人工智能技术在泌尿系结石中的应用与展望

李云鹏; 吕建林

doi:10.13201/j.issn.1001-1420.2022.12.014

人工智能技术在泌尿系结石中的应用与展望

李云鹏¹,
吕建林^1, ,

- 南京医科大学附属江宁医院泌尿外科(南京，210000)

详细信息

通讯作者: 吕建林，E-mail：ljlxx01@163.com

中图分类号: R691.4

收稿日期: 2021-12-22

刊出日期: 2022-12-06

Application and prospect of artificial intelligence technology in urinary calculi

LI Yunpeng¹,
LV Jianlin^1, ,

- Department of Urology, Jiangning Hospital of Nanjing Medical University, Nanjing, 210000, China

More Information

Corresponding author: LV Jianlin, E-mail: ljlxx01@163.com

Received Date: 22 December 2021

Publish Date: 06 December 2022

摘要

摘要: 人工智能(AI)是研究模拟、延伸和扩展人类智能的一门新的技术科学。随着数据储存、图像处理、模式识别和机器学习等技术的进步，AI技术在泌尿系结石的诊治方面应用广泛。基于AI的应用，可以使医务工作者的诊断更为精准，治疗更加个体化。然而，目前AI在临床应用中仍有一些不足之处需要进一步解决。本文就AI技术在泌尿系结石疾病诊疗中的应用及前景进行综述，并进一步探讨其局限性与未来的发展趋势。
- 人工智能 /
- 泌尿系结石 /
- 结石成分分析 /
- 体外冲击波碎石 /
- 经皮肾镜取石术
Abstract: Artificial intelligence (AI) is a new technological science that is researched and developed for simulating and expanding human intelligence. With the advancement of technologies such as data storage, image processing, pattern recognition, and machine learning, artificial intelligence technology has been widely used in the diagnosis and treatment of urinary calculi. The application of artificial intelligence can make the diagnosis of medical workers more accurate and the treatment more individualized. However, there are still some shortcomings in the clinical application of artificial intelligence that need to be further resolved. This article reviews the application and prospects of artificial intelligence technology in the diagnosis and treatment of urinary calculi diseases, and further discusses its limitations and future development trends.
- artificial intelligence /
- urinary calculi /
- stone composition analysis /
- extracorporeal shock wave lithotripsy /
- percutaneous nephrolithotomy

HTML全文

表 1 AI在泌尿系结石中的应用

作者	AI模型	预测准确率
Langkvist^[7]	DCNN	100%
Jendenber^[8]，Parakh^[9]	CNN	92%，90%
Perrot^[11]	ML	85.1%
Nithya^[13]，Poulaki^[15]	ANN	99.6%，92%
Hand^[16]	MSNN	79%
Seltzer^[18]	DL	88%

下载: 导出CSV

参考文献(26)

