A deep learning based strategy for identifying and associating mitotic activity with gene expression derived risk categories in estrogen receptor positive breast cancers.
A deep learning based strategy for identifying and associating mitotic activity with gene expression derived risk categories in estrogen receptor positive breast cancers.
复制标题
DOI：
10.1002/cyto.a.23065
复制
发表时间：
2017-06
期刊：
影响因子：
--
通讯作者：
Madabhushi A
中科院分区：
文献类型：
--
作者：
Romo-Bucheli D;Janowczyk A;Gilmore H;Romero E;Madabhushi A
早期雌激素受体阳性 (ER1) 乳腺癌的治疗和管理因难以识别需要辅助化疗的患者与对激素治疗有反应的患者而受到阻碍。为了区分侵袭性较高和侵袭性较小的乳腺肿瘤（这是选择适当治疗计划的基本标准），通常采用 Oncotype DX (ODX) 和其他基因表达测试。这些基因表达测试虽然信息丰富，但价格昂贵，具有组织破坏性，并且需要专门的设施。 Bloom-Richardson (BR) 分级是乳腺癌分级中常用的方案，已被证明与 Oncotype DX 风险评分相关。不幸的是，研究还表明，BR 等级决定了观察者之间存在显着的差异。 BR 分级的组成类别之一是有丝分裂指数。本研究的目标是开发一种深度学习 (DL) 分类器，以从 ER+ 乳腺癌的整个幻灯片图像中识别有丝分裂图，假设 DL 分类器识别的有丝分裂数量将与相应的 Oncotype DX 风险类别相关。有丝分裂检测器使用 6 倍验证设置在 AMIDA 有丝分裂数据集中产生的平均 F 分数为 0.556。对于具有相应 Oncotype DX 评分的早期 ER+ 乳腺癌的 174 个完整幻灯片图像队列，发现 DL 分类器识别的有丝分裂数量的分布在高风险组与低 Oncotype DX 风险组之间存在显着差异 (P < 0.01)。使用 ODX 评分和组织学分级对其他风险组进行比较，也发现呈现显着不同的自动有丝分裂分布。此外，支持向量机分类器经过训练，使用 DL 分类器确定的有丝分裂计数来区分低/高 Oncotype DX 风险类别，分类准确率达到 83.19%。
The treatment and management of early stage estrogen receptor positive (ER1) breast cancer is hindered by the difficulty in identifying patients who require adjuvant chemotherapy in contrast to those that will respond to hormonal therapy. To distinguish between the more and less aggressive breast tumors, which is a fundamental criterion for the selection of an appropriate treatment plan, Oncotype DX (ODX) and other gene expression tests are typically employed. While informative, these gene expression tests are expensive, tissue destructive, and require specialized facilities. Bloom-Richardson (BR) grade, the common scheme employed in breast cancer grading, has been shown to be correlated with the Oncotype DX risk score. Unfortunately, studies have also shown that the BR grade determined experiences notable inter-observer variability. One of the constituent categories in BR grading is the mitotic index. The goal of this study was to develop a deep learning (DL) classifier to identify mitotic figures from whole slides images of ER+ breast cancer, the hypothesis being that the number of mitoses identified by the DL classifier would correlate with the corresponding Oncotype DX risk categories. The mitosis detector yielded an average F-score of 0.556 in the AMIDA mitosis dataset using a 6-fold validation setup. For a cohort of 174 whole slide images with early stage ER+ breast cancer for which the corresponding Oncotype DX score was available, the distributions of the number of mitoses identified by the DL classifier was found to be significantly different between the high vs low Oncotype DX risk groups (P < 0.01). Comparisons of other risk groups, using both ODX score and histological grade, were also found to present significantly different automated mitoses distributions. Additionally, a support vector machine classifier trained to separate low/ high Oncotype DX risk categories using the mitotic count determined by the DL classifier yielded a 83.19% classification accuracy.
登录
查看更多内容
DOI：
10.1097/pai.0000000000000248
发表时间：
2016
期刊：
Applied immunohistochemistry & molecular morphology : AIMM
影响因子：
--
作者：
Khoury T;Huang X;Chen X;Wang D;Liu S;Opyrchal M
通讯作者：
Opyrchal M
影响因子：
2.4
作者：
Wang, Haibo;Cruz-Roa, Angel;Madabhushi, Anant
通讯作者：
Madabhushi, Anant
影响因子：
3
作者：
Chang H;Fontenay GV;Han J;Cong G;Baehner FL;Gray JW;Spellman PT;Parvin B
通讯作者：
Parvin B
影响因子：
7.5
作者：
Acs, Geza;Kiluk, John;Laronga, Christine
通讯作者：
Laronga, Christine
影响因子：
10.6
作者：
Larsen, Anders Boesen Lindbo;Vestergaard, Jacob Schack;Larsen, Rasmus
通讯作者：
Larsen, Rasmus