figure, or views or downloads the full-text. Learn more
562
Citations
Citations since 2017
14 Research Items
231 Citations
201720182019202020212022202301020304050
201720182019202020212022202301020304050
201720182019202020212022202301020304050
201720182019202020212022202301020304050
Introduction
Since 20 years I am leading Machine Learning researches on international projects related to Biology, Life science and Medical Imaging. As Bioretics' CEO we then port most of these techniques into Machine Vision solutions for demanding industrial scenarios.
Additional affiliations
August 2012 - present
Bioretics srl
Position
  • CEO
Description
  • www.bioretics.com
January 2001 - September 2013
University of Bologna
Position
  • PhD

Publications

Publications (49)
Preprint
Full-text available
Cells are not uniformly distributed in the human cerebral cortex. Rather, they are arranged in a regional and laminar fashion that span a range of scales. Here we demonstrate an innovative imaging and analysis pipeline to construct a reliable cell census across the human cerebral cortex. Magnetic resonance imaging (MRI) is used to establish a macro...
Article
Although neuronal density analysis on human brain slices is available from stereological studies, data on the spatial distribution of neurons in 3D are still missing. Since the neuronal organization is very inhomogeneous in the cerebral cortex, it is critical to map all neurons in a given volume rather than relying on sparse sampling methods. To ac...
Preprint
Full-text available
We still lack a detailed map of the anatomical disposition of neurons in the human brain. A complete map would be an important step for deeply understanding the brain function, providing anatomical information useful to decipher the neuronal pattern in healthy and diseased conditions. Here, we present several important advances towards this goal, o...
Preprint
Full-text available
Semantic segmentation of neuronal structures in 3D high-resolution fluorescence microscopy imaging of the human brain cortexcan take advantage of bidimensional CNNs, which yield good resultsin neuron localization but lead to inaccurate surface reconstruction. 3DCNNs on the other hand would require manually annotated volumet-ric data on a large scal...
Preprint
Full-text available
The 3D analysis of the human brain architecture at cellular resolution is still a big challenge. In this work, we propose a pipeline that solves the problem of performing neuronal mapping in large human brain samples at micrometer resolution. First, we introduce the SWITCH/TDE protocol: a robust methodology to clear and label human brain tissue. Th...
Conference Paper
Full-text available
Using a custom light sheet fluorescence microscope, we image large stained human brain portions, labelled for NeuN and GAD67 neuronal markers, discerning the inhibitory population via neural-network based image analysis and exposing the brain connectivity.
Conference Paper
We still lack a detailed map of the anatomical disposition of neurons in the human brain. A complete map would be an important step for deeply understanding the brain function, providing anatomical information useful to decipher the neuronal pattern in healthy and diseased conditions. Here, we present several important advances towards this goal, o...
Chapter
Semantic segmentation of neuronal structures in 3D high-resolution fluorescence microscopy imaging of the human brain cortex can take advantage of bidimensional CNNs, which yield good results in neuron localization but lead to inaccurate surface reconstruction. 3D CNNs on the other hand would require manually annotated volumetric data on a large sc...
Thesis
Full-text available
A definite trend in Biomedical Imaging is the one towards the integration of increasingly complex interpretative layers to the pure data acquisition process. One of the most interesting and looked-forward goals in the field is the automatic segmentation of objects of interest in extensive acquisition data, target that would allow Biomedical Imaging...
Chapter
Quantitative analysis of brain cytoarchitecture requires effective and efficient segmentation of the raw images. This task is highly demanding from an algorithmic point of view, because of the inherent variations of contrast and intensity in the different areas of the specimen, and of the very large size of the datasets to be processed. Here, we re...
Conference Paper
We present a software pipeline for high throughput stitching and processing of high-resolution tomographies of whole mouse brains. We then employ machine learning techniques for automatic segmentation and classification of neurons in the acquired datasets.
Conference Paper
Full-text available
Non Destructive Testing (NDT) is one of the most important aspect in modern manufacturing companies. Automation of this task improves productivity and reliability of distribution chains. We present an optimized implementation of common pattern recognition algorithms that performs NDT on factory products. To the aim of enhancing the industrial integ...
Article
Full-text available
Matheuristic algorithms have begun to demonstrate that they can be the state of the art for some optimization problems. This paper puts forth that they can represent a viable option also in an applicative context. The possibility to get a solution quality vali-dation or a model grounded construction may become a significant competitive advantage ag...
