Research advances of CT and AI technology in predicting the composition of urinary calculi
-
摘要: 尿石症是泌尿外科最常见的一种疾病,且患病率逐年增长。因此,对结石的诊断、治疗、预防成为泌尿外科医生主要的工作。结石成分的分析结果通常在术后才能获得,这对个性化治疗方案的选择无明显益处。过去,国内外学者主要使用结石的CT值、有效原子序数或双能量比等参数在体内外区分结石成分。近5年,越来越多的研究者利用分类算法、神经网络或预测模型判断结石的成分及性质,其预测的效率及准确性均较前显著提升。本文综述了电子计算机断层扫描和人工智能技术预测泌尿系结石成分的研究进展。Abstract: Urolithiasis is one of the most common diseases in urology, and the prevalence rate is increasing year by year. Therefore, the diagnosis, treatment and prevention of stones has become a major task for urologists. The results of stone composition analysis are usually not available until surgery, which does not provide any significant benefit in the selection of individual treatment plans. In the past, scholars at home and abroad mainly used parameters such as CT value, effective atomic number or dual energy ratio of stones to differentiate stone composition in vivo and ex vivo. In the last five years, an increasing number of researchers have used classification algorithms, neural networks or predictive models to determine the composition and nature of stones, and their predictions have become significantly more efficient and accurate than before. This paper reviews the progress of research in predicting the composition of urinary stones by using computed tomography (CT) and artificial intelligence (AI) techniques.
-
Key words:
- urinary calculi /
- stone composition /
- prediction /
- computed tomography /
- artificial intelligence
-
[1] Hokamp NG, Lennartz S, Salem J, et al. Dose independent characterization of renal stones by means of dual energy computed tomography and machine learning: an ex-vivo study[J]. Eur Radiol, 2020, 30(3): 1397-1404. doi: 10.1007/s00330-019-06455-7
[2] Eisner BH, Goldfarb DS. A nomogram for the prediction of kidney stone recurrence[J]. J Am Soc Nephrol, 2014, 25(12): 2685-2687. doi: 10.1681/ASN.2014060631
[3] Espinosa-Ortiz EJ, Eisner BH, Lange D, et al. Current insights into the mechanisms and management of infection stones[J]. Nat Rev Urol, 2019, 16(1): 35-53. doi: 10.1038/s41585-018-0120-z
[4] Kang DH, Cho KS, Ham WS, et al. Ureteral stenting can be a negative predictor for successful outcome following shock wave lithotripsy in patients with ureteral stones[J]. Investig Clin Urol, 2016, 57(6): 408-416. doi: 10.4111/icu.2016.57.6.408
[5] Chatterjee P, Chakraborty A, Mukherjee AK. Phase composition and morphological characterization of human kidney stones using IR spectroscopy, scanning electron microscopy and X-ray Rietveld analysis[J]. Spectrochim Acta A Mol Biomol Spectrosc, 2018, 200: 33-42. doi: 10.1016/j.saa.2018.04.005
[6] Batchelar DL, Chun SS, Wollin TA, et al. Predicting urinary stone composition using X-ray coherent scatter: a novel technique with potential clinical applications[J]. J Urol, 2002, 168(1): 260-265. doi: 10.1016/S0022-5347(05)64904-X
[7] Hidas G, Eliahou R, Duvdevani M, et al. Determination of renal stone composition with dual-energy CT: in vivo analysis and comparison with x-ray diffraction[J]. Radiology, 2010, 257(2): 394-401. doi: 10.1148/radiol.10100249
[8] Türk C, Petřík A, Sarica K, et al. EAU guidelines on diagnosis and conservative management of urolithiasis[J]. Eur Urol, 2016, 69(3): 468-474. doi: 10.1016/j.eururo.2015.07.040
[9] Evan AP. Physiopathology and etiology of stone formation in the kidney and the urinary tract[J]. Pediatr Nephrol, 2010, 25(5): 831-841. doi: 10.1007/s00467-009-1116-y
