Dataset Information

S-Detect Software vs. EU-TIRADS Classification: A Dual-Center Validation of Diagnostic Performance in Differentiation of Thyroid Nodules.

ABSTRACT: Computer-aided diagnosis (CAD) and other risk stratification systems may improve ultrasound image interpretation. This prospective study aimed to compare the diagnostic performance of CAD and the European Thyroid Imaging Reporting and Data System (EU-TIRADS) classification applied by physicians with S-Detect 2 software CAD based on Korean Thyroid Imaging Reporting and Data System (K-TIRADS) and combinations of both methods (MODELs 1 to 5). In all, 133 nodules from 88 patients referred to thyroidectomy with available histopathology or with unambiguous results of cytology were included. The S-Detect system, EU-TIRADS, and mixed MODELs 1-5 for the diagnosis of thyroid cancer showed a sensitivity of 89.4%, 90.9%, 84.9%, 95.5%, 93.9%, 78.9% and 93.9%; a specificity of 80.6%, 61.2%, 88.1%, 53.7%, 73.1%, 89.6% and 80.6%; a positive predictive value of 81.9%, 69.8%, 87.5%, 67%, 77.5%, 88.1% and 82.7%; a negative predictive value of 88.5%, 87.2%, 85.5%, 92.3%, 92.5%, 81.1% and 93.1%; and an accuracy of 85%, 75.9%, 86.5%, 74.4%, 83.5%, 84.2%, and 87.2%, respectively. Comparison showed superiority of the similar MODELs 1 and 5 over other mixed models as well as EU-TIRADS and S-Detect used alone (p-value < 0.05). S-Detect software is characterized with high sensitivity and good specificity, whereas EU-TIRADS has high sensitivity, but rather low specificity. The best diagnostic performance in malignant thyroid nodule (TN) risk stratification was obtained for the combined model of S-Detect ("possibly malignant" nodule) and simultaneously obtaining 4 or 5 points (MODEL 1) or exactly 5 points (MODEL 5) on the EU-TIRADS scale.

SUBMITTER: Szczepanek-Parulska E

PROVIDER: S-EPMC7464710 | biostudies-literature | 2020 Aug

REPOSITORIES: biostudies-literature

ACCESS DATA

Publications

S-Detect Software vs. EU-TIRADS Classification: A Dual-Center Validation of Diagnostic Performance in Differentiation of Thyroid Nodules.

Szczepanek-Parulska Ewelina E Wolinski Kosma K Dobruch-Sobczak Katarzyna K Antosik Patrycja P Ostalowska Anna A Krauze Agnieszka A Migda Bartosz B Zylka Agnieszka A Lange-Ratajczak Malgorzata M Banasiewicz Tomasz T Dedecjus Marek M Adamczewski Zbigniew Z Slapa Rafal Z RZ Mlosek Robert K RK Lewinski Andrzej A Ruchala Marek M

Journal of clinical medicine 20200803 8

Computer-aided diagnosis (CAD) and other risk stratification systems may improve ultrasound image interpretation. This prospective study aimed to compare the diagnostic performance of CAD and the European Thyroid Imaging Reporting and Data System (EU-TIRADS) classification applied by physicians with S-Detect 2 software CAD based on Korean Thyroid Imaging Reporting and Data System (K-TIRADS) and combinations of both methods (MODELs 1 to 5). In all, 133 nodules from 88 patients referred to thyroid ...[more]

