arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2401.15638cs.CV
收藏

Cyto R-CNN与CytoNuke数据集:面向明场组织学图像中可靠的全细胞分割

Cyto R-CNN and CytoNuke Dataset: Towards reliable whole-cell segmentation in bright-field histological images

University Hospital RWTH Aachen(亚琛工业大学医院);Institute of Medical Informatics, University Hospital RWTH Aachen(亚琛工业大学医院医学信息学研究所);Institute for Artificial Intelligence in Medicine (IKIM), University Hospital Essen (AöR)(埃森大学医院(公法法人)医学人工智能研究所);Cancer Research Center Cologne Essen (CCCE), West German Cancer Center Essen, University Hospital Essen (AöR)(埃森大学医院(公法法人)科隆埃森癌症研究中心(CCCE)、西德埃森癌症中心);Institute of Pathology, University Hospital RWTH Aachen(亚琛工业大学医院病理学研究所);Institute of Pathology, Ludwig Maximilian University of Munich(慕尼黑大学病理学研究所)
Johannes Raufeisen, Kunpeng Xie, Fabian Hörst, Till Braunschweig, Jianning Li, Jens Kleesiek, Rainer Röhrig, Jan Egger, Bastian Leibe, Frank Hölzle, Alexander H… 展开作者

Johannes Raufeisen, Kunpeng Xie, Fabian Hörst, Till Braunschweig, Jianning Li, Jens Kleesiek, Rainer Röhrig, Jan Egger, Bastian Leibe, Frank Hölzle, Alexander Hermans, Behrus Puladi

AI总结:

针对明场组织学图像难以分割全细胞的问题,提出Cyto R-CNN架构并构建CytoNuke数据集,在全细胞分割精度和细胞特征可靠性上均优于现有主流方法,可助力数字病理诊断。

摘要:

研究背景:明场组织学切片中的细胞分割是医学图像分析领域的关键课题。获取精准的分割结果可帮助研究者探究细胞形态与临床观测结果之间的关联。遗憾的是,目前已知的多数分割方法仅局限于细胞核分割,无法实现细胞质的分割。\n材料与方法:我们提出了一种新型网络架构Cyto R-CNN,能够在明场图像中精准分割包含细胞核和细胞质的完整细胞。我们同时发布了全新数据集CytoNuke,该数据集包含数千份头颈部鳞状细胞癌细胞的人工标注结果。基于该数据集,我们将Cyto R-CNN的性能与其他主流细胞分割算法进行了对比,包括QuPath内置算法、StarDist和Cellpose。为评估分割性能,我们计算了AP50、AP75指标,并为所有检测到的细胞测量了17项形态学与染色相关特征。我们采用Kolmogorov-Smirnov检验,将这些测量结果与人工分割的金标准进行了比对。\n结果:Cyto R-CNN在全细胞分割任务中取得了58.65%的AP50和11.56%的AP75,优于所有其他对比方法(QuPath为19.46%/0.91%;StarDist为45.33%/2.32%;Cellpose为31.85%/5.61%)。由Cyto R-CNN得到的细胞特征与金标准的一致性最佳(平均D值=0.15),优于QuPath(平均D值=0.22)、StarDist(平均D值=0.25)和Cellpose(平均D值=0.23)。\n结论:我们新提出的Cyto R-CNN架构在全细胞分割任务上性能优于现有算法,同时能提供比其他所有模型更可靠的细胞测量结果。这一成果可优化数字病理工作流程,有望提升诊断水平。此外,我们公开发布的数据集可用于未来更多模型的开发。

英文摘要:

Background: Cell segmentation in bright-field histological slides is a crucial topic in medical image analysis. Having access to accurate segmentation allows researchers to examine the relationship between cellular morphology and clinical observations. Unfortunately, most segmentation methods known today are limited to nuclei and cannot segmentate the cytoplasm. Material & Methods: We present a new network architecture Cyto R-CNN that is able to accurately segment whole cells (with both the nucleus and the cytoplasm) in bright-field images. We also present a new dataset CytoNuke, consisting of multiple thousand manual annotations of head and neck squamous cell carcinoma cells. Utilizing this dataset, we compared the performance of Cyto R-CNN to other popular cell segmentation algorithms, including QuPath's built-in algorithm, StarDist and Cellpose. To evaluate segmentation performance, we calculated AP50, AP75 and measured 17 morphological and staining-related features for all detected cells. We compared these measurements to the gold standard of manual segmentation using the Kolmogorov-Smirnov test. Results: Cyto R-CNN achieved an AP50 of 58.65% and an AP75 of 11.56% in whole-cell segmentation, outperforming all other methods (QuPath $19.46/0.91\%$; StarDist $45.33/2.32\%$; Cellpose $31.85/5.61\%$). Cell features derived from Cyto R-CNN showed the best agreement to the gold standard ($\bar{D} = 0.15$) outperforming QuPath ($\bar{D} = 0.22$), StarDist ($\bar{D} = 0.25$) and Cellpose ($\bar{D} = 0.23$). Conclusion: Our newly proposed Cyto R-CNN architecture outperforms current algorithms in whole-cell segmentation while providing more reliable cell measurements than any other model. This could improve digital pathology workflows, potentially leading to improved diagnosis. Moreover, our published dataset can be used to develop further models in the future.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