BiCC: Bidirectional Connected-Component Loss for Instance-Aware Segmentation

2026-09-24

AI Summary

This study addresses the limitations of conventional segmentation losses in handling small lesions and the inability of existing instance-aware losses to penalize false positives. To this end, we propose a Bidirectional Connected Component (BCC) loss. This method pioneers deriving instances from predictions to independently score false positive components, integrates annotation- and prediction-based partitioning for bidirectional connected component analysis, and introduces a balancing parameter to modulate the lesion-level precision-recall trade-off. Experiments built upon the nnU-Net framework demonstrate that the proposed approach significantly outperforms Blob Loss and CC-DiceCE across five datasets. It effectively improves the lesion F1 score while avoiding an excessive bias toward recall.

Abstract

Common segmentation losses aggregate errors voxel-wise, so lesions influence the objective in proportion to their volume, giving small but clinically critical lesions disproportionately little weight. Instance-aware losses aim to address this mismatch by assigning each lesion its own term. However, blob loss and CC-DiceCE derive their regions solely from annotations, so false-positive components receive no instance-level term. This matters in computer-assisted review, where each false-positive component may require separate inspection, making precision and false-positive burden important alongside recall. We introduce the bidirectional connected-component loss (BiCC), which pairs annotation- and prediction-derived partitions to score predicted components on their own scale. By deriving instances from the predictions, this branch directly penalizes false-positive components regardless of their size. The balance parameter $α$ allows control over the lesion-wise precision-recall trade-off. Across five datasets with five-fold cross-validation using nnU-Net, BiCC outperforms CC-DiceCE in lesion-wise F1 on four datasets and blob loss on all five. It significantly improves over DiceCE on three datasets and matches it on two; CC-DiceCE instead loses up to 0.363 precision by favoring recall. Code is available at https://github.com/TIO-IKIM/BiCC-Loss.

Problem

• Instance-aware segmentation
• Connected-component loss
• False-positive penalty
• Lesion-wise precision-recall
• Medical image segmentation

Innovation

• Bidirectional Connected-Component Loss
• Instance-Aware Segmentation
• False-Positive Penalization
• Precision-Recall Trade-off
• Medical Image Segmentation