Maria Elena Susi

Dr. Maria Elena Susi

orcid

Research Focus & Metrics

Academic Career Length

2Years (2025-Present)

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

Representative Publications

View All Publications
24 April 2026 in Journal of Clinical Medicine
Verified
Journal Article
Open access
PDF file
VAVeronica Armato
Veronica Armato
MSMaria Elena Susi
Maria Elena Susi
Riccardo PicassoRiccardo Picasso
Riccardo Picasso
MMMarta Macciò
Marta Macciò
Federico PistoiaFederico Pistoia
Federico Pistoia
Alberto Stefano TagliaficoAlberto Stefano Tagliafico
Alberto Stefano Tagliafico
Background: This study aims to systematically review the current literature on the application of radiomic features and artificial intelligence (AI) in the diagnosis and prognosis of common peripheral nerve-related conditions, including carpal tunnel syndrome (CTS), chronic inflammatory demyelinating polyneuropathy (CIDP), polyneuropathy, organomegaly, endocrinopathy, monoclonal gammopathy and skin abnormalities (POEMS) syndrome, and in distinguishing between benign and malignant tumors. Methods: A comprehensive literature search was conducted in PubMed and Google Scholar for studies published between January 2019 and September 2025. Inclusion criteria comprised studies that used radiomics or AI-based radiomics approaches with diagnostic or prognostic purposes in peripheral nerve disorders. Results: A total of 40 studies were identified, of which 17 met the inclusion criteria. Among these, 9 studies employed magnetic resonance imaging (MRI), including one combined with PET/CT, while 8 used ultrasound (US). Most studies were retrospective and limited by small sample sizes, lack of external validation, and predominance of single-center designs. Conclusions: Since a seminal study published in 2019, there has been increasing evidence supporting the role of radiomics and AI in improving the diagnosis and prognosis of peripheral nerve disorders, particularly using MRI and US. However, significant challenges remain, including variability in imaging data, segmentation complexity, and limited availability of validated datasets. Future advancements in imaging technologies and multidisciplinary collaboration are essential to enhance clinical applicability.

Verified
Journal Article
Open access
PDF file
Federico PistoiaFederico Pistoia
Federico Pistoia
MMMarta Macciò
Marta Macciò
Riccardo PicassoRiccardo Picasso
Riccardo Picasso
FZFederico Zaottini
Federico Zaottini
MSMaria Elena Susi
Maria Elena Susi
CMCarlo Martinoli
Carlo Martinoli
Background/Objectives: Skin and soft-tissue infections represent a critical diagnostic challenge in the emergency department, requiring rapid differentiation between superficial processes and life-threatening necrotizing conditions. Methods: This clinical update analyzes the central role of CT in the assessment of these pathologies, proposing a management-oriented algorithm to support risk stratification and therapeutic planning. Results: By reviewing the fundamental semiological features of contrast-enhanced CT, this work highlights how the identification of critical markers directly guides the choice between medical management and urgent surgical intervention. In addition to consolidating protocols based on conventional CT, the article examines current perspectives and clinical limitations of emerging technologies, including Spectral CT (DECT and PCD-CT) and artificial intelligence, evaluating their potential to improve image quality and tissue characterization. Conclusions: In conclusion, while technological evolution offers new diagnostic frontiers, a rigorous and systematic interpretation of CT findings remains the fundamental pillar for optimizing patient outcomes and reducing unnecessary interventions.

