Skip to main content
Download PDF

Prediction model based on MRI morphological features for distinguishing benign and malignant thyroid nodules

BMC Cancer volume 24, Article number: 256 (2024) Cite this article

Abstract

Background

The low specificity of Thyroid Imaging Reporting and Data System (TI-RADS) for preoperative benign-malignant diagnosis leads to a large number of unnecessary biopsies. This study developed and validated a predictive model based on MRI morphological features to improve the specificity.

Methods

A retrospective analysis was conducted on 825 thyroid nodules pathologically confirmed postoperatively. Univariate and multivariate logistic regression were used to obtain β coefficients, construct predictive models and nomogram incorporating MRI morphological features in the training cohort, and validated in the validation cohort. The discrimination, calibration, and decision curve analysis of the nomogram were performed. The diagnosis efficacy, area under the curve (AUC) and net reclassification index (NRI) were calculated and compared with TI-RADS.

Results

572 thyroid nodules were included (training cohort: n = 397, validation cohort: n = 175). Age, low signal intensity on T2WI, restricted diffusion, reversed halo sign in delay phase, cystic degeneration and wash-out pattern were independent predictors of malignancy. The nomogram demonstrated good discrimination and calibration both in the training cohort (AUC = 0.972) and the validation cohort (AUC = 0.968). The accuracy, sensitivity, specificity, PPV, NPV and AUC of MRI-based prediction were 94.4%, 96.0%, 93.4%, 89.9%, 96.5% and 0.947, respectively. The MRI-based prediction model exhibited enhanced accuracy (NRI>0) in comparison to TI-RADSs.

Conclusions

The prediction model for diagnosis of benign and malignant thyroid nodules demonstrated a more notable diagnostic efficacy than TI-RADS. Compared with the TI-RADSs, predictive model had better specificity along with a high sensitivity and can reduce overdiagnosis and unnecessary biopsies.

Key points

  1. 1.

    MRI morphological features were predictors of malignant thyroid nodules.

  2. 2.

    Prediction model achieved a high AUC, sensitivity, and specificity in predicting malignant thyroid nodules.

  3. 3.

    Prediction mode outperformed TI-RADSs in diagnosing malignant thyroid nodules.

Peer Review reports

Introduction

Thyroid nodules are very common, and with the advances of high-resolution ultrasound, the detection rate in the general population ranges from 19 to 68%. The majority of thyroid nodules are benign, and only a small fraction is clinically significant [1,2,3]. The incidence of thyroid cancer continues to rise and is ranked as the fifth most common cancer among women in the United States currently [4]. The clinical management of thyroid nodules depends on the benignity or malignancy [5] and early qualitative diagnosis plays a crucial role in optimizing treatment and improving patient outcomes.

Various Ultrasonography risk stratification systems have been developed to effectively manage of thyroid nodules, including the American College of Radiology Thyroid Imaging Reporting and Data System (ACR- TIRADS) [6], Korean TIRADS (K-TIRADS) [7], European TIRADS (EU-TIRADS) [8], Kwak-TIRADS [9] and Chinese-TIRADS (C-TIRADS) [10]. While these TI-RADSs demonstrated high sensitivity (>90%) in identifying nodules, their specificity remains relatively unsatisfactory [11]. Additionally, differentiated thyroid cancer accounts for over 90% of cases, and has an excellent prognosis, with a 5-year survival rate exceeding 98% [12]. The high sensitivity and relatively low specificity of TI-RADS systems have led to the diagnosis of numerous thyroid nodules that lack clinical significance, resulting in unnecessary fine-needle aspiration (FNA) and overtreatment. FNA is considered the gold standard for the preoperative diagnosis of thyroid cancer. However, it is an invasive procedure, and approximately 20–30% of the puncture results are either nondiagnostic or of uncertain significance [13, 14].

Magnetic resonance imaging (MRI) has gained significant popularity in the diagnosis of head and neck tumors due to its numerous advantages, including multi-parameter measurement, arbitrary planar imaging, low risk of contrast allergy, no ionizing radiation, and high soft tissue contrast [15]. In recent years, there has been a growing trend in utilizing MRI for the preoperative evaluation of thyroid nodules [16,17,18,19,20]. However, few studies have explored the use of morphological features on multiparametric MRI to assess the benignity or malignancy of thyroid nodules.

In this study, we investigated the value of MRI morphological features in distinguishing between benign and malignant thyroid nodules. We also developed and validated a prediction model and compared its performance with the ultrasound-based TI-RADS system.

Materials and methods

Patients and study design

This study was a retrospective observational study conducted in accordance with the Declaration of Helsinki. Informed consent requirements were waived due to the retrospective nature of the study by the Institutional Review Board of Fudan University Minhang Hospital (2020-008-01 K).

Consecutive patients who underwent surgical thyroidectomy at our institution from January 2017 to December 2022 were retrospectively analyzed. Inclusion criteria were as follows: (1) patients underwent preoperative thyroid MRI; (2) nodules with postoperative pathological confirmation as either benign or malignant. Exclusion criteria were as follows: (1) diffuse bilateral lesions of different pathological types; (2) poor image quality with severe artefacts that cannot be used for diagnostic analysis; (3) patients who underwent FNA or partial thyroidectomy prior to MRI; (4) unclear postoperative pathological findings; (5) absence of nodules on MRI; (6) incomplete imaging data; and (7) lesions<5 mm. The surgical indications for thyroid nodules include those categorized as TI-RADS grade≥4, indicating a high suspicion of thyroid cancer, as well as symptomatic benign thyroid tumors resulting from compression, hyper-functioning thyroid adenomas, or concomitant hyperthyroidism.

