A multi-resolution model for histopathology image classification and localization with multiple instance learning.

A multi-resolution model for histopathology image classification and localization with multiple instance learning.
复制标题

通过多个实例学习的组织病理学图像分类和本地化的多分辨率模型。

DOI:
10.1016/j.compbiomed.2021.104253
复制
发表时间:
2021-04
影响因子:
7.7
通讯作者:
Arnold CW
Arnold CW
中科院分区:
工程技术2区
文献类型:
--
作者:
Li J;Li W;Sisk A;Ye H;Wallace WD;Speier W;Arnold CW

文献摘要

参考文献

被引文献

相似文献

大量的组织病理学图像已被数字化为高分辨率的完整切片图像,这为开发计算图像分析工具提供了机会,以减少病理学家的工作量,并潜在地改善观察者之间和内部的一致性。以往关于整体幻灯片图像分析的工作主要集中在对预先选定的小范围感兴趣区域进行分类或分割,这需要细粒度的标注,并且对于大规模的整体幻灯片分析来说是非常重要的。在本文中,我们提出了一个多分辨率多实例学习模型,该模型利用显著图来检测可疑区域以进行细粒度的等级预测。与依赖昂贵的区域或像素级注释不同,我们的模型可以端到端地训练,只使用幻灯片级别的标签。该模型是在包含830名患者的20,229张切片的大规模前列腺活检数据集上开发的。该模型对良性、低级别(1级)和高级别(≥2级)的预测准确率为92.7%,Kappa值为81.8%,受试者工作特征曲线下面积为98.2%,良、恶性判别的平均准确率(AP)为97.4%。对于外部数据集上的癌症检测,该模型获得了99.4%的AUROC和99.8%的AP。
Large numbers of histopathological images have been digitized into high resolution whole slide images, opening opportunities in developing computational image analysis tools to reduce pathologists’ workload and potentially improve inter- and intra- observer agreement. Most previous work on whole slide image analysis has focused on classification or segmentation of small preselected regions-of-interest, which requires fine-grained annotation and is non-trivial to extend for large-scale whole slide analysis. In this paper, we proposed a multi-resolution multiple instance learning model that leverages saliency maps to detect suspicious regions for fine-grained grade prediction. Instead of relying on expensive region- or pixel-level annotations, our model can be trained end-to-end with only slide-level labels. The model is developed on a large-scale prostate biopsy dataset containing 20,229 slides from 830 patients. The model achieved 92.7% accuracy, 81.8% Cohen’s Kappa for benign, low grade (i.e. Grade group 1) and high grade (i.e. Grade group ≥ 2) prediction, an area under the receiver operating characteristic curve (AUROC) of 98.2% and an average precision (AP) of 97.4 % for differentiating malignant and benign slides. The model obtained an AUROC of 99.4% and an AP of 99.8% for cancer detection on an external dataset.
DOI: 10.3390/cancers10080249
发表时间: 2018-07-28
期刊: Cancers
影响因子: 5.2
作者:
Chaddad A;Kucharczyk MJ;Niazi T
通讯作者: Niazi T
DOI: 10.1016/j.artint.2013.06.003
发表时间: 2013-08-01
影响因子: 14.4
作者:
Amores, Jaume
通讯作者: Amores, Jaume
DOI: 10.1016/j.patcog.2017.10.009
发表时间: 2018-05-01
影响因子: 8
作者:
Carbonneau, Marc-Andre;Cheplygina, Veronika;Gagnon, Ghyslain
通讯作者: Gagnon, Ghyslain
DOI: 10.1016/j.media.2019.03.009
发表时间: 2019-05-01
影响因子: 10.9
作者:
Cheplygina, Veronika;de Bruijne, Marleen;Pluim, Josien P. W.
通讯作者: Pluim, Josien P. W.
DOI: 10.1016/j.eururo.2015.06.046
发表时间: 2016-03
期刊: EUROPEAN UROLOGY
影响因子: 23.4
作者:
Epstein, Jonathan I.;Zelefsky, Michael J.;Sjoberg, Daniel D.;Nelson, Joel B.;Egevad, Lars;Magi-Galluzzi, Cristina;Vickers, Andrew J.;Parwani, Anil V.;Reuter, Victor E.;Fine, Samson W.;Eastham, James A.;Wiklund, Peter;Han, Misop;Reddy, Chandana A.;Ciezki, Jay P.;Nyberg, Tommy;Klein, Eric A.
通讯作者: Klein, Eric A.