Evaluating the agreement between the empirical volumes of tumor lesions and the estimated volumes of tumor lesions based on the longest diameter.

Abstract

635 Background: Tumor lesions are commonly evaluated by RECIST or WHO criteria, which involves reducing the development of a three-dimensional tumor to a two-dimensional process. However, volume measurements might reflect the clinical impact of the disease process more precisely. Therefore, we investigated if the volume of a tumor lesion can be reconstructed from RECIST- or WHO-based measurements. Methods: 20 colorectal cancer patients underwent routine staging MDCT examinations as part of the multicenter phase II CIOX trial comparing cetuximab + XELOX versus cetuximab + XELIRI. Two hepatic target lesions per patient were defined at baseline and measured using 1) semi-automated volumetry (Siemens Syngo Via Oncology, Siemens Healthcare) with manual correction and 2) semi-automated measurement of the longest diameter (LD) according to RECIST 1.1 and the corresponding longest orthogonal diameter (LOD). Patient lesions were followed over time using the same measurement strategies. An algorithm was developed for reconstructing the volume of a lesion based on the LD and the corresponding LOD. Agreement of the volume data generated by both methods was analyzed by a Bland-Altman plot. The limits of agreements were calculated using a variance components model considering repeated tumor assessments based on the log-transformed sum over the volume of a patient’s lesions. Results: 151 lesions from the 20 patients were measured at 73 tumor assessments. Volume was slightly overestimated by the algorithm compared to the volumetric measurements (p = 0.07). The Bland-Altman plot showed good agreement (mean difference −0.05, limits of agreement [−0.40, 0.30]). As expected, three out of the 73 measurements fell outside the limits of agreement. Conclusions: The proposed algorithm for the WHO-based reconstruction of the tumor volume provides a good approximation to the true sum of the volumes of the lesions. In future studies, volumetric tumor information can be included even if not all centers have full volumetric software available. This enables further research on the impact of changes in tumor volume on disease prognosis and/or prediction of treatment efficacy.