Artificial intelligence on diabetic retinopathy diagnosis: an automatic classification method based on grey level co-occurrence matrix and naive Bayesian model
|
摘要
AIM: To develop an automatic tool on screening diabetic retinopathy(DR) from diabetic patients.METHODS: We extracted textures from eye fundus images of each diabetes subject using grey level co-occurrence matrix method and trained a Bayesian model based on these textures. The receiver operating characteristic(ROC) curve was used to estimate the sensitivity and specificity of the Bayesian model.RESULTS: A total of 1000 eyes fundus images from diabetic patients in which 298 eyes were diagnosed as DR by two ophthalmologists. The Bayesian model was trained using four extracted textures including contrast, entropy, angular second moment and correlation using a training dataset. The Bayesian model achieved a sensitivity of 0.949 and a specificity of 0.928 in the validation dataset. The area under the ROC curve was 0.938, and the 10-fold cross validation method showed that the average accuracy rate is 93.5%.CONCLUSION: Textures extracted by grey level cooccurrence can be useful information for DR diagnosis, and a trained Bayesian model based on these textures can be an effective tool for DR screening among diabetic patients.
AIM: To develop an automatic tool on screening diabetic retinopathy(DR) from diabetic patients.METHODS: We extracted textures from eye fundus images of each diabetes subject using grey level co-occurrence matrix method and trained a Bayesian model based on these textures. The receiver operating characteristic(ROC) curve was used to estimate the sensitivity and specificity of the Bayesian model.RESULTS: A total of 1000 eyes fundus images from diabetic patients in which 298 eyes were diagnosed as DR by two ophthalmologists. The Bayesian model was trained using four extracted textures including contrast, entropy, angular second moment and correlation using a training dataset. The Bayesian model achieved a sensitivity of 0.949 and a specificity of 0.928 in the validation dataset. The area under the ROC curve was 0.938, and the 10-fold cross validation method showed that the average accuracy rate is 93.5%.CONCLUSION: Textures extracted by grey level cooccurrence can be useful information for DR diagnosis, and a trained Bayesian model based on these textures can be an effective tool for DR screening among diabetic patients.
AIM: To develop an automatic tool on screening diabetic retinopathy(DR) from diabetic patients.METHODS: We extracted textures from eye fundus images of each diabetes subject using grey level co-occurrence matrix method and trained a Bayesian model based on these textures. The receiver operating characteristic(ROC) curve was used to estimate the sensitivity and specificity of the Bayesian model.RESULTS: A total of 1000 eyes fundus images from diabetic patients in which 298 eyes were diagnosed as DR by two ophthalmologists. The Bayesian model was trained using four extracted textures including contrast, entropy, angular second moment and correlation using a training dataset. The Bayesian model achieved a sensitivity of 0.949 and a specificity of 0.928 in the validation dataset. The area under the ROC curve was 0.938, and the 10-fold cross validation method showed that the average accuracy rate is 93.5%.CONCLUSION: Textures extracted by grey level cooccurrence can be useful information for DR diagnosis, and a trained Bayesian model based on these textures can be an effective tool for DR screening among diabetic patients.
引文
1 Zatic T,Bendelic E,Paduca A,Rabiu M,Corduneanu A,Garaba A,Novac V,Curca C,Sorbala I,Chiaburu A,Verega F,Andronic V,Guzun I,C?p??in?O,Zam?-Mardari I.Rapid assessment of avoidable blindness and diabetic retinopathy in Republic of Moldova.Br J Ophthalmol2015;99(6):832-836.
2 Song PG,Yu JY,Chan KY,Theodoratou E,Rudan I.Prevalence,risk factors and burden of diabetic retinopathy in China:a systematic review and meta-analysis.J Glob Health 2018;8(1):010803.
3 Flaxman SR,Bourne RRA,Resnikoff S,Ackland P,Braithwaite T,Cicinelli MV,Das A,Jonas JB,Keeffe J,Kempen JH,Leasher J,Limburg H,Naidoo K,Pesudovs K,Silvester A,Stevens GA,Tahhan N,Wong TY,Taylor HR;Vision Loss Expert Group of the Global Burden of Disease Study.Global causes of blindness and distance vision impairment1990-2020:a systematic review and meta-analysis.Lancet Glob Health2017;5(12):e1221-e1234.