[10] Moran ME, Abrahams HM, Burday DE, et al. Utility of oral dissolution therapy in the management of referred patients with secondarily treated uric acid stones[J]. Urology, 2002, 59(2): 206-210. doi: 10.1016/S0090-4295(01)01499-6
[11] Graser A, Johnson TR, Bader M, et al. Dual energy CT characterization of urinary calculi: initial in vitro and clinical experience[J]. Invest Radiol, 2008, 43(2): 112-119. doi: 10.1097/RLI.0b013e318157a144
[12] Zheng J, Yu H, Batur J, et al. A multicenter study to develop a non-invasive radiomic model to identify urinary infection stone in vivo using machine-learning[J]. Kidney Int, 2021, 100(4): 870-880. doi: 10.1016/j.kint.2021.05.031
[13] 苏晓伟, 王大明, 丁德茂, 等. 感染性结石的相关临床易感因素研究[J]. 临床泌尿外科杂志, 2021, 36(4): 284-287. doi: 10.13201/j.issn.1001-1420.2021.04.008
[14] 张艳, 李纲. 全体积CT纹理分析在泌尿系结石的临床应用研究[J]. 中华泌尿外科杂志, 2021, 36(7): 543-548. https://www.cnki.com.cn/Article/CJFDTOTAL-LCMW202107008.htm
[15] Yilmaz S, Sindel T, Arslan G, et al. Renal colic: comparison of spiral CT, US and IVU in the detection of ureteral calculi[J]. Eur Radiol, 1998, 8(2): 212-217. doi: 10.1007/s003300050364
[16] Harrington K, Torreggiani W. CT analysis of renal stone composition: a novel and non invasive method to analyse stones[J]. Ir Med J, 2014, 107(3): 69.
[17] Nakada SY, Hoff DG, Attai S, et al. Determination of stone composition by noncontrast spiral computed tomography in the clinical setting[J]. Urology, 2000, 55(6): 816-819. doi: 10.1016/S0090-4295(00)00518-5
[18] 陈志强, 周哲, 叶章群, 等. 螺旋CT判定尿结石成分的体外研究[J]. 中华泌尿外科杂志, 2021, 36(10): 35-37. https://www.cnki.com.cn/Article/CJFDTOTAL-LCMW200510014.htm
[19] Celik S, Sefik E, Basmacı I, et al. A novel method for prediction of stone composition: the average and difference of Hounsfield units and their cut-off values[J]. Int Urol Nephrol, 2018, 50(8): 1397-1405. doi: 10.1007/s11255-018-1929-3
[20] 李炯明, 王光, 刘建和, 等. 螺旋CT扫描预测上尿路结石成分的体内研究[J]. 中华泌尿外科杂志, 2021, 36(2): 98-100. https://www.cnki.com.cn/Article/CJFDTOTAL-LCMW201002007.htm
[21] Lidén M. A new method for predicting uric acid composition in urinary stones using routine single-energy CT[J]. Urolithiasis, 2018, 46(4): 325-332. doi: 10.1007/s00240-017-0994-x
[22] Lee JS, Cho KS, Lee SH, et al. Stone heterogeneity index on single-energy noncontrast computed tomography can be a positive predictor of urinary stone composition[J]. PLoS One, 2018, 13(4): e0193945. doi: 10.1371/journal.pone.0193945
[23] 汝建, 康露, 向映光, 等. 宝石能谱CT GSI成像和常规成像在上腹部应用价值的对比研究[J]. 现代生物医学进展, 2018, 18(15): 2930-2933, 2941. https://www.cnki.com.cn/Article/CJFDTOTAL-SWCX201815029.htm
[24] 黄科峰, 周宝成, 黄金山, 等. 能谱CT有效平均原子序数对离体尿路结石成分分析的前瞻性研究[J]. 临床军医杂志, 2011, 39(4): 615-617, 816. doi: 10.3969/j.issn.1671-3826.2011.04.05
[25] Zhang S, Huang Y, Wu W, et al. Trends in urinary stone composition in 23, 182 stone analyses from 2011 to 2019: a high-volume center study in China[J]. World J Urol, 2021, 39(9): 3599-3605. doi: 10.1007/s00345-021-03680-y
[26] Blaschko SD, Miller J, Chi T, et al. Microcomposition of human urinary calculi using advanced imaging techniques[J]. J Urol, 2013, 189(2): 726-734. doi: 10.1016/j.juro.2012.09.098
[27] Ogawa N, Sato S, Ida K, et al. Evaluation of urinary stone composition and differentiation between urinary stones and phleboliths using single-source dual-energy computed tomography[J]. Acta Med Okayama, 2017, 71(2): 91-96.
