人工智能在类器官研究中的应用进展与挑战

吴洪基, 王海霞, 汪玲, 罗小刚, 邹冬玲

  1. 1.重庆大学生物工程学院,重庆 400030
    2.重庆大学附属肿瘤医院妇科肿瘤中心,重庆 400030
    3.重庆市卵巢癌专病医学研究中心,重庆 400030
    4.重庆大学附属肿瘤医院,肿瘤转移与个体化诊治转化研究重庆市重点实验室,类器官转化研究实验室,重庆 400030
  • 收稿日期:2023-07-24 修回日期:2023-10-03 出版日期:2024-02-29 发布日期:2024-03-14
  • 通信作者: 邹冬玲
  • 作者简介:吴洪基(ORCID:0009-0007-4405-7411),硕士研究生在读。
  • 基金资助:
    国家自然科学基金(82073129);重庆市科技局项目(2023ZDXM029);重庆市科技局项目(2023MSXM043);重庆市科技局项目(cstc2022jxjl120039);宁夏回族自治区重点研发计划项目(2023BEG02037);重庆市教委科学技术研究项目(KJQN20230013);重庆大学附属肿瘤医院科研能力提升专项(2023nlts005)

摘要/Abstract

摘要:

类器官是一种优异的肿瘤和干细胞研究模型,对其生长或药筛等过程的各种类型数据进行分析,有助于提升对类器官本身以及所代表疾病的了解。但人工观察和筛选类器官以及使用传统统计学方法在处理类器官数据时,存在分析准确度与效率低、难度系数大、人工成本高以及带有一定主观性等问题。而人工智能在很多生物学和医学研究领域已被证明会产生卓越效果。将人工智能引入类器官研究,有助于提升研究的客观性、准确性和速度,从而使类器官能更好地实现疾病建模、药物筛选、个性化医疗等。首先,类器官图像数据的人工智能分析取得了显著进展。结合深度学习的图像分析能够更精准地捕捉类器官的微观结构和变化,提高对类器官形态和生长的自动识别能力,达到较高的准确度,节约研究时间与成本。其次,对于类器官的组学数据,人工智能技术的引入同样取得了重要突破:可提高数据的处理效率以及发现潜在的基因表达模式,为细胞发育和疾病机制的解析提供新的工具。再次,类器官其他类型的数据如电信号和光谱等通过人工智能技术可实现对类器官类型和状态客观的分类,为类器官的全面表征进行了有益的尝试。而在类器官重要应用领域—药物筛选方面,人工智能可为过程监测和结果预测提供强有力的支持。通过高内涵显微镜图像和深度学习模型,研究者们能够实时监测类器官对药物的响应,实现了对药物作用的非侵入性检测,使药物筛选更加精准和高效。然而,尽管人工智能在类器官研究中取得了显著成果,仍然存在一系列挑战。数据获取的难度、样本质量和样本量的不足、模型解释性的问题等制约了其广泛应用。为了克服这些问题,未来的研究需要致力于提高数据的一致性,增强模型解释性,并探索多模态数据融合的方法,以更全面、可靠地应用人工智能于类器官研究中。因此本文认为人工智能技术的引入为类器官研究带来了前所未有的机遇,也取得了明显的研究进展。然而,我们仍然需要跨学科的研究与合作,共同应对挑战,推动人工智能在类器官研究中的更深层次应用。未来,人工智能有望在类器官研究中发挥更大的作用,加速其向临床转化和精准治疗的应用进程。

关键词: 类器官, 人工智能, 机器学习, 精准医疗

Abstract:

Organoids, recognized as invaluable models in tumor and stem cell research, assume a pivotal role in the meticulous analysis of diverse datasets pertaining to their growth dynamics, drug screening processes and related phenomena. However, the manual scrutiny and conventional statistical methodologies employed in handling organoid data often grapple with challenges such as diminished precision and efficiency, heightened complexity, escalated human resource requirements, and a degree of subjectivity. Acknowledging the remarkable efficacy of artificial intelligence (AI) in the realms of biology and medicine, the incorporation of AI into organoid research stands poised to enhance the objectivity, precision and expediency of analyses. This integration empowers organoids to more effectively fulfill objectives such as disease modeling, drug screening and precision medicine. Notably, significant strides have been made in AI-driven analyses of organoid image data. The amalgamation of deep learning into image analysis facilitates a more meticulous delineation of the microstructural intricacies and nuanced changes within organoids, achieving a level of accuracy akin to that of experts. This not only elevates the precision of organoid morphology and growth recognition, but also contributes to substantial time and cost savings in research endeavors. Furthermore, the infusion of AI technology has yielded breakthroughs in the processing of organoid omics data, resulting in heightened efficiency in data processing and the identification of latent gene expression patterns. This furnishes novel tools for comprehending cellular development and unraveling the intricate mechanisms underlying various diseases. In addition to image data, AI techniques applied to diverse organoid datasets, encompassing electrical signals and spectra, have realized an unbiased classification of organoid types and states, embarking on a comprehensive journey towards characterizing organoids holistically. In the pivotal domain of drug screening for organoids, AI emerges as a stalwart companion, providing robust support for real-time process monitoring and result prediction. Leveraging high-content microscopy images and sophisticated deep learning models, researchers can dynamically monitor organoid responses to drugs, effecting non-invasive detection of drug impacts and amplifying the precision and efficiency of drug screening processes. Despite the significant strides made by AI in organoid research, challenges persist, encompassing hurdles in data acquisition, constraints in sample quality and quantity, and quandaries associated with model interpretability. Overcoming these challenges necessitates dedicated future research efforts aimed at enhancing data consistency, fortifying model interpretability, and exploring methodologies for the seamless fusion of multimodal data. Such endeavors are poised to usher in a more comprehensive and dependable application of AI in organoid research. In summation, the integration of AI technology introduces unparalleled opportunities to organoid research, resulting in noteworthy advancements. Nevertheless, interdisciplinary research and collaborative efforts remain imperative to navigate challenges and propel the more profound integration of AI into organoid research. The future holds promise for AI to assume an even more prominent role in advancing organoid research toward clinical translation and precision medicine.

Key words: Organoids, Artificial intelligence, Machine learning, Precision medicine

中图分类号: 

相关文章

[1] 刘洋, 胡奕炀, 刘月平, 牛淑瑶, 丁平安, 田园, 郭洪海, 杨沛刚, 张泽, 郑涛, 檀碧波, 范立侨, 李勇, 赵群. 人工智能辅助技术在胃癌新辅助化疗患者HER2表达评估中的价值[J]. 中国癌症杂志, 2023, 33(4): 377-387.
[2] 芦瑜, 席雨梦, 何晓明, 杨少坤, 张佳, 王雷, 何朝星, 向柏. 共培养策略在类器官研究中的应用进展[J]. 中国癌症杂志, 2023, 33(3): 293-302.
[3] 高鹤丽, 徐近, 陈洁, 虞先濬. 胰腺神经内分泌瘤的精准诊疗进展[J]. 中国癌症杂志, 2023, 33(11): 993-1001.
[4] 沈洁, 刘雅静, 莫淼, 周瑾, 王泽洲, 周昌明, 周世崇, 常才, 郑莹. 人工智能辅助超声对中国女性乳腺病灶识别的有效性研究[J]. 中国癌症杂志, 2023, 33(11): 1002-1008.
[5] 崔灵珺, 田超, 程梓轩, 郑佳彬, 苏菲, 谭煌英. 胃肠胰神经内分泌肿瘤临床前模型的研究进展[J]. 中国癌症杂志, 2022, 32(9): 779-785.
[6] 中国抗癌协会肿瘤多学科诊疗专业委员会, 中国抗癌协会肿瘤内分泌专业委员会. 肿瘤类器官诊治平台的质量控制标准中国专家共识(2022年版)[J]. 中国癌症杂志, 2022, 32(7): 657-668.
[7] 王若彤, 王欣, 沈波. 类器官在肿瘤转化医学中的应用和进展[J]. 中国癌症杂志, 2022, 32(11): 1105-1114.
[8] 徐文浩, 田熙, 艾合太木江·安外尔, 瞿元元, 施国海, 张海梁, 叶定伟. 人工智能在泌尿系统肿瘤中的应用研究进展[J]. 中国癌症杂志, 2022, 32(1): 68-74.
[9] 杨 鑫  , 章 真 . 基于深度学习的人工智能在数字病理学中的进展[J]. 中国癌症杂志, 2021, 31(2): 151-155.
[10] 张婷婷,渠 宁,郑 璞,等. 机器学习在甲状腺肿瘤诊疗中的应用[J]. 中国癌症杂志, 2017, 27(12): 992-995.