1,721,097 research outputs found
Computational imaging for precision medicine: the emergence of radiomics, pathomics and deep learning
No full textThe purpose of this Ph.D. thesis is to illustrate the research works carried out during the conceptualization, design, implementation, and evaluation of novel Clinical Decision Support Systems (CDSSs) based on Radiomics, Pathomics and Deep Learning (DL) techniques.
CDSSs can be effective systems for implementing Precision Medicine into clinical practice since they permit the objective and repeatable evaluation of patients. Precision Medicine can enable the improvement of the healthcare system by employing a personal healthcare process for the health status of an individual patient, which evolves in a unique way.
The methodologies concerning CDSSs were developed with different underlying goals: improvement of the clinical results, availability and usability of the method, and feasibility of the integration into the routine clinical practice. The applications considered span from Radiology to Digital Pathology. Tasks under consideration in Medical Imaging applications, from a computer vision perspective, concerned object detection, instance segmentation, semantic segmentation, color normalization, and characterization and classification of regions of interest. Data under consideration were either provided by local hospitals or obtained from public repositories. Validation of the developed systems has been done in accordance with the physicians. Moreover, the explainability of the realized systems has been investigated, by analyzing features' structure or by means of perceptive saliency maps.
In the aforementioned scenario, the main purpose of this thesis is to develop new systems based on Deep Learning, Radiomics and Pathomics for the processing and analysis of medical images.
Computational Imaging is a promising methodology to incorporate in the framework of Precision Medicine. Indeed, it creates the possibility to characterize the lesions in large datasets of images belonging to Radiology and Digital Pathology domains in an effective way, offering a personalized evaluation of the patient.
Merits and shortcomings regarding DL in the field of Medical Imaging have been investigated for applications in Radiology and Digital Pathology. Technical contributions include devising novel algorithms, improving existing workflows, and assembling complex CDSSs by combining in an original and effective way different techniques proposed in the literature.
In the Radiology domain, the following tasks have been tackled for what concerns applications related to Image-guided Surgery (IGS): liver segmentation, including also the classification into anatomical segments; vertebrae segmentation and identification; prostate segmentation and registration for image fusion.
Radiomics has been exploited for characterizing lung lesions in COVID-19 patients, in order to discover a prognostic signature for those with a higher risk of developing pulmonary thromboembolism.
With regard to Digital Pathology, applications included colorectal cancer (CRC) tissue classification; hematoxylin and eosin (H&E) stain color normalization; nuclei segmentation and detection; glomeruli lesions classifications according to Oxford score for IgA nephropathy patients. These automatic pipelines for histological data analysis can enable Pathomics, allowing the objective quantification and evaluation of tissue patterns.
The developed solutions in all these scenarios were put in comparison with state-of-the-art approaches proposed in the literature, and were validated with physicians when possible. In many cases, data have also been collected from local institutions.
This thesis work is organized into five chapters.
Chapter 1 introduces the objective and the technical contribution of the thesis.
Chapter 2 describes the state-of-the-art in all the considered clinical scenarios, with a particular focus on Radiology and Digital Pathology, encompassing emerging trends such as Radiomics and Pathomics.
Chapter 3 describes the contributions proposed in the Radiology field. In particular, IGS applications concern liver segmentation and classification into segments, vertebrae segmentation and identification, and prostate segmentation and registration. Also, a Radiomics-based analysis of lung lesions of patients diagnosed with COVID-19 is presented.
Chapter 4 presents the contributions proposed in the field of Digital Pathology, concerning tissue segmentation, normalization and classification, and detection of objects of interest, such as nuclei of cells.
Lastly, final remarks and considerations for future works are drawn in Chapter 5
Intelligent Frameworks for Diagnosis in the Precision Medicine Era
Full text linkQuesta tesi di dottorato mira a descrivere tutti i lavori di ricerca condotti per la progettazione, lo sviluppo e la valutazione di framework intelligenti per supportare la diagnosi in diverse unità cliniche del sistema sanitario rispetto all’approccio della medicina di precisione.
Il lavoro presentato si concentra sugli aspetti innovativi dei sistemi di diagnosi assistita dal computer impiegati nell’area radiologica e in campo patologico e sui sistemi di supporto alle decisioni nell’area neurologica e psicologica. Sono anche studiati e discussi sistemi per supportare le attività di fisiatria per eseguire e supportare la riabilitazione delle persone affette da malattie neurodegenerative.
