{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,4,11]],"date-time":"2025-04-11T13:26:17Z","timestamp":1744377977319},"reference-count":46,"publisher":"Wiley","issue":"6","license":[{"start":{"date-parts":[[2023,1,11]],"date-time":"2023-01-11T00:00:00Z","timestamp":1673395200000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/onlinelibrary.wiley.com\/termsAndConditions#vor"}],"funder":[{"DOI":"10.13039\/100012615","name":"University of Texas Health Science Center at Houston","doi-asserted-by":"publisher","id":[{"id":"10.13039\/100012615","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100000002","name":"National Institutes of Health","doi-asserted-by":"publisher","award":["R01DE027027"],"award-info":[{"award-number":["R01DE027027"]}],"id":[{"id":"10.13039\/100000002","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["aapm.onlinelibrary.wiley.com"],"crossmark-restriction":true},"short-container-title":["Medical Physics"],"published-print":{"date-parts":[[2023,6]]},"abstract":"<jats:title>Abstract<\/jats:title><jats:sec><jats:title>Background<\/jats:title><jats:p>Medical images have already become an essential tool for the diagnosis of many diseases. Thus a large number of medical images are being generated due to the daily routine inspection. An efficient image\u2010based disease retrieval system will not only make full use of existing data, but also help physicians to prognosis the diseases. Medical image retrieval is represented by the classification and localization of common thorax diseases in x\u2010ray images. Although extensive efforts have been put into this field, there are still many\u00a0challenges.<\/jats:p><\/jats:sec><jats:sec><jats:title>Purpose<\/jats:title><jats:p>Most of the existing fine\u2010grained image research methods just apply existing deep learning frameworks in extracting the image features. However, these high\u2010level features mainly focus on the global representations of the object, rather than simultaneously considering the local ones. It requires fine\u2010grained details to classify the images with similar lesion areas. Thus, it is necessary to combine the global features and local ones to make the features more discriminative. On the other hand, training CNN models based on current existing strategies have a high time complexity, and is hard to get the discriminative features mentioned above. In addition, the visual retrieval method of fine\u2010grained medical images still has the problem of insufficient sample data with accurate annotation\u00a0information.<\/jats:p><\/jats:sec><jats:sec><jats:title>Methods<\/jats:title><jats:p>To address above challenges, we introduced a novel fine\u2010grained medical images retrieval method. First, a centralized contrastive loss (CCLoss) is proposed as our metric learning loss function. Parameters are updated by using the center point, which not only improves the distinguishing performance of features, but also effectively reduces the time complexity of the algorithm. In addition, a weakly supervised progressive feature extraction method is proposed to gradually extract the combined features. And the attention mechanism module is applied to screen the target information after the initial positioning for fine refinement, so as to separate the features with a high degree of discrimination. The retrieval of 14 different chest diseases is evaluated on the chest x\u2010ray\u00a0datasets.<\/jats:p><\/jats:sec><jats:sec><jats:title>Results<\/jats:title><jats:p>Compared with the existing research methods, the proposed method shows a better retrieval result for Recall@8 by 2.26 and achieves a very efficient training speed which is 100 times faster than the pair\u2010wise loss\u2010based training strategy. We also assessed the effects of Recall@k (<jats:italic>k<\/jats:italic>= 2, 4, 6, 8) for progressive features extracted from different steps to obtain a model with the best retrieval\u00a0performance.