PMID: 32756510

Similar Datasets

Project description:PurposeTo explore the characteristics of C-TIRADS by comparing it with ACR-TIRADS, Kwak-TIRADS, KSThR-TIRADS and EU-TIRADS.MethodsA total of 1096 nodules were collected from 884 patients undergoing thyroidectomy in our center between May 2018 and December 2020. Divided the nodules into two groups: ">10mm" and "≤10mm". Ultrasound characteristics of each nodule were observed and recorded by 2 doctors, then classified based on ACR-TIRADS, Kwak-TIRADS, KSThR-TIRADS, EU-TIRADS, and C-TIRADS.ResultsA total of 682 benign nodules cases (62.23%) and 414 malignant nodules cases (37.77%) were identified. The ICC value of each guideline was:0.937(ACR-TIRADS), 0.858(EU-IRADS), 0.811(Kwak-TIRADS), 0.835(KTA/KSThR-TIRADS) and 0.854(C-TIRADS). The nodule malignancy rates in the groups(Kwak-TIRADS 4B, C-TIRADS 4B、4C) of two sizes were significantly different (all p<0.05). There was no statistical difference in the other grades of two sizes (all p>0.05). Unnecessary biopsy rates were the lowest in C-TIRADS (49.02% p<0.001). Furthermore, Kwak-TIRADS had the highest sensitivity and NPV (89.9%, 91.0%, all p<0.05), while C-TIRADS had the highest specificity and PPV (82.3%, 69.2%, all p<0.05). C-TIRADS and Kwak-TIRADS had the highest accuracy (76.0%, 72.5%, P=0.071). The AUCs of the 5 guidelines were C-TIRADS(0.816, P<0.05), Kwak-TIRADS(0.789, P<0.05) KTA/KSThR-TIRADS and ACR-TIRADS(0.773, 0.763, P=0.305), EU-TIRADS(0.734, P<0.05). The AUCs of the five guidelines were not statistically different between "nodules>10mm" and "nodules ≤ 10mm" (all P>0.05).ConclusionsAll five guides showed excellent interobserver agreement. C-TIRADS was slightly efficient than Kwak-IRADS, KTA/KSThR-TIRADS and ACR-TIRADS, and had greater advantages than EU-TIRADS. The diagnostic abilities of the five guidelines for "nodules ≤ 10mm" were not inferior to that of "nodules> 10mm". C-TIRADS is simple and easy to implement and can provide effective thyroid tumor risk stratification for thyroid nodule diagnosis, especially in China.

Project description:The aim was to compare the usefulness of selected thyroid sonographic risk-stratification systems in the diagnostics of nodules with indeterminate/suspicious cytology or unequivocal cytology in a population with a history of iodine deficiency. The diagnostic efficacy of ACR-TIRADS (the American College of Radiology Thyroid Imaging Reporting and Data Systems), EU-TIRADS (European Thyroid Association TIRADS), Korean-TIRADS, Kwak-TIRADS, AACE/ACE-AME-guidelines (American Association of Clinical Endocrinologists/ American College of Endocrinology-Associazione Medici Endocrinologi guidelines) and ATA-guidelines (American Thyroid Association guidelines) was evaluated in 1000 nodules with determined histopathological diagnosis: 329 FLUS/AUS (10.6% cancers), 167 SFN/SHT (11.6% cancers), 44 SM (77.3% cancers), 298 BL (benign lesions), 162 MN (malignant neoplasms). The percentage of PTC (papillary thyroid carcinoma) among cancers was higher in Bethesda MN (86.4%) and SM (suspicion of malignancy) nodules (91.2%) than in FLUS/AUS (57.1%, p < 0.005) and SFN/SHT (suspicion of follicular neoplasm/ suspicion of Hürthle cell tumor) nodules (36.8%, p < 0.001). TIRADS efficacy was higher for MN (AUC: 0.827-0.874) and SM nodules (AUC: 0.775-0.851) than for FLUS/AUS (AUC: 0.655-0.701) or SFN/SHT nodules (AUC: 0.593-0.621). FLUS/AUS (follicular lesion of undetermined significance/ atypia of undetermined significance) nodules assigned to a high risk TIRADS category had malignancy risk of 25%. In the SFN/SHT subgroup none TIRADS category changed nodule's malignancy risk. EU-TIRADS and AACE/ACE-AME-guidelines would allow diagnosing the highest number of PTC, FTC (follicular thyroid carcinoma), HTC (Hürthle cell carcinoma), MTC (medullary thyroid carcinoma). The highest OR value was for Kwak-TIRADS (12.6) and Korean-TIRADS (12.0). Conclusions: TIRADS efficacy depends on the incidence of PTC among cancers. All evaluated TIRADS facilitate the selection of FLUS/AUS nodules for the surgical treatment but these systems are not efficient in the management of SFN/SHT nodules.