[28] 周云, 钱仲余. 能谱CT有效平均原子序数对尿路结石成分分析[J]. 影像技术, 2014, 26(6): 40-41. doi: 10.3969/j.issn.1001-0270.2014.06.16
[29] 甘毅, 徐志锋, 潘爱珍, 等. 能谱CT有效原子序数对泌尿系结石成分的诊断价值[J]. 现代医用影像学, 2021, 30(11): 2070-2072. doi: 10.3969/j.issn.1006-7035.2021.11.026
[30] Rompsaithong U, Jongjitaree K, Korpraphong P, et al. Characterization of renal stone composition by using fast kilovoltage switching dual-energy computed tomography compared to laboratory stone analysis: a pilot study[J]. Abdom Radiol(NY), 2019, 44(3): 1027-1032. doi: 10.1007/s00261-018-1787-6
[31] Bonatti M, Lombardo F, Zamboni GA, et al. Renal stones composition in vivo determination: comparison between 100/Sn140 kV dual-energy CT and 120 kV single-energy CT[J]. Urolithiasis, 2017, 45(3): 255-261. doi: 10.1007/s00240-016-0905-6
[32] Matlaga BR, Kawamoto S, Fishman E. Dual source computed tomography: a novel technique to determine stone composition[J]. Urology, 2008, 72(5): 1164-1168. doi: 10.1016/j.urology.2008.03.051
[33] 凃备武, 周洁, 李惠民, 等. 泌尿系结石成分的体内双源双能量CT分析[J]. 中国医学计算机成像杂志, 2013, 19(1): 57-60. https://www.cnki.com.cn/Article/CJFDTOTAL-YJTY201301018.htm
[34] 黎川, 傅强, 梁勇, 等. 双源CT预测泌尿系统结石化学成分的临床价值[J]. 第三军医大学学报, 2015, 37(6): 568-572. doi: 10.16016/j.1000-5404.201409123
[35] 张学斌, 李汉忠, 孙昊, 等. 双源CT体内预测尿路结石成分的临床应用研究(附40例报告)[J]. 临床泌尿外科杂志, 2021, 36(2): 93-96. https://www.cnki.com.cn/Article/CJFDTOTAL-LCMW201402002.htm
[36] 曾宪春, 江杰, 吴莉, 等. 双源CT双能量成像体外分析泌尿系结石成分[J]. 中国医学影像学杂志, 2015, 23(2): 96-99. https://www.cnki.com.cn/Article/CJFDTOTAL-ZYYZ201502005.htm
[37] Zhang GM, Sun H, Xue HD, et al. Prospective prediction of the major component of urinary stone composition with dual-source dual-energy CT in vivo[J]. Clin Radiol, 2016, 71(11): 1178-1183.
[38] Mahalingam H, Lal A, Mandal AK, et al. Evaluation of low-dose dual energy computed tomography for in vivo assessment of renal/ureteric calculus composition[J]. Korean J Urol, 2015, 56(8): 587-593.
[39] Mussmann B, Hardy M, Jung H, et al. Can dual energy CT with fast kv-switching determine renal stone composition accurately?[J]. Acad Radiol, 2021, 28(3): 333-338.
[40] Rudenko V, Serova N, Kapanadze L, et al. Dual-energy computed tomography for stone type assessment: a pilot study of dual-energy computed tomography with five indices[J]. J Endourol, 2020, 34(9): 893-899.
[41] 苏鸿林, 吴小辉, 熊晓玲, 等. 双能量能谱CT扫描诊断尿路结石成分的临床价值[J]. 实用医技杂志, 2021, 28(8): 990-992. https://www.cnki.com.cn/Article/CJFDTOTAL-SYYJ202108018.htm
[42] 蔡磊, 叶冬晖, 陈剑锋, 等. 双能CT在人体泌尿系结石成分分析中的价值[J]. 现代泌尿外科杂志, 2021, 26(7): 578-581. https://www.cnki.com.cn/Article/CJFDTOTAL-MNWK202107008.htm
[43] Yang B, Veneziano D, Somani BK. Artificial intelligence in the diagnosis, treatment and prevention of urinary stones[J]. Curr Opin Urol, 2020, 30(6): 782-787.
[44] Mannil M, von Spiczak J, Hermanns T, et al. Three-Dimensional texture analysis with machine learning provides incremental predictive information for successful shock wave lithotripsy in patients with kidney stones[J]. J Urol, 2018, 200(4): 829-836.