Article
Peer-to-peer (P2P) computing already accounts for a large part of the traffic on the Internet, and it is likely to become as ubiquitous as current client/server architectures in next generation information systems. This paper addresses a central problem of P2P systems: the design of an optimal overlay communication network for a set of processes on...
Conference Paper
Full-text available
Matheuristics are heuristic algorithms made by the interoperation of metaheuristics and mathematic programming (MP) techniques. An essential feature is the exploitation in some part of the algorithms of features derived from the mathematical model of the problems of interest, thus the definition “model-based metaheuristics” appearing in the title o...
Chapter
Decomposition techniques are well-known as a means for obtaining tight lower bounds for combinatorial optimization problems, and thus as a component for solution methods. Moreover a long-established research literature uses them for defining problem-specific heuristics. More recently it has been observed that they can be the basis also for designin...
Conference Paper
Full-text available
An established research line in ACO systems supports the intuition that ant algorithms are particularly fit for dynamic optimization problems because of their ability to construct an internal representation of the essential elements of the problem to solve, a representation which needs to be updated and not reconstructed when the instance changes.
Chapter
Full-text available
Solid waste collection in urban areas is a central topic for local environmental agencies. The operational problem, the definition of collection routes given the vehicle fleet, can greatly benefit of computerized support already for medium sized town. While the operational constraints can vary, the core problem can be identified as a capacitated ar...
Article
Full-text available
Ant Colony Optimization (ACO) is a class of metaheuristic algorithms sharing the common approach of constructing a solution on the basis of information provided both by a standard constructive heuristic and by previously constructed solutions. This paper is composed of three parts. The first one frames ACO in current trends of research on metaheuri...
Article
Full-text available
This work presents an original algorithmic model of some essential features of psychogenetic theory, as was proposed by J.Piaget. Specifically, we modeled some elements of cognitive structure learning in children from 0 to 4 months of life. We are in fact convinced that the study of well-established cognitive models of human learning can suggest ne...
Conference Paper
Full-text available
Simulation and forecast of traffic flows raise significant computational issues, to be faced by means of advanced optimization techniques. The solution obtained depends moreover on a number of operational parameters, whose setting heavily affects the proposed results. We present an application implementing an original traffic flow simulation and fo...
Conference Paper
Industrial companies routinely face computationally intensive problems and deploy heuristic solutions, chosen only on the basis that no more computing power is available to search for possibly better solutions. Recent advances on heuristic and metaheuristic solution approaches have led to the development of very effective methodologies, several of...
Article
Today, on-line entertainment is an important quality of life issue and represents a cornerstone of human culture and communication. With the wide diffusion of mobile and multimodal devices, on-line gaming is more and more often considered in an anytime, anywhere, anyone dimension. The game industry and the academic research are thus facing the poss...
Conference Paper
Full-text available
As a consequence of the increasing mobile and multimodal devices diffusion, on-line gaming is more and more often considered as a dimension of an anytime, anywhere and anyone spaces. Providing accessible games is one of game industry and academic research purposes, in order to comply with the anyone issue in spite of disability. Such an issue assum...
Conference Paper
Full-text available
A novel approach to the detection of masses and clustered microcalcification is presented. Lesion detection is considered as a two-class pattern recognition problem. In order to get an effective and stable representation, the detection scheme codifies the image by using a ranklet transform. The vectors of ranklet coefficients obtained are classifie...
Chapter
Full-text available
The identification of social groups remains one of the main analytical themes in the analysis of social networks and, in more general terms, in the study of social organization. Traditional network approaches to group identification encounter a variety of problems when the data to be analyzed involve two-mode networks, i.e., relations between two d...
Article
Full-text available
A common thinking about the science is that every possible achievement can be pursued, provided that we have time and funds available for that purpose. On top of all this, recent technological achievements have carried this thinking to extremes, due to the speed of technological change sweeping through the world, which led to new momentous discover...
Article
