Saved in:
| Main Authors: | , , , , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2024
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2404.15718 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866909180160376832 |
|---|---|
| author | Ulrich, Constantin Knobloch, Catherine Holzschuh, Julius C. Wald, Tassilo Rokuss, Maximilian R. Zenk, Maximilian Fischer, Maximilian Baumgartner, Michael Isensee, Fabian Maier-Hein, Klaus H. |
| author_facet | Ulrich, Constantin Knobloch, Catherine Holzschuh, Julius C. Wald, Tassilo Rokuss, Maximilian R. Zenk, Maximilian Fischer, Maximilian Baumgartner, Michael Isensee, Fabian Maier-Hein, Klaus H. |
| contents | Despite considerable strides in developing deep learning models for 3D medical image segmentation, the challenge of effectively generalizing across diverse image distributions persists. While domain generalization is acknowledged as vital for robust application in clinical settings, the challenges stemming from training with a limited Field of View (FOV) remain unaddressed. This limitation leads to false predictions when applied to body regions beyond the FOV of the training data. In response to this problem, we propose a novel loss function that penalizes predictions in implausible body regions, applicable in both single-dataset and multi-dataset training schemes. It is realized with a Body Part Regression model that generates axial slice positional scores. Through comprehensive evaluation using a test set featuring varying FOVs, our approach demonstrates remarkable improvements in generalization capabilities. It effectively mitigates false positive tumor predictions up to 85% and significantly enhances overall segmentation performance. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2404_15718 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Mitigating False Predictions In Unreasonable Body Regions Ulrich, Constantin Knobloch, Catherine Holzschuh, Julius C. Wald, Tassilo Rokuss, Maximilian R. Zenk, Maximilian Fischer, Maximilian Baumgartner, Michael Isensee, Fabian Maier-Hein, Klaus H. Image and Video Processing Computer Vision and Pattern Recognition Despite considerable strides in developing deep learning models for 3D medical image segmentation, the challenge of effectively generalizing across diverse image distributions persists. While domain generalization is acknowledged as vital for robust application in clinical settings, the challenges stemming from training with a limited Field of View (FOV) remain unaddressed. This limitation leads to false predictions when applied to body regions beyond the FOV of the training data. In response to this problem, we propose a novel loss function that penalizes predictions in implausible body regions, applicable in both single-dataset and multi-dataset training schemes. It is realized with a Body Part Regression model that generates axial slice positional scores. Through comprehensive evaluation using a test set featuring varying FOVs, our approach demonstrates remarkable improvements in generalization capabilities. It effectively mitigates false positive tumor predictions up to 85% and significantly enhances overall segmentation performance. |
| title | Mitigating False Predictions In Unreasonable Body Regions |
| topic | Image and Video Processing Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2404.15718 |