Project description:Simple Summary Thyroid nodules of category III in the Bethesda system do not constitute a uniform group, so it is still a challenge to produce a recommendation for the management of patients with such nodules. The aim of the study was to examine the benefits of the joint use of repeat FNA and a sonographic risk stratification system in category III nodules in relation to the kind of atypia: cytologic/nuclear vs. architectural. Our results indicate that in both kinds of these nodules, the joint evaluation of repeat FNA outcome and sonographic risk of malignancy shows better effectiveness than any of these methods separately. Such a combination allows the identification of patients with a high risk of malignancy as well as a group of patients in which surgical treatment may be safely put aside. Abstract The aim of the study was to examine the benefits of the joint use of repeat FNA (rFNA) and EU-TIRADS in category III nodules in relation to the kind of atypia: nuclear vs. architectural (denoted by AUS and FLUS respectively). The study included 127 AUS and 1739 FLUS nodules with a known category of EU-TIRADS. Repeat FNA was performed in 82 AUS and 934 FLUS nodules of which 57 and 515 were excised, respectively. AUS nodules had higher malignancy risk than FLUS nodules. EU-TIRADS showed higher accuracy for AUS nodules, the opposite to rFNA, that had higher accuracy for FLUS nodules. The combined criterion for AUS nodules (at least rFNA-V or EU-TIRADS-4) maximized sensitivity (92.3%) with acceptable specificity (70.0%); OR: 28.0. In the case of FLUS nodules, the combined criterion (rFNA-V or EU-TIRADS-5) maximized specificity (95.2%) with 57.7% sensitivity and a low percentage (13.9%) of positive nodules, OR: 27.0. In both types of nodules, the low risk category in EU-TIRADS and benign result of rFNA excluded cancer. Concluding, category III nodules with and without nuclear atypia differ in their risk of malignancy and, consequently, diagnostic criteria adopted for the evaluation of these nodules with rFNA and EU-TIRADS should be specific to AUS and FLUS nodules.

Project description:Background The incidence of thyroid lumps is more and more high in population, and most biopsies of thyroid nodules are benign. To develop a practical risk stratification system based on five ultrasound features to stratify the malignancy risk of thyroid neoplasms. Methods This retrospective investigation enrolled 999 consecutive patients with 1,236 thyroid nodules who underwent ultrasound screening. Fine-needle aspiration and/or surgery was performed, and pathology results were obtained at the Seventh Affiliated Hospital of Sun Yat-sen University in Shenzhen, China, which is a tertiary referral center, from May 2018 to February 2022. Each thyroid nodule’s score was calculated based on five ultrasound features: composition, echogenicity, shape, margin, and echogenic foci. Additionally, each nodule’s malignancy rate was calculated. The chi-square test was used to test whether the malignancy rate was different among the three subcategories (scores of 4–6, 7–8, and 9 or more) of thyroid nodules. We proposed the revised Thyroid Imaging Reporting and Data System (R-TIRADS), and its sensitivity and specificity were compared to the two existing systems [the American College of Radiology TIRADS (ACR TIRADS) and the Korean Society of Thyroid Radiology TIRADS (K-TIRADS)]. Results The final dataset consisted of 425 nodules from 370 patients. The malignancy rates of three subcategories [malignancy rate: 28.8% (scores from 4–6), 64.7% (scores from 7–8), and 84.2% (scores of 9 or more)] were significantly different (P<0.01). The unnecessary biopsy rates of the three systems (ACR TIRADS, R-TIRADS, and K-TIRADS) were 28.7%, 25.2%, and 14.8%, respectively. The R-TIRADS presented better diagnostic performance than the ACR TIRADS or K-TIRADS [area under the curve: 0.79 (95% CI: 0.74–0.83) vs. 0.69 (95% CI: 0.64–0.75), P=0.046; 0.79 (95% CI: 0.74–0.83) vs. 0.66 (95% CI: 0.60–0.71), P=0.041, respectively]. The R-TIRADS had the highest sensitivity [0.746 (95% CI: 0.689–0.803)], followed by the K-TIRADS [0.399 (95% CI: 0.335–0.463), P=0.000] and ACR TIRADS [0.377 (95% CI: 0.314–0.441), P=0.000]. Conclusions The R-TIRADS enables radiologists to diagnose thyroid nodules efficiently, and the number of unnecessary fine-needle aspirations can be considerably reduced.

Dataset Information

S-Detect Software vs. EU-TIRADS Classification: A Dual-Center Validation of Diagnostic Performance in Differentiation of Thyroid Nodules.

Publications

S-Detect Software vs. EU-TIRADS Classification: A Dual-Center Validation of Diagnostic Performance in Differentiation of Thyroid Nodules.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets