High frequency of brain metastases after adjuvant therapy for high-risk melanoma

Abstract

The incidence of CNS progression in patients with high-risk regional melanoma (stages IIIAN2a-IIIC) is not well characterized. Data from the S0008 trial provided an opportunity to examine the role of CNS progression in treatment failure and survival. All patients were surgically staged. Following wide excision and full regional lymphadenectomy, patients were randomized to receive adjuvant biochemotherapy (BCT) or high-dose interferon alfa-2B (HDI). CNS progression was retrospectively identified from data forms. Survival was measured from date of CNS progression. A total of 402 eligible patients were included in the analysis (BCT: 199, HDI: 203). Median follow-up (if alive) was over 7 years (range: 1 month to 11 years). The site of initial progression was identifiable in 80% of relapsing patients. CNS progression was a component of systemic melanoma relapse in 59/402 patients (15% overall). In 34/402 patients (9%) CNS progression represented the initial site of treatment failure. CNS progression was a component of initial progression in 27% of all patients whose melanoma relapsed (59/221). The risk of CNS progression was highest within 3 years of randomization. The difference in CNS progression rates between treatment arms was not significant (BCT = 25, HDI = 34, P = 0.24). Lymph node macrometastases strongly associated with CNS progression (P = 0.001), while ulceration and head and neck primaries were not significant predictors. This retrospective analysis of the S0008 trial identified a high brain metastasis rate (15%) in regionally advanced melanoma patients. Further studies are needed to establish whether screening plus earlier treatment would improve survival following CNS progression.

Keywords: Biochemotherapy; brain metastases; interferon; lymph node metastases; melanoma; ulceration.

Figure 1

CONSORT flow chart outlining the patient sample used for this retrospective data analysis.

Figure 2

(A) Cumulative incidence of CNS progression in all patients. CNS progression occurred in 59/221 patients who relapsed during the clinical trial (27%). Inset chart shows year‐by‐year incidence. (B) Cumulative incidence of CNS progression by treatment arm. A total of 402 eligible patients were registered to S0008. Brain metastases occurred in 25/199 patients treated with biochemotherapy (BCT) and 34/203 patients treated with high‐dose interferon (HDI).

Figure 3

(A) Cumulative incidence of CNS progression related to ulceration of primary tumor. (B) Cumulative incidence of CNS progression related to trunk and extremity, head and neck or unknown primary sites. (C) Cumulative incidence of CNS progression related to macro‐ versus micrometastases. (D) Cumulative incidence of CNS progression by treatment arm, based on macro‐ versus micrometastases.

Figure 4

Cumulative incidence of CNS progression by stage. The cumulative incidence of CNS progression in patients enrolled on S0008 was compared between patients with stage stages IIIA(N2a)‐IIIC/disease.

Figure 5

Survival following CNS progression by treatment arm. A Kaplan–Meier plot of survival from the date of diagnosis of CNS progression is shown by treatment arm.