Discrimination of benign and malignant thyroid nodules by molecular profiling

Abstract

Background: The evaluation of thyroid nodules by fine-needle aspiration has been the standard for almost 30 years, despite significant shortcomings in sensitivity and specificity. Recent data from our laboratory have suggested that molecular profiling permits the discrimination of specific types of thyroid nodules. These studies were undertaken to determine whether molecular profiling can discriminate between benign and malignant thyroid nodules with the necessary sensitivity and specificity required of a screening test.

Methods: Molecular profiles of 11 papillary thyroid carcinomas, 13 follicular variant of papillary thyroid carcinomas, 9 follicular thyroid carcinomas, and 26 benign tumors (follicular adenomas and hyperplastic nodules) were analyzed by oligonucleotide microarray analysis. A gene list was created based on 45 samples. Seventeen samples were then added to the analysis as unknowns. A hierarchical clustering analysis was performed on all 62 samples to examine the groups for potential differences and the ability of the gene list to distinguish tumor types.

Results: Cluster analysis of all 62 samples produced 2 distinct groups, 1 containing the carcinomas and 1 containing the benign lesions. The sensitivity for a diagnosis of cancer was 91.7% with a specificity of 96.2% (3 follicular variant of papillary thyroid carcinomas clustered with the benign lesions). The cancer gene profiles contained both known cancer-associated genes (MET, galectin-3) and previously unidentified genes.

Conclusions: Molecular profiling readily distinguishes between benign and malignant thyroid tumors with excellent sensitivity and specificity. Elucidated genes may provide insight into the molecular pathogenesis of thyroid cancer. Gene profiling may significantly enhance the evaluation of thyroid nodules in the future.

FIGURE 1. Test set cluster analysis. Dendrogram cluster analysis of 45 thyroid tumor samples (14 FA, 7 HYP, 9 FC, 7 PTC, and 8 FVPTC) based on the pattern of expression of 627 differentially expressed genes. Note 2 distinct cluster groups, distinguishing benign from malignant tumors. Red denotes relative overexpression of a gene; blue relative underexpression of a gene. The sample names are located at the right of the diagram.

FIGURE 2. Cluster analysis of test set and unknown samples. Dendrogram cluster analysis of the 45 test set samples with 14 unknown samples (HYP 008–010, FA 016–017, PTC 008–011, FVPTC 009–013) based on the pattern of expression of 627 differentially expressed genes. Red indicates relative overexpression, blue relative underexpression. Sample names listed at the right of the diagram.

FIGURE 3. Cluster analysis of all samples (including MTC). Dendrogram cluster analysis of all 62 thyroid tumor samples, including the 3 medullary thyroid carcinomas, based on the pattern of expression of 627 differentially expressed genes. All 3 MTC clustered tightly together within the malignant group cluster. Red denotes relative overexpression of a gene; blue relative underexpression of a gene. The sample names are located at the right of the diagram.

FIGURE 4. High-risk versus low-risk cluster analysis. Dendrogram cluster analysis of 35 thyroid carcinoma samples (14 high risk and 21 low risk) based on the pattern of expression of 339 differentially expressed genes. High risk tumors are highlighted in yellow.