http://orcid.org/0000-0002-6212-1495
Figures
Abstract
Purpose
To evaluate whether if ultrasonography (US)-based radiomics enables prediction of the presence of BRAFV600E mutations among patients diagnosed as papillary thyroid carcninoma (PTC).
Methods
From December 2015 to May 2017, 527 patients who had been treated surgically for PTC were included (training: 387, validation: 140). All patients had BRAFV600E mutation analysis performed on surgical specimen. Feature extraction was performed using preoperative US images of the 527 patients (mean size of PTC: 16.4mm±7.9, range, 10–85 mm). A Radiomics Score was generated by using the least absolute shrinkage and selection operator (LASSO) regression model. Univariable/multivariable logistic regression analysis was performed to evaluate the factors including Radiomics Score in predicting BRAFV600E mutation. Subgroup analysis including conventional PTC <20-mm (n = 389) was performed (training: 280, validation: 109).
Results
Of the 527 patients diagnosed with PTC, 428 (81.2%) were positive and 99 (18.8%) were negative for BRAFV600E mutation. In both total 527 cancers and 389 conventional PTC<20-mm, Radiomics Score was the single factor showing significant association to the presence of BRAFV600E mutation on multivariable analysis (all P<0.05). C-statistics for the validation set in the total cancers and the conventional PTCs<20-mm were lower than that of the training set: 0.629 (95% CI: 0.516–0.742) to 0.718 (95% CI: 0.650–0.786), and 0.567 (95% CI: 0.434–0.699) to 0.729 (95% CI: 0.632–0.826), respectively.
Citation: Yoon JH, Han K, Lee E, Lee J, Kim E-K, Moon HJ, et al. (2020) Radiomics in predicting mutation status for thyroid cancer: A preliminary study using radiomics features for predicting BRAFV600E mutations in papillary thyroid carcinoma. PLoS ONE 15(2): e0228968. https://doi.org/10.1371/journal.pone.0228968
Editor: Jeeun Kang, Johns Hopkins University, UNITED STATES
Received: August 2, 2019; Accepted: January 27, 2020; Published: February 13, 2020
Copyright: © 2020 Yoon et al. This is an open access article distributed under the terms of the Creative Commons Attribution License, which permits unrestricted use, distribution, and reproduction in any medium, provided the original author and source are credited.
Data Availability: Data cannot be shared publicly because of patient confidentiality issues. The institutional review board of Severance Hospital, Yonsei University has given approval for this study, recommending patient confidentiality when using image data. contact: hpc@yuhs.ac.
Funding: This work was supported by the National Research Foundation of Korea(NRF) grant funded by the Korea government(MSIT) (2019R1A2C1002375). This study was also supported by a CMB-Yuhan research grant of Yonsei University College of Medicine (6-2017-0170). The funders had no role in study design, data collection and analysis, decision to publish, or preparation of the manuscript.
Competing interests: The authors have declared that no competing interests exist.
Introduction
During the past decade, the incidence of thyroid cancer has rapidly increased worldwide, regardless of the demographic groups [1–3]. The majority of thyroid cancers that are being newly detected are papillary thyroid cancers (PTC) [4,5], a subtype consisting of more than 80% of all differentiated thyroid carcinomas [5,6]. In general, PTC is known to have excellent patient outcomes, 5-year survival rates approaching 98–99% [7,8], but approximately 10–15% of patients had aggressive tumor behavior, local recurrence/distant metastasis after treatment or mortality [9–12]. At present, even with the well-known poor prognostic factors such as age over 45 years, male gender, radioactive iodine resistance [9], it is difficult to descriminate to predict which patient has more aggressive forms of PTCs, and effort has been made using various biomarkers in predicting PTC patients with poor outcome.