5 August 2026 in Muscle & Nerve
Verified
Journal Article
Open access
Federico PistoiaFederico Pistoia
Federico Pistoia
EFElena Faedo
Elena Faedo
MMMarta Macciò
Marta Macciò
GMGiovanni Marcenaro
Giovanni Marcenaro
MSMaria Elena Susi
Maria Elena Susi
CMCarlo Martinoli
Carlo Martinoli
Aims: Facioscapulohumeral muscular dystrophy (FSHD) is a genetic progressive muscle disorder often presenting with facial weakness. However, imaging studies specifically evaluating facial muscle involvement and its relationship with clinical severity remain limited. This preliminary study explored magnetic resonance imaging (MRI) and ultrasound (US) assessment of facial muscle involvement and correlations with clinical severity. Methods: This single‐center prospective study enrolled 12 genetically confirmed FSHD1 patients (mean age 57.8 years). Clinical evaluation included the FSHD score, Comprehensive Clinical Evaluation Form (CCEF), and Facial Weakness Score (FWS). Muscle thickness of the orbicularis oris (OOr) and zygomaticus major (ZMj) was measured on both MRI and US, while MRI was additionally used for qualitative assessment of muscle bulk. Inter‐rater reliability was assessed for imaging measurements. Results: MRI and US showed comparable facial muscle thickness, with mean ZMj thickness of 2.34 ± 0.75 mm and 2.12 ± 0.55 mm, and OOr thickness of 2.28 ± 0.70 mm and 2.20 ± 0.67 mm, respectively. Inter‐rater reliability for MRI was high (ICC = 0.84), and reduced ZMj thickness showed moderate to strong correlation with greater disease severity ( ρ up to 0.87, p < 0.001) and impaired facial gestures ( ρ = 0.50–0.77, p < 0.05). Discussion: Despite the small sample size, MRI, and US assessment of facial muscles correlated with clinical severity and functional outcomes in FSHD, supporting their use as complementary tools. Longitudinal studies are required to establish imaging's role in monitoring changes over time.

9 December 2025 in Journal of Clinical Medicine
Verified
Journal Article
Open access
PDF file
Riccardo PicassoRiccardo Picasso
Riccardo Picasso
MSMaria Elena Susi
Maria Elena Susi
GMGiovanni Marcenaro
Giovanni Marcenaro
MMMarta Macciò
Marta Macciò
FZFederico Zaottini
Federico Zaottini
CMCarlo Martinoli
Carlo Martinoli
Background/Objectives: Respiratory muscle sarcopenia worsens outcomes in chronic lung disease, and quantitative Computed Tomography (CT) may provide objective biomarkers; this study aimed to develop a time-efficient segmentation protocol and identify radiomic biomarkers of respiratory muscle sarcopenia. Methods: This retrospective study analyzed 30 unenhanced chest CT from adult patients. The whole volume of the pectoralis major (PM), pectoralis minor (Pm), serratus anterior (SA), and fourth intercostal (4I) muscles was manually segmented. Patients were classified as sarcopenic or non-sarcopenic. Radiomics features and mean muscle density were extracted using PyRadiomics. Features associated with sarcopenia were selected using Least Absolute Shrinkage and Selection Operator (LASSO) regression and backward stepwise selection. Four sets of slices consisting of one, three, five, and seven slices were then sampled from each muscle around a fixed anatomical landmark. Deviations of each set of slices from whole-muscle metrics were evaluated using Mean Absolute Error (MAE) and Mean Absolute Percentage Error (MAPE). Results: Features selection identified 25 biomarkers of sarcopenia in PM, 24 in Pm, and 34 in SA. Variability-related features were significantly associated with sarcopenia (OR = 2.26; p = 0.012), while structural features showed an inverse association (OR = 0.18; p = 0.004). Mean muscle density and most radiomic features were well represented by single slice for every muscle. In the PM and Pm, eight and six radiomic features were better approximated segmenting more than one slice (p < 0.05). Conclusions: Radiomics enables quantitative assessment of sarcopenia. For SA, a simplified segmentation protocol consisting of a single slice enables approximating muscle density and radiomics of whole muscle volume. For PM and Pm, three or more slices allow a better representation of 8 and 6 radiomic features, respectively.

