Deep learning for the prediction of early on-treatment response in metastatic colorectal cancer from serial medical imaging.
Deep learning for the prediction of early on-treatment response in metastatic colorectal cancer from serial medical imaging.
复制标题
DOI：
10.1038/s41467-021-26990-6
复制
发表时间：
2021-11-17
影响因子：
16.6
通讯作者：
Schwartz LH
中科院分区：
文献类型：
--
作者：
Lu L;Dercle L;Zhao B;Schwartz LH
在目前的临床实践中，肿瘤缓解评估通常基于连续计算机断层扫描（CT）扫描图像上的肿瘤大小变化。然而，在转移性结直肠癌（mCRC）中评价肿瘤对抗血管内皮生长因子治疗的反应是有限的，因为肿瘤的形态变化可能早于肿瘤大小变化。在这里，我们提出了一项利用深度学习（DL）网络来表征肿瘤形态学变化的分析，以评估mCRC患者的反应。我们回顾性分析了1,028例前瞻性纳入VEGFUR试验（NCT 00561470）的mCRC患者。我们发现DL网络能够预测mCRC的早期治疗反应，并且表现出比基于大小的对应物更好的性能，C指数：0.649（95% CI：0.619，0.679）vs. 0.627（95% CI：0.567，0.638），p = 0.009，z检验。DL网络与基于尺寸的方法学的整合可以进一步将预测性能提高到C-Index：0.694（95%CI：0.661，0.720），这上级仅基于尺寸/DL的模型（所有p < 0.001，z检验）。我们的研究表明，DL网络可以提供一种非侵入性的手段，定量和全面表征肿瘤形态学变化，这可能有利于个性化的早期治疗决策。在转移性结直肠癌（mCRC）中评价肿瘤对抗血管内皮生长因子治疗的反应是有限的，因为肿瘤的形态学变化可能比肿瘤大小变化更早发生或更关键。在这里，作者提出了一项利用深度学习网络来表征肿瘤形态变化以及肿瘤大小变化的分析，以评估mCRC患者的反应。
In current clinical practice, tumor response assessment is usually based on tumor size change on serial computerized tomography (CT) scan images. However, evaluation of tumor response to anti-vascular endothelial growth factor therapies in metastatic colorectal cancer (mCRC) is limited because morphological change in tumor may occur earlier than tumor size change. Here we present an analysis utilizing a deep learning (DL) network to characterize tumor morphological change for response assessment in mCRC patients. We retrospectively analyzed 1,028 mCRC patients who were prospectively included in the VELOUR trial (NCT00561470). We found that DL network was able to predict early on-treatment response in mCRC and showed better performance than its size-based counterpart with C-Index: 0.649 (95% CI: 0.619,0.679) vs. 0.627 (95% CI: 0.567,0.638), p = 0.009, z-test. The integration of DL network with size-based methodology could further improve the prediction performance to C-Index: 0.694 (95% CI: 0.661,0.720), which was superior to size/DL-based-only models (all p < 0.001, z-test). Our study suggests that DL network could provide a noninvasive mean for quantitative and comprehensive characterization of tumor morphological change, which may potentially benefit personalized early on-treatment decision making. Evaluation of tumor response to antivascular endothelial growth factor therapies in metastatic colorectal cancer (mCRC) is limited because morphological change in tumor may occur earlier or be more critical than tumor size change. Here, the authors present an analysis utilizing a deep learning network to characterize tumor morphological change as well as tumor size changes for response assessment in mCRC patients.
登录
查看更多内容
影响因子：
120.7
作者：
Chun, Yun Shin;Vauthey, Jean-Nicolas;Boonsirikamchai, Piyaporn;Maru, Dipen M.;Kopetz, Scott;Palavecino, Martin;Curley, Steven A.;Abdalla, Eddie K.;Kaur, Harmeet;Charnsangavej, Chusilp;Loyer, Evelyne M.
通讯作者：
Loyer, Evelyne M.
影响因子：
8.4
作者：
Eisenhauer, E. A.;Therasse, P.;Verweij, J.
通讯作者：
Verweij, J.
影响因子：
50.5
作者：
Lassau, N.;Coiffier, B.;Koscielny, S.
通讯作者：
Koscielny, S.
影响因子：
45.3
作者：
Choi, Haesun;Charnsangavej, Chuslip;Benjamin, Robert S.
通讯作者：
Benjamin, Robert S.
影响因子：
64.8
作者：
Esteva A;Kuprel B;Novoa RA;Ko J;Swetter SM;Blau HM;Thrun S
通讯作者：
Thrun S