深度学习在肾结石影像诊断的应用进展

doi:10.16180/j.cnki.issn1007-7820.2024.12.010

摘要/Abstract

摘要：

针对较多复杂而高维的结石图像数据和不同成像技术导致的不确定、破碎分散、异构的结石信息等问题,深度学习是一种高效的大数据处理工具,具有较好的特征提取和非线性识别能力,已成为提升肾结石管理水平的智能方案。深度学习应用于肾结石影像数据分析,可以针对不同类型结石数据的特征进行适应,并利用多变量综合评估结石,实现其精准量化,提高了诊断和评估的效率和准确度,协助医生制定更优的结石治疗方案。文中综述了近年来深度学习在肾结石影像的进展,介绍了各类深度学习算法,阐明其相对于传统方法以及机器学习算法的新颖性和优越性,并提出不足之处,旨在为后续的研究工作提供参考和方向。

关键词: 肾结石, 结石分析, 结石诊断, 结石分类, 计算机科学, 深度学习, 机器学习, 医疗大数据, 智能医疗

Abstract:

In view of the massive complex and high dimensional stone image data and the uncertain, fragmented and heterogeneous stone information caused by different imaging techniques, deep learning is an efficient big data processing tool with excellent feature extraction and nonlinear recognition capabilities, and has become an intelligent solution to improve the level of kidney stone management. The application of deep learning in kidney stone image data analysis can adapt to the characteristics of different types of stone data, and use multi-variable comprehensive assessment of stones to achieve accurate quantification, improve the efficiency and accuracy of diagnosis and evaluation, and assist doctors to develop better stone treatment plan. This study reviews the progress of deep learning in kidney stone imaging in recent years, focuses on various deep learning algorithms, illustrates their novelty and advantages over traditional methods and machine learning algorithms, and points out their shortcomings, aiming to provide reference and direction for subsequent research work.

Key words: kidney stones, stone analysis, stone diagnosis, stone classification, computer science, deep learning, machine learning, medical big data, intelligent healthcare

中图分类号:

TP183

梁水芬, 郭志勇. 深度学习在肾结石影像诊断的应用进展[J]. 电子科技, 2024, 37(12): 67-72.

LIANG Shuifen, GUO Zhiyong. Advancements of Deep Learning in Imaging Diagnosis of Kidney Stone[J]. Electronic Science and Technology, 2024, 37(12): 67-72.

