The value of a neural network based on multi-scale feature fusion to ultrasound images for the differentiation in thyroid follicular neoplasms.

OBJECTIVE: The objective of this research was to create a deep learning network that utilizes multiscale images for the classification of follicular thyroid carcinoma (FTC) and follicular thyroid adenoma (FTA) through preoperative US. METHODS: This retrospective study involved the collection of ultrasound images from 279 patients at two tertiary level hospitals. To address the issue of false positives caused by small nodules, we introduced a multi-rescale fusion network (MRF-Net). Four different deep learning models, namely MobileNet V3, ResNet50, DenseNet121 and MRF-Net, were studied based on the feature information extracted from ultrasound images. The performance of each model was evaluated using various metrics, including sensitivity, specificity, positive predictive value (PPV), negative predictive value (NPV), accuracy, F1 value, receiver operating curve (ROC), area under the curve (AUC), decision curve analysis (DCA), and confusion matrix. RESULTS: Out of the total nodules examined, 193 were identified as FTA and 86 were confirmed as FTC. Among the deep learning models evaluated, MRF-Net exhibited the highest accuracy and area under the curve (AUC) with values of 85.3% and 84.8%, respectively. Additionally, MRF-Net demonstrated superior sensitivity and specificity compared to other models. Notably, MRF-Net achieved an impressive F1 value of 83.08%. The curve of DCA revealed that MRF-Net consistently outperformed the other models, yielding higher net benefits across various decision thresholds. CONCLUSION: The utilization of MRF-Net enables more precise discrimination between benign and malignant thyroid follicular tumors utilizing preoperative US.

Uptake of 99m Tc-DTPA in Bone Metastases From Follicular Thyroid Carcinoma.

ABSTRACT: A 53-year-old man with follicular thyroid carcinoma (FTC) was referred for renal scintigraphy using 99m Tc-DTPA to assess the kidney function. Unexpectedly, the images showed an abnormal uptake of radiotracer in the right pelvic region. It corresponded to the site of metastasis in the right ilium revealed on 131 I SPECT/CT images. The biopsy pathology of the ilium lesion demonstrated follicular thyroid cancer.

Association of Ultrasonography Features of Follicular Thyroid Carcinoma With Tumor Invasiveness and Prognosis Based on WHO Classification and TERT Promoter Mutation.

OBJECTIVE: To investigate the association of ultrasound (US) features of follicular thyroid carcinoma (FTC) with tumor invasiveness and prognosis based on the World Health Organization (WHO) classification and telomerase reverse transcriptase (TERT) promoter mutations. MATERIALS AND METHODS: This retrospective study included 54 surgically confirmed FTC patients with US images and TERT promoter mutations (41 females and 13 males; median age [interquartile range], 40 years [30-51 years]). The WHO classification consisted of minimally invasive (MI), encapsulated angioinvasive (EA), and widely invasive (WI) FTCs. Alternative classifications included Group 1 (MI-FTC and EA-FTC with wild type TERT), Group 2 (WI-FTC with wild type TERT), and Group 3 (EA-FTC and WI-FTC with mutant TERT). Each nodule was categorized according to the US patterns of the Korean Thyroid Imaging Reporting and Data System (K-TIRADS) and American College of Radiology-TIRADS (ACR-TIRADS). The Jonckheere-Terpstra and Cochran-Armitage tests were used for statistical analysis. RESULTS: Among 54 patients, 29 (53.7%) had MI-FTC, 16 (29.6%) had EA-FTC, and nine (16.7%) had WI-FTC. In both the classifications, lobulation, irregular margins, and final assessment categories showed significant differences (all Ps ≤ 0.04). Furthermore, the incidences of lobulation, irregular margin, and high suspicion category tended to increase with increasing tumor invasiveness and worse prognosis (all Ps for trend ≤ 0.006). In the WHO groups, hypoechogenicity differed significantly among the groups (P = 0.01) and tended to increase in proportion as tumor invasiveness increased (P for trend = 0.02). In the alternative group, punctate echogenic foci were associated with prognosis (P = 0.03, P for trend = 0.03). CONCLUSION: Increasing tumor invasiveness and worsening prognosis in FTC based on the WHO classification and TERT promoter mutation results were positively correlated with US features that indicate malignant probability according to both K-TIRADS and ACR-TIRADS.

Generating a multimodal artificial intelligence model to differentiate benign and malignant follicular neoplasms of the thyroid: A proof-of-concept study.

BACKGROUND: Machine learning has been increasingly used to develop algorithms that can improve medical diagnostics and prognostication and has shown promise in improving the classification of thyroid ultrasound images. This proof-of-concept study aims to develop a multimodal machine-learning model to classify follicular carcinoma from adenoma. METHODS: This is a retrospective study of patients with follicular adenoma or carcinoma at a single institution between 2010 and 2022. Demographics, imaging, and perioperative variables were collected. The region of interest was annotated on ultrasound and used to perform radiomics analysis. Imaging features and clinical variables were then used to create a random forest classifier to predict malignancy. Leave-one-out cross-validation was conducted to evaluate classifier performance using the area under the receiver operating characteristic curve. RESULTS: Patients with follicular adenomas (n = 7) and carcinomas (n = 11) with complete imaging and perioperative data were included. A total of 910 features were extracted from each image. The t-distributed stochastic neighbor embedding method reduced the dimension to 2 primary represented components. The random forest classifier achieved an area under the receiver operating characteristic curve of 0.76 (clinical only), 0.29 (image only), and 0.79 (multimodal data). CONCLUSION: Our multimodal machine learning model demonstrates promising results in classifying follicular carcinoma from adenoma. This approach can potentially be applied in future studies to generate models for preoperative differentiation of follicular thyroid neoplasms.

Investigation of pre-operative demographic, biochemical, sonographic and cytopathological findings in low-risk thyroid neoplasms.

OBJECTIVE: The present article analyses pre-operative demographic, biochemical, sonographic and histopathological characteristics of low-risk thyroid neoplasms (LRTNs), with a focus on four subgroups, "well-differentiated carcinoma-not otherwise specified" (WDC-NOS), "non-invasive follicular thyroid neoplasm with papillary like nuclear features" (NIFTP), "well-differentiated tumours of uncertain malignant potential" (WDT-UMP) and "follicular tumour of uncertain malignant potential" (FT-UMP). METHODS: The study retrospectively analyzed the histopathology of 2453 malignant thyroids and the final analyses included 99 cases diagnosed with LRTNs. The demographic and clinical features, pre-operative thyroid function, ultrasonography results, cytopathology results, histopathology results and prognostic classifications were assessed. RESULTS: The groups were similar demographic characteristics and the majority of clinical data, including comorbidities, thyroid function tests, thyroid cancer/neck radiotherapy history. NIFTPs represented 69.7% of all LRTNs. All (100%) WDT-UMPs had solitary nodules. Index nodule volume differed among the groups (p = .036), it was the lowest in WDC-NOS [0.68 (0.63-0.72 cc)] and highest in FT-UMP [12.6 (0.5-64 cc)]. Echogenicity findings were similar. Index nodule TIRADS demonstrated a significant difference (p = .021) but index nodule halo sign and BETHESDA scores were similar in all groups. The diameter, localisation and multicentric structure of LRTNs were again similar for all groups. Finally, prognostic scores suggested similar outcomes in all groups. CONCLUSION: The majority of LRTNs were NIFTPs in our population and all WDT-UMPs were solitary lesions. Index nodule volume was the most essential discriminating sonographic finding but further research must be performed before discriminatory potential can be described.

Comparison of the diagnostic performance of three ultrasound thyroid nodule risk stratification systems for follicular thyroid neoplasm: K-TIRADS, ACR -TIRADS and C-TIRADS.

OBJECTIVE: To explore the diagnostic performance of the currently used ultrasound-based thyroid nodule risk stratification systems (K-TIRADS, ACR -TIRADS, and C-TIRADS) in differentiating follicular thyroid adenoma (FTA) from follicular thyroid carcinoma (FTC). METHODS: Clinical data and preoperative ultrasonographic images of 269 follicular thyroid neoplasms were retrospectively analyzed. All of them were detected by Color Doppler ultrasound instruments equipped with high-frequency liner array probes (e.g. Toshiba Apoli500 with L5-14MHZ; Philips IU22 with L5-12MHZ; GE LOGIQ E9 with L9-12MHZ and MyLab Class C with L9-14MHZ). The diagnostic performance of three TIRADS classifications for differentiating FTA from FTC was evaluated by drawing the receiver operating characteristic (ROC) curves and calculating the cut-off values. RESULTS: Of the 269 follicular neoplasms (mean size, 3.67±1.53 cm), 209 were FTAs (mean size, 3.56±1.38 cm) and 60 were FTCs (mean size, 4.07±1.93 cm). There were significant differences in ultrasound features such as margins, calcifications, and vascularity of thyroid nodules between the FTA and FTC groups (P < 0.05). According to the ROC curve comparison analysis, the diagnostic cut-off values of K-TIRADS, ACR-TIRADS, and C-TIRADS for identifying FTA and FTC were K-TR4, ACR-TR4, and C-TR4B, respectively, and the areas under the curves were 0.676, 0.728, and 0.719, respectively. The difference between ACR-TIRADS and K-TIRADS classification was statistically significant (P = 0.0241), whereas the differences between ACR-TIRADS and C-TIRADS classification and between K-TIRADS and C-TIRADS classification were not statistically significant (P > 0.05). CONCLUSION: The three TIRADS classifications were not conducive to distinguishing FTA from FTC. It is necessary to develop a novel malignant risk stratification system specifically for the identification of follicular thyroid neoplasms.

Identification of Diagnostic Metabolic Signatures in Thyroid Tumors Using Mass Spectrometry Imaging.

"Gray zone" thyroid follicular tumors are difficult to diagnose, especially when distinguishing between benign follicular thyroid adenoma (FTA) and malignant carcinoma (FTC). Thus, proper classification of thyroid follicular diseases may improve clinical prognosis. In this study, the diagnostic performance of metabolite enzymes was evaluated using imaging mass spectrometry to distinguish FTA from FTC and determine the association between metabolite enzyme expression with thyroid follicular borderline tumor diagnosis. Air flow-assisted desorption electrospray ionization mass spectrometry imaging (AFAIDESI-MSI) was used to build a classification model for thyroid follicular tumor characteristics among 24 samples. We analyzed metabolic enzyme marker expression in an independent validation set of 133 cases and further evaluated the potential biological behavior of 19 thyroid borderline lesions. Phospholipids and fatty acids (FAs) were more abundant in FTA than FTC (p < 0.001). The metabolic enzyme panel, which included FA synthase and Ca2+-independent PLA2, was further validated in follicular thyroid tumors. The marker combination showed optimal performance in the validation group (area under the ROC, sensitivity, and specificity: 73.6%, 82.1%, and 60.6%, respectively). The findings indicate that AFAIDESI-MSI, in combination with low metabolic enzyme expression, could play a role in the diagnosis of thyroid follicular borderline tumors for strict follow-up.

Ultrasound features and risk stratification system in NIFT-P and other follicular-patterned thyroid tumors.

OBJECTIVE: Noninvasive follicular thyroid neoplasm with papillary-like nuclear features (NIFT-P) is an encapsulated follicular variant of papillary thyroid carcinoma (PTC) with nonaggressive clinical behavior. However, since its diagnosis is exclusively possible after surgery, it represents a clinical challenge. Neck ultrasound (US) shows good sensitivity and specificity in suggesting malignancy in thyroid nodules. However, little information is available about its ability in identifying NIFT-P. DESIGN: The aim of this study was to evaluate the US features of NIFT-P, comparing them with other follicular-patterned thyroid tumors, and to test the ability of the main US risk stratification system (RSS) in identifying NIFT-P. METHODS: We retrospectively evaluated 403 consecutive patients submitted to thyroid surgery, with positive histology for at least 1 nodule being NIFT-P, follicular variant of PTC (FV-PTC), follicular thyroid carcinoma (FTC), or follicular adenoma (FA). RESULTS: The US features of NIFT-P (n = 116), FV-PTC (n = 170), FTC (n = 76), and FA (n = 90) were reported. Follicular variant of PTC and FTC more frequently showed irregular margins, presence of calcifications, "taller than wide" shape, and the absence of halo compared with NIFT-P. Furthermore, FTC and also FA were larger and more frequently hypoechoic than NIFT-P. Most cases (77%) showed an indeterminate cytology. Regardless of the US RSS considered, NIFT-P and FA were less frequently classified in the high-suspicious category compared with FV-PTC and FTC. CONCLUSIONS: Ultrasound features of NIFT-P are frequently superimposable to those of nodules with low suspicion of malignancy. The NIFT-P is almost never classified in the high-suspicious category according to the main US RSS. Therefore, although the preoperative identification of NIFT-P remains a challenge, neck US can be integrated in the algorithm of management of nodules with indeterminate cytology, suggesting a possible conservative approach in those with low-suspicious features.

Cytological and Ultrasound Features of Thyroid Nodules Correlate With Histotypes and Variants of Thyroid Carcinoma.

CONTEXT: Prognosis is excellent for papillary thyroid carcinoma (PTC), noninvasive follicular thyroid neoplasia with papillary-like nuclear features (NIFT-P), and follicular thyroid carcinoma (FTC) but is poor for poorly differentiated thyroid carcinoma (PDTC) and anaplastic thyroid carcinoma (ATC). Among PTCs, the prognosis is more favorable for follicular (FV-PTC) and classic (CV-PTC) than for tall cell (TCV-PTC), and solid (SV-PTC) variants. OBJECTIVE: To associate histotypes and variants of thyroid carcinoma with ultrasound and cytological features. METHODS: Histology of 1018 benign tumors and 514 PTC (249 CV, 167 FV, 49 TC, 34 SV, and 15 other variants), 52 NIFT-P, 50 FTC, 11 PDTC, and 3 ATC was correlated with fine-needle aspiration biopsy categories (Italian classification: TIR1, TIR2, TIR3A, TIR3B, TIR4, and TIR5) and ultrasound features at the Endocrinology Unit, University Hospital of Pisa. In total, 1117 patients with thyroid nodule(s) who underwent thyroidectomy were included. RESULTS: Of PTC, 36.3% had indeterminate cytology (TIR3A or TIR3B), 56.6% were suspicious for malignancy or malignant (TIR4 or TIR5); 84.0% FTC and 69.3% NIFT-P were TIR3A or TIR3B; 72.5% FV-PTC and 73.6% SV-PTC were TIR3A or TIR3B; 79.9% CV-PTC and 95.9% TCV-PTC were TIR4 or TIR5. The association of a hypoechoic pattern, irregular margins, and no microcalcifications was more frequent in TCV-PTC than in CV-PTC (P = .02, positive predictive value = 38.9%; negative predictive value = 85.5%). CONCLUSION: At cytology, most FTC, NIFT-P, FV-PTC, and SV-PTC were indeterminate, most CV-PTC and TCV-PTC were suspicious for malignancy or malignant. Ultrasound can be helpful in ruling out TCV-PTC.

Intratumoural metastasis of primary lung adenocarcinoma to non-invasive follicular thyroid neoplasm with papillary-like nuclear features.

Metastasis to the thyroid gland is very uncommon with an incidence of 2-3% of all thyroid malignancies. A higher incidence is noted in autopsy studies indicating incidental detection. However, tumour-to-tumour metastasis is extremely uncommon with a handful of cases published in the literature to date. Also, non-invasive follicular thyroid neoplasm with papillary-like nuclear features (NIFT-P) is a rare neoplasm; diagnosis requires meticulous sampling of the entire capsule and fulfilment of other diagnostic criteria. We report a case of primary adenocarcinoma of lung in a 57-year-old female who additionally had a left thyroid nodule which appeared suspicious on ultrasonography. Histology of lung tumour was conventional papillary adenocarcinoma while aspiration cytology from the thyroid raised suspicion of metastatic adenocarcinoma. On hemithyroidectomy, the thyroid nodule showed metastatic adenocarcinoma in the centre of the nodule, while the peripheral portion showed non-invasive follicular thyroid neoplasm with papillary-like nuclear features; the diagnosis of which was confirmed with complete sampling of the thyroid capsule. The immunoprofile also supported the above dual histology. This is an extremely uncommon occurrence and metastasis within a NIFT-P has not been reported to the best of our knowledge.

