数据与复现临床医学与医药FreedomIntelligence/OpenClaw-Medical-Skills数据与复现

bone-marrow-ai-agent

维护者 FreedomIntelligence · 最近更新 2026年4月1日

Bone marrow analysis: blast counting, immunophenotyping, disease classification.

OpenClawNanoClaw分析处理复现实验bone-marrow-ai-agent🧠 bioos extended suitehematology & blood disordersbone

原始来源

FreedomIntelligence/OpenClaw-Medical-Skills

https://github.com/FreedomIntelligence/OpenClaw-Medical-Skills/tree/main/skills/bone-marrow-ai-agent

技能摘要

2 min

Bone Marrow AI Agent provides comprehensive AI-driven analysis of bone marrow aspirate 、 biopsy specimens. It performs automated cell identification，differential counting，morphological assessment，、 pattern recognition ，用于 hematologic disease diagnosis。
When performing automated bone marrow differential counts ，面向 aspirate smears。
To identify morphological abnormalities (dysplasia，blasts，abnormal cells)。
用于 pattern recognition in myelodysplastic syndromes (MDS)，leukemias，、 other disorders。
When assessing cellularity，fibrosis，、 infiltration in trephine biopsies。

原始文档

Cell Classification: Deep learning identification and classification of 15+ bone marrow cell types with >95% accuracy.
Automated Differential: Rapid 500-cell differential counts from digital aspirate images.
Dysplasia Detection: AI recognition of dyserythropoiesis, dysgranulopoiesis, and dysmegakaryopoiesis.
Blast Quantification: Accurate blast percentage enumeration for AML/MDS classification.
Biopsy Analysis: Cellularity estimation, fibrosis grading, and infiltration pattern recognition.
Quality Assessment: Automated specimen adequacy and hemodilution detection.

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

Input: Bone marrow aspirate images (Wright-Giemsa stained) or biopsy sections (H&E).
Preprocessing: Color normalization, focus stacking, region of interest selection.
Cell Detection: Instance segmentation to identify individual cells.
Classification: CNN/CoAtNet model assigns cell type labels.
Differential: Aggregate counts and calculate percentages.
Pattern Recognition: Identify disease-associated morphological patterns.
Output: Differential count, morphology report, diagnostic suggestions.

When performing automated bone marrow differential counts ，面向 aspirate smears。
To identify morphological abnormalities (dysplasia，blasts，abnormal cells)。
用于 pattern recognition in myelodysplastic syndromes (MDS)，leukemias，、 other disorders。
When assessing cellularity，fibrosis，、 infiltration in trephine biopsies。