Confidence-Based Annotation Of Brain Tumours In Ultrasound
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866911099781120000 |
|---|---|
| author | Weld, Alistair Dixon, Luke Roddan, Alfie Anichini, Giulio Camp, Sophie Giannarou, Stamatia |
| author_facet | Weld, Alistair Dixon, Luke Roddan, Alfie Anichini, Giulio Camp, Sophie Giannarou, Stamatia |
| contents | Purpose: An investigation of the challenge of annotating discrete segmentations of brain tumours in ultrasound, with a focus on the issue of aleatoric uncertainty along the tumour margin, particularly for diffuse tumours. A segmentation protocol and method is proposed that incorporates this margin-related uncertainty while minimising the interobserver variance through reduced subjectivity, thereby diminishing annotator epistemic uncertainty. Approach: A sparse confidence method for annotation is proposed, based on a protocol designed using computer vision and radiology theory. Results: Output annotations using the proposed method are compared with the corresponding professional discrete annotation variance between the observers. A linear relationship was measured within the tumour margin region, with a Pearson correlation of 0.8. The downstream application was explored, comparing training using confidence annotations as soft labels with using the best discrete annotations as hard labels. In all evaluation folds, the Brier score was superior for the soft-label trained network. Conclusion: A formal framework was constructed to demonstrate the infeasibility of discrete annotation of brain tumours in B-mode ultrasound. Subsequently, a method for sparse confidence-based annotation is proposed and evaluated. Keywords: Brain tumours, ultrasound, confidence, annotation. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2502_15484 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Confidence-Based Annotation Of Brain Tumours In Ultrasound Weld, Alistair Dixon, Luke Roddan, Alfie Anichini, Giulio Camp, Sophie Giannarou, Stamatia Computer Vision and Pattern Recognition Purpose: An investigation of the challenge of annotating discrete segmentations of brain tumours in ultrasound, with a focus on the issue of aleatoric uncertainty along the tumour margin, particularly for diffuse tumours. A segmentation protocol and method is proposed that incorporates this margin-related uncertainty while minimising the interobserver variance through reduced subjectivity, thereby diminishing annotator epistemic uncertainty. Approach: A sparse confidence method for annotation is proposed, based on a protocol designed using computer vision and radiology theory. Results: Output annotations using the proposed method are compared with the corresponding professional discrete annotation variance between the observers. A linear relationship was measured within the tumour margin region, with a Pearson correlation of 0.8. The downstream application was explored, comparing training using confidence annotations as soft labels with using the best discrete annotations as hard labels. In all evaluation folds, the Brier score was superior for the soft-label trained network. Conclusion: A formal framework was constructed to demonstrate the infeasibility of discrete annotation of brain tumours in B-mode ultrasound. Subsequently, a method for sparse confidence-based annotation is proposed and evaluated. Keywords: Brain tumours, ultrasound, confidence, annotation. |
| title | Confidence-Based Annotation Of Brain Tumours In Ultrasound |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2502.15484 |