MRI Acquisition

MRI examinations were performed on a GE Healthcare 1.5T MRI scanner (Excite HD; GE Healthcare, Milwaukee, WI, USA) with an 8-channel phased-array thyroid coil (Shanghai Chenguang Medical Technologies, Shanghai, China).

The MRI protocols included: (1) coronal fat-suppressed T2WI; (2) axial T1-weighted imaging (T1WI); (3) axial fat-suppressed T2W; (4) diffusion weighted imaging (DWI), b value = 0 and 800 s/mm2; (5) multiphasic contrast-enhanced T1WI (MCE-T1WI). Contrast agent (Magen Vixen; Bayer Pharmaceuticals, Berlin, Germany) was injected at a dose of 0.2 ml/kg and rate of 3 ml/s, followed by 15 ml saline flush. Six sequential MCE-T1WI scans were performed at 30 s, 60 s, 120 s, 180 s, 240 s, and 300 s after the contrast agent injection. Patients were instructed to hold their breath during the scan. The total scan duration was approximately 16 min. Table S1 lists the detailed MRI acquisition parameters.

MRI morphological analysis

Two radiologists, each with 5 and 9 years of experience in diagnostic thyroid MRI, independently evaluated the MRI images using the Advantage Workstation 4.5 workstation (GE Healthcare, Waukesha, WI, USA) and Picture Archiving and Communication System (PACS). Both radiologists were unaware of the pathological results of lesions and consensus was reached in cases where there was a disagreement.

The following parameters were utilized to assess the lesion: (1) size of the lesion, measured by the diameter of the largest dimension of the nodule, classified as 5-10 mm, 10-40 mm or ≥4 cm); (2) number of nodules, classified as unifocal or multifocal. The qualitative MRI morphological features are as follows: (1) non-enhanced features, including light pearl sign, black-white flower sign, restricted diffusion, cystic degeneration, flow-void signal, high signal intensity on T2WI, high signal intensity on T1WI, and low signal intensity on T2WI; (2) contrast-enhanced features, including enhancement patterns like no enhancement, gap-filling enhancement, pseudocapsule, hyperintense on T2WI with enhancement, wash-out pattern, fissure-filling enhancement, reversed halo sign in delay phase, hyperenhancement in early phase and change of lesion size in multiphasic enhancement. Detailed definitions and illustrations of the MRI morphological features are shown in Appendix S1.

TI-RADS

Two experienced US specialists with over 10 years of experience, who were unaware of the histopathological findings, performed the retrospective analysis of the US feature of thyroid nodules and reached a consensus. The US features evaluated encompassed composition, echogenicity, margins, shape, and calcification. All thyroid nodules were then classified according to the ACR-TIRADS, K-TIRADS, EU-TIRADS, Kwak-TIRADS, and C-TIRADS. In the cases of ACR-TIRADS, K-TIRADS, and EU-TIRADS, nodules categorized as ≥4 or 5 were considered to be malignant. For Kwak-TIRADS and C-TIRADS, nodules categorized as ≥4b and 4c, respectively, were regarded as malignant. The diagnostic performance of these five different TIRADS systems was subsequently calculated.

Nomogram construction and evaluation

Univariate and multivariate logistic stepwise regression analysis were employed to identify independent predictors in the training cohort and then a nomogram was developed. The optimal model was selected based on the Akaike Information Criteria.The goodness-of-fit of the model was assessed using the Hosmer-Lemeshow test, with a significance level of P≥0.05 indicating a good fit. To evaluate the performance of the nomogram, receiver operating characteristic (ROC) analysis, calibration curve analysis, and decision curve analysis (DCAs) were conducted.

Construction and performance of the MRI-based prediction model

The risk score derived from the regression coefficients (β coefficients) of the independent predictors by multiples of the minimum β coefficient (multiples are rounded to the nearest whole number) was used to develop a risk scoring system (RSS). To establish an optimal cut-off value for the risk score, the Yorden-index is maximized. The MRI-based prediction model was constructed using the aforementioned RSS and specific morphological features. The diagnostic performance of the model was evaluated by assessing sensitivity, specificity, accuracy, positive predictive value (PPV), negative predictive value (NPV) and area under the ROC curve (AUC), and compared it with five different US TI-RADS. The AUCs were compared using the Delong test. The Net reclassification index (NRI) was utilized to determine the enhancement in predictive accuracy of the model.

Statistical analysis

All statistical tests were carried out using SPSS statistical software 26.0, R software 4.2.0 (http://www.r-project.org, and Medcalc Software (version 20.100). Continuous variables were represented as mean±standard deviation (SD), while categorical variables were expressed as percentages. The t-test was employed to compare continuous variables, whereas the chi-square test or Fisher’s exact test was used to compared categorical variables. Concordance between two radiologists was assessed using the Kappa concordance test. The construction of the nomogram was accomplished using the R software package “rms”. Statistical analyses were conducted with two-tailed p values and 95% confidence intervals (CI). A significance level of P<0.05 was deemed statistically significant.

Results

Clinicopathological characteristics

The flowchart illustrating the inclusion process is shown in Fig. 1. A total of 825 lesions from 491 patients were finally included in the study, comprising 508 benign and 317 malignant lesions. We removed lesions with specific features that were not included in the modelling below. There were 572 lesions remaining (337 benign and 235 malignant) finally. These lesions were randomly divided into the training cohort (397 thyroid nodules, including 230 benign and 167 malignant nodules) and the validation cohort (175 thyroid nodules, 107 benign and 68 malignant nodules) at a 7:3 ratio. The clinicalcopatholgical characteristics of 572 thyroid nodules are shown in Table 1. The pathological types of all thyroid nodules are shown in Table S2.

Fig. 1
figure 1

Flowchart of the study inclusion process

Full size image
Table 1 Patient characteristics
Full size table

MRI morphological features

The statistical results of MRI-based specific morphological features are provided in Table S3. Significantly, nodules exhibiting no enhancement (n = 123) and the presence of the light pearl sign (n = 47) were exclusively observed in benign cases. Conversely, the black-and-white flower sign (n = 49) and gap-filling enhancement (n = 38) were predominantly detected in malignant nodules. The morphological features of thyroid nodules are described in Table 2. There was no statistically significant difference identified in the morphological features between the training and validation cohorts (P>0.05) excepting hypointense on T2WI. Kappa coefficients for different features ranged from 0.725 to 0.92.

Table 2 MRI qualitative features of thyroid nodules in training and validation cohorts
Full size table

Table 3 show the factors associated with malignant thyroid nodules. In the univariate and multivariate analysis, independent predictors of malignant thyroid nodules were age (OR=1.96, P<0.001), low signal intensity on T2WI (OR = 3.92, P = 0.003), diffusion restriction (OR = 39.54, P < 0.001), reversed halo sign in delay phase (OR = 19.26, P < 0.001), cystic degeneration (OR = 4.44, P = 0.031) and wash-out pattern (OR = 3.04, P = 0.009).

Table 3 Univariate and multivariate analysis to identify factors associated with malignant thyroid nodule and a scoring system developed from β coefficient in training cohort
Full size table

TI-RADS

A total of 729 nodules were included in the final analysis. Out of these, 452 nodules (62.0%) were determined to be benign, while 277 nodules (38.0%) were classified as malignant. Table S4 presents the distribution of TI-RADS classification. The malignancy rate exhibited a progressive increase with higher grade classifications, and the differences between the classifications were found to be statistically significant (P<0.001).

Development and validation of the nomogram

The results of the multivariate logistic regression analysis were used to construct the nomogram for predicting malignant thyroid nodules, as depicted in Fig. 2. The AUCs of the nomogram in the training cohort and validation cohort were 0.972 (95% CI: 0.958–0.985) and 0.968 (95% CI: 0.944–0.992), respectively (Fig. 3a and d). The calibration curve (Fig. 3b and e) and Hosmer-Lemeshow test statistic (P = 0.094 and 0.409) demonstrated excellent calibration. Furthermore, the DCA analysis (Fig. 3c and f) indicated a larger overall net benefit for the nomogram.

Fig. 2
figure 2

Nomogram for preoperative estimation of malignant thyroid nodule. When using the nomogram, find the position of each feature on the axis, and identify the corresponding point vertically. On the bottom scale, the points of all features were added up and converted into the probability of a malignant thyroid nodule

Full size image
Fig. 3
figure 3

Predictive performance of the nomogram in the training and validation cohorts. (a) and (d) ROC curves of the nomogram in the training and validation cohorts; (b) and (e) Calibration curves of the nomogram in the training and validation cohorts. Nomogram-predicted probability of malignant thyroid nodules is on the X-axis; observed malignant thyroid nodules are shown on the Y-axis; and the grey solid line represents a perfect prediction. (c) and (f) Decision curves of the nomogram for predicting the probability of malignant thyroid nodules in the training and validation cohorts. The horizontal and vertical axes represent the threshold probability and net benefit, respectively. The blue line is the expected net beneft of per patient based on the predictive nomogram

Full size image

MRI-based risk scoring system

The β coefficients corresponding for age, low signal intensity on T2WI, diffusion restriction, reversed halo sign in delay phase, cystic degeneration and wash-out pattern were 0.672, 1.367、3.677、2.958、1.490 and 1.112, respectively, and were subsequently assigned point values of 2, 4, 11, 9, 4, and 3 to developed the RSS. The optimal threshold for the RSS was 12 points. The AUCs for distinguishing between benign and malignant nodules were 0.914 (95%CI = 0.882–0.945) in the training cohort and 0.911 (95%CI = 0.880–0.962) in the validation cohort (Figure S1). The performance of the RSS is further elaborated in Table S5. Figure 4 depicts representative MRI images of both benign and malignant thyroid nodules.

Fig. 4
figure 4

A 35-year-old female with a 1.8 cm papillary thyroid carcinoma in the right lobe of the thyroid gland (a, b, c and d) and A 47-year-old female with a 2 cm nodular goiter in the right lobe of the thyroid gland (e, f, g and h). Axial T2-weighted imaging (a) shows a striped low signal area; Axial diffusion-weighted imaging (DWI) (b) and apparent diffusion coefficient (ADC) map (c) show restricted diffusion of the lesion (high signal intensity on DWI, low signal intensity on ADC); The delayed phase contrast-enhanced T1-weighted imaging (d) reveals a greater enhancement in the peripheral area compared to the central area of the lesion, with a blurred border between them, which corresponds to the reversed halo sign in delay phase. The characteristics of the lesion (a, b, c, and d) including age < 48, low signal intensity on T2WI, restricted diffusion, and the presence of the reversed halo sign in delay phase, are consistent with an MRI risk scoring system score of 26 and indicate a determination of malignancy. Axial T2-weighted imaging (e) show a striped low signal area; Axial DWI (f) and ADC map (g) show high signal intensity of lesion; The delayed phase contrast-enhanced T1-weighted imaging (h) shows heterogeneous enhancement of lesion. The characteristics of the lesion (e, f, g and h) including age < 48 and low signal intensity on T2WI, are consistent with an MRI risk scoring system score of 6 and indicate a determination of benignity

Full size image

MRI-based prediction model

The construction of the MRI-based prediction model is depicted in Fig. 5. The diagnostic performance of the MRI-based prediction model and TI-RADSs is presented in Table 4. The MRI-based prediction model exhibited a larger AUC value of 0.947 (Delong test: P < 0.05), surpassing the AUC values of the other TI-RADSs (ranging from 0.747 to 0.858) as illustrated in Fig. 6. The sensitivity, specificity, accuracy, PPV, and NPV of the MRI-based prediction model were 96.0%, 93.4%, 94.4%, and 89.9%, respectively. The MRI-based prediction model demonstrated relatively superior specificity and NPV compared to the other five TI-RADSs, as well as improved predictive performance (NRI > 0, P < 0.05).

