Shin Hyunku, Oh Seunghyun, Hong Soonwoo, Kang Minsung, Kang Daehyeon, Ji Yong-Gu, Choi Byeong Hyeon, Kang Ka-Won, Jeong Hyesun, Park Yong, Hong Sunghoi, Kim Hyun Koo, Choi Yeonho
Department of Bio-convergence Engineering, Korea University, Seoul 02841, Republic of Korea.
School of Biomedical Engineering, Korea University, Seoul 02841, Republic of Korea.
ACS Nano. 2020 May 26;14(5):5435-5444. doi: 10.1021/acsnano.9b09119. Epub 2020 Apr 17.
Lung cancer has a high mortality rate, but an early diagnosis can contribute to a favorable prognosis. A liquid biopsy that captures and detects tumor-related biomarkers in body fluids has great potential for early-stage diagnosis. Exosomes, nanosized extracellular vesicles found in blood, have been proposed as promising biomarkers for liquid biopsy. Here, we demonstrate an accurate diagnosis of early-stage lung cancer, using deep learning-based surface-enhanced Raman spectroscopy (SERS) of the exosomes. Our approach was to explore the features of cell exosomes through deep learning and figure out the similarity in human plasma exosomes, without learning insufficient human data. The deep learning model was trained with SERS signals of exosomes derived from normal and lung cancer cell lines and could classify them with an accuracy of 95%. In 43 patients, including stage I and II cancer patients, the deep learning model predicted that plasma exosomes of 90.7% patients had higher similarity to lung cancer cell exosomes than the average of the healthy controls. Such similarity was proportional to the progression of cancer. Notably, the model predicted lung cancer with an area under the curve (AUC) of 0.912 for the whole cohort and stage I patients with an AUC of 0.910. These results suggest the great potential of the combination of exosome analysis and deep learning as a method for early-stage liquid biopsy of lung cancer.
肺癌死亡率很高，但早期诊断有助于获得良好的预后。一种能够捕获和检测体液中肿瘤相关生物标志物的液体活检技术在早期诊断方面具有巨大潜力。血液中发现的纳米级细胞外囊泡——外泌体，已被认为是液体活检中有前景的生物标志物。在此，我们展示了利用基于深度学习的外泌体表面增强拉曼光谱（SERS）对早期肺癌进行准确诊断。我们的方法是通过深度学习探索细胞外泌体的特征，并找出人血浆外泌体中的相似性，而无需学习不充分的人类数据。该深度学习模型使用源自正常和肺癌细胞系的外泌体的SERS信号进行训练，能够以95%的准确率对它们进行分类。在43名患者（包括I期和II期癌症患者）中，深度学习模型预测，90.7%患者的血浆外泌体与肺癌细胞外泌体的相似性高于健康对照的平均值。这种相似性与癌症进展成正比。值得注意的是，该模型对整个队列预测肺癌的曲线下面积（AUC）为0.912，对I期患者预测肺癌的AUC为0.910。这些结果表明，外泌体分析与深度学习相结合作为肺癌早期液体活检方法具有巨大潜力。
