{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,8]],"date-time":"2026-05-08T16:25:04Z","timestamp":1778257504753,"version":"3.51.4"},"reference-count":57,"publisher":"Wiley","issue":"10","license":[{"start":{"date-parts":[[2019,8,31]],"date-time":"2019-08-31T00:00:00Z","timestamp":1567209600000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/onlinelibrary.wiley.com\/termsAndConditions#vor"}],"content-domain":{"domain":["aapm.onlinelibrary.wiley.com"],"crossmark-restriction":true},"short-container-title":["Medical Physics"],"published-print":{"date-parts":[[2019,10]]},"abstract":"<jats:sec><jats:title>Background and objective<\/jats:title><jats:p>The detection of abnormalities such as lesions or leakage from retinal images is an important health informatics task for automated early diagnosis of diabetic and malarial retinopathy or other eye diseases, in order to prevent blindness and common systematic conditions. In this work, we propose a novel retinal lesion detection method by adapting the concepts of saliency.<\/jats:p><\/jats:sec><jats:sec><jats:title>Methods<\/jats:title><jats:p>Retinal images are first segmented as superpixels, two new saliency feature representations: <jats:italic>uniqueness<\/jats:italic> and <jats:italic>compactness<\/jats:italic>, are then derived to represent the superpixels. The pixel level saliency is then estimated from these superpixel saliency values via a bilateral filter. These extracted saliency features form a matrix for low\u2010rank analysis to achieve saliency detection. The precise contour of a lesion is finally extracted from the generated saliency map after removing confounding structures such as blood vessels, the optic disk, and the fovea. The main novelty of this method is that it is an effective tool for detecting different abnormalities at the pixel level from different modalities of retinal images, without the need to tune parameters.<\/jats:p><\/jats:sec><jats:sec><jats:title>Results<\/jats:title><jats:p>To evaluate its effectiveness, we have applied our method to seven public datasets of diabetic and malarial retinopathy with four different types of lesions: exudate, hemorrhage, microaneurysms, and leakage. The evaluation was undertaken at the pixel level, lesion level, or image level according to ground truth availability in these datasets.<\/jats:p><\/jats:sec><jats:sec><jats:title>Conclusions<\/jats:title><jats:p>The experimental results show that the proposed method outperforms existing state\u2010of\u2010the\u2010art ones in applicability, effectiveness, and accuracy.<\/jats:p><\/jats:sec>","DOI":"10.1002\/mp.13746","type":"journal-article","created":{"date-parts":[[2019,8,5]],"date-time":"2019-08-05T15:13:27Z","timestamp":1565018007000},"page":"4531-4544","update-policy":"https:\/\/doi.org\/10.1002\/crossmark_policy","source":"Crossref","is-referenced-by-count":11,"title":["Automated retinal lesion detection via image saliency analysis"],"prefix":"10.1002","volume":"46","author":[{"given":"Qifeng","family":"Yan","sequence":"first","affiliation":[{"name":"University of Chinese Academy of Sciences Beijing 100049 China"},{"name":"Cixi Institute of Biomedical Engineering Ningbo Institute of Materials Technology and Engineering Chinese Academy of Sciences Cixi 315399 China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yitian","family":"Zhao","sequence":"additional","affiliation":[{"name":"Cixi Institute of Biomedical Engineering Ningbo Institute of Materials Technology and Engineering Chinese Academy of Sciences Cixi 315399 China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yalin","family":"Zheng","sequence":"additional","affiliation":[{"name":"Cixi Institute of Biomedical Engineering Ningbo Institute of Materials Technology and Engineering Chinese Academy of Sciences Cixi 315399 China"},{"name":"Department of Eye and Vision Science University of Liverpool Liverpool L7 8TX UK"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yonghuai","family":"Liu","sequence":"additional","affiliation":[{"name":"Department of Computer Science Edge Hill University Ormskirk L39 4QP UK"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Kang","family":"Zhou","sequence":"additional","affiliation":[{"name":"Cixi Institute of Biomedical Engineering Ningbo Institute of Materials Technology and Engineering Chinese Academy of Sciences Cixi 315399 China"},{"name":"School of Information Science and Technology ShanghaiTech University Shanghai 201210 China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Alejandro","family":"Frangi","sequence":"additional","affiliation":[{"name":"Cixi Institute of Biomedical Engineering