蔡宏民，华南理工大学 计算机科学与工程-凯发k8官网下载客户端

蔡宏民, 华南理工大学计算机学科学与技术学院教授、博士生导师，京都大学客座教授，2016科技部重点领域创新团队“机器智能创新团队”成员，广东省重点实验室成员，2014广东省优秀青年教师，京都大学客座教授。全国系统生物学专业委员会委员，生物信息学与人工生命专业委员会委员、常委委员，ccf生物信息学专委会委员、常委委员。1997年09-2003年07月在哈尔滨工业大学获得本科、硕士学位。2007年11月香港大学数学系取得博士学位。2012年9月至今在华南理工大学任教，2016年9月破格晋升博士生导师，同年破格晋升教授。哈佛大学、宾夕法尼亚大学访问学者，京都大学、香港浸会大学和清华大学生物信息国家重点实验室高级访问学者。isb 2019/2018/2017/2016/2015/2014，isbra 2018/2017/2016, icic 2019/2018/2017/2016, besc 2018, cbc 2018/2017/2016, cibb2015, giw 2017/2018/2019国际会议程序委员。danth 2014/2013，icdke 2012的国际会议共同主席，ccf-cbc 2019会议组织主席。应邀在国内外做~50次会议报告。在国际顶级杂志及一流会议上发表论文60多篇，包括bioinformatics、neuroimage、ieee trans image processing、ieee trans. biomedical engineering、european radiology，neural networks。主持或完成国家级、省部级项目十多项。 研究兴趣包括医学图像分析与理解、多源生物数据信息分析和人工智能理论及医学大数据应用。

2003 年 09 月 – 2007  年 09 月                    香港大学, 香港，理学博士应用数学       导师: prof. s.p. yung

2001 年 09 月 – 2003年 07 月                       哈尔滨工业大学，理学硕士应用数学       导师: 吴从炘教授

1997 年 09 月 – 2001年 07 月                        哈尔滨工业大学，理学学士信息与计算科学

2019 年 06月－2019年10月，                             京都大学，客座教授

2016 年 09月－至今                                              华南理工大学，教授（破格），博士生导师（破格）

2012 年 03月－2016年09月                               华南理工大学， 副教授，先上岗教授

2013 年 06 月－2013年09月                                institute of chemical research，京都大学，日本，访问教授

2008 年 09 月－2012年03月                              中山大学 信息科学与技术学院，讲师、硕士导师

2006 年 06 月－2006 年 12 月                           section for biomedical image，analysis, 宾州大学(upenn),  美国，访问学者

2005 年 04 月- 2005 年 10月                             centerfor bioinformatics, 哈佛大学， 美国 ，研究员

ø  生物医学图像信息挖掘

ø  生物医学表型和多组学整合分析

ø  肿瘤组学大数据分析

ø  人工智能与模式识别

， bibm 2016/2017/2018/2019mso-hansi-font-family:'georgia', georgia, 'times new roman', times, 'microsoft yahei', simsun, simhei, serif;"times new roman"">等国际会议程序委员。danth
2014/2013"times new roman"">，icdke 2012的国际会议共同主席；ccf-cbc2019会议组织主席

"times new roman"">全国生物信息学与人工生命专业委员会委员、常任委员；全国ccf生物信息学专委会委员、常任委员；全国系统生物学专业委员会委员；全国自动化协会智能健康与生物信息学专委会委员；广东省转化医学眼科分会副主委；广东省精准医学应用学会-"times new roman"">数字智能化分会副主任委员；cipsmso-hansi-font-family:'georgia', georgia, 'times new roman', times, 'microsoft yahei', simsun, simhei, serif;"times new roman"">医疗健康与生物信息专委；广东省计算机协会大数据专业委员会委员

interdisciplinary sciences: computational life
sciences mso-hansi-font-family:'georgia', georgia, 'times new roman', times, 'microsoft yahei', simsun, simhei, serif;"times new roman";color:#4472c4;mso-bidi-font-weight:
bold">副主编；current chinese science mso-bidi-font-weight:bold">编委；frontiers in geneticsmso-hansi-font-family:'georgia', georgia, 'times new roman', times, 'microsoft yahei', simsun, simhei, serif;"times new roman";color:#4472c4">客座编委