图/表 1

参考文献 43

[1]	Alelign T, Petros B. Kidney stone disease:An update on current concepts[J]. Advances in Urology, 2018, 35(3):306-308.
[2]	Bultitude M. Urolithiasis around the world[J]. BJU International, 2017, 120(5):601-603. doi: 10.1111/bju.14033 pmid: 29035016
[3]	Zeng G, Mai Z, Xia S, et al. Prevalence of kidney stones in China: An ultrasonography based cross-sectional study[J]. BJU International, 2017, 120(1):109-116. doi: 10.1111/bju.13828 pmid: 28236332
[4]	Sorokin I, Mamoulakis C, Miyazawa K, et al. Epidemiology of stone disease across the world[J]. World Journal of Urology, 2017, 35(9):1301-1320. doi: 10.1007/s00345-017-2008-6 pmid: 28213860
[5]	Kanagasingam Y, Xiao D, Vignarajan J, et al. Evaluation of artificial intelligence-based grading of diabetic retinopathy in primary care[J]. JAMA Network Open, 2018, 1(5):182-185.
[6]	Miotto R, Wang F, Wang S, et al. Deep learning for healthcare:Review,opportunities and challenges[J]. Briefings in Bioinformatics, 2018, 19(6): 1236-1246.
[7]	Haenssle H A, Winkler J K, Fink C, et al. Skin lesions of face and scalp-classification by a market-approved convolutional neural network in comparison with 64 dermatologists[J]. European Journal of Cancer, 2021, 144(7):192-199
[8]	Rajpurkar P, Irvin J, Ball R L, et al. Deep learning for chest radiograph diagnosis:A retrospective comparison of the CheXNeXt algorithm to practicing radiologists[J]. Plos Medicine, 2018, 15(11):106-109.
[9]	Al-Antari M A, Al-Masni M A, Kim T S. Deep learning computer-aided diagnosis for breast lesion in digital mammogram[J]. Advances in Experimental Medicine and Biology, 2020, 12(13):59-72.
[10]	左斌, 李菲菲. 基于注意力机制和Inf-Net的新冠肺炎图像分割方法[J]. 电子科技, 2023, 36(2):7-10.
	Zuo Bin, Li Feifei. An effective segmentation method for COVID-19 CT image based on attention mechanism and Inf-Net[J]. Electronic Science and Technology, 2023, 36(2):7-10.
[11]	Yann L C, Yoshua B, Geoffrey H. Deep learning[J]. Nature, 2015, 521(7553):436-444.
[12]	He K, Zhang X, Ren S, et al. Deep residual learning for image recognition[C]. Las Vegas: Conference on Computer Vision and Pattern Recognition, 2016, 18(3):121-127.
[13]	罗枭. 基于深度学习的自然语言处理研究综述[J]. 智能计算机与应用, 2020, 10(4):133-137.
	Luo Xiao. A survey of natural language processing based ondeep learning[J]. Intelligent Computer and Applications, 2020, 10(4):133-137.
[14]	孔祥勇. ChatGPT在医疗行业的创新机遇与挑战[J]. 张江科技评论, 2023, 37(2):68-71.
	Kong Xiangyong. Innovation opportunities and challenges of ChatGPT in the medical industry[J]. Zhangjiang Technology Review, 2023, 37(2):68-71.
[15]	Türk C, Petřík A, Sarica K, et al. EAU guidelines on diagnosis and conservative management of urolithiasis[J]. European Urology, 2016, 69(3):468-474. doi: 10.1016/j.eururo.2015.07.040 pmid: 26318710
[16]	Liu S, Yi W, Xin Y, et al. Deep learning in medical ultrasound analysis:A review[J]. Engineering, 2019, 5(2):15-19.
[17]	Sudharson S, Kokil P. An ensemble of deep neural networks for kidney ultrasound image classification[J]. Computer Methods and Programs in Biomedicine, 2020, 197(8):57-59.
[18]	Sudharson S, Kokil P. Computer-aided diagnosis system for the classification of multi-class kidney abnormalities in the noisy ultrasound images[J]. Computer Methods and Programs in Biomedicine, 2021, 205(74):607-610
[19]	Tsai M C, Lu H H, Chang Y C, et al. Automatic screening of pediatric renal ultrasound abnormalities:Deep learning and transfer learning approach[J]. JMIR Medical Informatics, 2022, 10(11): 408-410.
[20]	Heidenreich A, Desgrandschamps F, Terrier F. Modern approach of diagnosis and management of acute flank pain: Review of all imaging modalities[J]. European Urology, 2002, 41(4):351-362. doi: 10.1016/s0302-2838(02)00064-7 pmid: 12074804
[21]	Lee D H, Li Y, Shin B S. Generalization of intensity distribution of medical images using GANs[J]. Human-Centric Computing and Information Sciences, 2020, 10(1):34-39.
[22]	Rani G, Thakkar P, Verma A, et al. KUB-UNet: Segmentation of organs of urinary system from a KUB X-ray image[J]. Computer Methods and Programs in Biomedicine, 2022, 224(7):107-110.
[23]	Liu Y Y, Huang Z H, Huang K W. Deep learning model for computer-aided diagnosis of urolithiasis detection from kidney-ureter-bladder images[J]. Bioengineering-Basel, 2022, 9(12):811-815.