Ningbo Institute of Materials Technology and Engineering Chinese Academy of Sciences Cixi 315399 China"},{"name":"School of Computing University of Leeds Leeds S2 9JT UK"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jiang","family":"Liu","sequence":"additional","affiliation":[{"name":"Cixi Institute of Biomedical Engineering Ningbo Institute of Materials Technology and Engineering Chinese Academy of Sciences Cixi 315399 China"},{"name":"Department of Computer Science and Engineering Southern University of Science and Technology Shenzhen 518055 China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"311","published-online":{"date-parts":[[2019,8,31]]},"reference":[{"key":"e_1_2_9_2_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.media.2006.09.006"},{"key":"e_1_2_9_3_1","first-page":"2119","article-title":"Cerebral malaria in children: using the retina to study the brain","volume":"2014","author":"MacCormick I","journal-title":"Brain"},{"key":"e_1_2_9_4_1","doi-asserted-by":"publisher","DOI":"10.1109\/TMI.2015.2509785"},{"key":"e_1_2_9_5_1","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2018.2815345"},{"key":"e_1_2_9_6_1","doi-asserted-by":"publisher","DOI":"10.1109\/JBHI.2015.2498104"},{"key":"e_1_2_9_7_1","unstructured":"ShenX WuY.A unified approach to salient object detection via low rank matrix recovery.In:Proceedings of CVPR;2012:853\u2013860."},{"key":"e_1_2_9_8_1","doi-asserted-by":"publisher","DOI":"10.1109\/34.730558"},{"key":"e_1_2_9_9_1","first-page":"219","article-title":"Shifts in selective visual attention: towards the underlying neural circuitry","volume":"44","author":"Koch C","year":"1985","journal-title":"Human Neurobiol"},{"key":"e_1_2_9_10_1","doi-asserted-by":"publisher","DOI":"10.1109\/TMI.2015.2418534"},{"key":"e_1_2_9_11_1","doi-asserted-by":"publisher","DOI":"10.1109\/LSP.2010.2053200"},{"key":"e_1_2_9_12_1","doi-asserted-by":"publisher","DOI":"10.1364\/JOSAA.23.002462"},{"key":"e_1_2_9_13_1","doi-asserted-by":"crossref","unstructured":"ZhaoY ZhengY ZhaoY et\u00a0al.Uniqueness\u2010Driven Saliency Analysis For Automated Abnormalities Detection with Application to Retinal Diseases.In:Proceedings of MICCAI;2018:109\u2013118.","DOI":"10.1007\/978-3-030-00934-2_13"},{"key":"e_1_2_9_14_1","doi-asserted-by":"publisher","DOI":"10.1109\/JBHI.2013.2294635"},{"key":"e_1_2_9_15_1","doi-asserted-by":"publisher","DOI":"10.1109\/RBME.2017.2705064"},{"key":"e_1_2_9_16_1","doi-asserted-by":"publisher","DOI":"10.1109\/TMI.2006.879953"},{"key":"e_1_2_9_17_1","doi-asserted-by":"crossref","unstructured":"GiancardoL M\u00e9riaudeauF LiY TobinKW ChaumE.Microaneurysm detection with radon transform\u2010based classification on retina images.In:Proceedings of EMBC;2011:5939\u20135942.","DOI":"10.1109\/IEMBS.2011.6091562"},{"key":"e_1_2_9_18_1","doi-asserted-by":"publisher","DOI":"10.1109\/TMI.2012.2227119"},{"key":"e_1_2_9_19_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.ins.2014.10.059"},{"key":"e_1_2_9_20_1","doi-asserted-by":"publisher","DOI":"10.1371\/journal.pone.0161556"},{"key":"e_1_2_9_21_1","doi-asserted-by":"publisher","DOI":"10.1007\/BF00920219"},{"key":"e_1_2_9_22_1","doi-asserted-by":"publisher","DOI":"10.1109\/TMI.2002.806290"},{"key":"e_1_2_9_23_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.media.2009.05.005"},{"key":"e_1_2_9_24_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.media.2011.05.004"},{"key":"e_1_2_9_25_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.compmedimag.2009.10.001"},{"key":"e_1_2_9_26_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.media.2011.07.004"},{"key":"e_1_2_9_27_1","doi-asserted-by":"publisher","DOI":"10.1109\/JBHI.2013.2296399"},{"key":"e_1_2_9_28_1","doi-asserted-by":"publisher","DOI":"10.1167\/iovs.14-15457"},{"key":"e_1_2_9_29_1","doi-asserted-by":"publisher","DOI":"10.1109\/TMI.2016.2593725"},{"key":"e_1_2_9_30_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.compmedimag.2016.09.001"},{"key":"e_1_2_9_31_1","doi-asserted-by":"publisher","DOI":"10.1109\/TBME.2012.2201717"},{"key":"e_1_2_9_32_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.media.2014.05.004"},{"key":"e_1_2_9_33_1","doi-asserted-by":"crossref","unstructured":"GondalWM K\u00f6hlerJM GrzeszickR FinkGA HirschM.Weakly\u2010supervised localization of diabetic retinopathy lesions.In: retinal fundus images.Proceedings of ICIP;2017:2069\u20132073.","DOI":"10.1109\/ICIP.2017.8296646"},{"key":"e_1_2_9_34_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.media.2017.04.012"},{"key":"e_1_2_9_35_1","doi-asserted-by":"crossref","unstructured":"PerazziF PritchY HornungA.Saliency filters: Contrast based filtering for