Browsing by Author "Grani, Giorgio"

Now showing 1 - 3 of 3
  • No Thumbnail Available
    Item
    Artificial Intelligence for Thyroid Nodule Characterization : Where Are We Standing?
    (2022-07-10) Sorrenti, Salvatore; Dolcetti, Vincenzo; Radzina, Maija; Bellini, Maria Irene; Frezza, Fabrizio; Munir, Khushboo; Grani, Giorgio; Durante, Cosimo; D'Andrea, Vito; David, Emanuele; Calò, Pietro Giorgio; Lori, Eleonora; Cantisani, Vito; Rīga Stradiņš University
    Machine learning (ML) is an interdisciplinary sector in the subset of artificial intelligence (AI) that creates systems to set up logical connections using algorithms, and thus offers predictions for complex data analysis. In the present review, an up-to-date summary of the current state of the art regarding ML and AI implementation for thyroid nodule ultrasound characterization and cancer is provided, highlighting controversies over AI application as well as possible benefits of ML, such as, for example, training purposes. There is evidence that AI increases diagnostic accuracy and significantly limits inter-observer variability by using standardized mathematical algorithms. It could also be of aid in practice settings with limited sub-specialty expertise, offering a second opinion by means of radiomics and computer-assisted diagnosis. The introduction of AI represents a revolutionary event in thyroid nodule evaluation, but key issues for further implementation include integration with radiologist expertise, impact on workflow and efficiency, and performance monitoring.
  • No Thumbnail Available
    Item
    Non‐Marked Hypoechogenic Nodules : Multicenter Study on the Thyroid Malignancy Risk Stratification and Accuracy Based on TIRADS Systems Comparison
    (2022-02-09) Prieditis, Peteris; Radzina, Maija; Mikijanska, Madara; Liepa, Mara; Stepanovs, Kaspars; Grani, Giorgio; Durante, Cosimo; Lamartina, Livia; Trimboli, Pierpaolo; Cantisani, Vito; Department of Radiology
    Background and Objectives: The aim of the study was to evaluate the predictive value of the ultrasound criterion “non‐marked hypoechogenicity” for malignancy and to determine whether classification of these nodules as TIRADS 3 could improve the overall accuracy of consequently adjusted M‐TIRADS score. Materials and Methods: A total of 767 patients with 795 thyroid nodules were subject to ultrasonography examination and ultrasound‐guided fine needle aspiration biopsy. Nodules were classified by Kwak TIRADS and modified (M‐TIRADS) categories 4A, 4B, and 5 according to number of suspicious US features (marked hypoechogenicity, microlobulated or irregular margins, microcalcifications, taller‐than‐wide shape, metastatic lymph nodes). Non‐marked hypoechoic nodules were classified as TIRADS 3. Results: Thyroid nodules were classified as TIRADS 2, 3, 4A, 4B, and 5 in 14.5, 57.5, 14.2, 8.1, and 5.7%, respectively. Only histopathologic results (125 nodules underwent surgery) and highly specific cytology results (Bethesda II, VI) were accepted as a standard of reference, forming a sub‐cohort of 562/795 nodules (70.7%). Malignancy was found in 7.7%. Overall, M‐TIRADS showed sensitivity/specificity of 93.02/81.31%, and for PPV/NPV, these were 29.2/99.29%, respectively (OR—18.62). Irregular margins showed the highest sensitivity and specificity (75.68/93.74%, respectively). In TIRADS 3 category, 37.2% nodules were isoechoic, 6.6% hyperechoic, and 52.2% hypoechoic (there was no difference of malignancy risk in hypoechoic nodules between M‐TIRADS and Kwak systems—0.9 vs. 0.8, respectively). Accuracy of M‐TIRADS classification in this cohort was 78.26% vs. 48.11% for Kwak. Conclusions: The non‐marked hypoechoic nodule pattern correlated with low risk of malignancy; classification of these nodules as TIRADS 3 significantly improved the predictive value and overall accuracy of the proposed M‐TIRADS scoring with malignancy risk increase in TIRADS 4 categories by 20%; and no significant alteration of malignancy risk in TIRADS 3 could contribute to reducing overdiagnosis, obviating the need for FNA.
  • No Thumbnail Available
    Item
    Performance of EU-TIRADS in malignancy risk stratification of thyroid nodules : A meta-analysis
    (2020-09) Castellana, Marco; Grani, Giorgio; Radzina, Maija; Guerra, Vito; Giovanella, Luca; Deandrea, Maurilio; Ngu, Rose; Durante, Cosimo; Trimboli, Pierpaolo; Department of Radiology
    Objective: Several thyroid imaging reporting and data systems (TIRADS) ha ve been proposed to stratify the malignancy risk of thyroid nodule by ultrasound. The TIRADS by the Europea n Thyroid Association, namely EU-TIRADS, was the last one to be published. Design: We conducted a meta-analysis to assess the prevalence of malig nancy in each EU-TIRADS class and the performance of EU-TIRADS class 5 vs 2, 3 and 4 in detecting mal ignant lesions. Methods: Four databases were searched until December 2019. Original art icles reporting the performance of EU-TIRADS and adopting histology as reference standard were inc luded. The number of malignant nodules in each class and the number of nodules classified as true/false positiv e/negative were extracted. A random-effects model was used for pooling data. Results: Seven studies were included, evaluating 5672 thyroid nodules. The prevalence of malignancy in each EU-TIRADS class was 0.5% (95% CI: 0.0-1.3), 5.9% (95% CI: 2.6-9 .2), 21.4% (95% CI: 11.1-31.7), and 76.1% (95% CI: 63.7-88.5). Sensitivity, specificity, PPV, NPV, LR+, LR- A nd DOR of EU-TIRADS class 5 were 83.5% (95% CI: 74.5-89.8), 84.3% (95% CI: 66.2-93.7), 76.1% (95% CI: 63.7-88.5), 85.4% (95 % CI: 79.1-91.8), 4.9 (95% CI: 2.9-8.2), 0.2 (95% CI: 0.1-0.3), and 24.5 (95% CI: 11.7-51.0), respectively. A further improved performance was found after excluding two studies because of limited sample size and low prevalence of ma lignancy in class 5. Conclusions: A limited number of studies generally conducted using a retros pective design was found. Acknowledging this limitation, the performance of EU-TIRADS in stratifying th e risk of thyroid nodules was high. Also, EU-TIRADS class 5 showed moderate evidence of detecting malignant lesions.