<\/jats:p><\/jats:sec><jats:sec><jats:title>Conclusions<\/jats:title><jats:p>The proposed model is capable of learning discriminative representations from chest x\u2010ray datasets, and it achieves better performance compared with other state\u2010of\u2010the\u2010art methods. Therefore, the developed model would be useful in the diagnosis of common thorax disease or unknown chest\u00a0disease.<\/jats:p><\/jats:sec>","DOI":"10.1002\/mp.16144","type":"journal-article","created":{"date-parts":[[2022,12,14]],"date-time":"2022-12-14T14:02:25Z","timestamp":1671026545000},"page":"3560-3572","update-policy":"http:\/\/dx.doi.org\/10.1002\/crossmark_policy","source":"Crossref","is-referenced-by-count":3,"title":["Centralized contrastive loss with weakly supervised progressive feature extraction for fine\u2010grained common thorax disease retrieval in chest x\u2010ray"],"prefix":"10.1002","volume":"50","author":[{"given":"Fang","family":"Chen","sequence":"first","affiliation":[{"name":"School of Electronics and Information Engineering Tongji University Shanghai China"},{"name":"School of Biomedical Informatics The University of Texas Health Science Center at Houston Houston Texas USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Lei","family":"You","sequence":"additional","affiliation":[{"name":"School of Biomedical Informatics The University of Texas Health Science Center at Houston Houston Texas USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Weiling","family":"Zhao","sequence":"additional","affiliation":[{"name":"School of Biomedical Informatics The University of Texas Health Science Center at Houston Houston Texas USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xiaobo","family":"Zhou","sequence":"additional","affiliation":[{"name":"School of Biomedical Informatics The University of Texas Health Science Center at Houston Houston Texas USA"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"311","published-online":{"date-parts":[[2023,1,11]]},"reference":[{"key":"e_1_2_9_2_1","doi-asserted-by":"crossref","unstructured":"MunjalMN BhatiaS.A novel technique for effective image gallery search using content based image retrieval system.2019 International Conference on Machine Learning Big Data Cloud and Parallel Computing (COMITCon) Taiyuan China.2019:25\u201029.","DOI":"10.1109\/COMITCon.2019.8862206"},{"key":"e_1_2_9_3_1","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2015.2408566"},{"key":"e_1_2_9_4_1","unstructured":"ChenH ChenCL TangXO.Local similarity\u2010aware deep feature embedding.NIPS'16: Proceedings of the 30th International Conference on Neural Information Processing Systems Barcelona Spain.2016:1270\u20101278."},{"key":"e_1_2_9_5_1","doi-asserted-by":"crossref","unstructured":"SongHY YuX StefanieJ SilvioS.Deep metric learning via lifted structured feature embedding.Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition Las Vegas USA.2016:4004\u20104012.","DOI":"10.1109\/CVPR.2016.434"},{"key":"e_1_2_9_6_1","doi-asserted-by":"crossref","unstructured":"WangXS PengYF LeL.TieNet: text\u2010image embedding network for common thorax disease classification and reporting in chest X\u2010rays.2018 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR) SLC USA.2018:9049\u20109058.","DOI":"10.1109\/CVPR.2018.00943"},{"key":"e_1_2_9_7_1","doi-asserted-by":"crossref","unstructured":"WangXS PengYF LuL LuZY BagheriM SummersRM.ChestX\u2010ray8: hospital\u2010scale chest X\u2010ray database and benchmarks on weakly\u2010supervised classification and localization of common thorax diseases.2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) Hawaii USA.2017:3462\u20103471.","DOI":"10.1109\/CVPR.2017.369"},{"key":"e_1_2_9_8_1","doi-asserted-by":"crossref","unstructured":"LeeHJ KimJU LeeS KimHG RoYM.Structure boundary preserving segmentation for medical image with ambiguous boundary.2020 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR) Seattle USA.2020:4817\u20104826.","DOI":"10.1109\/CVPR42600.2020.00487"},{"key":"e_1_2_9_9_1","doi-asserted-by":"crossref","unstructured":"MahapatraD