Zhao Yuhang,Wang Yang,Chen Runsen,et al.Advances in research on deep learning-based intelligent auscultation technology in the diagnosis and treatment of congenital heart disease[J].Journal of Clinical Pediatric Surgery,,():633-640.[doi:10.3760/cma.j.cn101785-202404026-006]
Advances in research on deep learning-based intelligent auscultation technology in the diagnosis and treatment of congenital heart disease
- Keywords:
- Congenital Heart Disease; Artificial Intelligence; Deep Learning; Surgical Procedures; Operative; Child
- Abstract:
- Congenital heart disease (CHD) is one of the most common congenital birth defects.With the increasing understanding of CHD and advancements in screening methods,children with CHD can be diagnosed and treated early,thereby improving survival rates and quality of life.Early screening for CHD primarily uses a dual-indicator method,namely heart sound auscultation and pulse oximetry.While there are mature commercial devices for pulse oximetry,heart sound auscultation is highly influenced by individual experience and external factors,making misdiagnosis and missed diagnosis more likely.In recent years,the continuous development of artificial intelligence (AI) has led to the maturation of digital acquisition,storage,and analysis of technologies for heart sound signals,thus making intelligent auscultation-assisted diagnosis for cardiovascular diseases possible.Currently,many studies focus on AI algorithms based on deep learning (DL) for assisting in heart sound auscultation diagnosis of CHD,though most remain at the algorithm research stage and are based on specific datasets,yet to be validated in clinical settings.This article reviews the current state of AI auscultation technology research,summarizing the current developments in DL-based intelligent auscultation technology in the field of CHD,and highlighting the issues that need to be addressed for clinical application of heart sound auscultation.
References:
[1] Pierpont ME,Brueckner M,Chung WK,et al.Genetic basis for congenital heart disease:revisited:a scientific statement from the American Heart Association[J].Circulation,2018,138(21):e653-e711.DOI:10.1161/cir.0000000000000606.
[2] Zhao QM,Ma XJ,Ge XL,et al.Pulse oximetry with clinical assessment to screen for congenital heart disease in neonates in China:a prospective study[J].Lancet,2014,384(9945):747-754.DOI:10.1016/s0140-6736(14)60198-7.
[3] Bengio Y,Courville A,Vincent P.Representation learning:a review and new perspectives[J].IEEE Trans Pattern Anal Mach Intell,2013,35(8):1798-1828.DOI:10.1109/tpami.2013.50.
[4] Clifford GD,Liu CY,Moody B,et al.Recent advances in heart sound analysis[J].Physiol Meas,2017,38(8):E10-E25.DOI:10.1088/1361-6579/aa7ec8.
[5] Cheng JW,Sun KX.Heart sound classification network based on convolution and transformer[J].Sensors (Basel),2023,23(19):8168.DOI:10.3390/s23198168.
[6] Bozkurt B,Germanakis I,Stylianou Y.A study of time-frequency features for CNN-based automatic heart sound classification for pathology detection[J].Comput Biol Med,2018,100:132-143.DOI:10.1016/j.compbiomed.2018.06.026.
[7] Chakir F,Jilbab A,Nacir C,et al.Phonocardiogram signals processing approach for PASCAL Classifying Heart Sounds Challenge[J].Signal Image Video Process,2018,12(6):1149-1155.DOI:10.1007/s11760-018-1261-5.
[8] Cheng XF,Zhang Z.Denoising method of heart sound signals based on self-construct heart sound wavelet[J].AIP Adv,2014,4(8):087108.DOI:10.1063/1.4891822.
[9] Abdollahpur M,Ghaffari A,Ghiasi S,et al.Detection of pathological heart sounds[J].Physiol Meas,2017,38(8):1616-1630.DOI:10.1088/1361-6579/aa7840.
[10] Li SY,Li F,Tang SJ,et al.A review of computer-aided heart sound detection techniques[J].Biomed Res Int,2020,2020:5846191.DOI:10.1155/2020/5846191.
[11] Mondal A,Saxena I,Tang H,et al.A noise reduction technique based on nonlinear kernel function for heart sound analysis[J].IEEE J Biomed Health Inform,2018,22(3):775-784.DOI:10.1109/jbhi.2017.2667685.