Percutaneous cryoablation of follicular thyroid carcinoma metastasis to the pancreas

The following is a technical report of the successful cryoablation of pancreatic metastasis originating from follicular thyroid carcinoma. The patient was a 72-year-old female who underwent total thyroidectomy and radioiodine ablation for follicular carcinoma. One year after surgery, a positron emission tomography-computed tomography (PET-CT) examination, performed to demonstrate the source of the increased thyroglobulin, showed a fluorodeoxyglucose (FDG) avid mass located in the body of the pancreas. A percutaneous tru-cut biopsy was performed that revealed follicular thyroid carcinoma metastasis to the pancreas. Because of the patient's comorbidities, the patient underwent percutaneous cryoablation and made a successful recovery over the following 13 months. At the most recent follow-up, the thyroglobulin level was undetectable, and a PET-CT scan showed no FDG avid mass in the pancreas. To our knowledge, follicular carcinoma metastasis of the pancreas is extremely rare, and this is the first report of successful cryoablation of a metastatic tumor in the pancreas.

An attempt to reduce unnecessary surgical procedures... Can ultrasound characteristics help in differentiating adenoma vs carcinoma in follicular thyroid neoplasms?

INTRODUCTION AND OBJECTIVES: Thyroid nodules frequently require ultrasound and Fine Needle Aspiration Cytology (FNAC) evaluation. However, FNA cytology does not allow differentiation between follicular adenoma and carcinoma on Bethesda type IV lesions. This situation leads to many unnecessary surgical procedures because it is not possible to assure the benignity of the lesions, even when most of the specimens correspond to adenomas or even other benign lesions. The objective is this study is to establish if there are any US characteristics that would help us to predict the risk of malignancy of nodules with a pathological diagnosis of follicular neoplasm in order to achieve a more conservative management for non-suspicious nodules. MATERIAL AND METHODS: We studied 61 nodules in 61 patients (51 women and 10 men) that underwent thyroid surgery and had histopathological results of either follicular adenoma or carcinoma. Different US characteristics of the nodules were analysed (composition, echogenicity, margin, calcification status, the presence of halo and overall observer suspicion of malignancy) and were correlated with the histopathological analysis. RESULTS: We have found a statistically significant association between the presence of calcifications, ill-defined borders and overall observer suspicion or impression (defined by well-known suspicious for malignancy ultrasonographic features, such as calcification, poorly defined margin, and a markedly hypoechoic solid nodule; and benign ultrasonographic features, such as predominantly cystic echogenic composition and the presence of a perinodular hypoechogenic halo) with follicular carcinoma. However all those features have shown low sensitivities in the present study (30%, 30% and 50%, respectively). On the other hand, the absence of halo sign has shown a sensitivity of 100% and a negative predictive value (NPV) of 100% in our study. CONCLUSIONS: The presence of calcifications, ill-defined borders and the overall impression or suspicion of malignancy associate with a higher risk for follicular carcinoma in Bethesda type IV thyroid nodules but their absence do not allow to predict benignity in these nodules. Inversely, when a halo sign lesion is observed, benign follicular neoplasm should be considered.

Clinical and histopathological features of follicular thyroid cancer in Chile.

Objective: Follicular thyroid carcinoma (FTC) is less frequent but has a worse prognosis than papillary carcinoma. The available evidence on pre-operative characteristics of FTC is controversial. Our objective was to characterize the clinical, ultrasound and histopathological presentation of FTC patients treated Chile. Subjects and methods: Retrospective analysis of 97 patients treated for FTC in 6 large centers in Chile. We analyzed their ultrasonographic features and classified the nodules according to ATA risk of malignancy and TI-RADS score, as well as the cytological findings according to the Bethesda system. We described their clinical and histopathological findings at diagnosis and classified their risk of recurrence and mortality according to ATA 2015 recurrence risk category and the eighth edition of the AJCC/UICC staging system, respectively. Results: Median age was 48 years and 73.2% were females. The median diameter was 38.8 mm; only 9.5% of them were microtumors. According to ATA risk of malignancy, 86% of the nodules were low or intermediate suspicious, while 78% were category 3 or 4A nodules according to the TI-RADS. Regarding the Bethesda system, 65.9% had indeterminate cytology (20.6% category III and 45.3% category IV). At histological examination, most were minimally-invasive and angio-invasive tumors with less than 4 foci (54.7% and 28.4% respectively). More than 90% of FTC were unifocal and there was no lymphovascular or extrathyroidal invasion or lymph node involvement. Four patients (4.1%) had distant metastases at diagnosis. Most patients (95%) had stage I or II disease according to the AJCC/UICC staging system, while the risk of recurrence was low at 51.5% when using the ATA risk of recurrence scale. Conclusion: At diagnosis, most FTCs were nodules of low or intermediate suspicion at ultrasound, nearly two thirds had indeterminate cytology according to the Bethesda system, and nearly 50% of them were of low risk of recurrence.

