Deep learning assisted mitotic counting for breast cancer
Deep learning assisted mitotic counting for breast cancer
复制标题
DOI：
10.1038/s41374-019-0275-0
复制
发表时间：
2019-11-01
影响因子：
5
通讯作者：
van der Laak, Jeroen A. W. M.
中科院分区：
文献类型：
--
作者：
Balkenhol, Maschenka C. A.;Tellez, David;van der Laak, Jeroen A. W. M.
作为常规组织学分级的一部分，对于每种浸润性乳腺癌，通过计算具有最高增殖活性的（视觉选择的）区域中的有丝分裂来评估有丝分裂计数。由于此过程容易受到主观影响，本研究将视觉有丝分裂计数与基于深度学习的自动有丝分裂计数和全自动热点选择进行比较。本研究使用了两个队列。 A 组包括 90 个前瞻性纳入的肿瘤，这些肿瘤是根据常规载玻片诊断期间给出的有丝分裂频率评分选择的。这位病理学家还评估了预选热点内的整个幻灯片图像 (WSI) 中这些肿瘤的有丝分裂计数。第二位观察者对该队列执行了相同的程序。预选的热点由卷积神经网络 (CNN) 生成，该网络经过训练可检测数字化苏木精和伊红 (H&E) 切片中的所有有丝分裂像。第二组由多中心、回顾性 TNBC 组（n = 298）组成，其中有丝分裂计数由三名独立观察者在载玻片上评估。相同的 CNN 应用于该队列，并将热点中有丝分裂图的绝对数量与观察者的平均有丝分裂数进行比较。 A 组中载玻片评估的观察者间基线一致性良好（kappa 0.689；95% CI 0.580-0.799）。在 WSI 中使用 CNN 生成的热点，一致性分数增加到 0.814 (95% CI 0.719-0.909)。 CNN 的自动计数与预定义热点区域中的观察者计数相比，得出的平均 kappa 为 0.724。我们的结论是，手动有丝分裂计数不受评估方式（载玻片、WSI）的影响，并且在 WSI 中计数有丝分裂图是可行的。使用预定义的热点区域可显着提高再现性。此外，有丝分裂评分的全自动评估似乎是可行的，不会引入额外的偏差或变异性。
As part of routine histological grading, for every invasive breast cancer the mitotic count is assessed by counting mitoses in the (visually selected) region with the highest proliferative activity. Because this procedure is prone to subjectivity, the present study compares visual mitotic counting with deep learning based automated mitotic counting and fully automated hotspot selection. Two cohorts were used in this study. Cohort A comprised 90 prospectively included tumors which were selected based on the mitotic frequency scores given during routine glass slide diagnostics. This pathologist additionally assessed the mitotic count in these tumors in whole slide images (WSI) within a preselected hotspot. A second observer performed the same procedures on this cohort. The preselected hotspot was generated by a convolutional neural network (CNN) trained to detect all mitotic figures in digitized hematoxylin and eosin (H&E) sections. The second cohort comprised a multicenter, retrospective TNBC cohort (n = 298), of which the mitotic count was assessed by three independent observers on glass slides. The same CNN was applied on this cohort and the absolute number of mitotic figures in the hotspot was compared to the averaged mitotic count of the observers. Baseline interobserver agreement for glass slide assessment in cohort A was good (kappa 0.689; 95% CI 0.580-0.799). Using the CNN generated hotspot in WSI, the agreement score increased to 0.814 (95% CI 0.719-0.909). Automated counting by the CNN in comparison with observers counting in the predefined hotspot region yielded an average kappa of 0.724. We conclude that manual mitotic counting is not affected by assessment modality (glass slides, WSI) and that counting mitotic figures in WSI is feasible. Using a predefined hotspot area considerably improves reproducibility. Also, fully automated assessment of mitotic score appears to be feasible without introducing additional bias or variability.