Background: A bone scan is a common method for monitoring bone metastases in patients with advanced prostate\ncancer. The Bone Scan Index (BSI) measures the tumor burden on the skeleton, expressed as a percentage of the total\nskeletal mass. Previous studies have shown that BSI is associated with survival of prostate cancer patients. The\nobjective in this study was to investigate to what extent regional BSI measurements, as obtained by an automated\nmethod, can improve the survival analysis for advanced prostate cancer.\nMethods: The automated method for analyzing bone scan images computed BSI values for twelve skeletal regions,\nin a study population consisting of 1013 patients diagnosed with prostate cancer. In the survival analysis we used the\nstandard Cox proportional hazards model and a more advanced non-linear method based on artificial neural\nnetworks. The concordance index (C-index) was used to measure the performance of the models.\nResults: A Cox model with age and total BSI obtained a C-index of 70.4%. The best Cox model with regional\nmeasurements from Costae, Pelvis, Scapula and the Spine, together with age, got a similar C-index (70.5%). The overall\nbest single skeletal localisation, as measured by the C-index, was Costae. The non-linear model performed equally well\nas the Cox model, ruling out any significant non-linear interactions among the regional BSI measurements.\nConclusion: The present study showed that the localisation of bone metastases obtained from the bone scans in\nprostate cancer patients does not improve the performance of the survival models compared to models using the\ntotal BSI. However a ranking procedure indicated that some regions are more important than others.
Loading....