Clinical and Sonographic Features of Noninvasive Follicular Thyroid Neoplasm With Papillary-Like Nuclear Features: A Retrospective Study.

ABSTRACT: This study was designed to investigate the clinical and sonographic features of noninvasive follicular thyroid neoplasm with papillary-like nuclear features (NIFTPs) as compared with classical papillary thyroid carcinoma (cPTC), follicular adenoma (FA), and follicular thyroid carcinoma (FTC). A total of 178 patients were enrolled in this study. The clinical characteristics and sonographic features of thyroid nodules were compared between NIFTP and cPTC or FA/FTC. All nodules were reclassified according to the Thyroid Ultrasound Imaging Reporting and Data System and American Thyroid Association guidelines classification. The mean size of NIFTP was 29.91 ± 14.71 mm, which was larger than that of cPTC ( P = 0.000). Significant difference was found in lymph node metastases between NIFTP and cPTC ( P = 0.000). Most NIFTPs showed solid composition, hypoechoic echogenicity, smooth margin, wider than tall shape, none echogenic foci, absence of halo, and perinodular vascularity, which were similar with FA and FTC. Compared with NIFTP, hypoechoic and very hypoechoic, taller than wide, irregular margin, punctate echogenic foci, absence of halo, and low vascularity were more commonly observed in cPTC. There were statistical differences both in American College of Radiology Thyroid Ultrasound Imaging Reporting and Data System and in American Thyroid Association classification between NIFTP and cPTC ( P < 0.05), but there were no significant differences between NIFTP and FTC/FA ( P > 0.05). The ultrasonographic characteristics of NIFTP were obviously different from cPTC but overlapped with FTC and FA. Ultrasound could help increase preoperative attention of NIFTP in an appropriate clinical setting, which may lead to a more conservative treatment approach.

Imaging of pediatric thyroid tumors: A COG Diagnostic Imaging Committee/SPR Oncology Committee White Paper.

Pediatric thyroid cancer is rare in children; however, incidence is increasing. Papillary thyroid cancer and follicular thyroid cancer are the most common subtypes, comprising about 90% and 10% of cases, respectively. This paper provides consensus imaging recommendations for evaluation of pediatric patients with thyroid cancer at diagnosis and during follow-up.

Two cases of flow void sign of temporal bone metastasis from follicular thyroid carcinoma.

This report describes CT and MRI findings of temporal bone metastasis from follicular thyroid carcinoma in two cases. Both of these had large, osteolytic, hypervascular masses of the temporal bone, accompanied by internal scattered bone fragments and extraosseous mass formation on unenhanced and contrast-enhanced CT images. In the first case, several dilated and tortuous vessels within the markedly hypervascular mass were observed on the arterial phase of dynamic contrast-enhanced CT images. Compared with the signal intensity of the cerebellum, temporal bone masses showed slightly hypo- to slightly hyperintense on T1-weighted images and slightly hypo- to moderately hyperintense on T2-weighted images. Both cases had flow voids in abnormally dilated vessels within the mass on T1- and T2-weighted images. Thyroid follicular carcinoma rarely metastasizes the temporal bone and presents with an osteolytic hypervascular mass with flow void sign.

Analysis of a pre-2017 follicular variant papillary thyroid carcinoma cohort reclassified as noninvasive follicular thyroid neoplasm with papillary-like features (NIFTP): an 11-year retrospective single institution experience.