Fig. 5
figure 5

The MRI morphological features-based model for predicting benign and malignant thyroid nodules

Full size image
Table 4 Comparison of diagnostic performance of MRI-based prediction model and five ultrasonography-based risk stratification systems
Full size table
Fig. 6
figure 6

The receiver operating characteristic (ROC) curves of the MRI-based prediction model and TI-RADSs at various cut-off values for distinguishing between benign and malignant thyroid nodules. Abbreviation: ACR-TIRADS, American College of Radiology Thyroid Imaging Reporting and Data System; K-TIRADS, Korean-TIRADS; EU-TIRADS, European-TIRADS; C-TIRADS, Chinese-TIRADS

Full size image

Table 5 presents a comprehensive analysis of the diagnostic accuracy of the MRI-based prediction model across different subgroups. The performance of the MRI-based prediction model was notably strong in both unifocal and multifocal nodules, with particularly high sensitivity (96.1%) and specificity (95.7%) observed in multifocal nodules. Furthermore, the sensitivity and specificity of the prediction model in the presence or absence of Hashimoto’s thyroiditis were 94.6% and 96.8%, and 94.7% and 92.6%, respectively. The MRI-based prediction model demonstrated a sensitivity of 96.5%, 97.4%, and 60% for nodules measuring 0.5 to 1 cm, 1 to 4 cm, and larger than 4 cm, respectively, with corresponding specificities of 87.0%, 95.3%, and 95.1%. Notably, among nodules larger than 4 cm, a total of 8 malignant nodules were missed diagnosis, comprising seven follicular thyroid carcinomas and one papillary thyroid carcinoma.

Table 5 Subgroup analysis of MRI-based prediction model
Full size table

Discussion

This study presented findings indicating that age, low signal intensity on T2WI, restricted diffusion, reversed halo sign in delay phase, cystic degeneration, and wash-out pattern were independent predictors for malignant thyroid nodules. The MRI-based nomogram was developed using these predictors showed satisfactory predictive ability and calibration in both training and validation cohorts. In addition, the MRI-based prediction model had superior specificity and NPV along with higher sensitivity compared to the other five TI-RADS, which improved the overall integrated prediction performance.

There have been a number of TI-RADSs that were developed as a result of previous studies using US to differentiate benign and malignant thyroid nodules. Kim DH et al. [11] found that ACR-TIRADS, K-TIRADS, and EU-TIRADS 4 and 5 category thyroid nodules had a good sensitivity greater than 90% in the meta-analysis. Their specificity, however, remained relatively low, with K-TIRADS having the highest specificity at 61%, followed by ACR-TIRADS (49%) and EU-TIRADS (48%). The suboptimal accuracy of thyroid cancer diagnosis has resulted in an increase in unnecessary FNA, which are both invasive and yield nondiagnostic outcomes in approximately 25% of cases [21]. This research study evaluated the performance of C-TIRADS, using a cut-off value of 4c category, and ACR-TIRADS, with a cut-off value of 5 category, in terms of specificity. C-TIRADS exhibited a specificity of 94.7%, while ACR-TIRADS demonstrated a specificity of 97.3%. However, both approaches sacrificed a significant amount of sensitivity, with values of only 51.3% and 64.6% respectively. In contrast, the MRI-based prediction model had the highest specificity of 93.4% while maintaining high sensitivity.

Risk stratification systems for thyroid nodules at ultrasound were frequently complicated and subject to low specificity and inadequate interobserver agreement. It is necessary to continuously improve these systems in order to minimize the unnecessary FNA. Wildman Tobriner et al. [22] showed that an artificial intelligence-optimized TI-RADS can moderately improve specificity and sensitivity compared to TI-RADS. In recent years, there has been a gradual increase in the research of MRI for diagnosing both benign and malignant thyroid nodules [23,24,25,26,27] and predicting the preoperative aggressiveness of papillary thyroid carcinoma [28,29,30,31,32,33,34], demonstrating promising application prospects. The ongoing advancements in MRI technology, as a functional medical imaging modality, warrant continuous exploration of its potential in diagnosing and evaluating thyroid nodules, ultimately leading to the development of its clinical application. Consequently, it becomes necessary to establish a prediction model for distinguishing between benign and malignant thyroid nodules based on MRI.

The predictive model developed in this study for distinguishing between benign and malignant thyroid nodules using MRI exhibited robust diagnostic efficacy. Integration of this model with the ultrasound TI-RADS grading system had the potential to improve diagnostic and treatment strategies for thyroid nodules. In clinical practice, patients categorized as TI-RADS category 4 or 5 may receive follow-up if the MRI-based predictive model suggests a benign nature, thereby avoiding unnecessary FNA. Conversely, if the model indicates malignancy, FNA and surgical intervention are recommended. However, further research was necessary to validate the effectiveness of the MRI-based prediction model in enhancing the ultrasound TI-RADS grading system. Subgroup analysis revealed a decreased sensitivity of the MRI-based prediction model for thyroid nodules larger than 4 cm, with missed diagnoses of 7 cases of thyroid follicular carcinoma and 1 case of thyroid papillary carcinoma. These findings indicated a limited diagnostic efficacy of the model for follicular thyroid neoplasms (FTNs) larger than 4 cm. Lin et al. [35] highlighted the ineffectiveness of various TIRADSs in managing FTNs, as evidenced by the high percentage (65.3 to 93.1%) of patients subjected to unnecessary FNA. This highlighted the importance of establishing a tailored stratification system for FTNs. Consequently, it was imperative to create MRI-based predictive models specifically designed for FTNs.