With the advancement in molecular genetics, various genetic alterations have been revealed and used as an adjunctive diagnostic method or for predicting patient prognosis [8,13,14]. BRAFV600E mutation, the most frequent oncogene in PTC, has been reported to be associated with aggressive clinical features such as large tumor size, extrathyroidal extension and presence of lymph node metastasis [8,14–16], leading to recurrence or mortality. But even with the ability of either mutation in detecting aggressive cancer types, genetic analysis requires specimen tissue for analysis, mostly obtained from invasive surgical procedures. Aside from the information obtained from conventional imaging, radiomics, using data extracted from medical images converted into high-dimensional, mineable, and quantitative imaging features has been applied to revealing tumor physiology. Other studies have linked imaging features to molecular properties of tumors among various organs [17–20], but to the best of our knowledge, no studies have applied radiomics in predicting molecular status of thyroid cancer that can be used in predicting tumor aggressiveness. Based on this, we evaluated whether if ultrasonography (US)-based radiomics enables prediction of the presence of BRAFV600E mutations among patients diagnosed as PTC.
Materials & methods
This retrospective study has been approved by the institutional review board (IRB) of Severance Hospital, Yonsei University (approval number: 4-2018-0172), with a waiver for patient consent due to the retrospective study design. Signed informed consent was obtained from all patients prior to biopsy or surgical procedures. Images used for data extraction were fully anonymized before data processing according to the instructions of our IRB.
Patients
We included 527 patients who had been treated surgically with cytologically-proven or suspicious thyroid cancer between December 2015 to May 2017 at Severance Hospital, Seoul, Korea. All patients had BRAFV600E mutation analysis performed on surgical specimen. The 387 consecutive patients who had surgery from December 2015 to December 2016 were used as the training cohort: 300 women, 87 men, mean age, 42.1 years±14.0 (range, 15–82 years). The 140 consecutive patients who had surgery from January 2017 to May 2017 were used as the validation cohort: 105 women, 35 men, mean age, 41.3 years±13.4 (range, 15–74 years). Mean age of the 527 patients were 41.9 years±13.8 (range, 15–82 years). Mean size of the thyroid masses was 16.4 mm±7.9 (range, 10–85 mm).
As the frequency of BRAFV600E mutation has been reported to be associated with tumor size and conventional PTC [21], subgroup analysis was performed including thyroid cancers confirmed as conventional PTCs measuring <20-mm (n = 389). Mean age of the 389 patients was 42.9 years±13.1 (range, 15–80 years). Mean size of the conventional PTCs was 14.9 mm±4.6 (range, 10–19 mm). Clinicopathologic data regarding tumor size, lymph node metastasis were obtained from review of medical records. Imaging features of the thyroid masses used for analysis were obtained from an institutional database.
US image selection and feature extraction
One radiologist (J.Y.K.) reviewed the preoperative US examinations of the 527 patients on the picture archiving and communication system (PACS) and selected representative transverse or longitudinal images of the tumor. The selected representative images were converted into JPEG files for manual segmentation. One radiologist (J.H.Y.) who had 9 years of experience in thyroid imaging manually set a region-of-interest (ROI) along the boundary of the selected tumor using Paint software of Windows (Fig 1). Since ROI marking with colored brush using Paint software alters original intensities in image, the manual ROI segmentation is conducted over the duplicate images of collected JPEG files. Before starting ROI extracting procedure, all images were normalized for fair comparison. First the location information of ROI marking (coordinate information of red curves in Fig 1) was sought and then applied to the original JPEG image to extract ROI only. This procedure ensures that the original intensity of the image was not affected by the ROI extraction process. Once ROI was extracted, a total of 730 feature information were gathered. The 730 features include the first order statistics (energy, entropy, kurtosis, skewness and so on), the second order statistics (the gray level co-occurrence matrix (GLCM) and gray level run-length matrix (GLRLM) were established and the corresponding features were extracted), and features from four discrete one-level wavelet decompositions. The detailed calculation for these features can be found in [22]. To obtain the feature quantities, the house code in MATLAB 2018b was used. Here, 256 bins using a bin with of 1 were utilized for intensity histogram and 4 angles of 0, 45, 90, and 135 degrees were utilized for GLCM and GLRLM anaylsis.
A diagonal region-of-interest (ROI) was drawn along the tumor border (red line) for feature extraction.