salient region detection.In:Proceedings of CVPR2012.","DOI":"10.1109\/CVPR.2012.6247743"},{"key":"e_1_2_9_36_1","doi-asserted-by":"crossref","unstructured":"ChengM ZhangG MitraN HuS.Global Contrast based Salient Region Detection.In:Proceedings of CVPR;2011:409\u2013416.","DOI":"10.1109\/CVPR.2011.5995344"},{"key":"e_1_2_9_37_1","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2012.120"},{"key":"e_1_2_9_38_1","doi-asserted-by":"publisher","DOI":"10.1145\/1970392.1970395"},{"key":"e_1_2_9_39_1","unstructured":"WrightJ GaneshA RaoS PengY MaY.Robust Principal Component Analysis: Exact Recovery of Corrupted Low\u2010Rank Matrices via Convex Optimization.In:Proceedings of NIPS;2009:2080\u20132088."},{"key":"e_1_2_9_40_1","doi-asserted-by":"publisher","DOI":"10.1109\/TMI.2015.2409024"},{"key":"e_1_2_9_41_1","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2010.2069690"},{"key":"e_1_2_9_42_1","doi-asserted-by":"publisher","DOI":"10.1038\/srep10425"},{"key":"e_1_2_9_43_1","doi-asserted-by":"publisher","DOI":"10.1109\/TMI.2013.2247770"},{"key":"e_1_2_9_44_1","doi-asserted-by":"publisher","DOI":"10.1109\/TMI.2007.902801"},{"key":"e_1_2_9_45_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.cmpb.2014.01.010"},{"key":"e_1_2_9_46_1","doi-asserted-by":"crossref","unstructured":"KauppiT KalesnykieneV SorriI et\u00a0al.The DIARETDB1 Diabetic Retinopathy Database and Evaluation Protocol.In:Proceedings of BMVC;2007.","DOI":"10.5244\/C.21.15"},{"key":"e_1_2_9_47_1","doi-asserted-by":"publisher","DOI":"10.1109\/TMI.2009.2033909"},{"key":"e_1_2_9_48_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.irbm.2013.01.010"},{"key":"e_1_2_9_49_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.compmedimag.2014.11.010"},{"key":"e_1_2_9_50_1","doi-asserted-by":"publisher","DOI":"10.1109\/TBME.2012.2193126"},{"key":"e_1_2_9_51_1","doi-asserted-by":"crossref","unstructured":"ZhouL LiP YuQ et\u00a0al.Automatic hemorrhage detection in color fundus images based on gradual removal of vascular branches.In:Proceedings of ICIP;2016:399\u2013403.","DOI":"10.1109\/ICIP.2016.7532387"},{"key":"e_1_2_9_52_1","doi-asserted-by":"crossref","unstructured":"HouX ZhangL.Saliency detection: A spectral residual approach. inProceedings of CVPR;2007:1\u20138.","DOI":"10.1109\/CVPR.2007.383267"},{"key":"e_1_2_9_53_1","doi-asserted-by":"crossref","unstructured":"AchantaR HemamiS EstradaF SusstrunkS.Frequency\u2010tuned salient region detection.In:Proceedings of CVPR;2009:1597\u20131604.","DOI":"10.1109\/CVPR.2009.5206596"},{"key":"e_1_2_9_54_1","doi-asserted-by":"crossref","unstructured":"HarelJ KochC PeronaP.Graph\u2010based visual saliency.In:Proceedings of NIPS;2006:545\u2013552.","DOI":"10.7551\/mitpress\/7503.003.0073"},{"key":"e_1_2_9_55_1","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2011.272"},{"key":"e_1_2_9_56_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.compmedimag.2016.08.001"},{"key":"e_1_2_9_57_1","doi-asserted-by":"publisher","DOI":"10.1109\/TBME.2016.2585344"},{"key":"e_1_2_9_58_1","unstructured":"HaloiM DandapatS SinhaR.A Gaussian Scale Space Approach For Exudates Detection Classification And Severity PredictionCoRR.2015;abs\/1505.00737."}],"container-title":["Medical Physics"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/onlinelibrary.wiley.com\/doi\/pdf\/10.1002\/mp.13746","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/onlinelibrary.wiley.com\/doi\/full-xml\/10.1002\/mp.13746","content-type":"application\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/aapm.onlinelibrary.wiley.com\/doi\/pdf\/10.1002\/mp.13746","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,9,5]],"date-time":"2023-09-05T11:43:59Z","timestamp":1693914239000},"score":1,"resource":{"primary":{"URL":"https:\/\/aapm.onlinelibrary.wiley.com\/doi\/10.1002\/mp.13746"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2019,8,31]]},"references-count":57,"journal-issue":{"issue":"10","published-print":{"date-parts":[[2019,10]]}},"alternative-id":["10.1002\/mp.13746"],"URL":"https:\/\/doi.org\/10.1002\/mp.13746","archive":["Portico"],"relation":{},"ISSN":["0094-2405","2473-4209"],"issn-type":[{"value":"0094-2405","type":"print"},{"value":"2473-4209","type":"electronic"}],"subject":[],"published":{"date-parts":[[2019,8,31]]},"assertion":[{"value":"2019-05-14","order":0,"name":"received","label":"Received","group":{"name":"publication_history","label":"Publication History"}},{"value":"2019-07-22","order":1,"name":"accepted","label":"Accepted","group":{"name":"publication_history","label":"Publication History"}},{"value":"2019-08-31","order":2,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}