In this study, all nodules that exhibit non-enhancement and the light pearl sign were confirmed to be benign. It was observed that these two features were identified as specific characteristics indicated benignity. The presence of the black-white flower sign and gap-filling enhancement were found to be specific features associated with malignant nodules. The black-white flower sign was defined as petaloid and cerebrospinal fluid-like high signal on T2WI with an irregular apparent low signal in the centre of the lesion. From a pathological perspective, this sign corresponds to the stromal appearance, where it segregated follicular cells into irregular petal-like structures that aggregate in the central area of the lesion. The stroma contains few fluid content, resulting in low signal intensity on T2WI, whereas the presence of numerous follicular cells with higher fluid content contributes to the high signal on T2WI. Gap-filling enhancement was defined as a lesion located in the perithyroid region with a progressive enhancement pattern, with disruption of the contour line in the early phases and an intact contour line in the delayed phases. In the early phases of enhancement, interrupted thyroid contour was a sign of involvement of the thyroid envelope by the stromal component of the lesion [36], whereas in the delayed phase this stromal enhancement leads to filling of the interrupted envelope.

In the RSS, restricted diffusion and reversed halo sign in delay phase were the two independent predictors with the highest scores of 11 and 9 points. DWI has been widely employed in the field of oncology for the purposes of diagnosing, monitoring, and prognosticating malignancies [37]. The apparent diffusion coefficient (ADC) has been established as a valuable tool in the differentiation of benign and malignant thyroid nodules [38,39,40]. Restricted diffusion was defined by the presence of a solid component within the lesion, which manifested as high signal intensity on DWI and low signal intensity on ADC. The assessment of restricted diffusion provided a direct and pragmatic approach in contrast to the utilization of quantitative ADC values. The reversed halo sign in delay phase was defined by the wash-out pattern of the central portion of the lesion, continuous enhancement in the peripheral area relative to the central part during the delay phase, and a blurred border. This finding aligns with a previous study conducted by Wang et al. [41]. The interpretation implied that the central region of the tumor exhibits active proliferation of neoplastic cells, whereas the peripheral area primarily consisted of connective tissue with a profusion of tomur stroma, leading to sustained enhancement in the delay phase.

This study exhibited several limitations. Firstly, it adopted a retrospective design, thereby introducing an inherent selection bias, as it exclusively includes cases that underwent surgery intervention for pathological examination. Consequently, the exclusion of nodules selected for follow-up after FNA or those deemed too small for FNA may have influenced the outcomes. Secondly, the study did not encompass nodules smaller than 5 mm due to the limitation imposed by MRI imaging techniques. Thirdly, the qualitative parameters selected in this study possessed a certain degree of subjectivity. Although quantitative parameters were considered objective, their accuracy can be affected by various factors such as equipment, parameters, and measurement methods in clinical practice. In contrast, qualitative indicators provided convenience in clinical settings. Lastly, this study was limited to a single-center, and incorporating multi-center cases would enhance the validation of the MRI-based prediction model.

In conclusion, the utilization of MRI morphological features in the prediction model for benign and malignant thyroid nodules demonstrated a notable diagnostic efficacy, thereby establishing a reliable basis for clinical diagnosis and treatment decision-making. Moreover, the incorporation of MRI morphological features holds promise in enhancing the diagnostic accuracy of TI-RADS.

Data availability

The data sets generated and/or analyzed in the current study were not made public because patients’ personal information was included. Available from the corresponding author upon reasonable request.

Abbreviations

US:

Ultrasonography

ACR:

American College of Radiology

TI-RADS:

Thyroid Imaging Reporting and Data System

K-TIRADS:

Korean Thyroid Imaging Reporting and Data System

EU-TIRADS:

European Thyroid Imaging Reporting and Data System

C-TIRADS:

Chinese Thyroid Imaging Reporting and Data System

FNA:

Fine-needle aspiration

T1WI:

T1 weighted imaging

T2WI:

T2 weighted imaging

DWI:

Diffusion-weighted imaging

MCE-T1WI:

multiphasic contrast-enhanced T1WI

ROC:

Receiver operating characteristic

DCA:

Decision curve analysis

RSS:

Risk scoring system

PPV:

Positive predictive value

NPV:

Negative predictive value

NRI:

Net reclassification index

SD:

Standard deviation

CI:

Confidence intervals

ADC:

Apparent diffusion coefficient

References

  1. Alexander EK, Cibas ES. Diagnosis of thyroid nodules. Lancet Diabetes Endocrinol. 2022;10(7):533–9.

    Article  PubMed  Google Scholar 

  2. Durante C, Grani G, Lamartina L, Filetti S, Mandel SJ, Cooper DS. The diagnosis and management of thyroid nodules: a review. JAMA. 2018;319(9):914–24.

    Article  PubMed  Google Scholar 

  3. Gharib H, Papini E, Garber JR, Duick DS, Harrell RM, Hegedus L, Paschke R, Valcavi R, Vitti P. Nodules AAATFoT: American Association of Clinical Endocrinologists, American College of Endocrinology, and Associazione Medici Endocrinologi Medical Guidelines for clinical practice for the diagnosis and management of thyroid Nodules–2016 update. Endocr Pract. 2016;22(5):622–39.

    PubMed  Google Scholar 

  4. Megwalu UC, Moon PK. Thyroid Cancer Incidence and Mortality trends in the United States: 2000–2018. Thyroid. 2022;32(5):560–70.

