基于深度学习的两步联合模型实现了在血清性溢出中智能识别脱皮细胞
Yige Yin1, Xiaotao Li2, Dongsheng Li3
1Department of Orthopaedic, 989th Hospital of PLA, Luoyang 471031, China; Hefei Cancer Hospital of CAS, Institute of Health and Medical Technology, Hefei Institutes of Physical Science, Chinese Academy of Sciences, Hefei 230031, China; School of Basic Medical Sciences, Anhui Medical University, Hefei 230032, China.
这项研究引入了一个两步的深度学习框架,用于精确的细胞病理学诊断血清溢出. 人工智能模型增强了异常细胞的检测和正常细胞的分类,提高了诊断的一致性.
科学领域:
- 计算病理学计算病理学
- 医学中的人工智能
背景情况:
- 血清性输液的细胞学检查对于恶性瘤的诊断至关重要.
- 主观的解释导致诊断不一致和错误诊断,特别是在资源有限的地区.
研究的目的:
- 开发一个标准化和增强的深度学习框架,用于客观的细胞病理诊断.
- 为了提高精度和减少血清溢出分析的诊断错误.
主要方法:
- 实施了两步的深度学习方法.
- 通过在线卷积修复参数化 (OREPA) 模块来增强YOLOv8模型,用于检测异常细胞.
- 双重注意力视觉变压器 (DaViT) 用于正常细胞的分类.
主要成果:
- 经OREPA改进的YOLOv8模型在检测异常细胞方面获得了93.09%的灵敏度.
- 达维特模型在分类正常细胞 (淋巴细胞,中皮细胞,囊细胞,中性粒细胞) 中显示了98.74%的准确性.
结论:
- 综合深度学习框架为快速和客观的细胞病理诊断提供了强大的工具.
- 这种人工智能驱动的方法解决了临床需求,特别是在资源有限的环境中,通过减少错过的诊断和提供详细的细胞组成见解.
更多相关视频
09:37Combining Reflectance Confocal Microscopy with Optical Coherence Tomography for Noninvasive Diagnosis of Skin Cancers via Image Acquisition
Published on: August 18, 2022
04:48Application of Deep Learning-Based Medical Image Segmentation via Orbital Computed Tomography
Published on: November 30, 2022
相关概念视频
Classification of Epithelial Tissues: Stratified Epithelium
Classification of Epithelial Tissues: Simple Epithelium
Because of the thinness of the cells, simple squamous epithelium is present where the rapid passage of chemical compounds is observed. For example, the endothelium that lines the capillaries and vessels...
Classification of Epithelial Tissues: Overview
Based on the number of cell layers,...
Classification of Leukocytes
Neutrophils are the most abundant type of granular leukocytes, comprising 50-70% of all leukocytes. They feature small, evenly distributed granules and a...
