Attention-Enhanced Unpaired xAI-GANs for Transformation of Histological Stain Images
Histological staining is the primary method for confirming cancer diagnoses, but certain types, such as p63 staining, can be expensive and potentially damaging to tissues. In our research, we innovate by generating p63-stained images from H&E-stained slides for metaplastic breast cancer. This is...
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2024-01-01
|
| Series: | Journal of Imaging |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2313-433X/10/2/32 |
| _version_ | 1827343425521844224 |
|---|---|
| author | Tibor Sloboda Lukáš Hudec Matej Halinkovič Wanda Benesova |
| author_facet | Tibor Sloboda Lukáš Hudec Matej Halinkovič Wanda Benesova |
| author_sort | Tibor Sloboda |
| collection | DOAJ |
| description | Histological staining is the primary method for confirming cancer diagnoses, but certain types, such as p63 staining, can be expensive and potentially damaging to tissues. In our research, we innovate by generating p63-stained images from H&E-stained slides for metaplastic breast cancer. This is a crucial development, considering the high costs and tissue risks associated with direct p63 staining. Our approach employs an advanced CycleGAN architecture, xAI-CycleGAN, enhanced with context-based loss to maintain structural integrity. The inclusion of convolutional attention in our model distinguishes between structural and color details more effectively, thus significantly enhancing the visual quality of the results. This approach shows a marked improvement over the base xAI-CycleGAN and standard CycleGAN models, offering the benefits of a more compact network and faster training even with the inclusion of attention. |
| first_indexed | 2024-03-07T22:27:03Z |
| format | Article |
| id | doaj.art-cdcb2d79083945c3b6fe867641632704 |
| institution | Directory Open Access Journal |
| issn | 2313-433X |
| language | English |
| last_indexed | 2024-03-07T22:27:03Z |
| publishDate | 2024-01-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Journal of Imaging |
| spelling | doaj.art-cdcb2d79083945c3b6fe8676416327042024-02-23T15:22:44ZengMDPI AGJournal of Imaging2313-433X2024-01-011023210.3390/jimaging10020032Attention-Enhanced Unpaired xAI-GANs for Transformation of Histological Stain ImagesTibor Sloboda0Lukáš Hudec1Matej Halinkovič2Wanda Benesova3Faculty of Informatics and Information Technology, Slovak Technical University, Ilkovičova 2, 842 16 Bratislava, SlovakiaFaculty of Informatics and Information Technology, Slovak Technical University, Ilkovičova 2, 842 16 Bratislava, SlovakiaFaculty of Informatics and Information Technology, Slovak Technical University, Ilkovičova 2, 842 16 Bratislava, SlovakiaFaculty of Informatics and Information Technology, Slovak Technical University, Ilkovičova 2, 842 16 Bratislava, SlovakiaHistological staining is the primary method for confirming cancer diagnoses, but certain types, such as p63 staining, can be expensive and potentially damaging to tissues. In our research, we innovate by generating p63-stained images from H&E-stained slides for metaplastic breast cancer. This is a crucial development, considering the high costs and tissue risks associated with direct p63 staining. Our approach employs an advanced CycleGAN architecture, xAI-CycleGAN, enhanced with context-based loss to maintain structural integrity. The inclusion of convolutional attention in our model distinguishes between structural and color details more effectively, thus significantly enhancing the visual quality of the results. This approach shows a marked improvement over the base xAI-CycleGAN and standard CycleGAN models, offering the benefits of a more compact network and faster training even with the inclusion of attention.https://www.mdpi.com/2313-433X/10/2/32CycleGANhistologybreast cancerp63attentiongeneration |
| spellingShingle | Tibor Sloboda Lukáš Hudec Matej Halinkovič Wanda Benesova Attention-Enhanced Unpaired xAI-GANs for Transformation of Histological Stain Images Journal of Imaging CycleGAN histology breast cancer p63 attention generation |
| title | Attention-Enhanced Unpaired xAI-GANs for Transformation of Histological Stain Images |
| title_full | Attention-Enhanced Unpaired xAI-GANs for Transformation of Histological Stain Images |
| title_fullStr | Attention-Enhanced Unpaired xAI-GANs for Transformation of Histological Stain Images |
| title_full_unstemmed | Attention-Enhanced Unpaired xAI-GANs for Transformation of Histological Stain Images |
| title_short | Attention-Enhanced Unpaired xAI-GANs for Transformation of Histological Stain Images |
| title_sort | attention enhanced unpaired xai gans for transformation of histological stain images |
| topic | CycleGAN histology breast cancer p63 attention generation |
| url | https://www.mdpi.com/2313-433X/10/2/32 |
| work_keys_str_mv | AT tiborsloboda attentionenhancedunpairedxaigansfortransformationofhistologicalstainimages AT lukashudec attentionenhancedunpairedxaigansfortransformationofhistologicalstainimages AT matejhalinkovic attentionenhancedunpairedxaigansfortransformationofhistologicalstainimages AT wandabenesova attentionenhancedunpairedxaigansfortransformationofhistologicalstainimages |