Tumour size measurement in an oncology clinical trial: comparison between off-site and on-site measurements

Abstract

Aim: To evaluate the degree of variability between lesion measurements obtained by a single observer compared with multiple observers, and in selected cases evaluate which of the two measurements more accurately represented the lesion size.

Materials and methods: In this study we compared the performance of a single off-site observer to multiple on-site observers during measurement of 300 abdominal and thoracic lesions. Lesion measurements that were larger than 1cm(2), differed by more than 50%, but by less than 100%, were compared by a single adjudicator, who was blinded to the measurement source (n=46).

Results: Measurements of the 300 lesions differed by an average of 109% (SD 251%). Of 266 lesions larger than 1cm(2), results of the single observer compared with multiple observers differed by more than 10% for 249 lesions, more than 30% for 169 lesions, more than 50% for 126 lesions, and more than 100% for 66 lesions. Forty-six lesions were compared by the adjudicator. The adjudicator selected the measurement of the single observer for 37 lesions (80.4%), and the measurement determined by one of the multiple observers for nine lesions (19.6%; p=0.00002).

Conclusion: Measurement of lesion size by a single observer compared with multiple observers reveals a high degree of variability. An adjudicator selected the measurement of the single observer more frequently than that of multiple observers, with statistical significance. These findings suggest that studies designed to quantify imaging features should limit the number of observers.