Random Expert Sampling for Deep Learning Segmentation of Acute Ischemic Stroke on Non-contrast CT
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , , , , , , , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2023
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866909148559441920 |
|---|---|
| author | Ostmeier, Sophie Axelrod, Brian Pulli, Benjamin Verhaaren, Benjamin F. J. Mahammedi, Abdelkader Liu, Yongkai Federau, Christian Zaharchuk, Greg Heit, Jeremy J. |
| author_facet | Ostmeier, Sophie Axelrod, Brian Pulli, Benjamin Verhaaren, Benjamin F. J. Mahammedi, Abdelkader Liu, Yongkai Federau, Christian Zaharchuk, Greg Heit, Jeremy J. |
| contents | Purpose: Multi-expert deep learning training methods to automatically quantify ischemic brain tissue on Non-Contrast CT Materials and Methods: The data set consisted of 260 Non-Contrast CTs from 233 patients of acute ischemic stroke patients recruited in the DEFUSE 3 trial. A benchmark U-Net was trained on the reference annotations of three experienced neuroradiologists to segment ischemic brain tissue using majority vote and random expert sampling training schemes. We used a one-sided Wilcoxon signed-rank test on a set of segmentation metrics to compare bootstrapped point estimates of the training schemes with the inter-expert agreement and ratio of variance for consistency analysis. We further compare volumes with the 24h-follow-up DWI (final infarct core) in the patient subgroup with full reperfusion and we test volumes for correlation to the clinical outcome (mRS after 30 and 90 days) with the Spearman method. Results: Random expert sampling leads to a model that shows better agreement with experts than experts agree among themselves and better agreement than the agreement between experts and a majority-vote model performance (Surface Dice at Tolerance 5mm improvement of 61% to 0.70 +- 0.03 and Dice improvement of 25% to 0.50 +- 0.04). The model-based predicted volume similarly estimated the final infarct volume and correlated better to the clinical outcome than CT perfusion. Conclusion: A model trained on random expert sampling can identify the presence and location of acute ischemic brain tissue on Non-Contrast CT similar to CT perfusion and with better consistency than experts. This may further secure the selection of patients eligible for endovascular treatment in less specialized hospitals. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2309_03930 |
| institution | arXiv |
| publishDate | 2023 |
| record_format | arxiv |
| spellingShingle | Random Expert Sampling for Deep Learning Segmentation of Acute Ischemic Stroke on Non-contrast CT Ostmeier, Sophie Axelrod, Brian Pulli, Benjamin Verhaaren, Benjamin F. J. Mahammedi, Abdelkader Liu, Yongkai Federau, Christian Zaharchuk, Greg Heit, Jeremy J. Computer Vision and Pattern Recognition Purpose: Multi-expert deep learning training methods to automatically quantify ischemic brain tissue on Non-Contrast CT Materials and Methods: The data set consisted of 260 Non-Contrast CTs from 233 patients of acute ischemic stroke patients recruited in the DEFUSE 3 trial. A benchmark U-Net was trained on the reference annotations of three experienced neuroradiologists to segment ischemic brain tissue using majority vote and random expert sampling training schemes. We used a one-sided Wilcoxon signed-rank test on a set of segmentation metrics to compare bootstrapped point estimates of the training schemes with the inter-expert agreement and ratio of variance for consistency analysis. We further compare volumes with the 24h-follow-up DWI (final infarct core) in the patient subgroup with full reperfusion and we test volumes for correlation to the clinical outcome (mRS after 30 and 90 days) with the Spearman method. Results: Random expert sampling leads to a model that shows better agreement with experts than experts agree among themselves and better agreement than the agreement between experts and a majority-vote model performance (Surface Dice at Tolerance 5mm improvement of 61% to 0.70 +- 0.03 and Dice improvement of 25% to 0.50 +- 0.04). The model-based predicted volume similarly estimated the final infarct volume and correlated better to the clinical outcome than CT perfusion. Conclusion: A model trained on random expert sampling can identify the presence and location of acute ischemic brain tissue on Non-Contrast CT similar to CT perfusion and with better consistency than experts. This may further secure the selection of patients eligible for endovascular treatment in less specialized hospitals. |
| title | Random Expert Sampling for Deep Learning Segmentation of Acute Ischemic Stroke on Non-contrast CT |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2309.03930 |