基于人工智能的矩阵式超大通量核酸检测系统
1. 中国计量大学, 信息工程学院, 浙江杭州 310018
2. 杭州安誉科技有限公司, 浙江杭州 310000
| 摘 要： | 自2019年底，新型冠状病毒肺炎在全世界广泛蔓延，中国采用精准防控方案，需要在最短时间内检测大量样本，特别是方舱、移动检测车等空间限制的特殊场所。因此提高设备单次核酸检测通量和提升检测速度显得十分重要。针对目前全世界最高通量的核酸检测仪器为96孔，如何在一台机器内增加通量而同时又减少扫描时间增加检测速度为关键核心技术。本文提出了创造性的使用矩阵的多分布式概念，将240孔检测通量设备分为了5个独立的子系统，既可以同时进行检测，在特殊情况下也可以单独运行。采用基于粒子群算法的智能调度算法智能识别各个独立分布子矩阵的状态进行控制，并结合基于荧光定量PCR的核酸快速检测技术，大大提高了核酸检测的效率。经实验，该设备实现240检测样本可以在50分钟完成，与传统核酸检测设备相比有较大提升。 |
| 关 键 词： | 新型冠状病毒肺炎; 矩阵的多分布式; 智能调度算法; PCR检测 |
| DOI： | 10.57237/j.cst.2024.01.001 |
View:
Downloads:
收稿日期: 2023-10-19
接受日期: 2023-11-13
在线出版日期: 2023-12-27
Matrix Ultra-Large Throughput Nucleic Acid Detection System Based on Artificial Intelligence
1. School of Information Engineering, China Jiliang University, Hangzhou 310018, China
2. Hangzhou Anyu Technologies Co., Ltd., Hangzhou 310000, China
| Abstract: | Since the end of 2019, the novel coronavirus pneumonia has spread widely around the world. China has adopted a precise prevention and control plan, which requires testing a large number of samples in the shortest possible time, especially in special places with limited space such as shelters and mobile testing vehicles. Therefore, it is very important to improve the single nucleic acid detection throughput of the equipment and increase the detection speed. Currently, the world's highest throughput nucleic acid detection instrument is 96-well. How to increase throughput in a machine while reducing scanning time and increasing detection speed is a key core technology. This paper proposes a creative multi-distribution concept using a matrix, which divides the 240-well detection throughput equipment into 5 independent subsystems, which can detect simultaneously or operate independently under special circumstances. The intelligent scheduling algorithm based on the particle swarm algorithm is used to intelligently identify the status of each independent distribution sub-matrix for control, and combined with the nucleic acid rapid detection technology based on fluorescence quantitative PCR, the efficiency of nucleic acid detection is greatly improved. After experiments, the equipment can complete the detection of 240 samples in 50 minutes, which is a great improvement compared with traditional nucleic acid detection equipment. |
| Keywords: | Novel Coronavirus Pneumonia; Multi-distribution of Matrices; Intelligent Scheduling Algorithm; PCR Test |
参考文献
| [1] | WHO. Novel Coronavirus (2019-n CoV) Situation Report-22. 2020. |
| [2] | Rothan H. A. and Byrareddy S. N., “The epidemiology and pathogenesis of coronavirusdisease (COVID-19) outbreak” J. Autoimmunity, vol. 109, May 2020. |
| [3] | 潘磊, 穆明, 杨平. “中国湖北省COVID-19消化系统症状患者的临床特征: 描述性, 横断面, 多中心研究,” Amer. J. Gastroenterol., 第115卷, 第5期, 第766-773页, 2020年5月. |
| [4] | 运城市财政局迅速行动支援核酸检测疫情防控工作 [J]. 山西财税, 2022, (04): 51. |
| [5] | 梁圣楠, 刘璇, 梅金红. 基于实时荧光RT-PCR法对新型冠状病毒核酸检测的研究 [J]. 病毒学报, 2020, 36(36): 1171-1176. |
| [6] | Rong X M, Yang L, Chu H D, Fan M. Effect of delay in diagnosis on transmission of COVID-19 [J]. Math Biosci Eng, 2020, 17(3): 2725-2740. |
| [7] | SHEN Y, SHENG V S, WANG L, et al. Empirical comparisons of deep learning networks on liver segmentation [J]. Comput Mater Con, 2020, 62(3): 1233-1247. |
| [8] | 吴树剑, 俞咏梅, 范莉芳等. 基于定量CT及临床危险因素列线图预测重症新型冠状病毒肺炎短期预后 [J]. 中国医学计算机成像杂志, 2023, 29(05): 498-504. |
| [9] | WANG Z, XIAO Y, LI Y, et al. Automatically discriminating and localizing COVID-19 from community-acquired pneumonia on chest X-rays [J]. Pattern Recogn, 2020, 110: 107613. |
| [10] | PATHAN S, SIDDALINGASWAMY P C, ALI T. Automated detection of COVID-19 from chest X-ray scans using an optimized CNN architecture [J]. Appl Soft Comput, 2021, 104(10223): 107238. |
| [11] | Tulin Ozturk, Muhammed Talo, Eylul Azra Yildirim, Ulas Baran Baloglu, Ozal Yildirim, and U Rajendra Acharya, Automated detection of covid-19 cases using deep neural networks with x-ray images. Comput. Biol. Med. 121(2020) 103792. |
| [12] | P. K. Harsh Panwar, Mohammad Khubeb Gupta, Ruben Morales Menendez Siddiqui, Vaishnavi Singh, Application of deep learning for fast detection of covid-19 in x-rays using ncovnet, Chaos Solitons Fractals 138(2020), 109944. |
| [13] | Shashank Vaid, Reza Kalantar, Mohit Bhandari, Deep learning covid-19 detection bias: accuracy through artificial intelligence, Int. Orthop. 44(2020) 1539–1542. |
| [14] | WANG L, KELLY B, LEE E H, et al. Multi-classifier-based identification of COVID-19 from chest computed tomography using generalizable and interpretable radiomics features [J]. Eur J of Radiol, 2021, 136: 109552. |
| [15] | 韩冬, 于勇, 贺太平等. 基于密度分布特征及机器学习诊断COVID 19相关性肺炎 [J]. 中国医学物理学杂志, 2021, 38(3): 387-391. |
