Towards Integrating Epistemic Uncertainty Estimation into the Radiotherapy Workflow
Fuente:
arXiv
Salvato in:
| Autori principali: | , , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2024
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866909327688728576 |
|---|---|
| author | Teichmann, Marvin Tom Datar, Manasi Kratzke, Lisa Vega, Fernando Ghesu, Florin C. |
| author_facet | Teichmann, Marvin Tom Datar, Manasi Kratzke, Lisa Vega, Fernando Ghesu, Florin C. |
| contents | The precision of contouring target structures and organs-at-risk (OAR) in radiotherapy planning is crucial for ensuring treatment efficacy and patient safety. Recent advancements in deep learning (DL) have significantly improved OAR contouring performance, yet the reliability of these models, especially in the presence of out-of-distribution (OOD) scenarios, remains a concern in clinical settings. This application study explores the integration of epistemic uncertainty estimation within the OAR contouring workflow to enable OOD detection in clinically relevant scenarios, using specifically compiled data. Furthermore, we introduce an advanced statistical method for OOD detection to enhance the methodological framework of uncertainty estimation. Our empirical evaluation demonstrates that epistemic uncertainty estimation is effective in identifying instances where model predictions are unreliable and may require an expert review. Notably, our approach achieves an AUC-ROC of 0.95 for OOD detection, with a specificity of 0.95 and a sensitivity of 0.92 for implant cases, underscoring its efficacy. This study addresses significant gaps in the current research landscape, such as the lack of ground truth for uncertainty estimation and limited empirical evaluations. Additionally, it provides a clinically relevant application of epistemic uncertainty estimation in an FDA-approved and widely used clinical solution for OAR segmentation from Varian, a Siemens Healthineers company, highlighting its practical benefits. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2409_18628 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Towards Integrating Epistemic Uncertainty Estimation into the Radiotherapy Workflow Teichmann, Marvin Tom Datar, Manasi Kratzke, Lisa Vega, Fernando Ghesu, Florin C. Image and Video Processing Artificial Intelligence Computer Vision and Pattern Recognition Machine Learning The precision of contouring target structures and organs-at-risk (OAR) in radiotherapy planning is crucial for ensuring treatment efficacy and patient safety. Recent advancements in deep learning (DL) have significantly improved OAR contouring performance, yet the reliability of these models, especially in the presence of out-of-distribution (OOD) scenarios, remains a concern in clinical settings. This application study explores the integration of epistemic uncertainty estimation within the OAR contouring workflow to enable OOD detection in clinically relevant scenarios, using specifically compiled data. Furthermore, we introduce an advanced statistical method for OOD detection to enhance the methodological framework of uncertainty estimation. Our empirical evaluation demonstrates that epistemic uncertainty estimation is effective in identifying instances where model predictions are unreliable and may require an expert review. Notably, our approach achieves an AUC-ROC of 0.95 for OOD detection, with a specificity of 0.95 and a sensitivity of 0.92 for implant cases, underscoring its efficacy. This study addresses significant gaps in the current research landscape, such as the lack of ground truth for uncertainty estimation and limited empirical evaluations. Additionally, it provides a clinically relevant application of epistemic uncertainty estimation in an FDA-approved and widely used clinical solution for OAR segmentation from Varian, a Siemens Healthineers company, highlighting its practical benefits. |
| title | Towards Integrating Epistemic Uncertainty Estimation into the Radiotherapy Workflow |
| topic | Image and Video Processing Artificial Intelligence Computer Vision and Pattern Recognition Machine Learning |
| url | https://arxiv.org/abs/2409.18628 |