Verified
Journal Article
Open access
PDF file
MBMartina Burlando
Martina Burlando
Lidia SacchelliLidia Sacchelli
Lidia Sacchelli
ABAlberta Bettacchi
Alberta Bettacchi
AVAlexandra Maria Giovanna Brunasso Vernetti
Alexandra Maria Giovanna Brunasso Vernetti
SCStefano Caccavale
Stefano Caccavale
ECEmanuele Cozzani
Emanuele Cozzani
Background/Objectives: Palmoplantar psoriasis (PP) is a challenging variant of psoriasis that affects high-impact areas such as palms and soles and significantly impairs quality of life despite often limited body surface involvement. Conventional topical and systemic therapies may be insufficient, and evidence on biologic treatments for this specific phenotype remains limited. Bimekizumab (BKZ), a monoclonal antibody targeting IL-17A and IL-17F, has shown high efficacy in plaque psoriasis. This study aimed to evaluate the real-world effectiveness and rapidity of action of BKZ in patients with palmoplantar psoriasis compared with patients with psoriasis vulgaris (PV). Methods: We conducted a multicenter retrospective cohort study using data from 22 Italian dermatological units within the IL-PSO (Italian Landscape-Psoriasis) database. Adult patients treated with BKZ between November 2022 and October 2024 were included and categorized into three groups: isolated PP, PP associated with PV (PP + PV), and PV without palmoplantar involvement. Clinical outcomes included the Psoriasis Area and Severity Index (PASI), Dermatology Life Quality Index (DLQI), and pruritus Visual Analogue Scale (VAS). Outcomes were assessed at baseline, week 4, and week 16. Results: A total of 47 patients were included. The baseline PASI was lower in the PP group compared with the PP + PV and PV groups, whereas the DLQI was highest in patients with isolated PP. Rapid clinical improvement was observed in all groups. The mean % PASI reduction at week 4 was 60.5%, 65.1%, and 77.0% in the PP, PP + PV, and PV groups, respectively, increasing to 94.8%, 90.4%, and 91.8% at week 16. The proportion of patients achieving complete clearance (PASI = 0) at week 16 was 73.3% (11/15), 68.2% (15/22), and 70.0% (7/10), respectively. Significant improvements were also observed in DLQI and pruritus scores over time. No significant safety concerns emerged. Conclusions: In this real-world multicenter cohort, bimekizumab demonstrated rapid and high efficacy in patients with palmoplantar psoriasis, both isolated and associated with psoriasis vulgaris. These findings support the use of BKZ as an effective therapeutic option for psoriasis involving high-impact areas, as the palmoplantar, although larger studies are needed to confirm these results.

1 October 2025 in Preprints.org
Verified
Preprint
Open access
PDF file
Riccardo PicassoRiccardo Picasso
Riccardo Picasso
MSMaria Elena Susi
Maria Elena Susi
GMGiovanni Marcenaro
Giovanni Marcenaro
MMMarta Macciò
Marta Macciò
FZFederico Zaottini
Federico Zaottini
CMCarlo Martinoli
Carlo Martinoli
Background/Objectives: Respiratory muscle sarcopenia worsens outcomes in chronic lung disease, and quantitative CT may provide objective biomarkers; this study aimed to develop a time-efficient segmentation protocol and identify radiomic biomarkers of respiratory muscle sarcopenia. Methods: This retrospective study analyzed 30 unenhanced chest CT from adult patients. The whole volume of the pectoralis major (PM), pectoralis minor (Pm), serratus anterior (SA), and fourth intercostal (4I) muscles were manually segmented. Patients were classified as sarcopenic or non-sarcopenic. Radiomics features and mean muscle density were extracted using PyRadiomics. Features associated with sarcopenia were selected using LASSO regression and backward stepwise selection. Four sets of slices consisting of one, three, five, and seven slices were then sampled from each muscle around a fixed anatomical landmark. Deviations of each set of slices from whole-muscle metrics were evaluated using MAE and MAPE. Results: Features selection identified 25 biomarkers of sarcopenia in PM, 24 in Pm, and 34 in SA. Variability-related features were significantly associated with sarcopenia (OR = 2.26; P = .012), while structural features showed an inverse association (OR = 0.18; P = .004). Mean muscle density and most radiomic features were well represented by single slice for every muscle. In the PM and Pm eight and six radiomic features were better approximated segmenting more than one slice (p < 0.05). Conclusions: Radiomics enables quantitative assessment of sarcopenia. For SA, a simplified segmentation protocol consisting of a single slice enables to approximate muscle density and radiomics of whole muscle volume. For PM and Pm, three or more slices allow a better representation of 8 and 6 radiomic features respectively.