BackSplit: The Importance of Sub-dividing the Background in Biomedical Lesion Segmentation
Fuente:
arXiv
Enregistré dans:
| Auteurs principaux: | , , , , , |
|---|---|
| Format: | Preprint |
| Publié: |
2025
|
| Sujets: | |
| Accès en ligne: | |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| _version_ | 1866911732695302144 |
|---|---|
| author | Saluja, Rachit Cihangir, Asli Deng, Ruining Paetzold, Johannes C. Liu, Fengbei Sabuncu, Mert R. |
| author_facet | Saluja, Rachit Cihangir, Asli Deng, Ruining Paetzold, Johannes C. Liu, Fengbei Sabuncu, Mert R. |
| contents | Segmenting small lesions in medical images remains notoriously difficult. Most prior work tackles this challenge by either designing better architectures, loss functions, or data augmentation schemes; and collecting more labeled data. We take a different view, arguing that part of the problem lies in how the background is modeled. Common lesion segmentation collapses all non-lesion pixels into a single "background" class, ignoring the rich anatomical context in which lesions appear. In reality, the background is highly heterogeneous-composed of tissues, organs, and other structures that can now be labeled manually or inferred automatically using existing segmentation models.
In this paper, we argue that training with fine-grained labels that sub-divide the background class, which we call BackSplit, is a simple yet powerful paradigm that can offer a significant performance boost without increasing inference costs. From an information theoretic standpoint, we prove that BackSplit increases the expected Fisher Information relative to conventional binary training, leading to tighter asymptotic bounds and more stable optimization. With extensive experiments across multiple datasets and architectures, we empirically show that BackSplit consistently boosts small-lesion segmentation performance, even when auxiliary labels are generated automatically using pretrained segmentation models. Additionally, we demonstrate that auxiliary labels derived from interactive segmentation frameworks exhibit the same beneficial effect, demonstrating its robustness, simplicity, and broad applicability. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2511_19394 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | BackSplit: The Importance of Sub-dividing the Background in Biomedical Lesion Segmentation Saluja, Rachit Cihangir, Asli Deng, Ruining Paetzold, Johannes C. Liu, Fengbei Sabuncu, Mert R. Computer Vision and Pattern Recognition Segmenting small lesions in medical images remains notoriously difficult. Most prior work tackles this challenge by either designing better architectures, loss functions, or data augmentation schemes; and collecting more labeled data. We take a different view, arguing that part of the problem lies in how the background is modeled. Common lesion segmentation collapses all non-lesion pixels into a single "background" class, ignoring the rich anatomical context in which lesions appear. In reality, the background is highly heterogeneous-composed of tissues, organs, and other structures that can now be labeled manually or inferred automatically using existing segmentation models. In this paper, we argue that training with fine-grained labels that sub-divide the background class, which we call BackSplit, is a simple yet powerful paradigm that can offer a significant performance boost without increasing inference costs. From an information theoretic standpoint, we prove that BackSplit increases the expected Fisher Information relative to conventional binary training, leading to tighter asymptotic bounds and more stable optimization. With extensive experiments across multiple datasets and architectures, we empirically show that BackSplit consistently boosts small-lesion segmentation performance, even when auxiliary labels are generated automatically using pretrained segmentation models. Additionally, we demonstrate that auxiliary labels derived from interactive segmentation frameworks exhibit the same beneficial effect, demonstrating its robustness, simplicity, and broad applicability. |
| title | BackSplit: The Importance of Sub-dividing the Background in Biomedical Lesion Segmentation |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2511.19394 |