4 Zuo H,Shi ZM,Hussain A.Prevalence,trends and risk factors for the diabetes epidemic in China:a systematic review and meta-analysis.Diabetes Res Clin Pract 2014;104(1):63-72.
5 Franklin SW,Rajan SE.An automated retinal imaging method for the early diagnosis of diabetic retinopathy.Technol Health Care2013;21(6):557-569.
6 Gulshan V,Peng L,Coram M,Stumpe MC,Wu D,Narayanaswamy A,Venugopalan S,Widner K,Madams T,Cuadros J,Kim R,Raman R,Nelson PC,Mega JL,Webster DR.Development and validation of a deep learning algorithm for detection of diabetic retinopathy in retinal fundus photographs.JAMA 2016;316(22):2402-2410.
7 Lam C,Yi D,Guo M,Lindsey T.Automated detection of diabetic retinopathy using deep learning.AMIA Jt Summits Transl Sci Proc2018;2017:147-155.
8 Ganesan K,Martis RJ,Acharya UR,Chua CK,Min LC,Ng EY,Laude A.Computer-aided diabetic retinopathy detection using trace transforms on digital fundus images.Med Biol Eng Comput 2014;52(8):663-672.
9 Casanova R,Saldana S,Chew EY,Danis RP,Greven CM,Ambrosius WT.Application of random forests methods to diabetic retinopathy classification analyses.PLo S One 2014;9(6):e98587.
10 Miranda E,Irwansyah E,Amelga AY,Maribondang MM,Salim M.Detection of cardiovascular disease risk’s level for adults using naive Bayes classifier.Healthc Inform Res 2016;22(3):196-205.
11 Sambo F,Trifoglio E,Di Camillo B,Toffolo GM,Cobelli C.Bag of Na?ve Bayes:biomarker selection and classification from genome-wide SNP data.BMC Bioinformatics 2012;13(Suppl 14):S2.
12 de Souza JWM,Alves SSA,Rebou?as ES,Almeida JS,Rebou?as Filho PP.A new approach to diagnose parkinson’s disease using a structural cooccurrence matrix for a similarity analysis.Comput Intell Neurosci 2018;2018:7613282.
13 An GZ,Omodaka K,Tsuda S,Shiga Y,Takada N,Kikawa T,Nakazawa T,Yokota H,Akiba M.Comparison of machine-learning classification models for glaucoma management.J Healthc Eng 2018;2018:6874765.
14 Mistry H,Auguste P,Lois N,Waugh N.Diabetic retinopathy and the use of laser photocoagulation:is it cost-effective to treat early?BMJ Open Ophthalmol 2017;2(1):e000021.
15 Jenkins AJ,Joglekar MV,Hardikar AA,Keech AC,O’Neal DN,Januszewski AS.Biomarkers in diabetic retinopathy.Rev Diabet Stud2015;12(1-2):159-195.
16 Maghbooli Z,Hossein-nezhad A,Larijani B,Amini M,Keshtkar A.Global DNA methylation as a possible biomarker for diabetic retinopathy.Diabetes Metab Res Rev 2015;31(2):183-189.
17 Cunha-Vaz J,Ribeiro L,Lobo C.Phenotypes and biomarkers of diabetic retinopathy.Prog Retin Eye Res 2014;41:90-111.
18 Khan AA,Rahmani AH,Aldebasi YH.Diabetic retinopathy:recent updates on different biomarkers and some therapeutic agents.Curr Diabetes Rev 2018;14(6):523-533.
19 Haralick RM.Statistical and structural approaches to texture.Proc IEEE 1979;67(5):786-804.
20 Song CI,Ryu CH,Choi SH,Roh JL,Nam SY,Kim SY.Quantitative evaluation of vocal-fold mucosal irregularities using GLCM-based texture analysis.Laryngoscope 2013;123(11):E45-E50.
21 Chen X,Wei XH,Zhang ZP,Yang RM,Zhu YJ,Jiang XQ.Differentiation of true-progression from pseudoprogression in glioblastoma treated with radiation therapy and concomitant temozolomide by GLCM texture analysis of conventional MRI.Clin Imaging 2015;39(5):775-780.
22 Lian MJ,Huang CL.Texture feature extraction of gray-level cooccurrence matrix for metastatic cancer cells using scanned laser picoprojection images.Lasers Med Sci 2018.
