# Chinese expert consensus on the technical and clinical practice specifications of artificial intelligence assisted morphology examination of blood cells (2024)

PMC · DOI: 10.3760/cma.j.cn121090-20240217-00064 · Chinese Journal of Hematology · 2024-04-01

## TL;DR

This paper presents a Chinese expert consensus on using AI for blood cell morphology exams, aiming to standardize technical and clinical practices.

## Contribution

The paper introduces standardized guidelines for AI-assisted blood cell morphology examination in China.

## Key findings

- AI improves efficiency and standardization in blood cell morphology exams.
- The consensus covers technical requirements, data management, and quality control for AI use.
- Emphasis is placed on accurate cell classification and data security in clinical settings.

## Abstract

血细胞形态学检查是血液疾病诊断的重要手段，传统人工镜检存在效率低、易受主观影响等问题。人工智能技术的应用提高了血细胞检查的效率和质量，促进了检测结果的标准化。目前，多种人工智能设备已在临床使用或研究中，但其技术要求和配置各异。中华医学会血液学分会实验诊断学组组织相关专家，制订了本共识。本共识内容包括术语定义、适用范围、技术要求、临床应用、数据管理和信息安全，强调了标本制备、图像采集、图像分割算法、细胞特征提取与识别分类的重要性，并提出了细胞识别谱的基本要求。同时，对病理细胞的细分类、细胞训练与测试的要求、质量控制标准、辅助人工出具诊断报告等方面进行了详细说明。此外，还强调了数据管理和信息安全的重要性，确保患者信息的安全和数据的准确性。

## Full-text entities

- **Diseases:** blood diseases (MESH:D006402)
- **Species:** Homo sapiens (human, species) [taxon 9606]

## Full text

_Full body text omitted from this summary view._ Fetch the complete paper as Markdown: https://tomesphere.com/paper/PMC11168004/full.md

## References

61 references — full list in the complete paper: https://tomesphere.com/paper/PMC11168004/full.md

---
Source: https://tomesphere.com/paper/PMC11168004