    Article  CAS  PubMed  Google Scholar 

  5. Haugen BR, Alexander EK, Bible KC, Doherty GM, Mandel SJ, Nikiforov YE, Pacini F, Randolph GW, Sawka AM, Schlumberger M, et al. 2015 American Thyroid Association Management Guidelines for adult patients with thyroid nodules and differentiated thyroid Cancer: the American Thyroid Association Guidelines Task Force on thyroid nodules and differentiated thyroid Cancer. Thyroid. 2016;26(1):1–133.

    Article  PubMed  PubMed Central  Google Scholar 

  6. Tessler FN, Middleton WD, Grant EG, Hoang JK, Berland LL, Teefey SA, Cronan JJ, Beland MD, Desser TS, Frates MC, et al. ACR thyroid imaging, reporting and Data System (TI-RADS): White Paper of the ACR TI-RADS Committee. J Am Coll Radiol. 2017;14(5):587–95.

    Article  PubMed  Google Scholar 

  7. Shin JH, Baek JH, Chung J, Ha EJ, Kim JH, Lee YH, Lim HK, Moon WJ, Na DG, Park JS, et al. Ultrasonography diagnosis and imaging-based management of thyroid nodules: revised Korean society of thyroid Radiology Consensus Statement and recommendations. Korean J Radiol. 2016;17(3):370–95.

    Article  PubMed  PubMed Central  Google Scholar 

  8. Russ G, Bonnema SJ, Erdogan MF, Durante C, Ngu R, Leenhardt L. European Thyroid Association Guidelines for Ultrasound Malignancy Risk stratification of thyroid nodules in adults: the EU-TIRADS. Eur Thyroid J. 2017;6(5):225–37.

    Article  PubMed  PubMed Central  Google Scholar 

  9. Kwak JY, Han KH, Yoon JH, Moon HJ, Son EJ, Park SH, Jung HK, Choi JS, Kim BM, Kim EK. Thyroid imaging reporting and data system for US features of nodules: a step in establishing better stratification of cancer risk. Radiology. 2011;260(3):892–9.

    Article  PubMed  Google Scholar 

  10. Zhou J, Yin L, Wei X, Zhang S, Song Y, Luo B, Li J, Qian L, Cui L, Chen W, et al. 2020 Chinese guidelines for ultrasound malignancy risk stratification of thyroid nodules: the C-TIRADS. Endocrine. 2020;70(2):256–79.

    Article  CAS  PubMed  Google Scholar 

  11. Kim DH, Chung SR, Choi SH, Kim KW. Accuracy of thyroid imaging reporting and data system category 4 or 5 for diagnosing malignancy: a systematic review and meta-analysis. Eur Radiol. 2020;30(10):5611–24.

    Article  PubMed  Google Scholar 

  12. Miller KD, Nogueira L, Mariotto AB, Rowland JH, Yabroff KR, Alfano CM, Jemal A, Kramer JL, Siegel RL. Cancer treatment and survivorship statistics, 2019. CA Cancer J Clin. 2019;69(5):363–85.

    Article  PubMed  Google Scholar 

  13. Collins J, Rossi ED, Chandra A, Ali SZ. Terminology and nomenclature schemes for reporting thyroid cytopathology: an overview. Semin Diagn Pathol. 2015;32(4):258–63.

    Article  PubMed  Google Scholar 

  14. Park YM, Oh KH, Cho JG, Baek SK, Kwon SY, Jung KY, Woo JS. Analysis of efficacy and safety of core-needle biopsy versus fine-needle aspiration cytology in patients with cervical lymphadenopathy and salivary gland tumour. Int J Oral Maxillofac Surg. 2018;47(10):1229–35.

    Article  CAS  PubMed  Google Scholar 

  15. Yuan Y, Chen L, Ren S, Wang Z, Chen Y, Jin A, Li S, Fang X, Wang T, Bian Y, et al. Diagnostic performance in T staging for patients with esophagogastric junction cancer using high-resolution MRI: a comparison with conventional MRI at 3 tesla. Cancer Imaging. 2019;19(1):83.

    Article  PubMed  PubMed Central  Google Scholar 

  16. Chen L, Xu J, Bao J, Huang X, Hu X, Xia Y, Wang J. Diffusion-weighted MRI in differentiating malignant from benign thyroid nodules: a meta-analysis. BMJ Open. 2016;6(1):e008413.

    Article  PubMed  PubMed Central  Google Scholar 

  17. Jiang L, Chen J, Huang H, Wu J, Zhang J, Lan X, Liu D, Zhang J. Comparison of the Differential Diagnostic performance of Intravoxel Incoherent Motion Imaging and Diffusion Kurtosis Imaging in malignant and benign thyroid nodules. Front Oncol. 2022;12:895972.

    Article  CAS  PubMed  PubMed Central  Google Scholar 

  18. Sakat MS, Sade R, Kilic K, Gozeler MS, Pala O, Polat G, Kantarci M. The Use of Dynamic contrast-enhanced perfusion MRI in differentiating Benign and malignant thyroid nodules. Indian J Otolaryngol Head Neck Surg. 2019;71(Suppl 1):706–11.

    Article  PubMed  Google Scholar 

  19. Song M, Yue Y, Jin Y, Guo J, Zuo L, Peng H, Chan Q. Intravoxel incoherent motion and ADC measurements for differentiating benign from malignant thyroid nodules: utilizing the most repeatable region of interest delineation at 3.0 T. Cancer Imaging. 2020;20(1):9.