23 Haralick RM,Shanmugam K,Dinstein I.Textural features for image classification.IEEE Trans Syst,Man,Cybern 1973;SMC-3(6):610-621.
24 Ulaby F,Kouyate F,Brisco B,Williams TH.Textural infornation in SAR images.IEEE Trans Geosci Remote Sensing 1986;GE-24(2):235-245.
25 Baraldi A,Parmiggiani F.An investigation of the textural characteristics associated with gray level cooccurrence matrix statistical parameters.IEEE Trans Geosci Remote Sensing 1995;33(2):293-304.
26 Al-Shabrawey M,Zhang WB,McDonald D.Diabetic retinopathy:mechanism,diagnosis,prevention,and treatment.Biomed Res Int2015;2015:854593.
27 Zhang XY,Zhao L,Hambly B,Bao SS,Wang KY.Diabetic retinopathy:reversibility of epigenetic modifications and new therapeutic targets.Cell Biosci 2017;7:42.
28 ShuangYu,DiXiao,Kanagasingam Y.Exudate detection for diabetic retinopathy with convolutional neural networks.Conf Proc IEEE Eng Med Biol Soc 2017;2017:1744-1747.
29 Roychowdhury S,Koozekanani DD,Parhi KK.DREAM:diabetic retinopathy analysis using machine learning.IEEE J Biomed Health Inform 2014;18(5):1717-1728.
30 Acharya UR,Ng EY,Tan JH,Sree SV,Ng KH.An integrated index for the identification of diabetic retinopathy stages using texture parameters.JMed Syst 2012;36(3):2011-2020.
31 Khojasteh P,Aliahmad B,Arjunan SP,Kumar DK.Introducing a novel layer in convolutional neural network for automatic identification of diabetic retinopathy.Conf Proc IEEE Eng Med Biol Soc 2018;2018:5938-5941.
2 Song PG,Yu JY,Chan KY,Theodoratou E,Rudan I.Prevalence,risk factors and burden of diabetic retinopathy in China:a systematic review and meta-analysis.J Glob Health 2018;8(1):010803.
3 Flaxman SR,Bourne RRA,Resnikoff S,Ackland P,Braithwaite T,Cicinelli MV,Das A,Jonas JB,Keeffe J,Kempen JH,Leasher J,Limburg H,Naidoo K,Pesudovs K,Silvester A,Stevens GA,Tahhan N,Wong TY,Taylor HR;Vision Loss Expert Group of the Global Burden of Disease Study.Global causes of blindness and distance vision impairment1990-2020:a systematic review and meta-analysis.Lancet Glob Health2017;5(12):e1221-e1234.
4 Zuo H,Shi ZM,Hussain A.Prevalence,trends and risk factors for the diabetes epidemic in China:a systematic review and meta-analysis.Diabetes Res Clin Pract 2014;104(1):63-72.
5 Franklin SW,Rajan SE.An automated retinal imaging method for the early diagnosis of diabetic retinopathy.Technol Health Care2013;21(6):557-569.
6 Gulshan V,Peng L,Coram M,Stumpe MC,Wu D,Narayanaswamy A,Venugopalan S,Widner K,Madams T,Cuadros J,Kim R,Raman R,Nelson PC,Mega JL,Webster DR.Development and validation of a deep learning algorithm for detection of diabetic retinopathy in retinal fundus photographs.JAMA 2016;316(22):2402-2410.
7 Lam C,Yi D,Guo M,Lindsey T.Automated detection of diabetic retinopathy using deep learning.AMIA Jt Summits Transl Sci Proc2018;2017:147-155.
8 Ganesan K,Martis RJ,Acharya UR,Chua CK,Min LC,Ng EY,Laude A.Computer-aided diabetic retinopathy detection using trace transforms on digital fundus images.Med Biol Eng Comput 2014;52(8):663-672.
9 Casanova R,Saldana S,Chew EY,Danis RP,Greven CM,Ambrosius WT.Application of random forests methods to diabetic retinopathy classification analyses.PLo S One 2014;9(6):e98587.
10 Miranda E,Irwansyah E,Amelga AY,Maribondang MM,Salim M.Detection of cardiovascular disease risk’s level for adults using naive Bayes classifier.Healthc Inform Res 2016;22(3):196-205.
11 Sambo F,Trifoglio E,Di Camillo B,Toffolo GM,Cobelli C.Bag of Na?ve Bayes:biomarker selection and classification from genome-wide SNP data.BMC Bioinformatics 2012;13(Suppl 14):S2.