INTRODUCTION: Noninvasive follicular thyroid neoplasm with papillary-like features (NIFTP), represents a distinct class of thyroid neoplasms with very low risk of adverse outcome and a set of strict histologic criteria. Introduction of NIFTP as a non-cancer has had an appreciable decrease in risk of malignancy and body of literature on this entity continues to grow. In this study, we reviewed clinical, fine-needle aspiration cytology (FNAC), imaging, and molecular findings of histologically proven NIFTPs at our institution. MATERIALS AND METHODS: Thyroid resections during an 11-year period, with histologic diagnosis of follicular variant of papillary thyroid carcinoma (FVPTC), were retrospectively reviewed to identify NIFTP. Ultrasonographic appearance, FNA findings, and molecular findings were also reviewed. RESULTS: Of 244 cases of FVPTC identified, 74 (30%) cases were reclassified as NIFTP. Mean tumor size was 2.5 cm. Of 33 patients with lymph node dissection, none had lymph node metastases. On imaging, 36 NIFTP (49%) showed vascularity, 25 (33%) were isoechoic to hypoechoic, there were calcifications in 14 cases (19%), and 7 cases (9%) showed a hypoechoic rim. Bethesda III/IV was the most common interpretation rendered on FNAC (31%). Seven cases had NRAS mutations and 1 case had BRAF V600E mutation. The remaining cases were either negative for BRAF V600E or had no identifiable molecular alterations. CONCLUSIONS: A significant percentage of tumors previously diagnosed as FVPTC were reclassified as NIFTP. This tumor cannot be reliably diagnosed preoperatively on FNAC, shows no characteristic features on ultrasound and has low suspicion of malignancy. BRAF V600E mutations are infrequent in NIFTP.

Breast metastasis in follicular thyroid cancer patient.

In this case report, we aimed to present the findings of a follicular thyroid carcinoma patient with breast metastasis, which is rarely reported in the literature. A 33-year-old female who had been operated for thyroid cancer 17 years ago, but whose pathology report could not be reached was suspected of recurrence in the left lobe region of the thyroid gland. Fine-needle aspiration biopsy was done in this region, and the biopsy result was reported as thyroid follicular carcinoma. 18F-fluorodeoxyglucose (18F-FDG) positron emission tomography/computed tomography (PET/CT) was performed for re-staging before surgery. In the PET/CT, it was found that there was residual thyroid tissue in the right and left lobe region and superior to these lesions in the left side, there were lesions which destruct to the hyoid bone, and there were multiple nodular lesions in both lungs which measured with maximum 15 mm × 12 mm, and all these lesions have increased 18F-FDG uptake. In addition to these lesions, a nodular lesion with the size of ~11 mm ×10 mm in the upper-middle quadrant of the right breast, and it was showing increased 18F-FDG uptake (maximum standardized uptake value: 3). Pathology results of the left neck region operation materials were reported as papillary and follicular carcinoma of the thyroid gland. Right lumpectomy was performed for the lesion in the right breast during the same session with thyroid operation. The pathology result of this lesion was also reported as metastasis of thyroid follicular cancer. Posttreatment iodine-131 whole-body scan after surgery was reported as there was abnormal accumulation in residual thyroid tissues on the right side of the neck and lung metastases. In patients with thyroid cancer, the possibility of metastasis of the breasts should be considered when there is a lesion in the breast tissue.

An artificial intelligence ultrasound system's ability to distinguish benign from malignant follicular-patterned lesions.

Objectives: To evaluate the application value of a generally trained artificial intelligence (AI) automatic diagnosis system in the malignancy diagnosis of follicular-patterned thyroid lesions (FPTL), including follicular thyroid carcinoma (FTC), adenomatoid hyperplasia nodule (AHN) and follicular thyroid adenoma (FTA) and compare the diagnostic performance with radiologists of different experience levels. Methods: We retrospectively reviewed 607 patients with 699 thyroid nodules that included 168 malignant nodules by using postoperative pathology as the gold standard, and compared the diagnostic performances of three radiologists (one junior, two senior) and that of AI automatic diagnosis system in malignancy diagnosis of FPTL in terms of sensitivity, specificity and accuracy, respectively. Pairwise t-test was used to evaluate the statistically significant difference. Results: The accuracy of the AI system in malignancy diagnosis was 0.71, which was higher than the best radiologist in this study by a margin of 0.09 with a p-value of 2.08×10-5. Two radiologists had higher sensitivity (0.84 and 0.78) than that of the AI system (0.69) at the cost of having much lower specificity (0.35, 0.57 versus 0.71). One senior radiologist showed balanced sensitivity and specificity (0.62 and 0.54) but both were lower than that of the AI system. Conclusions: The generally trained AI automatic diagnosis system can potentially assist radiologists for distinguishing FTC from other FPTL cases that share poorly distinguishable ultrasonographical features.