%A Wang,Chong %A Wei,Xiu-Li %A Li,Chen-Xi %A Wang,Yang-Zhen %A Wu,Yang %A Niu,Yan-Xiang %A Zhang,Chen %A Yu,Yi %D 2022 %J Frontiers in Oncology %C %F %G English %K hematological malignancies1,deep learning2,digital pathology3,weakly supervised4,hematopathology5 %Q %R 10.3389/fonc.2022.879308 %W %L %M %P %7 %8 2022-June-10 %9 Original Research %+ Chen Zhang,Department of Neurobiology, School of Basic Medical Sciences, Beijing Key Laboratory of Neural Regeneration and Repair, Advanced Innovation Center for Human Brain Protection, Capital Medical University,China,yywzfb_bme@outlook.com %+ Chen Zhang,Chinese Institute for Brain Research,China,yywzfb_bme@outlook.com %+ Yi Yu,School of Medical Engineering, Xinxiang Medical University,China,yywzfb_bme@outlook.com %+ Yi Yu,Henan Province Neural Sensing and Control Engineering Technology Research Center,China,yywzfb_bme@outlook.com %# %! Diagnosis of malignant hematological diseases %* %< %T Efficient and Highly Accurate Diagnosis of Malignant Hematological Diseases Based on Whole-Slide Images Using Deep Learning %U https://www.frontiersin.org/articles/10.3389/fonc.2022.879308 %V 12 %0 JOURNAL ARTICLE %@ 2234-943X %X Hematopoietic disorders are serious diseases that threaten human health, and the diagnosis of these diseases is essential for treatment. However, traditional diagnosis methods rely on manual operation, which is time consuming and laborious, and examining entire slide is challenging. In this study, we developed a weakly supervised deep learning method for diagnosing malignant hematological diseases requiring only slide-level labels. The method improves efficiency by converting whole-slide image (WSI) patches into low-dimensional feature representations. Then the patch-level features of each WSI are aggregated into slide-level representations by an attention-based network. The model provides final diagnostic predictions based on these slide-level representations. By applying the proposed model to our collection of bone marrow WSIs at different magnifications, we found that an area under the receiver operating characteristic curve of 0.966 on an independent test set can be obtained at 10× magnification. Moreover, the performance on microscopy images can achieve an average accuracy of 94.2% on two publicly available datasets. In conclusion, we have developed a novel method that can achieve fast and accurate diagnosis in different scenarios of hematological disorders.