12 de Souza JWM,Alves SSA,Rebou?as ES,Almeida JS,Rebou?as Filho PP.A new approach to diagnose parkinson’s disease using a structural cooccurrence matrix for a similarity analysis.Comput Intell Neurosci 2018;2018:7613282.
13 An GZ,Omodaka K,Tsuda S,Shiga Y,Takada N,Kikawa T,Nakazawa T,Yokota H,Akiba M.Comparison of machine-learning classification models for glaucoma management.J Healthc Eng 2018;2018:6874765.
14 Mistry H,Auguste P,Lois N,Waugh N.Diabetic retinopathy and the use of laser photocoagulation:is it cost-effective to treat early?BMJ Open Ophthalmol 2017;2(1):e000021.
15 Jenkins AJ,Joglekar MV,Hardikar AA,Keech AC,O’Neal DN,Januszewski AS.Biomarkers in diabetic retinopathy.Rev Diabet Stud2015;12(1-2):159-195.
16 Maghbooli Z,Hossein-nezhad A,Larijani B,Amini M,Keshtkar A.Global DNA methylation as a possible biomarker for diabetic retinopathy.Diabetes Metab Res Rev 2015;31(2):183-189.
17 Cunha-Vaz J,Ribeiro L,Lobo C.Phenotypes and biomarkers of diabetic retinopathy.Prog Retin Eye Res 2014;41:90-111.
18 Khan AA,Rahmani AH,Aldebasi YH.Diabetic retinopathy:recent updates on different biomarkers and some therapeutic agents.Curr Diabetes Rev 2018;14(6):523-533.
19 Haralick RM.Statistical and structural approaches to texture.Proc IEEE 1979;67(5):786-804.
20 Song CI,Ryu CH,Choi SH,Roh JL,Nam SY,Kim SY.Quantitative evaluation of vocal-fold mucosal irregularities using GLCM-based texture analysis.Laryngoscope 2013;123(11):E45-E50.
21 Chen X,Wei XH,Zhang ZP,Yang RM,Zhu YJ,Jiang XQ.Differentiation of true-progression from pseudoprogression in glioblastoma treated with radiation therapy and concomitant temozolomide by GLCM texture analysis of conventional MRI.Clin Imaging 2015;39(5):775-780.
22 Lian MJ,Huang CL.Texture feature extraction of gray-level cooccurrence matrix for metastatic cancer cells using scanned laser picoprojection images.Lasers Med Sci 2018.
23 Haralick RM,Shanmugam K,Dinstein I.Textural features for image classification.IEEE Trans Syst,Man,Cybern 1973;SMC-3(6):610-621.
24 Ulaby F,Kouyate F,Brisco B,Williams TH.Textural infornation in SAR images.IEEE Trans Geosci Remote Sensing 1986;GE-24(2):235-245.
25 Baraldi A,Parmiggiani F.An investigation of the textural characteristics associated with gray level cooccurrence matrix statistical parameters.IEEE Trans Geosci Remote Sensing 1995;33(2):293-304.
26 Al-Shabrawey M,Zhang WB,McDonald D.Diabetic retinopathy:mechanism,diagnosis,prevention,and treatment.Biomed Res Int2015;2015:854593.
27 Zhang XY,Zhao L,Hambly B,Bao SS,Wang KY.Diabetic retinopathy:reversibility of epigenetic modifications and new therapeutic targets.Cell Biosci 2017;7:42.
28 ShuangYu,DiXiao,Kanagasingam Y.Exudate detection for diabetic retinopathy with convolutional neural networks.Conf Proc IEEE Eng Med Biol Soc 2017;2017:1744-1747.
29 Roychowdhury S,Koozekanani DD,Parhi KK.DREAM:diabetic retinopathy analysis using machine learning.IEEE J Biomed Health Inform 2014;18(5):1717-1728.
30 Acharya UR,Ng EY,Tan JH,Sree SV,Ng KH.An integrated index for the identification of diabetic retinopathy stages using texture parameters.JMed Syst 2012;36(3):2011-2020.
31 Khojasteh P,Aliahmad B,Arjunan SP,Kumar DK.Introducing a novel layer in convolutional neural network for automatic identification of diabetic retinopathy.Conf Proc IEEE Eng Med Biol Soc 2018;2018:5938-5941.