    Article  CAS  PubMed  PubMed Central  Google Scholar 

  20. Tan H, Chen J, Zhao YL, Liu JH, Zhang L, Liu CS, Huang D. Feasibility of Intravoxel Incoherent Motion for differentiating Benign and malignant thyroid nodules. Acad Radiol. 2019;26(2):147–53.

    Article  PubMed  Google Scholar 

  21. Wang J, He X, Ma L, Li M, Sun L, Jiang J, Zhou Q. Multimode ultrasonic technique is recommended for the differential diagnosis of thyroid cancer. PeerJ. 2020;8:e9112.

    Article  PubMed  PubMed Central  Google Scholar 

  22. Wildman-Tobriner B, Buda M, Hoang JK, Middleton WD, Thayer D, Short RG, Tessler FN, Mazurowski MA. Using Artificial Intelligence to revise ACR TI-RADS risk stratification of thyroid nodules: diagnostic accuracy and utility. Radiology. 2019;292(1):112–9.

    Article  PubMed  Google Scholar 

  23. Monisha V, Rache Gowda N, Anil Kumar S. The role of Diffusion-Weighted Magnetic Resonance Imaging in differentiating Benign from malignant thyroid nodules: a descriptive observational study. Cureus. 2022;14(10):e30493.

    PubMed  PubMed Central  Google Scholar 

  24. Sharafeldeen A, Elsharkawy M, Khaled R, Shaffie A, Khalifa F, Soliman A, Abdel Razek AAK, Hussein MM, Taman S, Naglah A, et al. Texture and shape analysis of diffusion-weighted imaging for thyroid nodules classification using machine learning. Med Phys. 2022;49(2):988–99.

    Article  PubMed  Google Scholar 

  25. Shi R, Yao Q, Wu L, Zhou Q, Lu Q, Gao R, Hu J, Kao L, Bains A, Yan Z, et al. T2* mapping at 3.0T MRI for differentiation of papillary thyroid carcinoma from benign thyroid nodules. J Magn Reson Imaging. 2016;43(4):956–61.

    Article  PubMed  Google Scholar 

  26. Song MH, Jin YF, Guo JS, Zuo L, Xie H, Shi K, Yue YL. Application of whole-lesion intravoxel incoherent motion analysis using iZOOM DWI to differentiate malignant from benign thyroid nodules. Acta Radiol. 2019;60(9):1127–34.

    Article  PubMed  Google Scholar 

  27. Wang Q, Guo Y, Zhang J, Ning H, Zhang X, Lu Y, Shi Q. Diagnostic value of high b-value (2000 s/mm2) DWI for thyroid micronodules. Med (Baltim). 2019;98(10):e14298.

    Article  Google Scholar 

  28. Dai Z, Wei R, Wang H, Hu W, Sun X, Zhu J, Li H, Ge Y, Song B. Multimodality MRI-based radiomics for aggressiveness prediction in papillary thyroid cancer. BMC Med Imaging. 2022;22(1):54.

    Article  PubMed  PubMed Central  Google Scholar 

  29. Hu W, Wang H, Wei R, Wang L, Dai Z, Duan S, Ge Y, Wu PY, Song B. MRI-based radiomics analysis to predict preoperative lymph node metastasis in papillary thyroid carcinoma. Gland Surg. 2020;9(5):1214–26.

    Article  PubMed  PubMed Central  Google Scholar 

  30. Paudyal R, Lu Y, Hatzoglou V, Moreira A, Stambuk HE, Oh JH, Cunanan KM, Aramburu Nunez D, Mazaheri Y, Gonen M, et al. Dynamic contrast-enhanced MRI model selection for predicting tumor aggressiveness in papillary thyroid cancers. NMR Biomed. 2020;33(1):e4166.

    Article  PubMed  Google Scholar 

  31. Tang Q, Liu X, Jiang Q, Zhu L, Zhang J, Wu PY, Jiang Y, Zhou J. Unenhanced magnetic resonance imaging of papillary thyroid carcinoma with emphasis on diffusion kurtosis imaging. Quant Imaging Med Surg. 2023;13(4):2697–707.

    Article  PubMed  Google Scholar 

  32. Wang H, Song B, Ye N, Ren J, Sun X, Dai Z, Zhang Y, Chen BT. Machine learning-based multiparametric MRI radiomics for predicting the aggressiveness of papillary thyroid carcinoma. Eur J Radiol. 2020;122:108755.

    Article  PubMed  Google Scholar 

  33. Zhang H, Hu S, Wang X, Liu W, He J, Sun Z, Ge Y, Dou W. Using diffusion-weighted MRI to Predict Central Lymph Node Metastasis in Papillary thyroid carcinoma: a feasibility study. Front Endocrinol (Lausanne). 2020;11:326.

    Article  CAS  PubMed  Google Scholar 

  34. Zheng T, Hu W, Wang H, Xie X, Tang L, Liu W, Wu PY, Xu J, Song B. MRI-Based texture analysis for Preoperative Prediction of BRAF V600E mutation in papillary thyroid carcinoma. J Multidiscip Healthc. 2023;16:1–10.

    Article  PubMed  PubMed Central  Google Scholar 

  35. Lin Y, Lai S, Wang P, Li J, Chen Z, Wang L, Guan H, Kuang J. Performance of current ultrasound-based malignancy risk stratification systems for thyroid nodules in patients with follicular neoplasms. Eur Radiol. 2022;32(6):3617–30.

    Article  CAS  PubMed  PubMed Central  Google Scholar 

  36. Han ZJ, Shu YY, Lai XF, Chen WH. Value of computed tomography in determining the nature of papillary thyroid microcarcinomas: evaluation of the computed tomographic characteristics. Clin Imaging. 2013;37(4):664–8.