Full-text available
The classification of tumoral masses and normal breast tissue is targeted. A mass detection algorithm which does not refer explicitly to shape, border, size, contrast or texture of mammographic suspicious regions is evaluated. In the present approach, classification features are embodied by the image representation used to encode suspicious regions...
Conference Paper
Full-text available
The growth of the Internet brought a new age for game developers. New exciting, highly interactive Massively Multiplayer Online Games (MMOGs) may be now deployed on the Web, thanks to new scalable distributed solutions and amazing D graphics systems plugged directly into standard browsers. Along this line, taking advantage of a mirrored game server...
Article
Full-text available
Nowadays, social organizations (at macro-level) can be represented as complex self-organizing sys-tems that emerge from the interaction of complicated social behaviours (at micro-level). Modern multi-agent systems can be employed to explore "artificial societies" by reproducing complicated social behaviours. Unfortunately, promoting interactions on...
Article
Full-text available
In this work, we present a novel approach to mass detection in digital mammograms. The great variability of the appearance of masses is the main obstacle to building a mass detection method. It is indeed demanding to characterize all the varieties of masses with a reduced set of features. Hence, in our approach we have chosen not to extract any fea...
Conference Paper
Full-text available
New technological developments in wireless networks and location-based information systems are greatly affecting the prominent scenarios represented by mobile markets, commercial and industrial organizations, and cooperative social environments. To model and control such complex organizational systems, the use of scientific methodologies, such as p...
Article
Full-text available
Current CAD systems always demand better performance, both in terms of the best sensitivity-specificity tradeoff and of the processing time. In order to decrease the false positive rate and to increase the time responsiveness of our CAD system, we present a powerful algorithm that performs an intra-breast segmentation. Starting from a digital mammo...
Article
Full-text available
A novel featureless approach to the detection of masses and microcalcifications has been adopted, based on a Support Vector Machine (SVM) classifier. This method does not rely on any feature extraction task; on the contrary, the algorithm automatically learns to detect the lesions by the examples presented to it during the training phase. Our techn...
Article
Full-text available
In this paper we present a novel approach to mass detection in digital mammograms. The great variability of the masses appearance is the main obstacle of building a mass detection method. It is indeed demanding to characterize all the varieties of masses with a reduced set of features. Hence, in our approach we decide not to extract any feature, fo...
Article
Full-text available
In this paper we present a novel approach to mass detection in digital mammograms. The great variability of the masses appearance is the main obstacle of building a mass detection method. It is indeed demanding to characterize all the varieties of masses with a reduced set of features. Hence, in our approach we decide not to extract any feature, fo...
Conference Paper
Full-text available
An effective approach to cancer classification based upon gene expression monitoring using DNA microarray was introduced by [1]. Here they used DNA microarray analysis on primary breast tumours of 78 young patients without tumour cells in local lymph nodes at diagnosis, 34 from patients who developed distant metastasis within 5 years (poor prognosi...
Article
Full-text available
This paper presents a work we have done on the motion de- tection in the context of an outdoor traffic scene for visual surveillance purposes. Our motion detection algorithm is based both on background subtraction and three frame dif- ference. We propose quite innovative solutions for denois- ing, blobs filling and shadow detection without exploiti...
Article
Full-text available
La crescente domanda di videogiochi innovativi, l’imponente investimento commerciale nel settore e la possibilità di reperire online numerosi giocatori rendono il campo dei giochi multiplayer molto interessante per la ricerca nel campo dell’Intelligenza Artificiale. In questo lavoro mostreremo come tecniche avanzate di Machine Learning come le Supp...
Article
Full-text available
In this paper a two-class classification problem is faced. One class is constituted by tumoral masses, breast tumors with size ranging from 3 mm to 30 mm. The other class is constituted by non-masses. A Support Vector Machine (SVM) is used as a classifier. Both, masses and non-masses, are extracted from the University of South Florida (USF) mammogr...

Network

Cited By

Projects

Projects (3)
Project
Using a custom dual-view inverted confocal light sheet fluorescence microscope (di2CLSFM), we image large stained human brain areas, labelled for multiple neuronal markers. We discern different neuronal populations and vasculature via automated neural-network based image analysis and explore the brain connectivity and structure from the micrometer to the centimeter scale.