BozorgtabarB ShaoL.Pathological retinal region segmentation from OCT images using geometric relation based augmentation.2020 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR) Seattle USA.2020:9608\u20109617.","DOI":"10.1109\/CVPR42600.2020.00963"},{"key":"e_1_2_9_10_1","doi-asserted-by":"crossref","unstructured":"YiJ HuangJJ QinJ LuoY.Joint heterogeneous pair\u2010wise loss for top\u2010N recommendation.2019 IEEE\/WIC\/ACM International Conference on Web Intelligence Thessaloniki Greece.2019:188\u2010191.","DOI":"10.1145\/3350546.3352517"},{"key":"e_1_2_9_11_1","doi-asserted-by":"crossref","unstructured":"DhamyalH ZhouTY RajB SinghR.Optimizing neural network embeddings using a pair\u2010wise loss for text\u2010independent speaker verification.2019 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU) Sentosa Singapore.2019:742\u2010748.","DOI":"10.1109\/ASRU46091.2019.9003794"},{"key":"e_1_2_9_12_1","doi-asserted-by":"crossref","unstructured":"ZhaoYB YangC WangYS CaiJ XueYB.Face recognition for embedded system based on optimized triplet loss neural network.2020 3rd International Conference on Advanced Electronic Materials Computers and Software Engineering (AEMCSE) Shenzhen China.2020:260\u2010263.","DOI":"10.1109\/AEMCSE50948.2020.00063"},{"key":"e_1_2_9_13_1","doi-asserted-by":"crossref","unstructured":"YuanY ChenWY YangY WangZY.In defense of the triplet loss again: learning robust person re\u2010identification with fast approximated triplet loss and label distillation.2020 IEEE\/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW) Seattle WA USA.2020:1454\u20101463.","DOI":"10.1109\/CVPRW50498.2020.00185"},{"key":"e_1_2_9_14_1","doi-asserted-by":"crossref","unstructured":"LiaoLF LiZM.Deep hashing using n\u2010pair loss for image retrieval.2020 16th International Conference on Computational Intelligence and Security (CIS) Nanning China.2020:20\u201024.","DOI":"10.1109\/CIS52066.2020.00013"},{"key":"e_1_2_9_15_1","doi-asserted-by":"crossref","unstructured":"HirataK KatoT.Query visual example content based image retrieval.Advances in Database Technology \u2010 EDBT'92 3rd International Conference on Extending Database Technology Vienna Austria.1992.","DOI":"10.1007\/BFb0032423"},{"key":"e_1_2_9_16_1","doi-asserted-by":"crossref","unstructured":"ShekharR JawaharCV.Word image retrieval using bag of visual words.2012 10th IAPR International Workshop on Document Analysis Systems Queensland Australia.2012:297\u2010301.","DOI":"10.1109\/DAS.2012.96"},{"key":"e_1_2_9_17_1","doi-asserted-by":"crossref","unstructured":"MiaoH ZhangYS.Construction of polysemy table and search engine based on inverted index.2012 9th International Conference on Fuzzy Systems and Knowledge Discovery Sichuan China.2012:2287\u20102290.","DOI":"10.1109\/FSKD.2012.6234156"},{"key":"e_1_2_9_18_1","doi-asserted-by":"crossref","unstructured":"WangZQ LiZ SunJ XuYL.Selective convolutional features based generalized\u2010mean pooling for fine\u2010grained image retrieval.2018 IEEE Visual Communications and Image Processing (VCIP) Taiwan China.2018.","DOI":"10.1109\/VCIP.2018.8698729"},{"key":"e_1_2_9_19_1","doi-asserted-by":"crossref","unstructured":"GeW YuY.Borrowing treasures from the wealthy: deep transfer learning through selective joint fine\u2010tuning.IEEE Conference on Computer Vision and Pattern Recognition (CVPR) Hawaii USA.2017:10\u201019.","DOI":"10.1109\/CVPR.2017.9"},{"key":"e_1_2_9_20_1","doi-asserted-by":"crossref","unstructured":"ZhangN DonahueJ GirshickR DarrellT.Part\u2010based R\u2010CNNs for fine\u2010grained category detection.European Conference on Computer Vision.2014:834\u2010849.","DOI":"10.1007\/978-3-319-10590-1_54"},{"key":"e_1_2_9_21_1","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2017.2688133"},{"key":"e_1_2_9_22_1","doi-asserted-by":"crossref","unstructured":"LinTY RoyChowdhuryA MajiS.Bilinear CNN models for fine\u2010grained visual recognition.2015 IEEE International