bone-marrow-ai-agent

Core Capabilities

1. Cell Classification: Deep learning identification and classification of 15+ bone marrow cell types with >95% accuracy.

2. Automated Differential: Rapid 500-cell differential counts from digital aspirate images.

3. Dysplasia Detection: AI recognition of dyserythropoiesis, dysgranulopoiesis, and dysmegakaryopoiesis.

4. Blast Quantification: Accurate blast percentage enumeration for AML/MDS classification.

5. Biopsy Analysis: Cellularity estimation, fibrosis grading, and infiltration pattern recognition.

6. Quality Assessment: Automated specimen adequacy and hemodilution detection.

Cell Types Classified

Lineage	Cell Types	Key Features
Erythroid	Pronormoblast, basophilic, polychromatic, orthochromatic	Size, chromatin, cytoplasm color
Myeloid	Myeloblast, promyelocyte, myelocyte, metamyelocyte, band, seg	Granules, nuclear shape
Monocytic	Monoblast, promonocyte, monocyte	Nuclear folding, cytoplasm
Lymphoid	Lymphocyte, plasma cell	Size, chromatin density
Megakaryocytic	Megakaryocytes (all stages)	Size, nuclear lobation
Other	Mast cells, osteoblasts, osteoclasts	Distinctive morphology

Workflow

1. Input: Bone marrow aspirate images (Wright-Giemsa stained) or biopsy sections (H&E).

2. Preprocessing: Color normalization, focus stacking, region of interest selection.

3. Cell Detection: Instance segmentation to identify individual cells.

4. Classification: CNN/CoAtNet model assigns cell type labels.

5. Differential: Aggregate counts and calculate percentages.

6. Pattern Recognition: Identify disease-associated morphological patterns.

7. Output: Differential count, morphology report, diagnostic suggestions.