[12] Gradolewski D,Magenes G,Johansson S,et al.A wavelet transform-based neural network denoising algorithm for mobile phonocardiography[J].Sensors (Basel),2019,19(4):957.DOI:10.3390/s19040957.
[13] Ali MN,El-Dahshan ESA,Yahia AH.Denoising of heart sound signals using discrete wavelet transform[J].Circuits Syst Signal Process,2017,36(11):4482-4497.DOI:10.1007/s00034-017-0524-7.
[14] Vican I,Krekovi? G,Jambro?i? K.Can empirical mode decomposition improve heartbeat detection in fetal phonocardiography signals?[J].Comput Methods Programs Biomed,2021,203:106038.DOI:10.1016/j.cmpb.2021.106038.
[15] Zheng YN,Guo XM,Jiang H,et al.An innovative multi-level singular value decomposition and compressed sensing based framework for noise removal from heart sounds[J].Biomed Signal Process Control,2017,38:34-43.DOI:10.1016/j.bspc.2017.04.005.
[16] Shah G,Koch P,Papadias CB.On the blind recovery of cardiac and respiratory sounds[J].IEEE J Biomed Health Inform,2015,19(1):151-157.DOI:10.1109/jbhi.2014.2349156.
[17] Guo Y,Yang HB,Guo T,et al.A novel heart sound segmentation algorithm via multi-feature input and neural network with attention mechanism[J].Biomed Phys Eng Express,2022,9(1):015012.DOI:10.1088/2057-1976/ac9da6.
[18] Fernando T,Ghaemmaghami H,Denman S,et al.Heart sound segmentation using bidirectional LSTMs with attention[J].IEEE J Biomed Health Inform,2020,24(6):1601-1609.DOI:10.1109/jbhi.2019.2949516.
[19] Renna F,Oliveira J,Coimbra MT.Deep convolutional neural networks for heart sound segmentation[J].IEEE J Biomed Health Inform,2019,23(6):2435-2445.DOI:10.1109/jbhi.2019.2894222.
[20] Nivitha Varghees V,Ramachandran KI.Effective heart sound segmentation and murmur classification using empirical wavelet transform and instantaneous phase for electronic stethoscope[J].IEEE Sens J,2017,17(12):3861-3872.DOI:10.1109/jsen.2017.2694970.
[21] Springer DB,Tarassenko L,Clifford GD.Logistic regression-HSMM-based heart sound segmentation[J].IEEE Trans Biomed Eng,2016,63(4):822-832.DOI:10.1109/tbme.2015.2475278.
[22] Papadaniil CD,Hadjileontiadis LJ.Efficient heart sound segmentation and extraction using ensemble empirical mode decomposition and kurtosis features[J].IEEE J Biomed Health Inform,2014,18(4):1138-1152.DOI:10.1109/jbhi.2013.2294399.
[23] Zeng W,Yuan J,Yuan CZ,et al.A new approach for the detection of abnormal heart sound signals using TQWT,VMD and neural networks[J].Artif Intell Rev,2021,54(3):1613-1647.DOI:10.1007/s10462-020-09875-w.
[24] Kay E,Agarwal A.DropConnected neural networks trained on time-frequency and inter-beat features for classifying heart sounds[J].Physiol Meas,2017,38(8):1645-1657.DOI:10.1088/1361-6579/aa6a3d.
[25] Nogueira DM,Ferreira CA,Gomes EF,et al.Classifying heart sounds using images of motifs,MFCC and temporal features[J].J Med Syst,2019,43(6):168.DOI:10.1007/s10916-019-1286-5.
[26] Li F,Zhang Z,Wang LL,et al.Heart sound classification based on improved Mel-frequency spectral coefficients and deep residual learning[J].Front Physiol,2022,13:1084420.DOI:10.3389/fphys.2022.1084420.
[27] Aziz S,Khan MU,Alhaisoni M,et al.Phonocardiogram signal processing for automatic diagnosis of congenital heart disorders through fusion of temporal and cepstral features[J].Sensors (Basel),2020,20(13):3790.DOI:10.3390/s20133790.
[28] Potes C,Parvaneh S,Rahman A,et al.Ensemble of feature-based and deep learning-based classifiers for detection of abnormal heart sounds[J].Comput Cardiol,2016,43:621-624.DOI:10.22489/CinC.2016.182-399.