Conference on Computer Vision (ICCV) Santiago Chile.2015:1449\u20101457.","DOI":"10.1109\/ICCV.2015.170"},{"key":"e_1_2_9_23_1","doi-asserted-by":"crossref","unstructured":"Alzu'BiA AmiraA RamzanN.Compact Root bilinear CNNs for content\u2010based image retrieval.2016 International Conference on Image Vision and Computing (ICIVC) Portsmouth UK.2016:41\u201045.","DOI":"10.1109\/ICIVC.2016.7571271"},{"key":"e_1_2_9_24_1","doi-asserted-by":"crossref","unstructured":"HuT ZhuangBJ YanH CaiA.Depth extraction from a single image by sampling based on distance metric learning.2014 IEEE International Conference on Image Processing (ICIP) Paris France.2014:2017\u20102021.","DOI":"10.1109\/ICIP.2014.7025404"},{"key":"e_1_2_9_25_1","doi-asserted-by":"crossref","unstructured":"SultanLR SchultzSM CaryTW SehgalCM.Machine learning to improve breast cancer diagnosis by multimodal ultrasound.2018 IEEE International Ultrasonics Symposium (IUS) Kobe Japan.2018.","DOI":"10.1109\/ULTSYM.2018.8579953"},{"key":"e_1_2_9_26_1","unstructured":"XiaoYF ZhouWJ ShenL ChangC ZhouSC ShiJ.Ultrasound\u2010based diagnosis of breast tumor with parameter transfer multilayer kernel extreme learning machine.2019 41st Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC) Berlin Germany.2019."},{"key":"e_1_2_9_27_1","doi-asserted-by":"crossref","unstructured":"AhmedMF JayarathnaS ChoSH.Feasibility of X\u2010ray Fluorescence Computed Tomography (XFCT) imaging of human lung tumors loaded with gold nanoparticles: a Monte Carlo Study.2018 IEEE 12th International Conference on Nano\/Molecular Medicine and Engineering (NANOMED) Hawaii USA.2018.","DOI":"10.1109\/NANOMED.2018.8641551"},{"key":"e_1_2_9_28_1","doi-asserted-by":"crossref","unstructured":"BiagiL GagliardiV ReticoA et\u00a0al.Assessment of ultra\u2010high\u2010field magnetic resonance imaging safety via temperature increase monitoring with magnetic resonance thermometry.2020 IEEE International Symposium on Medical Measurements and Applications (MeMeA).2020.","DOI":"10.1109\/MeMeA49120.2020.9137190"},{"key":"e_1_2_9_29_1","doi-asserted-by":"crossref","unstructured":"YaoXK SunY.Noise suppression for surface nuclear magnetic resonance data based on frame energy spectrum subtraction.2019 3rd International Conference on Electronic Information Technology and Computer Engineering (EITCE) Xiamen China.2019.","DOI":"10.1109\/EITCE47263.2019.9095012"},{"key":"e_1_2_9_30_1","doi-asserted-by":"publisher","DOI":"10.1109\/TMI.2016.2615567"},{"key":"e_1_2_9_31_1","doi-asserted-by":"crossref","unstructured":"SinghD Dharmveer SinghB.A new morphology based approach for blood vessel segmentation in retinal images.2014 Annual IEEE India Conference (INDICON) Pune India.2014.","DOI":"10.1109\/INDICON.2014.7030686"},{"key":"e_1_2_9_32_1","doi-asserted-by":"crossref","unstructured":"KambaliI SuryantoH.Cancer imaging using positron emission tomography\/computed tomography.2020 International Seminar on Intelligent Technology and Its Applications (ISITIA).2020.","DOI":"10.1109\/ISITIA49792.2020.9163740"},{"key":"e_1_2_9_33_1","doi-asserted-by":"publisher","DOI":"10.1109\/TMI.2009.2037146"},{"key":"e_1_2_9_34_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.compmedimag.2009.06.003"},{"key":"e_1_2_9_35_1","doi-asserted-by":"crossref","unstructured":"CaoW ShanJ CzarnekN LiL.Microaneurysm detection in fundus images using small image patches and machine learning methods.2017 IEEE International Conference on Bioinformatics and Biomedicine (BIBM) USA.2017.","DOI":"10.1109\/BIBM.2017.8217671"},{"key":"e_1_2_9_36_1","doi-asserted-by":"publisher","DOI":"10.1038\/nature21056"},{"key":"e_1_2_9_37_1","doi-asserted-by":"crossref","unstructured":"ChenH DouQ WangX QinJ HengPA.Mitosis detection in breast cancer histology images via deep cascaded networks.AAAI Conference on Artificial Intelligence Phoenix USA.2016:1160\u20101166.","DOI":"10.1609\/aaai.v30i1.10140"},{"key":"e_1_2_9_38_1","doi-asserted-by":"crossref","unstructured":"GondalWM KohlerJM