Detection of SS18-SSX fusion transcripts in formalin-fixed paraffin-embedded neoplasms: analysis of conventional RT-PCR, qRT-PCR and dual color FISH as diagnostic tools for synovial sarcoma

Abstract

Synovial Sarcoma consistently harbors t(X;18) resulting in SS18-SSX1, SS18-SSX2 and rarely SS18-SSX4 fusion transcripts. Of 328 cases included in our study, synovial sarcoma was either the primary diagnosis or was very high in the differential diagnosis in 134 cases: of these, amplifiable cDNA was obtained from 131. SS18-SSX fusion products were found in 126 (96%) cases (74 SS18-SSX1, 52 SS18-SSX2), using quantitative and 120 by conventional reverse transcriptase-polymerase chain reaction (RT-PCR). One hundred and one cases in a tissue microarray, analyzed by fluorescence in situ hybridization (FISH), revealed that 87 (86%) showed SS18 rearrangement: four RT-PCR positive cases, reported as negative for FISH, showed loss of one spectrum green signal, and 15 cases had multiple copies of the SS18 gene: both findings are potentially problematic when interpreting results. One of three cases, not analyzed by RT-PCR reaction owing to poor quality RNA, was positive by FISH. SS18-SSX1 was present in 56 monophasic and 18 biphasic synovial sarcoma: SS18-SSX2 was detected in 41 monophasic and 11 biphasic synovial sarcoma. Poorly differentiated areas were identified in 44 cases (31%). There was no statistically significant association between biphasic, monophasic and fusion type. Five cases were negative for SS18 rearrangement by all methods, three of which were pleural-sited neoplasms. Following clinical input, a diagnosis of mesothelioma was favored in one case, a sarcoma, not otherwise specified in another and a solitary fibrous tumor in the third case. The possibility of a malignant peripheral nerve sheath tumor could not be excluded in the other two cases. We concluded that the employment of a combination of molecular approaches is a powerful aid to diagnosing synovial sarcoma giving at least 96% sensitivity and 100% specificity but results must be interpreted in the light of other modalities such as clinical findings and immunohistochemical data.