Saved in:
| Main Authors: | , , , , , , , , , , , , , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2024
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2408.08982 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866916486751191040 |
|---|---|
| author | Deltadahl, Simon Gilbey, Julian Van Laer, Christine Boeckx, Nancy Leers, Mathie Freeman, Tanya Aiken, Laura Farren, Timothy Smith, Matthew Zeina, Mohamad consortium, BloodCounts Rudd, James HF Piazzese, Concetta Taylor, Joseph Gleadall, Nicholas Schönlieb, Carola-Bibiane Sivapalaratnam, Suthesh Roberts, Michael Nachev, Parashkev |
| author_facet | Deltadahl, Simon Gilbey, Julian Van Laer, Christine Boeckx, Nancy Leers, Mathie Freeman, Tanya Aiken, Laura Farren, Timothy Smith, Matthew Zeina, Mohamad consortium, BloodCounts Rudd, James HF Piazzese, Concetta Taylor, Joseph Gleadall, Nicholas Schönlieb, Carola-Bibiane Sivapalaratnam, Suthesh Roberts, Michael Nachev, Parashkev |
| contents | Accurate classification of haematological cells is critical for diagnosing blood disorders, but presents significant challenges for machine automation owing to the complexity of cell morphology, heterogeneities of biological, pathological, and imaging characteristics, and the imbalance of cell type frequencies. We introduce CytoDiffusion, a diffusion-based classifier that effectively models blood cell morphology, combining accurate classification with robust anomaly detection, resistance to distributional shifts, interpretability, data efficiency, and superhuman uncertainty quantification. Our approach outperforms state-of-the-art discriminative models in anomaly detection (AUC 0.990 vs. 0.918), resistance to domain shifts (85.85% vs. 74.38% balanced accuracy), and performance in low-data regimes (95.88% vs. 94.95% balanced accuracy). Notably, our model generates synthetic blood cell images that are nearly indistinguishable from real images, as demonstrated by an authenticity test in which expert haematologists achieved only 52.3% accuracy (95% CI: [50.5%, 54.2%]) in distinguishing real from generated images. Furthermore, we enhance model explainability through the generation of directly interpretable counterfactual heatmaps. Our comprehensive evaluation framework, encompassing these multiple performance dimensions, establishes a new benchmark for medical image analysis in haematology, ultimately enabling improved diagnostic accuracy in clinical settings. Our code is available at https://github.com/CambridgeCIA/CytoDiffusion. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2408_08982 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Deep Generative Classification of Blood Cell Morphology Deltadahl, Simon Gilbey, Julian Van Laer, Christine Boeckx, Nancy Leers, Mathie Freeman, Tanya Aiken, Laura Farren, Timothy Smith, Matthew Zeina, Mohamad consortium, BloodCounts Rudd, James HF Piazzese, Concetta Taylor, Joseph Gleadall, Nicholas Schönlieb, Carola-Bibiane Sivapalaratnam, Suthesh Roberts, Michael Nachev, Parashkev Computer Vision and Pattern Recognition Accurate classification of haematological cells is critical for diagnosing blood disorders, but presents significant challenges for machine automation owing to the complexity of cell morphology, heterogeneities of biological, pathological, and imaging characteristics, and the imbalance of cell type frequencies. We introduce CytoDiffusion, a diffusion-based classifier that effectively models blood cell morphology, combining accurate classification with robust anomaly detection, resistance to distributional shifts, interpretability, data efficiency, and superhuman uncertainty quantification. Our approach outperforms state-of-the-art discriminative models in anomaly detection (AUC 0.990 vs. 0.918), resistance to domain shifts (85.85% vs. 74.38% balanced accuracy), and performance in low-data regimes (95.88% vs. 94.95% balanced accuracy). Notably, our model generates synthetic blood cell images that are nearly indistinguishable from real images, as demonstrated by an authenticity test in which expert haematologists achieved only 52.3% accuracy (95% CI: [50.5%, 54.2%]) in distinguishing real from generated images. Furthermore, we enhance model explainability through the generation of directly interpretable counterfactual heatmaps. Our comprehensive evaluation framework, encompassing these multiple performance dimensions, establishes a new benchmark for medical image analysis in haematology, ultimately enabling improved diagnostic accuracy in clinical settings. Our code is available at https://github.com/CambridgeCIA/CytoDiffusion. |
| title | Deep Generative Classification of Blood Cell Morphology |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2408.08982 |