GrzeszickR FinkGA HirschM.Weakly\u2010supervised localization of diabetic retinopathy lesions in retinal fundus images.2017 IEEE International Conference on Image Processing Beijing China.2017:2069\u20102073.","DOI":"10.1109\/ICIP.2017.8296646"},{"key":"e_1_2_9_39_1","doi-asserted-by":"publisher","DOI":"10.18280\/ts.370615"},{"key":"e_1_2_9_40_1","doi-asserted-by":"crossref","unstructured":"LiDQ ChenQY WangM HeSW YangDC.Research on location selection of distribution network repair center considering loss of load level.2019 IEEE 3rd International Electrical and Energy Conference (CIEEC) Beijing China.2019.","DOI":"10.1109\/CIEEC47146.2019.CIEEC-2019413"},{"key":"e_1_2_9_41_1","doi-asserted-by":"crossref","unstructured":"HeXW ZhouY ZhouZC BaiS BaiX.Triplet\u2010center loss for multi\u2010view 3D object retrieval.2018 IEEE\/CVF Conference on Computer Vision and Pattern Recognition Salt Lake City USA.2018:1945\u20101954.","DOI":"10.1109\/CVPR.2018.00208"},{"key":"e_1_2_9_42_1","doi-asserted-by":"crossref","unstructured":"JiangYH SongY YanJ DaiLR.Triplet\u2010center loss based deep embedding learning method for speaker verification.2019 Asia\u2010Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC) Lanzhou China.2019.","DOI":"10.1109\/APSIPAASC47483.2019.9023301"},{"key":"e_1_2_9_43_1","doi-asserted-by":"crossref","unstructured":"LiL XuM WangXF JiangL LiuH.Attention based glaucoma detection: a large\u2010scale database and CNN model.2019 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR) California USA.2019:413\u2010424.","DOI":"10.1109\/CVPR.2019.01082"},{"key":"e_1_2_9_44_1","doi-asserted-by":"crossref","unstructured":"ZhengFJ.Look closer to see better: recurrent attention convolutional neural network for fine\u2010grained image recognition.2017 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR) Hawaii USA.2017:4476\u20104484.","DOI":"10.1109\/ICCV.2017.557"},{"key":"e_1_2_9_45_1","unstructured":"IrvinJ RajpurkarP KoM et\u00a0al.CheXpert: A large chest radiograph dataset with uncertainty labels and expert comparison. Hawaii USA. 2019 Association for the Advancement of Artificial Intelligence (AAAI).2019."},{"key":"e_1_2_9_46_1","unstructured":"JohnsonAEW PollardTJ BerkowitzSJ et\u00a0al.MIMIC\u2010CXR: a large publicly available database of labeled chest radiographs. California USA. 2019 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR).2019."},{"key":"e_1_2_9_47_1","first-page":"255","author":"Naronglerdrit P","year":"2021","journal-title":"Data Science for COVID\u201019"}],"container-title":["Medical Physics"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/onlinelibrary.wiley.com\/doi\/pdf\/10.1002\/mp.16144","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/onlinelibrary.wiley.com\/doi\/full-xml\/10.1002\/mp.16144","content-type":"application\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/aapm.onlinelibrary.wiley.com\/doi\/pdf\/10.1002\/mp.16144","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,10,10]],"date-time":"2024-10-10T10:27:06Z","timestamp":1728556026000},"score":1,"resource":{"primary":{"URL":"https:\/\/aapm.onlinelibrary.wiley.com\/doi\/10.1002\/mp.16144"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,1,11]]},"references-count":46,"journal-issue":{"issue":"6","published-print":{"date-parts":[[2023,6]]}},"alternative-id":["10.1002\/mp.16144"],"URL":"https:\/\/doi.org\/10.1002\/mp.16144","archive":["Portico"],"relation":{},"ISSN":["0094-2405","2473-4209"],"issn-type":[{"type":"print","value":"0094-2405"},{"type":"electronic","value":"2473-4209"}],"subject":[],"published":{"date-parts":[[2023,1,11]]},"assertion":[{"value":"2022-03-14","order":0,"name":"received","label":"Received","group":{"name":"publication_history","label":"Publication History"}},{"value":"2022-11-14","order":1,"name":"accepted","label":"Accepted","group":{"name":"publication_history","label":"Publication History"}},{"value":"2023-01-11","order":2,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}