Identification Of Malignant Thyroid Nodules Research Articles

Comparison of ultrasound risk stratification systems for pediatric thyroid nodules.

There is currently insufficient data to validate adult-based US risk stratification systems (RSSs) for the identification of malignant thyroid nodules in a pediatric population. From October 2016 and May 2023, 173 thyroid nodules of pediatric patients (age ≤ 18 years) with definitive pathology results and ultrasound (US) examination within 1 month before surgery or fine-needle aspiration (FNA) biopsy in our institution were enrolled in this study. The clinical and US characteristics of these nodules were retrospectively reviewed and categorized according to the ACR-TIRADS, C-TIRADS, and ATA guidelines. The diagnostic performance of US-based FNA criteria (original and simulating) of the three guidelines in thyroid cancer detection was estimated. The three RSSs had similar AUC according to the categories(0.849-0.852, all P > 0.05). When combined with the original FNA criteria of the three RSSs to manage the nodules, the FNA rate of ACR-TIRADS and C-TIRADS were significantly less than ATA guidelines (53.18% vs. 64.63%, P < 0.05, and 52.60% vs. 64.63%, P < 0.05). The missed malignancy rate (MMR) and unnecessary FNA rate (UFR) of ATA guidelines (50.00%, 35.85%) was highest among the three RSSs, followed by the C-TIRADS (37.80%, 19.57%) and the ACR-TIRADS (37.04%, 19.57%). When nodules < 1cm with the highest category in each RSS biopsied, that is when using the simulating FNA thresholds, the MMR was reduced overall (all P < 0.001), without a change in the UFR (all P > 0.05). All the three RSSs showed a substantial improvement in accuracy and malignant detection rate (all P < 0.05). The ACR-TIRADS, C-TIRADS, and ATA guidelines showed high missed malignancy rates when using their original recommended FNA criteria. When nodules < 1cm with the highest category in each RSS biopsied, the missed malignancy rate of each RSS was decreased. Decreasing the FNA thresholds for highly suspicious malignant nodules may therefore be an effective means of managing malignant thyroid nodules in pediatric patients.

Classification of follicular-patterned thyroid lesions using a minimal set of epigenetic biomarkers.

The minimally invasive fine-needle aspiration cytology (FNAC) is the current gold standard for the diagnosis of thyroid nodule malignancy. However, the correct discrimination of follicular neoplasia often requires more invasive diagnostic techniques. The lack of suitable immunohistochemical markers to distinguish between follicular thyroid carcinoma and other types of follicular-derived lesions complicates diagnosis, and despite most of these tumours being surgically resected, only a small number will test positive for malignancy. As such, the development of new orthogonal diagnostic approaches may improve the accuracy of diagnosing thyroid nodules. This study includes a retrospective, multi-centre training cohort including 54 fresh-frozen follicular-patterned thyroid samples and two independent, multi-centre validation cohorts of 103 snap-frozen biopsies and 33 FNAC samples, respectively. We performed a genome-wide genetic and epigenetic profiling of 54 fresh-frozen follicular-patterned thyroid samples using exome sequencing and the Illumina Human DNA Methylation EPIC platform. An extensive validation was performed using the bisulfite pyrosequencing technique. Using a random forest approach, we developed a three-CpG marker-based diagnostic model that was subsequently validated using bisulfite pyrosequencing experiments. According to the validation cohort, this cost-effective method discriminates between benign and malignant nodules with a sensitivity and specificity of 97 and 88%, respectively (positive predictive value (PPV): 0.85, negative predictive value (NPV): 0.98). Our classification system based on a minimal set of epigenetic biomarkers can complement the potential of the diagnostic techniques currently available and would prioritize a considerable number of surgical interventions that are often performed due to uncertain cytology. In recent years, there has been a significant increase in the number of people diagnosed with thyroid nodules. The current challenge is their etiological diagnosis to discount malignancy without resorting to thyroidectomy. The method proposed here, based on DNA pyrosequencing assays, has high sensitivity (0.97) and specificity (0.88) for the identification of malignant thyroid nodules. This simple and cost-effective approach can complement expert pathologist evaluation to prioritize the classification of difficult-to-diagnose follicular-patterned thyroid lesions and track tumor evolution, including real-time monitoring of treatment efficacy, thereby stimulating adherence to health promotion programs.

