Suely Fazio Ferraciolli

Suely Fazio Ferraciolli

Auto-generated profile, based on publicly available information

Suely Fazio Ferraciolli

Department of Radiology, Massachusetts General Hospital, Boston, USA

Research Focus & Metrics

Academic Career Length

8Years (2019-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
7 January 2025 in Journal of Clinical Medicine
Verified
Journal Article
Open access
PDF file
MTMARIO TORTORA
MARIO TORTORA
FPFrancesco Pacchiano
Francesco Pacchiano
SFSuely Fazio Ferraciolli
Suely Fazio Ferraciolli
SCSabrina Criscuolo
Sabrina Criscuolo
CGCristina Gagliardo
Cristina Gagliardo
Alberto NegroAlberto Negro
Alberto Negro
The usage of digital twins (DTs) is growing across a wide range of businesses. The health sector is one area where DT use has recently increased. Ultimately, the concept of digital health twins holds the potential to enhance human existence by transforming disease prevention, health preservation, diagnosis, treatment, and management. Big data’s explosive expansion, combined with ongoing developments in data science (DS) and artificial intelligence (AI), might greatly speed up research and development by supplying crucial data, a strong cyber technical infrastructure, and scientific know-how. The field of healthcare applications is still in its infancy, despite the fact that there are several DT programs in the military and industry. This review’s aim is to present this cutting-edge technology, which focuses on neurology, as one of the most exciting new developments in the medical industry. Through innovative research and development in DT technology, we anticipate the formation of a global cooperative effort among stakeholders to improve health care and the standard of living for millions of people globally.

28 March 2025 in La radiologia medica
Verified
Journal Article
Open access
PDF file
MTMARIO TORTORA
MARIO TORTORA
ALAndre Luppi
Andre Luppi
FPFrancesco Pacchiano
Francesco Pacchiano
MMMariagrazia Marisei
Mariagrazia Marisei
FGFrancesca Grassi
Francesca Grassi
SFSuely Fazio Ferraciolli
Suely Fazio Ferraciolli
Extended reality (XR) technologies, including virtual reality (VR), augmented reality (AR), and mixed reality (MR), hold transformative potential for radiology. This review examines the current applications, benefits, limitations, and future prospects of XR in radiology, with a focus on education, diagnostics, interventional procedures, and patient interaction. A comprehensive literature search of PubMed, Scopus, and Web of Science databases identified relevant publications from 1992 to 2024. Key studies were selected for detailed discussion. XR technologies enhance radiology education by offering immersive learning experiences that improve the proficiency and confidence of professionals. In diagnostics, XR improves the accuracy and efficiency of ultrasound and CT imaging and aids in precise patient positioning. For interventional radiology, XR provides valuable tools for training and real-time procedural planning, leading to better patient outcomes. Additionally, XR improves patient–doctor interactions, reducing anxiety and enhancing the consent process. Despite challenges such as high costs, technical limitations, and the need for extensive clinical validation, the potential benefits of XR underscore its value as a significant tool in radiology. Addressing these challenges will be essential for the widespread adoption and integration of XR in radiology, ensuring its potential benefits are fully realized. This review highlights the transformative impact of XR technologies on radiology, emphasizing the need for further research and development to harness their full capabilities and improve patient care.

