Intensity-based Segmentation of Tissue Images Using a U-Net with a Pretrained ResNet-34 Encoder: Application to Mueller Microscopy
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2026
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866911437825245184 |
|---|---|
| author | Chae, Sooyong Giammattei, Dani Ajmal, Ajmal Pei, Junzhu Sanchez, Amanda Boonya-ananta, Tananant Rodriguez, Andres Novikova, Tatiana Ramella-Roman, Jessica |
| author_facet | Chae, Sooyong Giammattei, Dani Ajmal, Ajmal Pei, Junzhu Sanchez, Amanda Boonya-ananta, Tananant Rodriguez, Andres Novikova, Tatiana Ramella-Roman, Jessica |
| contents | Manual annotation of the images of thin tissue sections remains a time-consuming step in Mueller microscopy and limits its scalability. We present a novel automated approach using only the total intensity M11 element of the Mueller matrix as an input to a U-Net architecture with a pretrained ResNet-34 encoder. The network was trained to distinguish four classes in the images of murine uterine cervix sections: background, internal os, cervical tissue, and vaginal wall. With only 70 cervical tissue sections, the model achieved 89.71% pixel accuracy and 80.96% mean tissue Dice coefficient on the held-out test dataset. Transfer learning from ImageNet enables accurate segmentation despite limited size of training dataset typical of specialized biomedical imaging. This intensity-based framework requires minimal preprocessing and is readily extensible to other imaging modalities and tissue types, with publicly available graphical annotation tools for practical deployment. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2602_09787 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | Intensity-based Segmentation of Tissue Images Using a U-Net with a Pretrained ResNet-34 Encoder: Application to Mueller Microscopy Chae, Sooyong Giammattei, Dani Ajmal, Ajmal Pei, Junzhu Sanchez, Amanda Boonya-ananta, Tananant Rodriguez, Andres Novikova, Tatiana Ramella-Roman, Jessica Image and Video Processing Applied Physics Biological Physics Optics Manual annotation of the images of thin tissue sections remains a time-consuming step in Mueller microscopy and limits its scalability. We present a novel automated approach using only the total intensity M11 element of the Mueller matrix as an input to a U-Net architecture with a pretrained ResNet-34 encoder. The network was trained to distinguish four classes in the images of murine uterine cervix sections: background, internal os, cervical tissue, and vaginal wall. With only 70 cervical tissue sections, the model achieved 89.71% pixel accuracy and 80.96% mean tissue Dice coefficient on the held-out test dataset. Transfer learning from ImageNet enables accurate segmentation despite limited size of training dataset typical of specialized biomedical imaging. This intensity-based framework requires minimal preprocessing and is readily extensible to other imaging modalities and tissue types, with publicly available graphical annotation tools for practical deployment. |
| title | Intensity-based Segmentation of Tissue Images Using a U-Net with a Pretrained ResNet-34 Encoder: Application to Mueller Microscopy |
| topic | Image and Video Processing Applied Physics Biological Physics Optics |
| url | https://arxiv.org/abs/2602.09787 |