GAN-Guided Deformable Attention Network for Identifying Thyroid Nodules in Ultrasound Images.

Early detection and identification of malignant thyroid nodules, a vital precursory to the treatment, is a difficult task even for experienced clinicians. Many Computer-Aided Diagnose (CAD) systems have been developed to assist clinicians in performing this task on ultrasonic images. Learning-based CAD systems for thyroid nodules generally accommodate both nodule detection/ segmentation and fine-grained classification for its malignancy, and prior researches often treat aforementioned tasks in separate stages, leading to additional computational costs. In this paper, we utilize an online class activation mapping (CAM) mechanism to guide the network to learn discriminative features for identifying thyroid nodules in ultrasound images, called CAM attention network. It takes nodule masks as localization cues for direct spatial attention of the classification module, thereby avoiding isolated training for classification. Meanwhile, we propose a deformable convolution module to add offsets to the regular grid sampling locations in the standard convolution, guiding the network to capture more discriminative features of nodule areas. Furthermore, we use a generative adversarial network (GAN)to ensure reliable deformations of nodules from the deformable convolution module. Our proposed CAM attention network has already achieved the 2nd place in the classification task of TN-SCUI 2020, a MICCAI 2020 Challenge with the largest set of thyroid nodule ultrasound images according to our knowledge. The further inclusion of our proposed GAN-guided deformable module allows for capturing more fine-grained features between benign and malignant nodules, and further improves the classification accuracy to a new state-of-the-art level.

Role of sonographic features in predicting the malignant potential of thyroid nodules

However, while thyroid nodules are common, thyroid malignancy is relatively rare, constituting about 1% of all malignancies. The main point of the approach of the thyroid nodule is the detection of the malignant nodules and deciding for the surgical treatment. Ultrasonography (US) plays a crucial role in the diagnostic management of thyroid nodules. The aim was to assess the reliability of using hypoechoic, solid and ill-defined margin as independent predictors for the identification of malignant thyroid nodules on US. We retrospectively analysed the three suspicious US features of malignancy for 145 patients with 255 thyroid nodules who underwent thyroid resection. We used histological results as gold standard reference test. Of the 255 surgical resected nodules; hypoechoic nodules had a sensitivity of 66.7%, and positive predictive value (PPV) of 8.7%. Solid nodules had a sensitivity of 33.3% and PPV of 3.7%. Ill-defined margins nodules had a sensitivity of 66.7% and PPV of 6.9% in predicting malignancy. The present study adds further evidence on the poor PPV in our results, indicated, that individual US features are not reliable used as independent predictors for the identification of malignant potential thyroid nodules on US.

Development and validation of an ultrasound-based nomogram to improve the diagnostic accuracy for malignant thyroid nodules.

The aim of this study was to develop an ultrasound-based nomogram to improve the diagnostic accuracy of the identification of malignant thyroid nodules. A total of 1675 histologically proven thyroid nodules (1169 benign, 506 malignant) were included in this study. The nodules were grouped into the training dataset (n = 700), internal validation dataset (n = 479), or external validation dataset (n = 496). The grayscale ultrasound features included the nodule size, shape, aspect ratio, echogenicity, margins, and calcification pattern. We applied least absolute shrinkage and selection operator (lasso) regression to select the strongest features for the nomogram. Nomogram discrimination (area under the receiver operating characteristic curve, AUC) and calibration were assessed. The nomogram was subjected to bootstrapping validation (1000 bootstrap resamples) to calculate a mean AUC and 95% confidence interval (CI). The nomogram showed good discrimination in the training dataset, with an AUC of 0.936 (95% CI: 0.918-0.953) and good calibration. Application of the nomogram to the internal validation dataset also resulted in good discrimination (AUC: 0.935; 95% CI, 0.915-0.954) and good calibration. The model tested in an external validation dataset demonstrated a lower AUC of 0.782 (95% CI: 0.776-0.789). This ultrasound-based nomogram can be used to quantify the probability of malignant thyroid nodules. • Ultrasound examination is helpful in the differential diagnosis of malignant and benign thyroid nodules. • However, ultrasound accuracy relies heavily on examiner experience. • A less subjective diagnostic model is desired, and the developed nomogram for thyroid nodules showed good discrimination and good calibration.