期刊论文： 

 
[1] bin zhang, hongmin cai*, jiazhou chen, yu hu, jie huang, wentao rong, wanlin weng,qinjian huang, haiyan wang, hong peng, fast and accurate clustering of multiple modality data via feature matching. ieee transactions on cybernetics, 2020, accepted.（中科院和jcr分区分别为1区和1区，影响因子11.079) 

[2] h. peng, j. chen, y. hu, h. cai*, integrating tensor similarity to enhance clustering performance. ieee transactions on pattern analysis and machine intelligence, 2020, accepted. （中科院和jcr分区分别为1区和1区，影响因子17.73) 

[3] w. rong, e. zhuo, h. peng, j. chen, h. wang, h. cai*, learning a consensus affinity matrix for multi-view clustering via subspaces merging on grassmann manifold, information science, 2020, accepted. (中科院和jcr分区分别为1区和1区，影响因子 5.910) 

[4] h. wang, g. han, b. zhang, g. tao, h. cai*, exsavi: excavating both sample-wise and view-wise relationships to boost multi-view subspace clustering. neurocomputing, 2020, accepted. （中科院和jcr分区分别为2区和1区，影响因子4.438) 

[5] h. wang, g. han, h. li, g. tao, e. zhuo, l. liu, h. cai*, y. ou, collaborative dictionary learning model for nasopharyngeal carcinoma segmentation on multi-modalities mr sequences. computational and mathematical methods in medicine, 2020, accepted.（中科院和jcr分区分别为4区和3区，影响因子1.770)

 
[6] j. yang, x. dong, y. hu, h. cai* et al, fully automatic arteriovenous segmentation in retinal images via topology-aware generative adversarial networks. interdisciplinary sciences: computational life sciences, 2020, accepted. （中科院和jcr分区分别为3区和3区，影响因子1.512) 

[7] q. huang, y. zhang, h. peng, t. dan, h. cai*, deep subspace clustering to achieve jointly latent feature extraction and discriminative learning, neurocomputing, 404 (3) (2020) 340-350. （中科院和jcr分区分别为2区和1区，影响因子4.438) 

[8] x. chen, m. he, t. dan, n. wang, m. lin, l. zhang, j. xian, h. cai* and h. xie, automatic measurements of fetal lateral ventricles in 2d ultrasound images using deep learning, frontiers in neurology (2020)1664-2295. （中科院和jcr分区分别为3区和3区，影响因子2.635） 

[9] z, wei, y. zhang, w. weng, j. chen, h. cai*, survey and comparative assessments of computational multi-omics integrative methods with multiple regulatory networks identifying distinct tumor compositions across pan-cancer data sets, briefings in bioinformatics, bbaa102， 2020. （中科院和jcr分区分别为2区和1区，影响因子9.101） 

[10] j. huang, j. z. chen, b. zhang, l. zhu, h. cai*, evaluation of gene-drug common module identification methods using pharmacogenomics data, briefings in bioinformatics. 2020.（中科院和jcr分区分别为2区和1区，影响因子9.101） 

[11] b. xie, t. lei, n. wang, h cai, et al. computer-aided diagnosis for fetal brain ultrasound images using deep convolutional neural networks. international journal of computer assisted radiology and surgery, 15, 1303–1312 (2020). （中科院和jcr分区分别为4区和2区，影响因子2.473） 

[12] h. xie, n. wang, m. he, l. zhang, h. cai, j. xian, m. lin, j. zheng and y. yang, using deep learning algorithms to classify fetal brain ultrasound images as normal or abnormal. ultrasound in obstetrics gynecology. 2020（中科院和jcr分区分别是1区和1区，影响因子5.595） 

[13] j. zeng, h. cai*, h. peng, h. wang, y. zhang, t. akutsu, causalcall: nanopore basecalling using a temporal convolutional network, frontiers in genetics, 2019. （中科院和jcr分区分别是3区和1区，影响因子3.517） 