[1]	秦锋, 袁久洪. 人工智能在泌尿疾病诊断中的应用现状与趋势[J]. 生物医学工程学杂志, 2020, 37(2): 230-235. https://www.cnki.com.cn/Article/CJFDTOTAL-SWGC202002008.htm
[2]	Kulkarn I, Saga R. Artificial Intelligence in Medicine: Where Are We Now?[J]. Academic Radiol, 2020, 27(1): 62-70. doi: 10.1016/j.acra.2019.10.001
[3]	Sha H, Mila P. Artificial intelligence(AI)in urology-Current use and future directions: An iTRUE study[J]. Turkish J Urol, 2020, 46(Supp 1): S27-S39.
[4]	Kermany DS, Goldbaum M, Cai W, et al. Identifying medical diagnoses and treatable diseases by image-based deep learning[J]. Cell, 2018, 172(5): 1122-1131. e9. doi: 10.1016/j.cell.2018.02.010
[5]	Liang HY, Tsui BY, Ni H, et al. Evaluation and accuratediagnoses of pediatric diseases using artificial intelligence[J]. Nat Med, 2019, 25(3): 433-438. doi: 10.1038/s41591-018-0335-9
[6]	焦志灵, 徐国良, 李路鹏, 等. 经尿道输尿管镜钬激光碎石术后尿路感染调查及其对预后的影响[J]. 临床泌尿外科杂志, 2020, 35(5): 344-348. doi: 10.13201/j.issn.1001-1420.2020.05.003
[7]	Längkvist M, Jendeberg J, Thunberg P, et al. Computer aided detection of ureteral stones in thin slice computed tomography volumes using Convolutional Neural Networks[J]. Comput Biol Med, 2018, 97: 153-160. doi: 10.1016/j.compbiomed.2018.04.021
[8]	Jendeber G, Joha N. Differentiation of distal ureteral stones and pelvic phleboliths using a convolutional neural network[J]. Urolithiasis, 2021, 49(1): 41-49. doi: 10.1007/s00240-020-01180-z
[9]	Parakh A, Lee H, Lee JH, et al. Urinary stone detection on CT images using deep convolutional neural networks: evaluation of model performance and generalization[J]. Radiol Artif Intell, 2019, 1(4): e180066. doi: 10.1148/ryai.2019180066
[10]	伦晓璐, 刘宇保, 王永传, 等. 多镜联合手术治疗马蹄肾结石的临床疗效观察[J]. 临床泌尿外科杂志, 2021, 36(4): 293-296. doi: 10.13201/j.issn.1001-1420.2021.04.010
[11]	De Perro T, Thoma S. Differentiating kidney stones from phleboliths in unenhanced low-dose computed tomography using radiomics and machine learning[J]. Euro Radiol, 2019, 29(9): 4776-4782. doi: 10.1007/s00330-019-6004-7
[12]	Selvarani S, Rajendran P. Detection of Renal Calculi in Ultrasound Image Using Meta-Heuristic Support Vector Machine[J]. J Med Systems, 2019, 43(9): 300. doi: 10.1007/s10916-019-1407-1
[13]	Nithya A, Appathurai A, Venkatadri N, et al. Kidney disease detection and segmentation using artificialneural network and multi-kernel k-means clustering for ultra-sound images[J]. Meas J Int Meas Confed, 2020, 149: 300.
[14]	谢晓强, 陈斌, 林晓翰, 等. 双波源与单波源体外碎石机治疗肾及输尿管上段结石疗效的前瞻性双中心随机对照研究[J]. 临床泌尿外科杂志, 2020, 35(12): 949-953. doi: 10.13201/j.issn.1001-1420.2020.12.003
[15]	Poulaki S, Vassili S. Prediction of lower pole stone clearance after shock wave lithotripsy using an artificial neural network[J]. J Urolo, 2003, 169(4): 1250-1256. doi: 10.1097/01.ju.0000055624.65386.b9
[16]	Hand A, Rajash K. Development of a novel magnetic resonance imaging acquisition and analysis workflow for the quantification of shock wave lithotripsy-induced renal hemorrhagic injury[J]. Urolithiasis, 2017, 45(5): 507-513. doi: 10.1007/s00240-016-0959-5
[17]	Singla R, Lundeen C, Forbes C, et al. Fluoro-scopic targeting of renal calculi during extracorporeal shock-wave lithotripsy using a machine learning algorithm[J]. J Urol, 2019, 201(4): e474.
[18]	Seltzer R, Hamilton BD, Klett D, et al. The prediction of treatment success and complications ofshockwave lithotripsy using artificial intelligence[J]. J Endourol, 2019, 33: A291. doi: 10.1089/end.2018.0875
[19]	Viljoen A, Chaudhry R, Bycroft J. Renal stones[J]. Ann Clin Biochem, 2019, 56(1): 15-27.
[20]	Shabaniyan T, Parsaei H, Aminsharifi A, et al. An artificial intelligence-based clinical decision support system for large kidney stone treatment[J]. Australas Phys Eng Sci Med, 2019, 42(3): 771-779.
[21]	Taguchi K, Hamamoto S, Okada A, et al. Robot-assisted fluoroscopy versus ultrasound-guided renal access for nephrolithotomy: a phantom model benchtop study[J]. J Endourol, 2019, 33(12): 987-994.
[22]	Aminsharif A, Irani D, Tayebi S, et al. Predicting the postoperative outcome of percutaneous nephrolithotomy with machine learning system: software validation and comparative analysis with Guy's Stone Score and the CROES Nomogram[J]. J Endourol, 2020, 34(6): 692-699.
[23]	Kriegshauser JS, Silva AC, Paden RG, et al. Ex vivo renalstone characterization with single-source dual-energy computed tomography: a multiparametric approach[J]. Acad Radiol, 2016, 23(8): 969-976.
[24]	Kazemi Y, Mirroshandel SA. A novel method for predictingkidney stone type using ensemble learning[J]. Artif Intell Med, 2018, 84: 117-126.
[25]	Bejan CA, Lee DJ, Xu Y, et al. Performance of a natural language processing method to extract stone composition from the electronic health record[J]. Urology, 2019, 132: 56-62.
[26]	Hokamp NG, Lennartz S, Salem J, et al. Dose independent characterization of renalstones by means of dual energy computed tomography and machinelearning: an ex-vivo study[J]. Eur Radiol, 2020, 30(3): 1397-404.