[24]	Allison S J. Stones:Ultrasonography and computed tomography:Performance in detection of kidney stones[J]. Nature Reviews Nephrology, 2014, 10(11):611-613. doi: 10.1038/nrneph.2014.182 pmid: 25266209
[25]	Caglayan A, Horsanali M O, Kocadurdu K, et al. Deep learning model-assisted detection of kidney stones on computed tomography[J]. International Braz J Urol, 2022, 48(5):830-839. doi: 10.1590/S1677-5538.IBJU.2022.0132 pmid: 35838509
[26]	Yildirim K, Bozdag P G, Talo M, et al. Deep learning model for automated kidney stone detection using coronal CT images[J]. Computers in Biology and Medicine, 2021, 135(2):45-47.
[27]	Islam M N, Hasan M, Hossain M K, et al. Vision transformer and explainable transfer learning models for auto detection of kidney cyst,stone and tumor from CT-radiography[J]. Scientific Reports, 2022, 12(1):440-444.
[28]	Li D, Xiao C, Liu Y, et al. Deep segmentation networks for segmenting kidneys and detecting kidney stones in unenhanced abdominal CT images[J]. Diagnostics, 2022, 12(8):1788-1790.
[29]	Cui Y, Sun Z, Ma S, et al. Automatic detection and scoring of kidney stones on noncontrast CT images using S.T.O.N.E. nephrolithometry:Combined deep learning and thresholding methods[J]. Molecular Imaging and Biology, 2021, 23(3):436-445.
[30]	Okhunov Z, Friedlander J I, George A K, et al. S.T.O.N.E. nephrolithometry:Novel surgical classification system for kidney calculi[J]. Urology, 2013, 81(6):1154-1159.
[31]	Elton D C, Turkbey E B, Pickhardt P J, et al. A deep learning system for automated kidney stone detection and volumetric segmentation on noncontrast CT scans[J]. Medical Physics, 2022, 49(4):2545-2554. doi: 10.1002/mp.15518 pmid: 35156216
[32]	Babajide R, Lembrikova K, Ziemba J, et al. Automated machine learning segmentation and measurement of urinary stones on CT scan[J]. Urology, 2022, 169(2):41-46.
[33]	Cloutier J, Villa L, Traxer O, et al. Kidney stone analysis: "Give me your stone,I will tell you who you are!"[J]. World Journal of Urology, 2015, 33(2):157-169.
[34]	Daudon M, Jungers P, Bazin D, et al. Recurrence rates of urinary calculi according to stone composition and morphology[J]. Urolithiasis, 2018, 46(5):459-470. doi: 10.1007/s00240-018-1043-0 pmid: 29392338
[35]	Lopez F, Varelo A, Hinojosa O, et al. Assessing deep learning methods for the identification of kidney stones in endoscopic images[J]. Annual International Conference of the IEEE Engineering in Medicine and Biology Society, 2021(5):2778-2781.
[36]	Estrade V, Daudon M, Richard E, et al. Towards automatic recognition of pure and mixed stones using intra-operative endoscopic digital images[J]. BJU International, 2022, 129(2):234-242.
[37]	Estrade V, Daudon M, Richard E, et al. Deep morphological recognition of kidney stones using intra-operative endoscopic digital videos[J]. Physics in Medicine and Biology, 67(16):201-208.
[38]	Fernandez K, Korinek M, Camp J. Automatic detection of calcium phosphate deposit plugs at the terminal ends of kidney tubules[J]. Healthcare Technology Letters, 2019, 6(6):271-274. doi: 10.1049/htl.2019.0086 pmid: 32038870
[39]	Stone L. Assessing kidney stone composition using deep learning[J]. Nature Reviews Urology, 2020, 17(4):192-193. doi: 10.1038/s41585-020-0301-4 pmid: 32132704
[40]	Onal E G, Tekgul H. Assessing kidney stone composition using smartphone microscopy and deep neural networks[J]. BJUI Compass, 2022, 3(4):310-315. doi: 10.1002/bco2.137 pmid: 35783589
[41]	Black K M, Law H, Aldoukhi A, et al. Deep learning computer vision algorithm for detecting kidney stone composition[J]. BJU International, 2020, 125(6):920-924. doi: 10.1111/bju.15035 pmid: 32045113
[42]	张钹. 人工智能进入后深度学习时代[J]. 智能科学与技术学报, 2019, 1(1):4-6. doi: 10.11959/j.issn.2096-6652.201913
	Zhang Bo. Artificial intelligence is entering the post deep-learning era[J]. Chinese Journal of Intelligent Science and Technology, 2019, 1(1):4-6.
[43]	Dosovitskiy A, Beyer L, Kolesnikov A, et al. An image is worth 16×16 words:Transformers for image recognition at scale[C]. Online: The Ninth International Conference on Learning Representations,2021:106-111