Deep Learning on Multimodal Chemical and Whole Slide Imaging Data for Predicting Prostate Cancer Directly from Tissue Images.
Deep Learning on Multimodal Chemical and Whole Slide Imaging Data for Predicting Prostate Cancer Directly from Tissue Images.
复制标题
深度学习多模态化学和全切片成像数据，直接从组织图像预测前列腺癌。
DOI：
10.1021/jasms.2c00254
复制
发表时间：
2023-02-01
影响因子：
3.2
通讯作者：
Ovchinnikova, Olga S.
中科院分区：
文献类型：
--
作者：
Haque, Md Inzamam Ul;Mukherjee, Debangshu;Stopka, Sylwia A.;Agar, Nathalie Y. R.;Hinkle, Jacob;Ovchinnikova, Olga S.
前列腺癌是全球最常见的癌症之一，也是美国男性人群中第二大常见的癌症。在这里，我们开展了一项研究，将苏木精和伊红 (H&E) 染色的活检数据与相应组织的 MALDI 质谱成像数据相关联，以确定癌变区域及其独特的化学特征以及预测区域与原始病理注释的变化。我们通过深度学习从整个载玻片 H&E 染色数据的高分辨率光学显微照片中获取特征，并将它们与质谱成像 (MSI) 数据进行空间配准，以将化学特征与数据的组织解剖学相关联。然后，我们使用学习到的相关性，使用经过训练的配准 MSI 数据，根据观察到的 H&E 图像来预测前列腺癌。这种多模式方法可以以约 80% 的准确度预测癌变区域，这表明光学 H&E 特征与 MSI 中发现的化学信息之间存在相关性。我们表明，这种配对的多模态数据可用于在 H&E 数据上训练特征提取网络，从而无需获取昂贵的 MSI 数据，并且无需手动注释，从而节省了宝贵的时间。还发现两种化学生物标志物可以预测真实的癌症区域。这项研究表明，通过在共同配准的 MSI 数据的辅助下，直接根据现成的 H&E 染色活检图像来预测前列腺癌，有望改善患者的治疗轨迹。
Prostate cancer is one of the most common cancers globally and is the second most common cancer in the male population in the US. Here we develop a study based on correlating the hematoxylin and eosin (H&E)-stained biopsy data with MALDI mass-spectrometric imaging data of the corresponding tissue to determine the cancerous regions and their unique chemical signatures and variations of the predicted regions with original pathological annotations. We obtain features from high-resolution optical micrographs of whole slide H&E stained data through deep learning and spatially register them with mass spectrometry imaging (MSI) data to correlate the chemical signature with the tissue anatomy of the data. We then use the learned correlation to predict prostate cancer from observed H&E images using trained coregistered MSI data. This multimodal approach can predict cancerous regions with ~80% accuracy, which indicates a correlation between optical H&E features and chemical information found in MSI. We show that such paired multimodal data can be used for training feature extraction networks on H&E data which bypasses the need to acquire expensive MSI data and eliminates the need for manual annotation saving valuable time. Two chemical biomarkers were also found to be predicting the ground truth cancerous regions. This study shows promise in generating improved patient treatment trajectories by predicting prostate cancer directly from readily available H&E-stained biopsy images aided by coregistered MSI data.
登录
查看更多内容
影响因子：
28.1
作者：
Lu MY;Williamson DFK;Chen TY;Chen RJ;Barbieri M;Mahmood F
通讯作者：
Mahmood F
影响因子：
6.4
作者：
Steurer, Stefan;Borkowski, Carina;Schlueter, Hartmut
通讯作者：
Schlueter, Hartmut
影响因子：
4.8
作者：
Kurreck A;Vandergrift LA;Fuss TL;Habbel P;Agar NYR;Cheng LL
通讯作者：
Cheng LL
影响因子：
5.2
作者：
Chandramouli S;Leo P;Lee G;Elliott R;Davis C;Zhu G;Fu P;Epstein JI;Veltri R;Madabhushi A
通讯作者：
Madabhushi A
影响因子：
5.9
作者：
Andersen MK;Høiem TS;Claes BSR;Balluff B;Martin-Lorenzo M;Richardsen E;Krossa S;Bertilsson H;Heeren RMA;Rye MB;Giskeødegård GF;Bathen TF;Tessem MB
通讯作者：
Tessem MB