BRAFV600E mutational analysis
Direct DNA sequencing was used for the surgical specimen in mutation analysis. Exon 15, which contains the BRAFV600E mutation, was amplified by PCR with the foward primer AGGAAAGCATCTCACCTCATC and the reverse primer GATCACACCTGCCTTAAATTGC. The PCR parameters were as follows: 94°C for 5 minutes, 35 cycles at 94°C for 0.5 minutes, 60°C for 0.5 minutes, and 72°C for 10 minutes. The amplified products were purified with a QIAGEN PCR purification kit and sequenced using the foward primer described previously with Big Dye Terminator (ABI Systems, Applied Biosystems, Foster City, CA), and an ABI PRISM 3100 Avant Genetic Analyzer (Perkin-Elmer).
Data & statistical analysis
For feature selection, LASSO logistic regression model was applied to the 730 texture features extracted from the US images, and a Radiomics Score was calculated for each patient using a linear combination of selected features weighted by the respective coefficients.
Univariable and multivariable logistic regression analysis was performed to calculate the odds ratio with 95% confidence intervals (CI), including patient’s age, gender, tumor size, and radiomics score. For internal validation, bootstrap with 1,000 resampling was used. Calibration curves were plotted to assess the calibration of the model built using the factors included, using the Hosmer Lemeshow test. Harrell’s C-index was measured to evaluate the model’s discrimination ability.
R software (version 3.4.2, http://www.R-project.org) with the R package ‘glmnet’ was used for statistical analysis.
Results
Among the 527 patients diagnosed with PTC in this study, 428 (81.2%) were positive and 99 (18.8%) were negative for BRAFV600E mutation. Cancer subtype of the 527 masses were proven as follows: 493 (93.5%) as conventional PTC, 23 (4.4%) as follicular variant PTC, 7 (1.3%) as diffuse sclerosing variant PTC, 4 (0.8%) as oncocytic variant of PTC. Demographics according to the presence of BRAFV600E mutations are summarized in Table 1. Mean tumor size was significantly smaller in nodules positive for BRAFV600E mutation, 16.0±7.6 mm to 18.0±9.1 mm (P = 0.003). Similar tendency was observed in the training cohort (15.8±7.4 mm to 19.6±10.0 mm, P = 0.004), but not in the validation cohort or the conventional PTC <20-mm subgroup.
Feature selection and calcuation of radiomics score
Eight potential features were selected among 730 texture features in the training cohort with nonzero coefficients in the LASSO logistic regression model (Fig 2A and 2B). These 8 texture features were presented in the calculation formula below used to calculate the Radiomics Score,
(A) Tuning parameter (lambda, λ) selection in the LASSO model used 10-fold cross validation for 527 thyroid cancers. The mean deviance (goodness-of-fit statistics, red dots) was plotted versus log(λ), error bars displaying the range of standard error. Dotted vertical lines were drawn at the point of minimum deviance (λ value = 0.03229), and at the point where maximum λ was obtained among errors smaller than the standard error of minimum deviance (λ value = 0.08984). (B) LASSO coefficient profiles of the 730 texture features. A coefficient profile was plotted versus log(λ). The gray vertical line was drawn at the value selected using 10-fold cross validation, where the optimal λ resulted in 8 nonzero coefficients. (C) Tuning parameter (lambda, λ) selection in the LASSO model used 10-fold cross validation for 389 conventional PTCs <20-mm. The mean deviance (goodness-of-fit statistics, red dots) was plotted versus log(λ), error bars displaying the range of standard error. Dotted vertical lines were drawn at the point of minimum deviance (λ value = 0.0329208), and at the point where maximum λ was obtained among errors smaller than the standard error of minimum deviance (λ value = 0.072595). (D) LASSO coefficient profiles plotted versus log(λ), gray vertical line was drawn at the value selected using 10-fold cross validation, where the optimal λ resulted in 4 nonzero coefficients.
