Diffusion Models with Implicit Guidance for Medical Anomaly Detection
Fuente:
arXiv
Guardado en:
| Autores principales: | , , , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2024
|
| Materias: | |
| Acceso en línea: | |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866929274888388608 |
|---|---|
| author | Bercea, Cosmin I. Wiestler, Benedikt Rueckert, Daniel Schnabel, Julia A. |
| author_facet | Bercea, Cosmin I. Wiestler, Benedikt Rueckert, Daniel Schnabel, Julia A. |
| contents | Diffusion models have advanced unsupervised anomaly detection by improving the transformation of pathological images into pseudo-healthy equivalents. Nonetheless, standard approaches may compromise critical information during pathology removal, leading to restorations that do not align with unaffected regions in the original scans. Such discrepancies can inadvertently increase false positive rates and reduce specificity, complicating radiological evaluations. This paper introduces Temporal Harmonization for Optimal Restoration (THOR), which refines the de-noising process by integrating implicit guidance through temporal anomaly maps. THOR aims to preserve the integrity of healthy tissue in areas unaffected by pathology. Comparative evaluations show that THOR surpasses existing diffusion-based methods in detecting and segmenting anomalies in brain MRIs and wrist X-rays. Code: https://github.com/ci-ber/THOR_DDPM. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2403_08464 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Diffusion Models with Implicit Guidance for Medical Anomaly Detection Bercea, Cosmin I. Wiestler, Benedikt Rueckert, Daniel Schnabel, Julia A. Image and Video Processing Computer Vision and Pattern Recognition Machine Learning Diffusion models have advanced unsupervised anomaly detection by improving the transformation of pathological images into pseudo-healthy equivalents. Nonetheless, standard approaches may compromise critical information during pathology removal, leading to restorations that do not align with unaffected regions in the original scans. Such discrepancies can inadvertently increase false positive rates and reduce specificity, complicating radiological evaluations. This paper introduces Temporal Harmonization for Optimal Restoration (THOR), which refines the de-noising process by integrating implicit guidance through temporal anomaly maps. THOR aims to preserve the integrity of healthy tissue in areas unaffected by pathology. Comparative evaluations show that THOR surpasses existing diffusion-based methods in detecting and segmenting anomalies in brain MRIs and wrist X-rays. Code: https://github.com/ci-ber/THOR_DDPM. |
| title | Diffusion Models with Implicit Guidance for Medical Anomaly Detection |
| topic | Image and Video Processing Computer Vision and Pattern Recognition Machine Learning |
| url | https://arxiv.org/abs/2403.08464 |