Improved HER2 Tumor Segmentation with Subtype Balancing using Deep Generative Networks
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , , , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2022
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866916168700264448 |
|---|---|
| author | Öttl, Mathias Mönius, Jana Rübner, Matthias Geppert, Carol I. Qiu, Jingna Wilm, Frauke Hartmann, Arndt Beckmann, Matthias W. Fasching, Peter A. Maier, Andreas Erber, Ramona Breininger, Katharina |
| author_facet | Öttl, Mathias Mönius, Jana Rübner, Matthias Geppert, Carol I. Qiu, Jingna Wilm, Frauke Hartmann, Arndt Beckmann, Matthias W. Fasching, Peter A. Maier, Andreas Erber, Ramona Breininger, Katharina |
| contents | Tumor segmentation in histopathology images is often complicated by its composition of different histological subtypes and class imbalance. Oversampling subtypes with low prevalence features is not a satisfactory solution since it eventually leads to overfitting. We propose to create synthetic images with semantically-conditioned deep generative networks and to combine subtype-balanced synthetic images with the original dataset to achieve better segmentation performance. We show the suitability of Generative Adversarial Networks (GANs) and especially diffusion models to create realistic images based on subtype-conditioning for the use case of HER2-stained histopathology. Additionally, we show the capability of diffusion models to conditionally inpaint HER2 tumor areas with modified subtypes. Combining the original dataset with the same amount of diffusion-generated images increased the tumor Dice score from 0.833 to 0.854 and almost halved the variance between the HER2 subtype recalls. These results create the basis for more reliable automatic HER2 analysis with lower performance variance between individual HER2 subtypes. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2211_06150 |
| institution | arXiv |
| publishDate | 2022 |
| record_format | arxiv |
| spellingShingle | Improved HER2 Tumor Segmentation with Subtype Balancing using Deep Generative Networks Öttl, Mathias Mönius, Jana Rübner, Matthias Geppert, Carol I. Qiu, Jingna Wilm, Frauke Hartmann, Arndt Beckmann, Matthias W. Fasching, Peter A. Maier, Andreas Erber, Ramona Breininger, Katharina Image and Video Processing Computer Vision and Pattern Recognition Tumor segmentation in histopathology images is often complicated by its composition of different histological subtypes and class imbalance. Oversampling subtypes with low prevalence features is not a satisfactory solution since it eventually leads to overfitting. We propose to create synthetic images with semantically-conditioned deep generative networks and to combine subtype-balanced synthetic images with the original dataset to achieve better segmentation performance. We show the suitability of Generative Adversarial Networks (GANs) and especially diffusion models to create realistic images based on subtype-conditioning for the use case of HER2-stained histopathology. Additionally, we show the capability of diffusion models to conditionally inpaint HER2 tumor areas with modified subtypes. Combining the original dataset with the same amount of diffusion-generated images increased the tumor Dice score from 0.833 to 0.854 and almost halved the variance between the HER2 subtype recalls. These results create the basis for more reliable automatic HER2 analysis with lower performance variance between individual HER2 subtypes. |
| title | Improved HER2 Tumor Segmentation with Subtype Balancing using Deep Generative Networks |
| topic | Image and Video Processing Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2211.06150 |