1 July 2021 in Radiology: Artificial Intelligence
Verified
Journal Article
Closed access
RGRomane Gauriau
Romane Gauriau
BBBernardo C. Bizzo
Bernardo C. Bizzo
FKFelipe C. Kitamura
Felipe C. Kitamura
OJOsvaldo Landi Junior
Osvaldo Landi Junior
SFSuely F. Ferraciolli
Suely F. Ferraciolli
KAKatherine P. Andriole
Katherine P. Andriole
Purpose: To develop a deep learning model for detecting brain abnormalities on MR images. Materials and Methods: In this retrospective study, a deep learning approach using T2-weighted fluid-attenuated inversion recovery images was developed to classify brain MRI findings as "likely normal" or "likely abnormal." A convolutional neural network model was trained on a large, heterogeneous dataset collected from two different continents and covering a broad panel of pathologic conditions, including neoplasms, hemorrhages, infarcts, and others. Three datasets were used. Dataset A consisted of 2839 patients, dataset B consisted of 6442 patients, and dataset C consisted of 1489 patients and was only used for testing. Datasets A and B were split into training, validation, and test sets. A total of three models were trained: model A (using only dataset A), model B (using only dataset B), and model A + B (using training datasets from A and B). All three models were tested on subsets from dataset A, dataset B, and dataset C separately. The evaluation was performed by using annotations based on the images, as well as labels based on the radiology reports. Results: Model A trained on dataset A from one institution and tested on dataset C from another institution reached an F1 score of 0.72 (95% CI: 0.70, 0.74) and an area under the receiver operating characteristic curve of 0.78 (95% CI: 0.75, 0.80) when compared with findings from the radiology reports. Conclusion: The model shows relatively good performance for differentiating between likely normal and likely abnormal brain examination findings by using data from different institutions.

29 October 2019 in Child's Nervous System
Verified
Journal Article
Closed access
PDF file
BMBárbara Albuquerque Morais
Bárbara Albuquerque Morais
Davi SollaDavi Solla
Davi Solla
VYVitor Nagai Yamaki
Vitor Nagai Yamaki
SFSuely Fazio Ferraciolli
Suely Fazio Ferraciolli
CACesar Augusto P.F. Alves
Cesar Augusto P.F. Alves
MTManoel J Teixeira
Manoel J Teixeira

17 August 2023 in American Journal of Neuroradiology
Verified
Journal Article
Closed access
PDF file
CAC.A.P.F. Alves
C.A.P.F. Alves
JSJ. Sidpra
J. Sidpra
AMA. Manteghinejad
A. Manteghinejad
SSS. Sudhakar
S. Sudhakar
FMF.V. Massey
F.V. Massey
KMKshitij Mankad
Kshitij Mankad
BACKGROUND AND PURPOSE: Although cardinal imaging features for the diagnostic criteria of the Dandy-Walker phenotype have been recently defined, there is a large range of unreported malformations among these patients. The brainstem, in particular, deserves careful attention because malformations in this region have potentially important implications for clinical outcomes. In this article, we offer detailed information on the association of brainstem dysgenesis in a large, multicentric cohort of patients with the Dandy-Walker phenotype, defining different subtypes of involvement and their potential clinical impact. MATERIALS AND METHODS: In this established multicenter cohort of 329 patients with the Dandy-Walker phenotype, we include and retrospectively review the MR imaging studies and clinical records of 73 subjects with additional brainstem malformations. Detailed evaluation of the different patterns of brainstem involvement and their potential clinical implications, along with comparisons between posterior fossa measurements for the diagnosis of the Dandy-Walker phenotype, was performed among the different subgroups of patients with brainstem involvement. RESULTS: There were 2 major forms of brainstem involvement in patients with Dandy-Walker phenotype including the following: 1) the mild form with anteroposterior disproportions of the brainstem structures “only” (57/73; 78%), most frequently with pontine hypoplasia (44/57; 77%), and 2) the severe form with patients with tegmental dysplasia with folding, bumps, and/or clefts (16/73; 22%). Patients with severe forms of brainstem malformation had significantly increased rates of massive ventriculomegaly, additional malformations involving the corpus callosum and gray matter, and interhemispheric cysts. Clinically, patients with the severe form had significantly increased rates of bulbar dysfunction, seizures, and mortality. CONCLUSIONS: Additional brainstem malformations in patients with the Dandy-Walker phenotype can be divided into 2 major subgroups: mild and severe. The severe form, though less prevalent, has characteristic imaging features, including tegmental folding, bumps, and clefts, and is directly associated with a more severe clinical presentation and increased mortality.