For the conventional PTCs measuring <20-mm, 4 potential features were selected among the 730 texture features in the training cohort (Fig 2C and 2D). These 4 texture features were presented in the calculation formula below used to calculate the Radiomics Score (cPTC<20-mm),
Development, performance, and validation of prediction models
Table 2 summarizes the results of univariable and multivariable logistic regression analysis for predicting the presence of BRAFV600E mutations. In the training cohort of the total thyroid cancers, tumor size and Radiomics Score were factors with statistical significance on univariable analysis. Among the training cohort including conventional PTCs measuring <20-mm, Radiomics Score was the single factor showing statistical significance. In both total cancers and the conventional PTC<20-mm, Radiomics Score was the single factor showing significant association to the presence of BRAFV600E mutation on multivariable analysis (all P<0.05).
The calibration curve of the prediction model for the presence of BRAFV600E mutation demonstrated good agreement between prediction and observation in the training cohort among the thyroid cancers. The Hosmer-Lemeshow test yielded statistics of P = 0.502, suggesting good calibration (Fig 3A). C-statistics for the training set was 0.718 (95% CI: 0.650–0.786), and 0.629 (95% CI: 0.516–0.742) for the validation set (Table 3). The calibration curve of the prediction model for the presence of BRAFV600E mutation among conventional PTCs <20-mm demonstrated good calibration, with the Hosmer-Lemeshow test yielding statistics of P = 0.257 (Fig 3B). C-statistics for training set among the conventional PTCs<20-mm was 0.729 (95% CI: 0.632–0.826), and 0.567 (95% CI: 0.434–0.699) for the validation set.
For each plot, the y-axis represents the actual probability of BRAFV600E mutation, and the x-axis represents the predicted risk for BRAFV600E mutation. (A) Calibration plot for the total thyroid cancers and (B) conventional PTCs measuring <20-mm included in this study.
Discussion
One major challenge for thyroid cancer is how to distinguish patients who need aggressive treatment to survive to those who do not. There are no consistent predictors that reliably sorts out aggressive PTCs, and in addition to the lack of prospective data regarding appropriate treatment for PTCs due to its generally excellent survival [9], issues regarding overtreatment for low-risk patients who will not experience PTC-related mortality have surfaced and debated over the recent years. This reflects the need for a more effective and accurate biomarker in predicting aggressive PTCs, including molecular analysis such as BRAFV600E mutations. Mutation analysis requires invasive procedures such as biopsy or surgical resection to retrive specimen to be analyzed. Among the non-invasive imaging biomarkers, radiomics is an emerging method that has the potential to predict molecular characteristics of tumors, using quantitative imaging features extracted using data-characterization algorithms. The most widely used imaging modality in radiomics has been computed tomography (CT) or magnetic resonance imaging (MRI), however, US is the most sensitive and accurate imaging modality for the thyroid which we used in this study.
For feature selection in obtaining a Radiomics Score, the LASSO logistic regression model was used, which enables selecting features based on their strength of association on univariable analysis, and combining the selected features into a radiomics signature [23]. The Radiomics Score obtained was the single factor showing significant association in predicting the presence of BRAFV600E mutation in both univariable and multivariable analysis in the training cohorts (Table 3), showing good discrimination for thyroid cancers with BRAFV600E mutation in the training set (c-statistics 0.718 (95% CI: 0.650–0.786)), but with lower c-statistics for validation set (0.629 (95% CI: 0.516–0.742). Our results show that US-derived radiomics may have potential as a non-invasive biomarker, but currently does not enable accurate prediction of the presence of BRAFV600E mutation in PTCs. There have been other studies proving the potential of US-derived radiomics in predicting disease-free survival or in predicting lymph node metastasis in patients diagnosed with PTC [24,25], but to the best of our knowledge, there are currently no studies using US radiomics features in predicting the presence of BRAFV600E mutations in patients diagnosed with thyroid cancer. Further studies including larger number of cases are anticipated in the future to validate our results.
Among the clinical variables, higher rates of BRAFV600E mutation was seen in thyroid cancers of smaller size, which showed significant association on univariable analysis. As the tumor size and subtype of thyroid cancer has been reported to have association to the presence of BRAFV600E mutation [21], we performed a subgroup analysis using a separate Radiomics Score calculated among the 730 texture features from a subset of 389 thyroid cancers confirmed as conventional PTC<20-mm. When using the Radiomics Score (cPTC<20-mm), similar results were obtained with the total 527 PTCs; Radiomics Score (cPTC<20-mm) was the single factor showing significance on both univariable/multivariable analysis (all P<0.001), with c-statistics of 0.729 (95% CI: 0.632–0.826) for the training set, lower values for the validation set, 0.567 (95% CI: 0.434–0.699). This supports that US-radiomics has limited value in predicting BRAFV600E mutation in PTC patients, regardless of size.