[14] w. weng, w. zhou, z. chen, h. peng, h. cai*, enhancing multi-view clustering through common subspace integration by considering both global similarities and local structures, neurocomputing, 378 (2019) 375-386. （中科院和jcr分区分别为2区和1区，影响因子4.438） 

[15] z. li, z. zhang, j. qin, s. li, h. cai*, low-rank analysis-synthesis dictionary learning with adaptively ordinal locality, neural networks. 2019.（中科院和jcr分区分别为2区和1区，影响因子5.785） 

[16] j. chen, g. han, a. xu, h. cai*, identification of multidimensional regulatory modules through multi-graph matching with network constraints, ieee transactions on biomedical engineering. 2019.（中科院和jcr分区分别为2区和1区，影响因子4.491） 

[17] h. cai, x. pang, d. dong, y. ma, y. huang, x. fan, p. wu, h. chen, f. he, y. cheng, et al., molecular decision tree algorithms predict individual recurrence pattern for locally advanced nasopharyngeal carcinoma, journal of cancer 10 (15) (2019) 3323. （中科院和jcr分区分别为3区和2区，影响因子3.182） 

[18] xu, j. chen, h. peng, g. han, h. cai*, simultaneous interrogation of cancer omics to identify subtypes with significant clinical differences, frontiers in genetics 10 (2019) 236. （中科院和jcr分区分别为3区和1区，影响因子3.517）

 
[19] h. cai, q. huang, w. rong, y. song, j. li, j. wang, j. chen, l. li, breast microcalcification diagnosis using deep convolutional neural network from digital mammograms, computational and mathematical methods in medicine. 2019. （中科院和jcr分区分别为4区和2区，影响因子1.563） 

[20] e. zhuo, w. zhang, h. li, g. zhang, b. jing, j. zhou, c. cui, m chen, y. sun, l. liu, h. cai*, radiomics on multi-modalities mr sequences can subtype patients with non-metastatic nasopharyngeal carcinoma (npc) into distinct survival subgroups, european radiology (2019) 1–10. （中科院和jcr分区分别为2区和1区，影响因子3.962） 

[21] y. you, h. cai*, j. chen, low rank representation and its application in bioinformatics, current bioinformatics 13 (5) (2018) 508–517. （中科院和jcr分区分别为4区和3区，影响因子1.189） 

[22] x. yang, g. han, j. chen, h. cai*, finding correlated patterns via highorder matching for multiple sourced biological data, ieee transactions on biomedical engineering 66 (4) (2018) 1017–1025. （中科院和jcr分区分别为2区和1区，影响因子4.491） 

[23] x. jiang, f. xie, l. liu, y. peng, h. cai, l. li, discrimination of malignant and benign breast masses using automatic segmentation and features extracted from dynamic contrast-enhanced and diffusion-weighted mri, oncology letters 16 (2) (2018) 1521–1528. （中科院和jcr分区分别为4区和3区，影响因子1.871） 

[24] j. chen, h. peng, g. han, h. cai*, j. cai, hogmmnc: a higher order graph matching with multiple network constraints model for gene–drug regulatory modules identification, bioinformatics 35 (4) (2018) 602–610. （中科院和jcr分区分别为3 区和1区，影响因子4.531） 

[25] j. li, y. song, s. xu, j. wang, h. huang, w. ma, x. jiang, y. wu, h. cai, l. li, predicting underestimation of ductal carcinoma in situ: a comparison between radiomics and conventional approaches, international journal of computer assisted radiology and surgery 14 (4) (2019) 709–721. （中科院和jcr分区分别为3 区和1区，影响因子2.155） 

[26] h. cai, p. chen, j. chen, j. cai, y. song, g. han, wavedec: a wavelet approach to identify both shared and individual patterns of copy-number variations, ieee transactions on biomedical engineering 65 (2) (2017) 353–364. 5. （中科院和jcr分区分别为2区和1区，影响因子4.491） 

[27] j. cai, h. cai*, j. chen, x. yang, identifying many-to-many relationships between gene-expression data and drug-response data via sparse binary matching, ieee-acm transactions on computational biology and bioinformatics.2018. （中科院和jcr分区分别为3区和1区，影响因子2.896） 