    Article  PubMed  Google Scholar 

  37. Hundshammer C, Braeuer M, Muller CA, Hansen AE, Schillmaier M, Duwel S, Feuerecker B, Glaser SJ, Haase A, Weichert W, et al. Simultaneous characterization of tumor cellularity and the Warburg effect with PET, MRI and hyperpolarized (13)C-MRSI. Theranostics. 2018;8(17):4765–80.

    Article  CAS  PubMed  PubMed Central  Google Scholar 

  38. Zhou J, Zhang Y, Chang KT, Lee KE, Wang O, Li J, Lin Y, Pan Z, Chang P, Chow D, et al. Diagnosis of Benign and malignant breast lesions on DCE-MRI by using Radiomics and Deep Learning with consideration of Peritumor tissue. J Magn Reson Imaging. 2020;51(3):798–809.

    Article  PubMed  Google Scholar 

  39. Meyer HJ, Wienke A, Surov A. Discrimination between malignant and benign thyroid tumors by diffusion-weighted imaging - A systematic review and meta analysis. Magn Reson Imaging. 2021;84:41–57.

    Article  CAS  PubMed  Google Scholar 

  40. Shi RY, Yao QY, Zhou QY, Lu Q, Suo ST, Chen J, Zheng WJ, Dai YM, Wu LM, Xu JR. Preliminary study of diffusion kurtosis imaging in thyroid nodules and its histopathologic correlation. Eur Radiol. 2017;27(11):4710–20.

    Article  PubMed  Google Scholar 

  41. Wang H, Wei R, Liu W, Chen Y, Song B. Diagnostic efficacy of multiple MRI parameters in differentiating benign vs. malignant thyroid nodules. BMC Med Imaging. 2018;18(1):50.

    Article  PubMed  PubMed Central  Google Scholar 

Download references

Acknowledgements

We thank the Department of Radiology, Minhang Hospital, Fudan University, for providing the data.

Funding

This work was supported by the Nature Science Foundation of Shanghai (grant number: 19ZR1446200), Science and Technology Commission of Minhang District, Shanghai (grant number: 2020MHZ034) and Shanghai Municipal Health Commission (grant number: 202140325).

Author information

Author notes

  1. Tingting Zheng and Lanyun Wang contributed equally to this work and share the first authorship.

Authors and Affiliations

  1. Department of Radiology, Minhang Hospital, Fudan University, No 170, Xinsong Road, Minhang District, 201199, Shanghai, China

    Tingting Zheng, Lanyun Wang, Hao Wang & Bin Song

  2. Department of Ultrasound, Minhang Hospital, Fudan University, No 170, Xinsong Road, Minhang District, 201199, Shanghai, China

    Lang Tang & Qingyin Fu

  3. Department of Pathology, Minhang Hospital, Fudan University, No 170, Xinsong Road, Minhang District, 201199, Shanghai, China

    Xiaoli Xie

  4. GE Healthcare, MR Research China, Beijing, China

    Pu-Yeh Wu

Authors
  1. Tingting Zheng
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Lanyun Wang
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. Hao Wang
    View author publications

    You can also search for this author in PubMed Google Scholar

  4. Lang Tang
    View author publications

    You can also search for this author in PubMed Google Scholar

  5. Xiaoli Xie
    View author publications

    You can also search for this author in PubMed Google Scholar

  6. Qingyin Fu
    View author publications

    You can also search for this author in PubMed Google Scholar

  7. Pu-Yeh Wu
    View author publications

    You can also search for this author in PubMed Google Scholar

  8. Bin Song
    View author publications

    You can also search for this author in PubMed Google Scholar

Contributions

T.Z.: data collection and writing and editing of manuscript. L.W.: writing and editing of manuscript. H.W.: contribution of data and review of manuscript. L.T.: contribution to ultrasound data. X.X.: contribution to pathologic data. Q.F.: contribution to ultrasound data. P.W.: contribution to review and editing of manuscript. B.S.: data analysis and writing and review of manuscript.

Corresponding author

Correspondence to Bin Song.

Ethics declarations

Ethics approval and consent to participate

The institutional review board of Minhang hospital, Fudan University approved this study (2020-008-01 K), and informed consent was exempted due to the retrospective nature.

Consent for publication

Not applicable.

Competing interests

The authors declare no competing interests.

Additional information

Publisher’s Note

Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.

Electronic supplementary material

Below is the link to the electronic supplementary material.

Supplementary Material 1

Rights and permissions

Open Access This article is licensed under a Creative Commons Attribution 4.0 International License, which permits use, sharing, adaptation, distribution and reproduction in any medium or format, as long as you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons licence, and indicate if changes were made. The images or other third party material in this article are included in the article’s Creative Commons licence, unless indicated otherwise in a credit line to the material. If material is not included in the article’s Creative Commons licence and your intended use is not permitted by statutory regulation or exceeds the permitted use, you will need to obtain permission directly from the copyright holder. To view a copy of this licence, visit http://creativecommons.org/licenses/by/4.0/. The Creative Commons Public Domain Dedication waiver (http://creativecommons.org/publicdomain/zero/1.0/) applies to the data made available in this article, unless otherwise stated in a credit line to the data.

Reprints and permissions

About this article

Check for updates. Verify currency and authenticity via CrossMark

Cite this article

Zheng, T., Wang, L., Wang, H. et al. Prediction model based on MRI morphological features for distinguishing benign and malignant thyroid nodules. BMC Cancer 24, 256 (2024). https://0-doi-org.brum.beds.ac.uk/10.1186/s12885-024-11995-3

Download citation

  • Received:

  • Accepted:

  • Published:

  • DOI: https://0-doi-org.brum.beds.ac.uk/10.1186/s12885-024-11995-3

Keywords

BMC Cancer

ISSN: 1471-2407

Contact us