Salvato in:
| Autori principali: | , , , , , , , , , , , , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2026
|
| Soggetti: | |
| Accesso online: | https://arxiv.org/abs/2602.03998 |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866915805333028864 |
|---|---|
| author | Alagha, Ahmed Leclerc, Christopher Kotp, Yousef Metwally, Omar Moras, Calvin Rentopoulos, Peter Rostami, Ghodsiyeh Nguyen, Bich Ngoc Baig, Jumanah Khellaf, Abdelhakim Trinh, Vincent Quoc-Huy Mizouni, Rabeb Otrok, Hadi Bentahar, Jamal Hosseini, Mahdi S. |
| author_facet | Alagha, Ahmed Leclerc, Christopher Kotp, Yousef Metwally, Omar Moras, Calvin Rentopoulos, Peter Rostami, Ghodsiyeh Nguyen, Bich Ngoc Baig, Jumanah Khellaf, Abdelhakim Trinh, Vincent Quoc-Huy Mizouni, Rabeb Otrok, Hadi Bentahar, Jamal Hosseini, Mahdi S. |
| contents | Whole-slide image (WSI) preprocessing, comprising tissue detection followed by patch extraction, is foundational to AI-driven computational pathology but remains a major bottleneck for scaling to large and heterogeneous cohorts. We present AtlasPatch, a scalable framework that couples foundation-model tissue detection with high-throughput patch extraction at minimal computational overhead. Our tissue detector achieves high precision (0.986) and remains robust across varying tissue conditions (e.g., brightness, fragmentation, boundary definition, tissue heterogeneity) and common artifacts (e.g., pen/ink markings, scanner streaks). This robustness is enabled by our annotated, heterogeneous multi-cohort training set of ~30,000 WSI thumbnails combined with efficient adaptation of the Segment-Anything (SAM) model. AtlasPatch also reduces end-to-end WSI preprocessing time by up to 16$\times$ versus widely used deep-learning pipelines, without degrading downstream task performance. The AtlasPatch tool is open-source, efficiently parallelized for practical deployment, and supports options to save extracted patches or stream them into common feature-extraction models for on-the-fly embedding, making it adaptable to both pathology departments (tissue detection and quality control) and AI researchers (dataset creation and model training). AtlasPatch software package is available at https://github.com/AtlasAnalyticsLab/AtlasPatch. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2602_03998 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | AtlasPatch: Efficient Tissue Detection and High-throughput Patch Extraction for Computational Pathology at Scale Alagha, Ahmed Leclerc, Christopher Kotp, Yousef Metwally, Omar Moras, Calvin Rentopoulos, Peter Rostami, Ghodsiyeh Nguyen, Bich Ngoc Baig, Jumanah Khellaf, Abdelhakim Trinh, Vincent Quoc-Huy Mizouni, Rabeb Otrok, Hadi Bentahar, Jamal Hosseini, Mahdi S. Image and Video Processing Computer Vision and Pattern Recognition Quantitative Methods Whole-slide image (WSI) preprocessing, comprising tissue detection followed by patch extraction, is foundational to AI-driven computational pathology but remains a major bottleneck for scaling to large and heterogeneous cohorts. We present AtlasPatch, a scalable framework that couples foundation-model tissue detection with high-throughput patch extraction at minimal computational overhead. Our tissue detector achieves high precision (0.986) and remains robust across varying tissue conditions (e.g., brightness, fragmentation, boundary definition, tissue heterogeneity) and common artifacts (e.g., pen/ink markings, scanner streaks). This robustness is enabled by our annotated, heterogeneous multi-cohort training set of ~30,000 WSI thumbnails combined with efficient adaptation of the Segment-Anything (SAM) model. AtlasPatch also reduces end-to-end WSI preprocessing time by up to 16$\times$ versus widely used deep-learning pipelines, without degrading downstream task performance. The AtlasPatch tool is open-source, efficiently parallelized for practical deployment, and supports options to save extracted patches or stream them into common feature-extraction models for on-the-fly embedding, making it adaptable to both pathology departments (tissue detection and quality control) and AI researchers (dataset creation and model training). AtlasPatch software package is available at https://github.com/AtlasAnalyticsLab/AtlasPatch. |
| title | AtlasPatch: Efficient Tissue Detection and High-throughput Patch Extraction for Computational Pathology at Scale |
| topic | Image and Video Processing Computer Vision and Pattern Recognition Quantitative Methods |
| url | https://arxiv.org/abs/2602.03998 |