[28] z. wei, c. shu, c. zhang, j. huang, h. cai*, a short review of variants calling for single-cell-sequencing data with applications, international journal of biochemistry & cell biology 92 (2017) 218–226. （中科院和jcr分区分别为3区和2区，影响因子3.144） 

[29] x. yang, g. han, h. cai*, y. song, recovering hidden diagonal structures via non-negative matrix factorization with multiple constraints, ieee-acm transactions on computational biology and bioinformatics.2017. （中科院和jcr分区分别为3区和1区，影响因子2.896） 

[30] b. xu, h. cai*, c. zhang, x. yang, g. han, copy number variants calling for single cell sequencing data by multi-constrained optimization, computational biology and chemistry 63 (2016) 15–20.100. （中科院和jcr分区分别为4区和2区，影响因子1.581） 

[31] c. zhang, h. cai*, j. huang, y. song, nbcnv: a multi-constrained optimization model for discovering copy number variants in single-cell sequencing data, bmc bioinformatics 17 (1) (2016) 384. （中科院和jcr分区分别为4区和1区，影响因子2.511） 

[32] j. wang, x. yang, h. cai£, w. tan, c. jin, l. li, discrimination of breast cancer with microcalcifications on mammography by deep learning, scientific reports 6 (2016) 27327. （中科院和jcr分区分别为3区和1区，影响因子4.011, esi 高引用论文） 

[33] r. jiang, r. you, x.-q. pei, x. zou, m.-x. zhang, t.-m. wang, r. sun, d.-h. luo, p.-y. huang, q.-y. chen, h.-m. cai£, development of a ten-signature classifier using a support vector machine integrated approach to subdivide the m1 stage into m1a and m1b stages of nasopharyngeal carcinoma with synchronous metastases to better predict patients’ survival, oncotarget 90 7 (3) (2016) 3645. （中科院和jcr分区分别是1区和1区，影响因子5.168） 

[34] x. cheng, h. cai*, y. zhang, b. xu, w. su, optimal combination of feature selection and classification via local hyperplane based learning strategy, bmc bioinformatics 16 (1) (2015) 219. （中科院和jcr分区分别为4区和1区，影响因子2.511） 

[35] h. tian, h. cai, j. lai, a novel diffusion system for impulse noise removal based on a robust diffusion tensor, neurocomputing 133 (2014) 222–230. （中科院和jcr分区分别为2区和1区，影响因子4.072） 

[36] h. cai, l. liu, y. peng, y. wu, l. li, diagnostic assessment by dynamic contrast-enhanced and diffusion-weighted magnetic resonance in differentiation of breast lesions under different imaging protocols, bmc cancer 14 (1) (2014) 366. （中科院和jcr分区分别为3区和2区，影响因子2.933） 

[37] x. cheng, h. cai*, p. he, y. zhang, r. tian, combination of effective machine learning techniques and chemometric analysis for evaluation of bupleuri radix through high-performance thin-layer chromatography, analytical methods 5 (22) (2013) 6325–6330. （中科院和jcr分区分别为3区和1区，影响因子2.378） 

 
[38] h. cai, p. ruan, m. ng, t. akutsu, feature weight estimation for gene selection: a local hyperlinear learning approach, bmc bioinformatics 15 (1) (2014) 70. （中科院和jcr分区分别为4区和1区，影响因子2.511） 

[39] h. cai, z. yang, x. cao, w. xia, x. xu, a new iterative triclass thresholding technique in image segmentation, ieee transactions on image processing 23 (3) (2014) 1038–1046. （中科院和jcr分区分别为1区和1区，影响因子6.790，下载前25%的明星论文） 

[40] h. cai, y. peng, c. ou, m. chen, l. li, diagnosis of breast masses from dynamic contrast-enhanced and diffusion-weighted mr: a machine learning approach, plos one 9 (1) (2014) e87387. （中科院和jcr分区分别为3区和1区，影响因子2.776）

