Unsupervised Detection of Fetal Brain Anomalies using Denoising Diffusion Models
Fuente:
arXiv
Enregistré dans:
| Auteurs principaux: | , , , , , , , , , |
|---|---|
| Format: | Preprint |
| Publié: |
2024
|
| Sujets: | |
| Accès en ligne: | |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| _version_ | 1866913460492697600 |
|---|---|
| author | Olsen, Markus Ditlev Sjøgren Ambsdorf, Jakob Lin, Manxi Taksøe-Vester, Caroline Svendsen, Morten Bo Søndergaard Christensen, Anders Nymark Nielsen, Mads Tolsgaard, Martin Grønnebæk Feragen, Aasa Pegios, Paraskevas |
| author_facet | Olsen, Markus Ditlev Sjøgren Ambsdorf, Jakob Lin, Manxi Taksøe-Vester, Caroline Svendsen, Morten Bo Søndergaard Christensen, Anders Nymark Nielsen, Mads Tolsgaard, Martin Grønnebæk Feragen, Aasa Pegios, Paraskevas |
| contents | Congenital malformations of the brain are among the most common fetal abnormalities that impact fetal development. Previous anomaly detection methods on ultrasound images are based on supervised learning, rely on manual annotations, and risk missing underrepresented categories. In this work, we frame fetal brain anomaly detection as an unsupervised task using diffusion models. To this end, we employ an inpainting-based Noise Agnostic Anomaly Detection approach that identifies the abnormality using diffusion-reconstructed fetal brain images from multiple noise levels. Our approach only requires normal fetal brain ultrasound images for training, addressing the limited availability of abnormal data. Our experiments on a real-world clinical dataset show the potential of using unsupervised methods for fetal brain anomaly detection. Additionally, we comprehensively evaluate how different noise types affect diffusion models in the fetal anomaly detection domain. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2408_03654 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Unsupervised Detection of Fetal Brain Anomalies using Denoising Diffusion Models Olsen, Markus Ditlev Sjøgren Ambsdorf, Jakob Lin, Manxi Taksøe-Vester, Caroline Svendsen, Morten Bo Søndergaard Christensen, Anders Nymark Nielsen, Mads Tolsgaard, Martin Grønnebæk Feragen, Aasa Pegios, Paraskevas Image and Video Processing Computer Vision and Pattern Recognition Congenital malformations of the brain are among the most common fetal abnormalities that impact fetal development. Previous anomaly detection methods on ultrasound images are based on supervised learning, rely on manual annotations, and risk missing underrepresented categories. In this work, we frame fetal brain anomaly detection as an unsupervised task using diffusion models. To this end, we employ an inpainting-based Noise Agnostic Anomaly Detection approach that identifies the abnormality using diffusion-reconstructed fetal brain images from multiple noise levels. Our approach only requires normal fetal brain ultrasound images for training, addressing the limited availability of abnormal data. Our experiments on a real-world clinical dataset show the potential of using unsupervised methods for fetal brain anomaly detection. Additionally, we comprehensively evaluate how different noise types affect diffusion models in the fetal anomaly detection domain. |
| title | Unsupervised Detection of Fetal Brain Anomalies using Denoising Diffusion Models |
| topic | Image and Video Processing Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2408.03654 |