Saved in:
| Main Authors: | , , , , , , , , , , , , , , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2511.00472 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866915591809400832 |
|---|---|
| author | Wijethilake, Navodini Ivory, Marina MacCormac, Oscar Kumar, Siddhant Kujawa, Aaron Macias, Lorena Garcia-Foncillas Burger, Rebecca Hitchings, Amanda Thomson, Suki Barazi, Sinan Maratos, Eleni Obholzer, Rupert Jiang, Dan McClenaghan, Fiona Chia, Kazumi Al-Salihi, Omar Thomas, Nick Connor, Steve Vercauteren, Tom Shapey, Jonathan |
| author_facet | Wijethilake, Navodini Ivory, Marina MacCormac, Oscar Kumar, Siddhant Kujawa, Aaron Macias, Lorena Garcia-Foncillas Burger, Rebecca Hitchings, Amanda Thomson, Suki Barazi, Sinan Maratos, Eleni Obholzer, Rupert Jiang, Dan McClenaghan, Fiona Chia, Kazumi Al-Salihi, Omar Thomas, Nick Connor, Steve Vercauteren, Tom Shapey, Jonathan |
| contents | Accurate segmentation of vestibular schwannoma (VS) on Magnetic Resonance Imaging (MRI) is essential for patient management but often requires time-intensive manual annotations by experts. While recent advances in deep learning (DL) have facilitated automated segmentation, challenges remain in achieving robust performance across diverse datasets and complex clinical cases. We present an annotated dataset stemming from a bootstrapped DL-based framework for iterative segmentation and quality refinement of VS in MRI. We combine data from multiple centres and rely on expert consensus for trustworthiness of the annotations. We show that our approach enables effective and resource-efficient generalisation of automated segmentation models to a target data distribution. The framework achieved a significant improvement in segmentation accuracy with a Dice Similarity Coefficient (DSC) increase from 0.9125 to 0.9670 on our target internal validation dataset, while maintaining stable performance on representative external datasets. Expert evaluation on 143 scans further highlighted areas for model refinement, revealing nuanced cases where segmentation required expert intervention. The proposed approach is estimated to enhance efficiency by approximately 37.4% compared to the conventional manual annotation process. Overall, our human-in-the-loop model training approach achieved high segmentation accuracy, highlighting its potential as a clinically adaptable and generalisable strategy for automated VS segmentation in diverse clinical settings. The dataset includes 190 patients, with tumour annotations available for 534 longitudinal contrast-enhanced T1-weighted (T1CE) scans from 184 patients, and non-annotated T2-weighted scans from 6 patients. This dataset is publicly accessible on The Cancer Imaging Archive (TCIA) (https://doi.org/10.7937/bq0z-xa62). |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2511_00472 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Longitudinal Vestibular Schwannoma Dataset with Consensus-based Human-in-the-loop Annotations Wijethilake, Navodini Ivory, Marina MacCormac, Oscar Kumar, Siddhant Kujawa, Aaron Macias, Lorena Garcia-Foncillas Burger, Rebecca Hitchings, Amanda Thomson, Suki Barazi, Sinan Maratos, Eleni Obholzer, Rupert Jiang, Dan McClenaghan, Fiona Chia, Kazumi Al-Salihi, Omar Thomas, Nick Connor, Steve Vercauteren, Tom Shapey, Jonathan Computer Vision and Pattern Recognition Artificial Intelligence Accurate segmentation of vestibular schwannoma (VS) on Magnetic Resonance Imaging (MRI) is essential for patient management but often requires time-intensive manual annotations by experts. While recent advances in deep learning (DL) have facilitated automated segmentation, challenges remain in achieving robust performance across diverse datasets and complex clinical cases. We present an annotated dataset stemming from a bootstrapped DL-based framework for iterative segmentation and quality refinement of VS in MRI. We combine data from multiple centres and rely on expert consensus for trustworthiness of the annotations. We show that our approach enables effective and resource-efficient generalisation of automated segmentation models to a target data distribution. The framework achieved a significant improvement in segmentation accuracy with a Dice Similarity Coefficient (DSC) increase from 0.9125 to 0.9670 on our target internal validation dataset, while maintaining stable performance on representative external datasets. Expert evaluation on 143 scans further highlighted areas for model refinement, revealing nuanced cases where segmentation required expert intervention. The proposed approach is estimated to enhance efficiency by approximately 37.4% compared to the conventional manual annotation process. Overall, our human-in-the-loop model training approach achieved high segmentation accuracy, highlighting its potential as a clinically adaptable and generalisable strategy for automated VS segmentation in diverse clinical settings. The dataset includes 190 patients, with tumour annotations available for 534 longitudinal contrast-enhanced T1-weighted (T1CE) scans from 184 patients, and non-annotated T2-weighted scans from 6 patients. This dataset is publicly accessible on The Cancer Imaging Archive (TCIA) (https://doi.org/10.7937/bq0z-xa62). |
| title | Longitudinal Vestibular Schwannoma Dataset with Consensus-based Human-in-the-loop Annotations |
| topic | Computer Vision and Pattern Recognition Artificial Intelligence |
| url | https://arxiv.org/abs/2511.00472 |