# CytoDINO: Risk-Aware and Biologically-Informed Adaptation of DINOv3 for Bone Marrow Cytomorphology

arXiv: https://arxiv.org/abs/2512.17930 · HTML: https://mlsanity.com/paper/2512.17930/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 5 of its 15 references that are in the map.
- First posted on arXiv 9 Dec 2025.

## Builds on (most cited first, 5 of 5)

- [DINOv2: Learning Robust Visual Features without Supervision](https://mlsanity.com/paper/2304.07193/) (2023)
- [Emerging Properties in Self-Supervised Vision Transformers](https://mlsanity.com/paper/2104.14294/) (2021)
- [Rethinking the Inception Architecture for Computer Vision](https://mlsanity.com/paper/1512.00567/) (2015)
- [Albumentations: fast and flexible image augmentations](https://mlsanity.com/paper/1809.06839/) (2018)
- [DinoBloom: A Foundation Model for Generalizable Cell Embeddings in Hematology](https://mlsanity.com/paper/2404.05022/) (2024)

## Built on by (most cited first, 2 of 2)

- [Are Vision Foundation Models Foundational for Electron Microscopy Image Segmentation?](https://mlsanity.com/paper/2602.08505/) (2026)
- [HemaHier: Chain-Conditioned Ordinal Hierarchies for Lineage-Aware Bone-Marrow Cytology](https://mlsanity.com/paper/2609.12835/) (2026)

## Abstract (arXiv)

Bone marrow cell cytomorphology analysis is critical for the diagnosis of hematological malignancies but remains a labor-intensive process subject to significant inter-observer variability. While recent foundation models have shown promise in computational pathology, they often require extensive computational resources and fail to account for the asymmetric risks associated with clinical misdiagnosis. We introduce CytoDINO, a framework that achieves state-of-the-art performance on the Munich Leukemia Laboratory (MLL) dataset by fine-tuning DINOv3 using Low-Rank Adaptation (LoRA). Our primary contribution is a novel Hierarchical Focal Loss with Critical Penalties, which encodes biological relationships between cell lineages and explicitly penalizes clinically dangerous misclassifications (e.g., classifying blasts as normal cells). CytoDINO achieves an 88.2% weighted F1 score and 76.5% macro F1 on a held-out test set of 21 cell classes. By utilizing parameter-efficient fine-tuning with only 8% trainable parameters on a single NVIDIA RTX 5080, we demonstrate that consumer-grade hardware can match specialized infrastructure. Furthermore, confidence-based selective prediction yields 99.5% accuracy on 67% of samples, suggesting a viable pathway for clinical deployment where high-uncertainty cases are flagged for expert review