 
[41] w. su, h. wu, y. li, j. zhao, f. h. lochovsky, h. cai, t. huang, under-standing query interfaces by statistical parsing, acm transactions on the web (tweb) 7 (2) (2013) 8. （中科院和jcr分区分别为3区和2区，影响因子1.580）
[42] 崔春艳, 李立, 蔡宏民, 田海英, 刘立志, 张敏, 中国ct和mri杂志 9 (4) (2011) 35–38.(并列第一) 

[43] c. cui, h. cai*, l. liu, l. li, h. tian, l. li, quantitative analysis and prediction of regional lymph node status in rectal cancer based on computed tomography imaging, european radiology 21 (11) (2011) 2318–2325. （中科院和jcr分区分别为2区和1区，影响因子3.962） 

[44] x. wan, y. zhao, x. fan, h. cai#, y. zhang, m. chen, j. xu, x. wu, h. li, y. zeng, et al., molecular prognostic prediction for locally advanced nasopharyngeal carcinoma by support vector machine integrated approach, plos one 7 (3) (2012) e31989. （中科院和jcr分区分别为3区和1区，影响因子2.776） 

[45] h. cai, c. cui, h. tian, m. zhang, l. li, a novel approach to segment and classify regional lymph nodes on computed tomography images, computational and mathematical methods in medicine 2012. （中科院和jcr分区分别为4区和2区，影响因子1.563） 

[46] h. cai, x. xu, j. lu, j. lichtman, s. yung, s. t. wong, using nonlinear diffusion and mean shift to detect and connect cross-sections of axons in 3d optical microscopy images, medical image analysis 12 (6) (2008) 666–675. （中科院和jcr分区分别为2区和1区，影响因子8.880） 

[47] r. verma, e. i. zacharaki, y. ou, h. cai, s. chawla, s.-k. lee, e. r. melhem, r. wolf, c. davatzikos, multiparametric tissue characterization of brain neoplasms and their recurrence using pattern classification of mr images, academic radiology 15 (8) (2008) 966–977. （中科院和jcr分区分别为3区和2区，影响因子2.267） 

[48] h. cai, x. xu, j. lu, j. w. lichtman, s. yung, s. t. wong, repulsive force based snake model to segment and track neuronal axons in 3d microscopy image stacks, neuroimage 32 (4) (2006) 1608–1620. （中科院和jcr分区分别为1区和1区，影响因子5.812） 

会议论文： 

[49] chen j, han g, cai h *, ma j, kim m, laurienti, p, wu g. estimating common harmonic waves of brain networks on stiefel manifold, miccai 2020. 

 
[50] fan z, dan t, yu h, liu b, cai h *. single fundus image super-resolution via cascaded channel-wise attention network, ieee embc 2020 

[51] zeng j, cai h *， akutsu t，breast cancer subtype by imbalanced omics data through a deep learning fusion model, 2020 10th international conference on bioscience, biochemistry and bioinformatics, 2020. japan 

[52] huang j, et.al., cai h *, “achieving accurate segmentation of nasopharyngeal carcinoma in mr images through recurrent attention”, miccai 2019, shenzhen, p.r. china 

[53] huang j, zhou y, cai h*, et. al, “a copy-number variation detection pipeline for single cell sequencing data on bgi online”, 2017 ieee international conference on bioinformatics and biomedicine (bibm)，kansas city, mo, usa，2017.11.13-2017.11.16 

[54] zhang c, cai h *, et. al., “multi-norm constrained optimization methods for calling copy number variants calling in single cell sequencing data”, bibm 2016, shenzhen, p.r. china, 2016.12.15-12.18 

[55] huang w, cai h*, et. al., “mdagenera: an efficient and accurate simulator for multiple displacement amplification”, icic 2016, lanzhou, p.r. china, 2016.8.2-8.5 

[56] bo x, zhang c, xi y, and cai h*，“copy number variants calling for single cell sequencing data by multi-constrained optimization”, apbc 2016, san francisco, the united states (u.s.), 2016.1.11-1.13 

[57] li t, zhang c, bo x, li f, and cai h*，“malbacsim: a multiple annealing and looping based amplification cycles simulator”, bibm 2015 washington d.c., the united states (u.s.), 2015.11.9-11.12 

[58] chen p, huang w, shao w, cai h*, “discrimination of recurrent cnvs from individual ones from multisample acgh by jointly constrained minimization”, acm bcb 2015, atlanta, the united states (u.s.), 2015.9.9-9.12 

[59] xu b, li t, luo y, xu r, cai h. an empirical algorithm for bias correction based on gc estimation for single cell sequencing[c]//pacific-asia conference on knowledge discovery and data mining. springer, cham, 2014: 15-21. 

