Diffusion Models with Ensembled Structure-Based Anomaly Scoring for Unsupervised Anomaly Detection
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , , , , , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2024
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866909144814977024 |
|---|---|
| author | Behrendt, Finn Bhattacharya, Debayan Maack, Lennart Krüger, Julia Opfer, Roland Mieling, Robin Schlaefer, Alexander |
| author_facet | Behrendt, Finn Bhattacharya, Debayan Maack, Lennart Krüger, Julia Opfer, Roland Mieling, Robin Schlaefer, Alexander |
| contents | Supervised deep learning techniques show promise in medical image analysis. However, they require comprehensive annotated data sets, which poses challenges, particularly for rare diseases. Consequently, unsupervised anomaly detection (UAD) emerges as a viable alternative for pathology segmentation, as only healthy data is required for training. However, recent UAD anomaly scoring functions often focus on intensity only and neglect structural differences, which impedes the segmentation performance. This work investigates the potential of Structural Similarity (SSIM) to bridge this gap. SSIM captures both intensity and structural disparities and can be advantageous over the classical $l1$ error. However, we show that there is more than one optimal kernel size for the SSIM calculation for different pathologies. Therefore, we investigate an adaptive ensembling strategy for various kernel sizes to offer a more pathology-agnostic scoring mechanism. We demonstrate that this ensembling strategy can enhance the performance of DMs and mitigate the sensitivity to different kernel sizes across varying pathologies, highlighting its promise for brain MRI anomaly detection. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2403_14262 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Diffusion Models with Ensembled Structure-Based Anomaly Scoring for Unsupervised Anomaly Detection Behrendt, Finn Bhattacharya, Debayan Maack, Lennart Krüger, Julia Opfer, Roland Mieling, Robin Schlaefer, Alexander Image and Video Processing Computer Vision and Pattern Recognition Machine Learning Supervised deep learning techniques show promise in medical image analysis. However, they require comprehensive annotated data sets, which poses challenges, particularly for rare diseases. Consequently, unsupervised anomaly detection (UAD) emerges as a viable alternative for pathology segmentation, as only healthy data is required for training. However, recent UAD anomaly scoring functions often focus on intensity only and neglect structural differences, which impedes the segmentation performance. This work investigates the potential of Structural Similarity (SSIM) to bridge this gap. SSIM captures both intensity and structural disparities and can be advantageous over the classical $l1$ error. However, we show that there is more than one optimal kernel size for the SSIM calculation for different pathologies. Therefore, we investigate an adaptive ensembling strategy for various kernel sizes to offer a more pathology-agnostic scoring mechanism. We demonstrate that this ensembling strategy can enhance the performance of DMs and mitigate the sensitivity to different kernel sizes across varying pathologies, highlighting its promise for brain MRI anomaly detection. |
| title | Diffusion Models with Ensembled Structure-Based Anomaly Scoring for Unsupervised Anomaly Detection |
| topic | Image and Video Processing Computer Vision and Pattern Recognition Machine Learning |
| url | https://arxiv.org/abs/2403.14262 |