Diagnostic performance of shear wave elastography in the identification of malignant thyroid nodules: a meta-analysis.

This meta-analysis aimed to assess the performance of shear wave elastography (SWE) in the identification of malignant thyroid nodules. Web of Science, Scopus, PubMed, and the references of narrative reviews were searched for relevant studies with a publication date through October 2013. The methodological quality was assessed using QUADAS tools. Data synthesis was calculated using the bivariate mixed-effects regression model. Of the 131 studies identified, 15 (11.5%) were included, in which SWE, point-SWE or 2D SWE, was used to evaluate 1,867 thyroid nodules in 1,525 patients. Methodological assessment revealed study quality was moderate to high. The pooled sensitivity, specificity, and area under the summary receiver operating characteristic curve of SWE for detecting malignant thyroid nodules were 84.3% (95% confidence interval [CI], 76.9-89.7%), 88.4% (95% CI, 84.0-91.7%), and 93% (95% CI, 90-95%), respectively. As a screening tool, positive and negative predictive values were 27.7-44.7% and 98.1-99.1%, respectively, calculated with a malignance prevalence of 5-10% in thyroid nodules. A publication bias regression test revealed no significant small-study bias. SWE is a highly accurate diagnostic modality for the identification of malignant thyroid nodules, with promise for integration into routine imaging protocols for thyroid nodules. • Shear wave elastography (SWE) is a group of novel ultrasound-based technologies. • Meta-analysis was employed to assess relevant studies of SWE of thyroid nodules. • SWE had high sensitivity and specificity in identifying malignant thyroid nodules. • The high negative predictive value of SWE can reduce unnecessary biopsies.

Evaluation and development of a real-time predictive model for ultrasound investigation of malignant thyroid nodules

Ultrasound investigations and correct identification of malignant thyroid nodules depend on the experience and qualifications of the investigators; thus, a model that provides better evaluation before needle aspiration is desired. Data from 687 patients with 726 thyroid nodules comprising 65 malignant nodules (61 papillary and 4 follicular carcinoma) and 661 benign nodules were used to construct a predictive model. Presence of micro-calcification, taller-than-wide shape, predominant solid echostructure, and irregular margins were shown to be good independent predictive parameters. A thyroid nodule was predicted as malignant with a score ≥3.3. Internal validation of this predictive tool by the bootstrapping method showed excellent overall model performance.

Thyroid Nodules with Microfollicular Findings Reported on Fine-Needle Aspiration: Invariably Surgical Treatment?

To assess whether fine-needle aspiration (FNA) can be a diagnostic procedure for identification of malignant thyroid nodules when the smear reveals the cytologic (microfollicular) finding of "follicular neoplasm" (FN). We reviewed a group of 79 patients with FN who underwent surgical treatment and evaluated the possible significance of the cytologic features of anisokaryosis, amount of colloid, and nuclear overlapping (NO). We excluded from the study those patients with FN who had other highly suspicious cytologic features, such as sporadic grooves and sporadic pseudonucleoli. In our series of 79 patients with FN at FNA, we found anisokaryosis in 49.4%, scant or no colloid in 31.6%, and NO in 5.1%. Thyroid cancer (TC)--follicular cancer or follicular variant of papillary cancer--was found in six patients (7.6%): four patients (10.2%) with anisokaryosis and two patients (5.0%) without anisokaryosis (P<0.5; chi2 test). All the patients with malignant lesions had scant or no colloid in the smears, and four of them were those with NO. Therefore, TC was found in 24.0% of nodules with scant or no colloid versus 0.0% of nodules with abundant colloid (P<0.001; chi2 test), and TC was found in 100% of nodules with NO versus 2.6% of nodules without NO (P<0.001; chi2 test). Because of the high prevalence of thyroid nodules and the frequency of FN at FNA, the number of unnecessary interventions may be very high. FNA cannot be diagnostic in FN because invasion of the tumor capsule and blood vessels can be evidenced only at histologic examination. Although it is common opinion that microfollicular nodules should be surgically treated, simple cytologic features can help select patients at low risk who can be monitored and reassessed clinically and by FNA. Patients with high-risk cytologic features such as NO should be advised that a total thyroidectomy may be necessary.