Beijing University of Chemical Technology

With voxel-level annotations on only 10% of CT scans, a heterogeneous ensemble of four independently trained models was applied to candidate-centred segmentation of 3–<6 mm pulmonary nodules. Against a single enhanced Mean Teacher, it raised Dice by 0.01488 on an internal held-out set and by 0.01118 on external LNDb without fine-tuning, with both confidence intervals excluding zero and concordant directions across three training seeds. The gain came with higher recall and lower precision, and did not establish that heterogeneous objectives beat homogeneous four-model ensembles.

With voxel-level annotations on only 10% of CT scans, a heterogeneous ensemble of four independently trained models was applied to candidate-centred segmentation of 3–<6 mm pulmonary nodules. Against a single enhanced Mean Teacher, it raised Dice by 0.01488 on an internal held-out set and by 0.01118 on external LNDb without fine-tuning, with both confidence intervals excluding zero and concordant directions across three training seeds. The gain came with higher recall and lower precision, and did not establish that heterogeneous objectives beat homogeneous four-model ensembles.