There are several limitations to this study. First, as the mutation analysis was performed in a selected group of PTC patients, results of our study does not represent mutation features of the general thyroid cancer population. Second, 81.2% of the PTCs in this study had BRAFV600E mutation analysis, which may have affected our results. PTCs among our population has been known for its high prevalence for BRAFV600E mutation [26], and results may have differed when conducted on different populations. Last, US images were used for feature extraction in obtaining a Radiomics Score that may be used in prediction of the presence of BRAFV600E mutation. Inherent observer variability of US compared to computed tomography (CT) or magnetic resonance imaging (MRI) may have affected our results, but since US is currently the generally applied imaging modality for detecting and differentiating thyroid nodules, feature extraction from US images may be more appropriate in extracting radiomics data among thyroid imaging. Also, ROIs for feature extraction was obtained from one radiologist, and observer variability among different radiologists were not considered in data analysis.
In conclusion, our results show that radiomics features extracted from US has limited value as a non-invasive biomarker for predicting the presence of BRAFV600E mutation status of PTC regardless of size.
References
- 1. Chen AY, Jemal A, Ward EM. Increasing incidence of differentiated thyroid cancer in the United States, 1988–2005. Cancer. 2009;115: 3801–3807. pmid:19598221
- 2.
George JR, Henderson YC, Williams MD, Roberts DB, Hei H, Lai SY, et al. Association of TERT Promoter Mutation, But Not BRAF Mutation, With Increased Mortality in PTC.
- 3. Magreni A, Bann DV, Schubart JR, Goldenberg D. The effects of race and ethnicity on thyroid cancer incidence. JAMA Otolaryngol Head Neck Surg. 2015;141: 319–323. pmid:25654447
- 4. Davies L, Welch HG. Increasing incidence of thyroid cancer in the United States, 1973–2002. JAMA. 2006;295: 2164–2167. pmid:16684987
- 5. Enewold L, Zhu K, Ron E, Marrogi AJ, Stojadinovic A, Peoples GE, et al. Rising thyroid cancer incidence in the United States by demographic and tumor characteristics, 1980–2005. Cancer Epidemiol Biomarkers Prev. 2009;18: 784–791. pmid:19240234
- 6. Yin DT, Yu K, Lu RQ, Li X, Xu J, Lei M, et al. Clinicopathological significance of TERT promoter mutation in papillary thyroid carcinomas: a systematic review and meta-analysis. Clin Endocrinol (Oxf). 2016;85: 299–305. pmid:26732020
- 7. Noone AM, Cronin KA, Altekruse SF, Howlader N, Lewis DR, Petkov VI, et al. Cancer Incidence and Survival Trends by Subtype Using Data from the Surveillance Epidemiology and End Results Program, 1992–2013. Cancer Epidemiol Biomarkers Prev. 2017;26: 632–641. pmid:27956436
- 8. Xing M, Alzahrani AS, Carson KA, Viola D, Elisei R, Bendlova B, et al. Association between BRAF V600E mutation and mortality in patients with papillary thyroid cancer. JAMA. 2013;309: 1493–1501. pmid:23571588
- 9. Brown RL, de Souza JA, Cohen EE. Thyroid cancer: burden of illness and management of disease. J Cancer. 2011;2: 193–199 pmid:21509149
- 10. Mazzaferri EL, Jhiang SM. Long-term impact of initial surgical and medical therapy on papillary and follicular thyroid cancer. Am J Med. 1994;97: 418–428 pmid:7977430
- 11. Xing MZ, Liu RY, Liu XL, Murugan AK, Zhu GW, Zeiger MA, et al. BRAF V600E and TERT Promoter Mutations Cooperatively Identify the Most Aggressive Papillary Thyroid Cancer With Highest Recurrence. Journal of Clinical Oncology. 2014;32: 2718–+. pmid:25024077
- 12. Loh KC, Greenspan FS, Gee L, Miller TR, Yeo PP. Pathological tumor-node-metastasis (pTNM) staging for papillary and follicular thyroid carcinomas: a retrospective analysis of 700 patients. J Clin Endocrinol Metab. 1997;82: 3553–3562. pmid:9360506
- 13. Penna GC, Vaisman F, Vaisman M, Sobrinho-Simoes M, Soares P. Molecular Markers Involved in Tumorigenesis of Thyroid Carcinoma: Focus on Aggressive Histotypes. Cytogenet Genome Res. 2016;150: 194–207. pmid:28231576
- 14.