[45] Saçlı B, Aydınalp C, Cansız G, et al. Microwave dielectric property based classification of renal calculi: Application of a kNN algorithm[J]. Comput Biol Med, 2019, 112: 103366.
[46] Zhang GM, Sun H, Shi B, et al. Uric acid versus non-uric acid urinary stones: differentiation with single energy CT texture analysis[J]. Clin Radiol, 2018, 73(9): 792-799.
[47] 高亚明, 刘兆邦, 陈斌, 等. 基于机器学习的辅助诊断算法在体内尿路结石成分鉴别中的应用[J]. 计算机应用与软件, 2020, 37(12): 133-139, 215. https://www.cnki.com.cn/Article/CJFDTOTAL-JYRJ202012022.htm
[48] 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.
[49] Fitri LA, Haryanto F, Arimura H, et al. Automated classification of urinary stones based on microcomputed tomography images using convolutional neural network[J]. Phys Med, 2020, 78: 201-208.
[50] Black KM, Law H, Aldoukhi A, et al. Deep learning computer vision algorithm for detecting kidney stone composition[J]. BJU Int, 2020, 125(6): 920-924.
[51] Kazemi Y, Mirroshandel SA. A novel method for predicting kidney stone type using ensemble learning[J]. Artif Intell Med, 2018, 84: 117-126.
[52] 李云鹏, 吕建林. 人工智能技术在泌尿系结石中的应用与展望[J]. 临床泌尿外科杂志, 2022, 37(12): 957-959. https://lcmw.whuhzzs.com/article/doi/10.13201/j.issn.1001-1420.2022.12.014
[53] Fram EB, Sorensen MD, Bird VG, et al. Geographic location is an important determinant of risk factors for stone disease[J]. Urolithiasis, 2017, 45(5): 429-433.
[54] Friedlander JI, Antonelli JA, Pearle MS. Diet: from food to stone[J]. World J Urol, 2015, 33(2): 179-185.
[55] 涂熹, 庄稀尧, 黄朝友, 等. 1495例上尿路结石成分分析单中心研究[J]. 临床泌尿外科杂志, 2022, 37(5): 364-368. https://lcmw.whuhzzs.com/article/doi/10.13201/j.issn.1001-1420.2022.05.007
[56] Wood BG, Urban MW. Detecting kidney stones using twinkling artifacts: survey of kidney stones with varying composition and size[J]. Ultrasound Med Biol, 2020, 46(1): 156-166.
[57] Manglaviti G, Tresoldi S, Guerrer CS, et al. In vivo evaluation of the chemical composition of urinary stones using dual-energy CT[J]. AJR Am J Roentgenol, 2011, 197(1): W76-83.
[58] Kaza RK, Platt JF, Cohan RH, et al. Dual-energy CT with single-and dual-source scanners: current applications in evaluating the genitourinary tract[J]. Radiographics, 2012, 32(2): 353-369.
[59] Zhang GM, Sun H, Xue HD, et al. Prospective prediction of the major component of urinary stone composition with dual-source dual-energy CT in vivo[J]. Clin Radiol, 2016, 71(11): 1178-1183.
[60] Li ZX, Jiao GL, Zhou SM, et al. Evaluation of the chemical composition of nephrolithiasis using dual-energy CT in Southern Chinese gout patients[J]. BMC Nephrol, 2019, 20(1): 273.
[61] Ganesan V, Pearle MS. Artificial intelligence in stone disease[J]. Curr Opin Urol, 2021, 31(4): 391-396.
[62] 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.
[63] Zhang S, Huang Y, Wu W, et al. Trends in urinary stone composition in 23, 182 stone analyses from 2011 to 2019: a high-volume center study in China[J]. World J Urol, 2021, 39(9): 3599-3605.
[64] Türk C, Pet ík A, Sarica K, et al. EAU guidelines on interventional treatment for urolithiasis[J]. Eur Urol, 2016, 69(3): 475-482.
[65] Torricelli FC, Marchini GS, De S, et al. Predicting urinary stone composition based on single-energy noncontrast computed tomography: the challenge of cystine[J]. Urology, 2014, 83(6): 1258-1263.
计量
- 文章访问数: 1536
- PDF下载数: 594
- 施引文献: 0