Saved in:
| Main Authors: | , , , , , , , , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2507.05383 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866913932001673216 |
|---|---|
| author | Kalinin, Alexandr A. Llanos, Paula Sommer, Theresa Maria Sestini, Giovanni Hou, Xinhai Sexton, Jonathan Z. Wan, Xiang Dinov, Ivo D. Athey, Brian D. Rivron, Nicolas Carpenter, Anne E. Cimini, Beth Singh, Shantanu O'Meara, Matthew J. |
| author_facet | Kalinin, Alexandr A. Llanos, Paula Sommer, Theresa Maria Sestini, Giovanni Hou, Xinhai Sexton, Jonathan Z. Wan, Xiang Dinov, Ivo D. Athey, Brian D. Rivron, Nicolas Carpenter, Anne E. Cimini, Beth Singh, Shantanu O'Meara, Matthew J. |
| contents | Microscopy enables direct observation of cellular morphology in 3D, with transmitted-light methods offering low-cost, minimally invasive imaging and fluorescence microscopy providing specificity and contrast. Virtual staining combines these strengths by using machine learning to predict fluorescence images from label-free inputs. However, training of existing methods typically relies on loss functions that treat all pixels equally, thus reproducing background noise and artifacts instead of focusing on biologically meaningful signals. We introduce Spotlight, a simple yet powerful virtual staining approach that guides the model to focus on relevant cellular structures. Spotlight uses histogram-based foreground estimation to mask pixel-wise loss and to calculate a Dice loss on soft-thresholded predictions for shape-aware learning. Applied to a 3D benchmark dataset, Spotlight improves morphological representation while preserving pixel-level accuracy, resulting in virtual stains better suited for downstream tasks such as segmentation and profiling. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2507_05383 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Foreground-aware Virtual Staining for Accurate 3D Cell Morphological Profiling Kalinin, Alexandr A. Llanos, Paula Sommer, Theresa Maria Sestini, Giovanni Hou, Xinhai Sexton, Jonathan Z. Wan, Xiang Dinov, Ivo D. Athey, Brian D. Rivron, Nicolas Carpenter, Anne E. Cimini, Beth Singh, Shantanu O'Meara, Matthew J. Computer Vision and Pattern Recognition Quantitative Methods I.4.9; J.3 Microscopy enables direct observation of cellular morphology in 3D, with transmitted-light methods offering low-cost, minimally invasive imaging and fluorescence microscopy providing specificity and contrast. Virtual staining combines these strengths by using machine learning to predict fluorescence images from label-free inputs. However, training of existing methods typically relies on loss functions that treat all pixels equally, thus reproducing background noise and artifacts instead of focusing on biologically meaningful signals. We introduce Spotlight, a simple yet powerful virtual staining approach that guides the model to focus on relevant cellular structures. Spotlight uses histogram-based foreground estimation to mask pixel-wise loss and to calculate a Dice loss on soft-thresholded predictions for shape-aware learning. Applied to a 3D benchmark dataset, Spotlight improves morphological representation while preserving pixel-level accuracy, resulting in virtual stains better suited for downstream tasks such as segmentation and profiling. |
| title | Foreground-aware Virtual Staining for Accurate 3D Cell Morphological Profiling |
| topic | Computer Vision and Pattern Recognition Quantitative Methods I.4.9; J.3 |
| url | https://arxiv.org/abs/2507.05383 |