[29] Deng SW,Han JQ.Towards heart sound classification without segmentation via autocorrelation feature and diffusion maps[J].Future Gener Comput Syst,2016,60:13-21.DOI:10.1016/j.future.2016.01.010.
[30] Yaseen,Son GY,Kwon S.Classification of heart sound signal using multiple features[J].Appl Sci,2018,8(12):2344.DOI:10.3390/app8122344.
[31] Dominguez-Morales JP,Jimenez-Fernandez AF,Dominguez-Mora-les MJ,et al.Deep neural networks for the recognition and classification of heart murmurs using neuromorphic auditory sensors[J].IEEE Trans Biomed Circuits Syst,2018,12(1):24-34.DOI:10.1109/tbcas.2017.2751545.
[32] Chen W,Sun Q,Chen XM,et al.Deep learning methods for heart sounds classification:a systematic review[J].Entropy (Basel),2021,23(6):667.DOI:10.3390/e23060667.
[33] Hinton G,Osindero S,Welling M,et al.Unsupervised discovery of nonlinear structure using contrastive backpropagation[J].Cogn Sci,2006,30(4):725-731.DOI:10.1207/s15516709cog0000_76.
[34] Huai XM,Kitada S,Choi D,et al.Heart sound recognition technology based on convolutional neural network[J].Inform Health Soc Care,2021,46(3):320-332.DOI:10.1080/17538157.2021.1893736.
[35] Oh SL,Jahmunah V,Ooi CP,et al.Classification of heart sound signals using a novel deep WaveNet model[J].Comput Methods Programs Biomed,2020,196:105604.DOI:10.1016/j.cmpb.2020.105604.
[36] Deng MQ,Meng TT,Cao JW,et al.Heart sound classification ba-sed on improved MFCC features and convolutional recurrent neural networks[J].Neural Netw,2020,130:22-32.DOI:10.1016/j.neunet.2020.06.015.
[37] Kui HR,Pan JH,Zong R,et al.Heart sound classification based on log Mel-frequency spectral coefficients features and convolutional neural networks[J].Biomed Signal Process Control,2021,69:102893.DOI:10.1016/j.bspc.2021.102893.
[38] Krishnan PT,Balasubramanian P,Umapathy S.Automated heart sound classification system from unsegmented phonocardiogram (PCG) using deep neural network[J].Phys Eng Sci Med,2020,43(2):505-515.DOI:10.1007/s13246-020-00851-w.
[39] Li F,Liu M,Zhao YJ,et al.Feature extraction and classification of heart sound using 1D convolutional neural networks[J].EURASIP J Adv Signal Process,2019,2019(1):59.DOI:10.1186/s13634-019-0651-3.
[40] Xiao B,Xu YQ,Bi XL,et al.Follow the sound of children’s heart:a deep-learning-based computer-aided pediatric CHDs diagnosis system[J].IEEE Internet Things J,2020,7(3):1994-2004.DOI:10.1109/jiot.2019.2961132.
[41] Xu WZ,Yu K,Ye JJ,et al.Automatic pediatric congenital heart disease classification based on heart sound signal[J].Artif Intell Med,2022,126:102257.DOI:10.1016/j.artmed.2022.102257.
[42] Zhu LL,Pan JH,Shi JH,et al.Research on recognition of CHD heart sound using MFCC and LPCC[J].J Phys Conf Ser,2019,1169(1):012011.DOI:10.1088/1742-6596/1169/1/012011.
[43] Chowdhury MEH,Khandakar A,Alzoubi K,et al.Real-time sma-rt-digital stethoscope system for heart diseases monitoring[J].Sensors (Basel),2019,19(12):2781.DOI:10.3390/s19122781.
[44] Leng S,Tan RS,Chai KTC,et al.The electronic stethoscope[J].Biomed Eng Online,2015,14(1):66.DOI:10.1186/s12938-015-0056-y.
[45] Sun SP,Jiang ZW,Wang HB,et al.Automatic moment segmentation and peak detection analysis of heart sound pattern via short-time modified Hilbert transform[J].Comput Methods Programs Biomed,2014,114(3):219-230.DOI:10.1016/j.cmpb.2014.02.004.
Memo
收稿日期:2024-4-7。
基金项目:江苏省卫生健康委科研项目(K2023036)
通讯作者:戚继荣,Email:qjr7@163.com