首页|基于Transformer与距离图谱的泛癌细胞核图像分割

基于Transformer与距离图谱的泛癌细胞核图像分割

扫码查看
原文链接
  • 国家科技期刊平台
  • NETL
  • NSTL
  • 万方数据
肿瘤细胞的密度、核质比和平均尺寸等指标对癌症的分级和预后有重要的意义.在计算病理学中,细胞核分割是肿瘤微环境分析的基础.通过对分割结果进行统计分析,对新的肿瘤标记物的探索有重大的意义.病理图像背景下的细胞核形态不规则,细胞核染色不均匀,且细胞核边缘之间存在黏连的问题,而现有的深度学习算法在细胞核主体分割正确的情况下,边缘的分割错误不会对总体的损失造成太大的影响,黏连的细胞核很容易被当作同一个分割目标.为了解决细胞核重叠问题,本文提出一种基于Transformer与距离图谱的分割模型,将Transformer中的核心多头自注意力机制与距离图谱引导算法相结合,重视细胞核内部,弱化细胞核边界,提升对图像局部和全局上下文信息的学习能力.本文方法在两个公开数据集上的平均Dice系数为 0.797 9、精度为 0.756 1、AJI 系数为 0.667 2、Hausdorff距离为 10.11.实验结果表明,相较其他分割算法,本文方法的性能更好,能够有效提高细胞核的分割精度,同时较好地解决了细胞核之间的黏连问题.
Segmentation of nuclei in pan-cancer images via Transformer and distance map
Indices such as tumor cell density,nucleocytoplasmic ratio,and average size have important implications for cancer grading and prognosis.Therefore,segmentation of nuclei is the fundamental prerequisite for tumor micro-environment analysis in computational pathology.Additionally,the exploration of new tumor markers is of great sig-nificance through statistical analysis of segmentation results.However,the morphology of nuclei in the background of pathological images is irregular,the staining of nuclei is uneven,and adhesion occurs between the edges of nuclei.While the segmentation error of the edge will make no difference on the overall loss as long as the main body of the nucl is correctly segmented,so the adhering nuclei can easily be regarded as the same segmentation target by exist-ing deep learning algorithms.To address the overlapping nuclei,a new segmentation algorithm based on the Trans-former and distance map,abbreviated as TDM-Net,is proposed,which integrates the core of multi-head self-attention mechanism in Transformer with contextual information to fully explore the proximity relationship and enhances the learning ability of image details by introducing distance map to emphasize the interior of nuclei and weaken the boundary of nuclei.The algorithm's Dice coefficient,precision,Aggregated Jaccard Index(AJI)and Hausdorff dis-tance are 0.797 9,0.756 1,0.667 2,and 10.11,respectively.The results show that the proposed TDM-Net outper-forms other segmentation algorithms,effectively improves nuclei segmentation accuracy and solves overlapping of dif-ferent nuclei.

deep learningpathological imagenuclei segmentationTransformermulti-head self-attentiondistance map

鲁浩达、梁实、顾松、王向学、徐军

展开 >

南京信息工程大学 自动化学院/智慧医疗研究院,南京,210044

深度学习 病理图像 细胞核分割 Transformer 多头自注意力 距离图谱

国家自然科学基金国家自然科学基金国家自然科学基金国家自然科学基金国家自然科学基金国家自然科学基金国家自然科学基金

U1809205621712309215930162101365617712499195920781871352

2024

10.13878/j.cnki.jnuist.20220521001

南京信息工程大学学报
南京信息工程大学

南京信息工程大学学报

CSTPCD北大核心
影响因子：0.737
ISSN：1674-7070
年,卷(期)：2024.16(1)
  • 3