[60] cai h，michale ng,“optimal combination of feature weight learning and classification based on local approximation”, icdke 2012, wuyishan, p.r. china, 2012.11.21-11.23 

[61] cai h，michale ng,“feature selection by relief through local hyperplane approximation”, pakdd 2012, , kuala lumpur, malaysia, 2012.5.29-6.1 

[62] cai h，“improvements over adaptive local hyperplane to achieve better classification”，icdm 2011, vancouver, canada, 2011.12.11-12.14（口头报告） 

[63] h.y tian, cai h*, lai j, x.y xu, “image noise removal based on a new edge indicator”, icip 2011, brussels, belgium, 2011.9.11-9.14 

[64] 田海英，蔡宏民*，赖剑煌，边缘检测新算子及其在去噪方面的应用，《第十五届全国图象图形学学术会议论文集》，2010，中国广州，2010.12.10-12.11 

[65] tian h, cai h, lai j h, et al. effective image noise removal based on difference eigenvalue[c]//2011 18th ieee international conference on image processing. ieee, 2011: 3357-3360. 

[66] h. y tian, cai h*, lai j, “improved partial differential equation-based method to remove noise in image enhancement”, wiamis 2011: 12th international workshop on image analysis for multimedia interactive services, delft, the netherlands, 2011.4.13-4.15 

 
[67] h. y tian, cai h*, cui c, lai j, li l “quality enhancement with adaptive edge preservation for lymph nodal images”, aip conference proceedings, 2011 international symposium on computational models for life sciences, vol.1371(1), pp. 341-342, toyama, japan, 2011.10.11-10.13 

 
[68] ou y, cai h, lee s k, et al. cascaded segmentation of brain tumors using multi-modality mr profiles[j]. international society for magnetic resonance in medicine (ismrm). 2007. 

[69] zhang y, xu x, cai h, yung sp, and wong stc, "new nonlinear diffusion method to improve image quality", ieee international conference on image processing, icip 2007, san antonio, texas, usa, 2007.9.16-9.19 

[70] cai h, xu x, lu j, lichtman j, yung sp, and wong stc, "shape-constrained repulsive snake method to segment and track neurons in 3d microscopy images", proc international symposium of biomedical imaging isbi 2006, pp. 538-541, arlington, va, usa, 2006.4.6-4.9 

[71] chen j, xu x, cai h, miller l, and wong stc, "a new snake algorithm to track neuronal structure in microscopy image", proceedings of the 2005 international symposium on intelligent signal processing and communication systems, pp. 537-541, hong kong, p.r. china, 

[72] cai h, verma r, ou y, lee s, melhem e.r, and davatzikos c, "probabilistic segmentation of brain tumor on multi-modaility mri", proc international symposium of biomedical imaging isbi 2007, pp:600 – 603, washington d.c., usa, 2007.4.12-4.16 

[73] cai h, xu x, lu j, lichtman j, yung sp, and wong stc, "use mean shift to track neuronal axons in 3d", life science systems and applications workshop, ieee/nlm, pp. 1-2, bethesda, md, usa, 2006.7.13-7.14 

[74] cai h, xu x, lu j, lichtman j, yung sp, and wong stc, "segment and track neurons in 3d by repulsive snake method", proceedings of the 2005 international symposium on intelligent signal processing and communication systems, pp. 529-531, hong kong, p.r. china, 2005.12.13-12.16

专著                                                                                                                               

cai hongmin, quality
enhancement and segmentation for biomedical images, lap lambert academic publishing gmbh & co. kg, 2011