Il primo capitolo introduce l'importanza di avere una valutazione obiettiva delle patologie mediante il supporto di sistemi automatici al fine di ridurre sia gli errori diagnostici sia i tempi per ottenere una diagnosi accurata. L'importanza dei sistemi di supporto alle decisioni per la medicina di precisione viene anche descritta specificando i vantaggi derivanti dall’utilizzo dei risultati clinici ottenibili da tali sistemi, integrati anche con i dati radiogenomici, o informazioni genetiche in generale, per l'esecuzione di terapie mirate al paziente.
Nel secondo capitolo, c'è una descrizione dei sistemi di diagnosi assistita dal computer introducendo il workflow tradizionale storicamente implementato da tali sistemi; successivamente, è descritta una classificazione di questi sistemi dal punto di vista delle metodologie di apprendimento automatico. Successivamente, viene introdotta la novità derivante dall’uso delle metodologie di Deep Learning a supporto della diagnosi, specificando anche il workflow implementato da questi nuovi classificatori. Infine, l'ultima sezione descrive il contributo dell’utilizzo delle tecnologie di realtà virtuale per supportare la diagnosi e la riabilitazione, compresa la valutazione cognitiva e fisiologica, e l'implementazione di protocolli che consentono la de-ospedalizzazione dei trattamenti riabilitativi.
Il terzo capitolo introduce tutti i contributi di ricerca volti al miglioramento dello stato dell’arte relativamente ai sistemi di supporto alle decisioni nelle aree cliniche di radiologia e anatomia patologica. Vengono descritti i framework innovativi e intelligenti per la valutazione radiologica, compresi sia gli approcci basati su classificazione, sia quelli di segmentazione delle immagini. In particolare, il capitolo tre riporta il contributo alla ricerca sulla progettazione e lo sviluppo di sistemi di supporto alla diagnosi assistita da computer per la diagnosi del carcinoma mammario, la stadiazione del tumore al fegato e la segmentazione dei reni affetti da malattia policistica autosomica dominante.
Il supporto all’anatomia patologia, invece, è dettagliato nelle aree della nefrologia ed ematologia, descrivendo sia gli approcci di Machine Learning, sia quelli che prevedono metodologia di Deep Learning. In particolare, vengono studiati nuovi approcci per la segmentazione di vasi e tubuli nelle biopsie renali e per il conteggio automatico dei globuli bianchi a partire da campioni di striscio di sangue periferico.
Il quarto capitolo descrive i lavori per la progettazione e lo sviluppo di framework intelligenti per la valutazione di diversi disturbi neurofisiologici, tra cui la malattia di Alzheimer e la fibromialgia, o il sostegno agli anziani nei loro ambienti di vita per migliorare le loro condizioni di benessere. Infine, viene anche descritto un lavoro di ricerca sulle metodologie di Machine Learning per supportare la stadiazione della progressione della malattia di Parkinson.
Il capitolo cinque riporta le conclusioni, evidenziando la grande importanza di integrare questi framework intelligenti nella pratica clinica, combinando informazioni provenienti da diverse fonti, al fine di procedere verso la vera nuova era della medicina di precisione.This Ph.D. thesis aims to describe all the research works conducted for the design, development and evaluation of intelligent frameworks for supporting the diagnosis in several clinical units of the healthcare system with respect to the precision medicine approach.
The presented work focuses on the innovative aspects of Computer-Aided Diagnosis Systems employed in the radiological area and pathological field, and on Decision Support Systems in the neurological and psychological area. Systems for supporting the physiatrics activities for performing and supporting the rehabilitation of people affected by neurodegenerative diseases are also investigated and discussed.
The first chapter introduces the importance of having an objective assessment of pathologies by the support of automatic systems in order to reduce both diagnostic errors and the time to obtain an accurate diagnosis. The importance of Decision Support Systems for precision medicine is also presented by describing the advantages of using their clinical outcomes, integrated with radiogenomics data, or genetic information in general, for performing targeted therapies.
In the second chapter, there is a description of Computer-Aided Diagnosis systems by introducing the traditional workflow historically implemented by such systems; subsequently, a classification of these systems is described from the Machine Learning perspective. Afterwards, the novelty from using Deep Learning methodologies for supporting diagnosis is described, also detailing the way of working of these new classifiers. Finally, the last section describes the contribution of using Virtual Reality for supporting diagnosis and rehabilitation, including cognitive and physiological assessment and implementation of protocols allowing the de-hospitalization of rehabilitation treatments.
