Mono2D: A Trainable Monogenic Layer for Robust Knee Cartilage Segmentation on Out-of-Distribution 2D Ultrasound Data
Fuente:
arXiv
Guardado en:
| Autores principales: | , , , , , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2025
|
| Materias: | |
| Acceso en línea: | |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866917964359401472 |
|---|---|
| author | Kimbowa, Alvin Parmar, Arjun Badii, Maziar Liu, David Harkey, Matthew Hacihaliloglu, Ilker |
| author_facet | Kimbowa, Alvin Parmar, Arjun Badii, Maziar Liu, David Harkey, Matthew Hacihaliloglu, Ilker |
| contents | Automated knee cartilage segmentation using point-of-care ultrasound devices and deep-learning networks has the potential to enhance the management of knee osteoarthritis. However, segmentation algorithms often struggle with domain shifts caused by variations in ultrasound devices and acquisition parameters, limiting their generalizability. In this paper, we propose Mono2D, a monogenic layer that extracts multi-scale, contrast- and intensity-invariant local phase features using trainable bandpass quadrature filters. This layer mitigates domain shifts, improving generalization to out-of-distribution domains. Mono2D is integrated before the first layer of a segmentation network, and its parameters jointly trained alongside the network's parameters. We evaluated Mono2D on a multi-domain 2D ultrasound knee cartilage dataset for single-source domain generalization (SSDG). Our results demonstrate that Mono2D outperforms other SSDG methods in terms of Dice score and mean average surface distance. To further assess its generalizability, we evaluate Mono2D on a multi-site prostate MRI dataset, where it continues to outperform other SSDG methods, highlighting its potential to improve domain generalization in medical imaging. Nevertheless, further evaluation on diverse datasets is still necessary to assess its clinical utility. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2503_09050 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Mono2D: A Trainable Monogenic Layer for Robust Knee Cartilage Segmentation on Out-of-Distribution 2D Ultrasound Data Kimbowa, Alvin Parmar, Arjun Badii, Maziar Liu, David Harkey, Matthew Hacihaliloglu, Ilker Image and Video Processing Computer Vision and Pattern Recognition Automated knee cartilage segmentation using point-of-care ultrasound devices and deep-learning networks has the potential to enhance the management of knee osteoarthritis. However, segmentation algorithms often struggle with domain shifts caused by variations in ultrasound devices and acquisition parameters, limiting their generalizability. In this paper, we propose Mono2D, a monogenic layer that extracts multi-scale, contrast- and intensity-invariant local phase features using trainable bandpass quadrature filters. This layer mitigates domain shifts, improving generalization to out-of-distribution domains. Mono2D is integrated before the first layer of a segmentation network, and its parameters jointly trained alongside the network's parameters. We evaluated Mono2D on a multi-domain 2D ultrasound knee cartilage dataset for single-source domain generalization (SSDG). Our results demonstrate that Mono2D outperforms other SSDG methods in terms of Dice score and mean average surface distance. To further assess its generalizability, we evaluate Mono2D on a multi-site prostate MRI dataset, where it continues to outperform other SSDG methods, highlighting its potential to improve domain generalization in medical imaging. Nevertheless, further evaluation on diverse datasets is still necessary to assess its clinical utility. |
| title | Mono2D: A Trainable Monogenic Layer for Robust Knee Cartilage Segmentation on Out-of-Distribution 2D Ultrasound Data |
| topic | Image and Video Processing Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2503.09050 |