Clementina Di Tonno

Dr. Clementina Di Tonno


Research Focus & Metrics

Academic Career Length

4Years (2023-Present)

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

Representative Publications

View All Publications
Verified
Journal Article
Open access
PDF file
JGJuliana Guarize
Juliana Guarize
CDCristina Diotti
Cristina Diotti
MCMonica Casiraghi
Monica Casiraghi
SDStefano Donghi
Stefano Donghi
CTClementina Di Tonno
Clementina Di Tonno
LSLorenzo Spaggiari
Lorenzo Spaggiari
Background. Endobronchial ultrasound-guided transbronchial needle aspiration (EBUS-TBNA) is a well-established diagnostic procedure for evaluating hilar and mediastinal lymphadenopathies and is the gold standard for lung cancer diagnosis and staging. Recent studies assessed the effectiveness of the 19-G flex needle in obtaining larger EBUS-TBNA samples, and prospective small series gave similar results in terms of diagnostic yield when testing different gauge needles. The lack of homogeneity between series and the small sample size of some prospective cohorts poses a limit to the validity of those results. This prospective controlled study compared the 19-G flex and 22-G needles in terms of diagnostic yield. An objective laboratory method was used to count cells and compare the two needles’ cytologic yields. Material. A prospective controlled study was conducted on 90 patients undergoing EBUS-TBNA for the diagnosis of hilar and mediastinal lymphadenopathies. The institutional ethic committee (IEO573) approved the study, and informed consent was obtained from all patients. Results. A total of 90 patients were enrolled in this study, 84.4% of whom were diagnosed with malignancy and 15.6% with non-neoplastic disease. Sensitivity for malignancy was 93.4% (CI: 87.4–97.1%) for the 19-G needle and 92.6% (CI: 86.3–96.5%) for the 22-G needle (p = 0.80). The percentage of malignant cells in the cell block was 63.9% and 61.5% for the 22-G and 19-G needles, respectively. The cell count assessed by flow cytometry was 2071 cells/µL (IQR: 600,2265) with the 22-G needle and 2761 cells/µL (IQR: 505,3250) with the 19-G needle (p = 0.79). The malignant cell count was 0.05 × 103 cells/µL with the 22-G and 0.08 × 103 cells/µL with the 19-G needle (p = 0.70). There was no difference in the presence of tissue cores in the samples, and rapid on-site evaluation (ROSE) cellularity was comparable between the two needles. Conclusions. The 19-G flex EBUS-TBNA needle is comparable to the 22-G needle in terms of diagnostic yield for cyto-histological evaluation of hilar and mediastinal lymphadenopathies. There is no difference between the 19-G and 22-G needle cell counts evaluated by flow cytometry.

31 October 2025 in Cancers
Verified
Journal Article
Open access
PDF file
MNMariachiara Negrelli
Mariachiara Negrelli
CFChiara Frascarelli
Chiara Frascarelli
FMFausto Maffini
Fausto Maffini
EMElisa Mangione
Elisa Mangione
CTClementina Di Tonno
Clementina Di Tonno
Nicola FuscoNicola Fusco
Nicola Fusco
Fine-needle aspiration cytology (FNAC) is the cornerstone of thyroid nodule evaluation, standardized by the Bethesda System. However, indeterminate categories (Bethesda III–IV) remain a major challenge, often leading to unnecessary surgery or delayed molecular testing. Deep learning (DL) has recently emerged as a promising adjunct in thyroid cytopathology, with applications spanning triage support, Bethesda category classification, and integration with molecular data. Yet, routine adoption is limited by preanalytical variability (staining, slide preparation, Z-stack acquisition, scanner heterogeneity), annotation bias, and domain shift, which reduce generalizability across centers. Most studies remain retrospective and single-institution, with limited external validation. This article provides a technical overview of DL in thyroid cytology, emphasizing preanalytical sources of variability, architectural choices, and potential clinical applications. We argue that standardized datasets, multicenter prospective trials, and robust explainability frameworks are essential prerequisites for safe clinical deployment. Looking forward, DL systems are most likely to enter practice as diagnostic co-pilots, Bethesda classifiers, and multimodal risk-stratification tools. With rigorous validation and ethical oversight, these technologies may augment cytopathologists, reduce interobserver variability, and help transform thyroid cytology into a more standardized and data-driven discipline.