Radiation injury vs. recurrent brain metastasis: combining textural feature radiomics analysis and standard parameters may increase 18 F-FET PET accuracy without dynamic scans.

OBJECTIVES: We investigated the potential of textural feature analysis of O-(2-[18 F]fluoroethyl)-L-tyrosine (18 F-FET) PET to differentiate radiation injury from brain metastasis recurrence.

METHODS: Forty-seven patients with contrast-enhancing brain lesions (n = 54) on MRI after radiotherapy of brain metastases underwent dynamic 18 F-FET PET. Tumour-to-brain ratios (TBRs) of 18 F-FET uptake and 62 textural parameters were determined on summed images 20-40 min post-injection. Tracer uptake kinetics, i.e., time-to-peak (TTP) and patterns of time-activity curves (TAC) were evaluated on dynamic PET data from 0-50 min post-injection. Diagnostic accuracy of investigated parameters and combinations thereof to discriminate between brain metastasis recurrence and radiation injury was compared.

RESULTS: Diagnostic accuracy increased from 81 % for TBRmean alone to 85 % when combined with the textural parameter Coarseness or Short-zone emphasis. The accuracy of TBRmax alone was 83 % and increased to 85 % after combination with the textural parameters Coarseness, Short-zone emphasis, or Correlation. Analysis of TACs resulted in an accuracy of 70 % for kinetic pattern alone and increased to 83 % when combined with TBRmax .

CONCLUSIONS: Textural feature analysis in combination with TBRs may have the potential to increase diagnostic accuracy for discrimination between brain metastasis recurrence and radiation injury, without the need for dynamic 18 F-FET PET scans.

KEY POINTS: • Textural feature analysis provides quantitative information about tumour heterogeneity • Textural features help improve discrimination between brain metastasis recurrence and radiation injury • Textural features might be helpful to further understand tumour heterogeneity • Analysis does not require a more time consuming dynamic PET acquisition.