{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,25]],"date-time":"2026-03-25T12:41:27Z","timestamp":1774442487889,"version":"3.50.1"},"reference-count":225,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2022,1,1]],"date-time":"2022-01-01T00:00:00Z","timestamp":1640995200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/legalcode"}],"funder":[{"name":"project \u2018\u2018Transparent Artificial Medical Intelligence (TAMI),\u2019\u2019"},{"name":"European Regional Fund (ERDF) through the Operational Program for Competitiveness and Internationalization-COMPETE2020"},{"name":"North Portugal Regional Operational Program-NORTE 2020","award":["NORTE-01-0247-FEDER 045905"],"award-info":[{"award-number":["NORTE-01-0247-FEDER 045905"]}]},{"DOI":"10.13039\/501100001871","name":"Portuguese Foundation for Science and Technology (FCT) through the CMU-Portugal International Partnership, the Ph.D.","doi-asserted-by":"publisher","award":["2020.06434.BD"],"award-info":[{"award-number":["2020.06434.BD"]}],"id":[{"id":"10.13039\/501100001871","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001871","name":"Portuguese Foundation for Science and Technology (FCT) through the CMU-Portugal International Partnership, the Ph.D.","doi-asserted-by":"publisher","award":["2020.07034.BD"],"award-info":[{"award-number":["2020.07034.BD"]}],"id":[{"id":"10.13039\/501100001871","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001871","name":"Portuguese Foundation for Science and Technology (FCT) through the CMU-Portugal International Partnership, the Ph.D.","doi-asserted-by":"publisher","award":["LA\/P\/0063\/2020"],"award-info":[{"award-number":["LA\/P\/0063\/2020"]}],"id":[{"id":"10.13039\/501100001871","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Access"],"published-print":{"date-parts":[[2022]]},"DOI":"10.1109\/access.2022.3206449","type":"journal-article","created":{"date-parts":[[2022,9,14]],"date-time":"2022-09-14T19:33:20Z","timestamp":1663184000000},"page":"98909-98935","source":"Crossref","is-referenced-by-count":54,"title":["A Survey on Attention Mechanisms for Medical Applications: are we Moving Toward Better Algorithms?"],"prefix":"10.1109","volume":"10","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-4744-9174","authenticated-orcid":false,"given":"Tiago","family":"Goncalves","sequence":"first","affiliation":[{"name":"Institute for Systems and Computer Engineering, Technology and Science, Porto, Portugal"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2302-8597","authenticated-orcid":false,"given":"Isabel","family":"Rio-Torto","sequence":"additional","affiliation":[{"name":"Institute for Systems and Computer Engineering, Technology and Science, Porto, Portugal"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4050-7880","authenticated-orcid":false,"given":"Luis F.","family":"Teixeira","sequence":"additional","affiliation":[{"name":"Institute for Systems and Computer Engineering, Technology and Science, Porto, Portugal"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3760-2473","authenticated-orcid":false,"given":"Jaime S.","family":"Cardoso","sequence":"additional","affiliation":[{"name":"Institute for Systems and Computer Engineering, Technology and Science, Porto, Portugal"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1007\/978-94-009-3833-5_5"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1016\/S0042-6989(99)00163-7"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1145\/375735.376414"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1016\/0004-3702(95)00025-9"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1016\/0004-3702(91)90080-4"},{"key":"ref6","first-page":"20","article-title":"Residual Q-learning applied to visual attention","volume-title":"Proc. ICML","author":"Bandera"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1038\/nature14539"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1016\/j.neunet.2014.09.003"},{"key":"ref9","first-page":"1","article-title":"Learn to pay attention","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Jetley"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.7717\/peerj-cs.865"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2012.89"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2015.2477044"},{"key":"ref13","article-title":"Survey on the attention based RNN model and its applications in computer vision","author":"Wang","year":"2016","journal-title":"arXiv:1601.06823"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1145\/3465055"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1088\/1742-6596\/1693\/1\/012173"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.3389\/fncom.2020.00029"},{"key":"ref17","first-page":"5998","article-title":"Attention is all you need","author":"Vaswani","year":"2017","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"ref18","first-page":"1","article-title":"An image is worth 16\u271716 words: Transformers for image recognition at scale","volume-title":"Int. Conf. Learn. Represent.","author":"Dosovitskiy"},{"key":"ref19","article-title":"A survey on vision transformer","author":"Han","year":"2020","journal-title":"arXiv:2012.12556"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1145\/3505244"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1007\/s41095-022-0271-y"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1007\/s41095-021-0247-3"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1016\/j.media.2023.102802"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1146\/annurev.psych.093008.100427"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1016\/j.clinph.2006.01.017"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1038\/35039043"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.3758\/s13414-015-0882-9"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.3389\/fpsyg.2019.02246"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1093\/oxfordhb\/9780199675111.013.017"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-50406-3_12"},{"key":"ref31","article-title":"Neural