ReStainGAN: Leveraging IHC to IF Stain Domain Translation for in-silico Data Generation
Fuente:
arXiv
Salvato in:
| Autori principali: | , , , , , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2024
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866917610413621248 |
|---|---|
| author | Winter, Dominik Triltsch, Nicolas Plewa, Philipp Rosati, Marco Padel, Thomas Hill, Ross Schick, Markus Brieu, Nicolas |
| author_facet | Winter, Dominik Triltsch, Nicolas Plewa, Philipp Rosati, Marco Padel, Thomas Hill, Ross Schick, Markus Brieu, Nicolas |
| contents | The creation of in-silico datasets can expand the utility of existing annotations to new domains with different staining patterns in computational pathology. As such, it has the potential to significantly lower the cost associated with building large and pixel precise datasets needed to train supervised deep learning models. We propose a novel approach for the generation of in-silico immunohistochemistry (IHC) images by disentangling morphology specific IHC stains into separate image channels in immunofluorescence (IF) images. The proposed approach qualitatively and quantitatively outperforms baseline methods as proven by training nucleus segmentation models on the created in-silico datasets. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2403_06545 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | ReStainGAN: Leveraging IHC to IF Stain Domain Translation for in-silico Data Generation Winter, Dominik Triltsch, Nicolas Plewa, Philipp Rosati, Marco Padel, Thomas Hill, Ross Schick, Markus Brieu, Nicolas Image and Video Processing Artificial Intelligence Computer Vision and Pattern Recognition Machine Learning I.2.10, J.3, I.4.6 The creation of in-silico datasets can expand the utility of existing annotations to new domains with different staining patterns in computational pathology. As such, it has the potential to significantly lower the cost associated with building large and pixel precise datasets needed to train supervised deep learning models. We propose a novel approach for the generation of in-silico immunohistochemistry (IHC) images by disentangling morphology specific IHC stains into separate image channels in immunofluorescence (IF) images. The proposed approach qualitatively and quantitatively outperforms baseline methods as proven by training nucleus segmentation models on the created in-silico datasets. |
| title | ReStainGAN: Leveraging IHC to IF Stain Domain Translation for in-silico Data Generation |
| topic | Image and Video Processing Artificial Intelligence Computer Vision and Pattern Recognition Machine Learning I.2.10, J.3, I.4.6 |
| url | https://arxiv.org/abs/2403.06545 |