Saved in:
| Main Authors: | , , , , , , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2026
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2602.18119 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866908843516100608 |
|---|---|
| author | Tomy, Chris Vali, Mo Pertzborn, David Alamatouri, Tammam Mühlig, Anna Guntinas-Lichius, Orlando Xylander, Anna Fantuzzi, Eric Michele Negro, Matteo Crisafi, Francesco Lio, Pietro Azevedo, Tiago |
| author_facet | Tomy, Chris Vali, Mo Pertzborn, David Alamatouri, Tammam Mühlig, Anna Guntinas-Lichius, Orlando Xylander, Anna Fantuzzi, Eric Michele Negro, Matteo Crisafi, Francesco Lio, Pietro Azevedo, Tiago |
| contents | Histopathology, the current gold standard for cancer diagnosis, involves the manual examination of tissue samples after chemical staining, a time-consuming process requiring expert analysis. Raman spectroscopy is an alternative, stain-free method of extracting information from samples. Using nnU-Net, we trained a segmentation model on a novel dataset of spatial Raman spectra aligned with tumour annotations, achieving a mean foreground Dice score of 80.9%, surpassing previous work. Furthermore, we propose a novel, interpretable, prototype-based architecture called RamanSeg. RamanSeg classifies pixels based on discovered regions of the training set, generating a segmentation mask. Two variants of RamanSeg allow a trade-off between interpretability and performance: one with prototype projection and another projection-free version. The projection-free RamanSeg outperformed a U-Net baseline with a mean foreground Dice score of 67.3%, offering a meaningful improvement over a black-box training approach. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2602_18119 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | RamanSeg: Interpretability-driven Deep Learning on Raman Spectra for Cancer Diagnosis Tomy, Chris Vali, Mo Pertzborn, David Alamatouri, Tammam Mühlig, Anna Guntinas-Lichius, Orlando Xylander, Anna Fantuzzi, Eric Michele Negro, Matteo Crisafi, Francesco Lio, Pietro Azevedo, Tiago Image and Video Processing Artificial Intelligence Computer Vision and Pattern Recognition Machine Learning Histopathology, the current gold standard for cancer diagnosis, involves the manual examination of tissue samples after chemical staining, a time-consuming process requiring expert analysis. Raman spectroscopy is an alternative, stain-free method of extracting information from samples. Using nnU-Net, we trained a segmentation model on a novel dataset of spatial Raman spectra aligned with tumour annotations, achieving a mean foreground Dice score of 80.9%, surpassing previous work. Furthermore, we propose a novel, interpretable, prototype-based architecture called RamanSeg. RamanSeg classifies pixels based on discovered regions of the training set, generating a segmentation mask. Two variants of RamanSeg allow a trade-off between interpretability and performance: one with prototype projection and another projection-free version. The projection-free RamanSeg outperformed a U-Net baseline with a mean foreground Dice score of 67.3%, offering a meaningful improvement over a black-box training approach. |
| title | RamanSeg: Interpretability-driven Deep Learning on Raman Spectra for Cancer Diagnosis |
| topic | Image and Video Processing Artificial Intelligence Computer Vision and Pattern Recognition Machine Learning |
| url | https://arxiv.org/abs/2602.18119 |