The third chapter introduces all the research contributions for improving the state of the art about Decision Support Systems in the clinical areas of radiology and pathology. Innovative and intelligent frameworks for the radiological assessment are described, including both classification and segmentation approaches. Specifically, chapter three reports the research contribution about the design and development of Computer-Aided Diagnosis systems for breast cancer diagnosis, liver tumour staging and segmentation of kidneys affected by Autosomal Dominant Polycystic Disease.
The pathological support, instead, is detailed in nephrological and haematological areas, describing both Machine Learning and Deep Learning approaches. Specifically, novel approaches for the segmentation of vessels and tubules in kidney biopsies and for automatically counting white blood cells are investigated.
The fourth chapter describes the works for designing and developing intelligent frameworks for assessing different neurophysiological disorders, including Alzheimer's Disease and Fibromyalgia, or supporting elderly people in their living environments for improving their living conditions. Finally, a research work about Machine Learning methodologies for support staging the Parkinson's Disease progression is also described.
Chapter five reports the conclusions, highlighting the great importance of integrating these intelligent frameworks in the clinical practice, combining information coming from different sources, in order to proceed toward the real new era of precision medicine
Il progetto isole : il videoteleconsulto sul territorio della a.s.l. na2 e l'area metropolitana di napoli
No full textHeart Rate Variability in Noltisalis Database: Twenty-Four-Hour Fractal Dimension Analysis
No full textNonlinear analysis of HRV has recently been recognized to provide valuable information in the
prognostic classification of cardiac patients. Among the numerous non-linear parameters related to the fractal
behaviour of the HRV signal, two classes have gained wide interest in the last years: that based on the 1/flike
relationship, starting from the spectral power, and that based on fractal features. We present results
obtained from the analysis of 50 heart rate variability series which have been extracted from Holter
recordings in the 24-hours in normal subjects and pathological patients. Data have been collected inside a
multicentric research program, which aimed at the nonlinear analysis of heart rate variability series.
Differently from methods usually used in literature to evaluate the fractal dimension, the parameter used in
this work has been extracted directly from the HRV sequences in the time domain, by means of the Higuchi's
algorithm. Results show that this fractal dimension can be used to separate normal subjects from patients
suffering from cardiovascular diseases and to evaluate the presence of circadianity in the HRV over the
whole twenty four hours
Going Beyond Counting First Authors in Author Co-citation Analysis
Full text linkThe present study examines one of the fundamental aspects of author co-citation analysis (ACA) - the way co-citation
counts are defined. Co-citation counting provides the data on which all subsequent statistical analyses and mappings
are based, and we compare ACA results based on two different types of co-citation counting - the traditional type that
only counts the first one among a cited work's authors on the one hand and a non-traditional type that takes into
account the first 5 authors of a cited work on the other hand. Results indicate that the picture produced through this non-traditional author co-citation counting contains more coherent author groups and is therefore considerably clearer. However, this picture represents fewer specialties in the research field being studied than that produced through the traditional first-author co-citation counting when the same number of top-ranked authors is selected and analyzed. Reasons for these effects are discussed
Variations on the Author
Full text link“Variations on the Author” discusses two of Eduardo Coutinho’s recent films (Um Dia na Vida, from 2010, and Últimas Conversas, posthumously released in 2015) and their contribution to the general question of documentary authorship. The director’s filmography is characterized by a consistent yet self-effacing form of authorial self-inscription: Coutinho often features as an interviewer that rather than express opinions propels discourses; an interviewer that is good at listening. This mode of self-inscription characterizes him as an author who is not expressive but who is nonetheless markedly present on the screen. In Um Dia na Vida, however, Coutinho is completely absent form the image, while Últimas Conversas, on the contrary, includes a confessional prologue that moves the director from the margins to the center of his films. This article examines the ways in which these works stand out in the filmography of a director who offers new insights into the notion of cinematic authorship
Appropriate Similarity Measures for Author Cocitation Analysis
Full text linkWe provide a number of new insights into the methodological discussion about author cocitation analysis. We first argue that the use of the Pearson correlation for measuring the similarity between authors’ cocitation profiles is not very satisfactory. We then discuss what kind of similarity measures may be used as an alternative to the Pearson correlation. We consider three similarity measures in particular. One is the well-known cosine. The other two similarity measures have not been used before in the bibliometric literature. Finally, we show by means of an example that our findings have a high practical relevance.information science;Pearson correlation;cosine;similarity measure;author cocitation analysis
- …
