A total of 862 lamb carcasses that were evaluated by both the VIAscan ® and the current EUROP classification system were deboned and the actual yield was measured. Models were derived for predicting lean meat yield of the legs (Leg%), loin (Loin%) and shoulder (Shldr%) using the best VIAscan ® variables selected by stepwise regression analysis of a calibration data set (n = 603). The equations were tested on validation data set (n = 259). The results showed that the VIAscan ® predicted lean meat yield in the leg, loin and shoulder with an R 2 of 0.60, 0.31 and 0.47, respectively, whereas the current EUROP system predicted lean yield with an R 2 of 0.57, 0.32 and 0.37, respectively, for the three carcass parts. The VIAscan ® also predicted the EUROP score of the trial carcasses, using a model derived from an earlier trial. The EUROP classification from VIAscan ® and the current system were compared for their ability to explain the variation in lean yield of the whole carcass (LMY%) and trimmed fat (FAT%). The predicted EUROP scores from the VIAscan ® explained 36% of the variation in LMY% and 60% of the variation in FAT%, compared with the current EUROP system that explained 49% and 72%, respectively. The EUROP classification obtained by the VIAscan ® was tested against a panel of three expert classifiers (n = 696). The VIAscan ® classification agreed with 82% of conformation and 73% of the fat classes assigned by a panel of expert classifiers. It was concluded that VIAscan ® provides a technology that can directly predict LMY% of lamb carcasses with more accuracy than the current EUROP classification system. The VIAscan ® is also capable of classifying lamb carcasses into EUROP classes with an accuracy that fulfils minimum demands for the Icelandic sheep industry. Although the VIAscan ® prediction of the Loin% is low, it is comparable to the current EUROP system, and should not hinder the adoption of the technology to estimate the yield of Icelandic lambs as it delivered a more accurate prediction for the Leg%, Shldr% and overall LMY% with negligible prediction bias.