Melo M, Gaspar da Rocha A, Batista R, Vinagre J, Martins MJ, Costa G, et al. TERT, BRAF, and NRAS in Primary Thyroid Cancer and Metastatic Disease.
- 15. Kim TH, Park YJ, Lim JA, Ahn HY, Lee EK, Lee YJ, et al. The association of the BRAF(V600E) mutation with prognostic factors and poor clinical outcome in papillary thyroid cancer: A Meta-Analysis. Cancer. 2011. pmid:21882184
- 16. Liu R, Bishop J, Zhu G, Zhang T, Ladenson PW, Xing M. Mortality Risk Stratification by Combining BRAF V600E and TERT Promoter Mutations in Papillary Thyroid Cancer: Genetic Duet of BRAF and TERT Promoter Mutations in Thyroid Cancer Mortality. LID - pmid:27581851
- 17.
Gevaert O, Echegaray S, Khuong A, Hoang CD, Shrager JB, Jensen KC, et al. Predictive radiogenomics modeling of EGFR mutation status in lung cancer.
- 18.
Braman NM, Etesami M, Prasanna P, Dubchuk C, Gilmore H, Tiwari P, et al. Intratumoral and peritumoral radiomics for the pretreatment prediction of pathological complete response to neoadjuvant chemotherapy based on breast DCE-MRI.
- 19. Zhang B, Tian J, Dong D, Gu D, Dong Y, Zhang L, et al. Radiomics Features of Multiparametric MRI as Novel Prognostic Factors in Advanced Nasopharyngeal Carcinoma. LID - pmid:28280088
- 20. Yang L, Dong D, Fang M, Zhu Y, Zang Y, Liu Z, et al. Can CT-based radiomics signature predict KRAS/NRAS/BRAF mutations in colorectal cancer? Eur Radiol. 2018;28: 2058–2067. pmid:29335867
- 21. Li C, Lee KC, Schneider EB, Zeiger MA. BRAF V600E mutation and its association with clinicopathological features of papillary thyroid cancer: a meta-analysis. J Clin Endocrinol Metab. 2012;97: 4559–4570. pmid:23055546
- 22. Aerts HJ, Velazquez ER, Leijenaar RT, Parmar C, Grossmann P, Carvalho S, et al. Decoding tumour phenotype by noninvasive imaging using a quantitative radiomics approach. Nat Commun. 2014;5: 4006. pmid:24892406
- 23.
Harell F. Regression Modeling Strategies With Applicators to Linear Models, Logistic regression, and Survival Analysis. New York, NY: Springer; 2015.
- 24. Park VY, Han K, Lee E, Kim EK, Moon HJ, Yoon JH, et al. Association Between Radiomics Signature and Disease-Free Survival in Conventional Papillary Thyroid Carcinoma. Sci Rep. 2019;9: 4501. pmid:30872763
- 25. Liu T, Zhou S, Yu J, Guo Y, Wang Y, Zhou J, et al. Prediction of Lymph Node Metastasis in Patients With Papillary Thyroid Carcinoma: A Radiomics Method Based on Preoperative Ultrasound Images. Technol Cancer Res Treat. 2019;18: 1533033819831713. pmid:30890092
- 26. Kim KH, Kang DW, Kim SH, Seong IO, Kang DY. Mutations of the BRAF gene in papillary thyroid carcinoma in a Korean population. Yonsei Med J. 2004;45: 818–821. pmid:15515191