Turing machines","author":"Graves","year":"2014","journal-title":"arXiv:1410.5401"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2013.6638947"},{"key":"ref33","first-page":"1764","article-title":"Towards end-to-end speech recognition with recurrent neural networks","volume-title":"Proc. 31st Int. Conf. Mach. Learn.","author":"Graves"},{"key":"ref34","first-page":"1017","article-title":"Generating text with recurrent neural networks","volume-title":"Proc. 28th Int. Conf. Int. Conf. Mach. Learn.","author":"Sutskever"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.31390\/gradschool_dissertations.4601"},{"key":"ref36","first-page":"3104","article-title":"Sequence to sequence learning with neural networks","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Sutskever"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1146\/annurev.neuro.26.041002.131047"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D15-1166"},{"key":"ref39","first-page":"577","article-title":"Attention-based models for speech recognition","volume-title":"Proc. 28th Int. Conf. Neural Inf. Process. Syst.","volume":"1","author":"Chorowski"},{"key":"ref40","article-title":"Deep voice 3: 2000-speaker neural text-to-speech","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Ping"},{"key":"ref41","article-title":"Augmenting self-attention with persistent memory","author":"Sukhbaatar","year":"2019","journal-title":"arXiv:1907.01470"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P19-1032"},{"key":"ref43","article-title":"Addressing some limitations of transformers with feedback memory","author":"Fan","year":"2020","journal-title":"arXiv:2002.09402"},{"key":"ref44","first-page":"1","article-title":"Delight: Deep and light-weight transformer","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Mehta"},{"key":"ref45","article-title":"Linformer: Self-attention with linear complexity","author":"Wang","year":"2020","journal-title":"arXiv:2006.04768"},{"key":"ref46","article-title":"Longformer: The long-document transformer","author":"Beltagy","year":"2020","journal-title":"arXiv:2004.05150"},{"key":"ref47","first-page":"1","article-title":"Reformer: The efficient transformer","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Kitaev"},{"key":"ref48","first-page":"10183","article-title":"Synthesizer: Rethinking self-attention for transformer models","volume-title":"Proc. 38th Int. Conf. Mach. Learn.","author":"Tay"},{"key":"ref49","article-title":"Single headed attention RNN: Stop thinking with your head","author":"Merity","year":"2019","journal-title":"arXiv:1911.11423"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.5555\/3045118.3045336"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.667"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00745"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/ICCVW.2019.00246"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58577-8_6"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00338"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.658"},{"key":"ref57","first-page":"1","article-title":"Recurrent models of visual attention","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"27","author":"Mnih"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.89"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00813"},{"key":"ref60","first-page":"1","article-title":"Gather-excite: Exploiting feature context in convolutional neural networks","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"31","author":"Hu"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.507"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00128"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2019.2911488"},{"key":"ref64","first-page":"1","article-title":"Training very deep networks","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"28","author":"Srivastava"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00060"},{"key":"ref66","article-title":"ResNeSt: Split-attention networks","author":"Zhang","year":"2020","journal-title":"arXiv:2004.08955"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01104"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01234-2_1"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01240-3_17"},{"key":"ref70","first-page":"7354","article-title":"Self-attention generative adversarial networks","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Zhang"},{"key":"ref71","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2017.2778563"},{"key":"ref72","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v31i1.11212"},{"key":"ref73","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2019.2894139"},{"key":"ref74","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2019.2924576"},{"key":"ref75","article-title":"Visual transformers: Token-based image representation and processing for computer vision","author":"Wu","year":"2020","journal-title":"arXiv:2006.03677"},{"key":"ref76","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58452-8_13"},{"key":"ref77","doi-asserted-by":"publisher","DOI":"10.1088\/1742-5468\/ac9830"},{"key":"ref78","article-title":"DeepViT: Towards deeper vision transformer","author":"Zhou","year":"2021","journal-title":"arXiv:2103.11886"},{"key":"ref79","first-page":"10347","article-title":"Training data-efficient image transformers & distillation through attention","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Touvron"},{"key":"ref80","article-title":"Vision transformer for classification of breast ultrasound images","author":"Gheflati","year":"2021","journal-title":"arXiv:2110.14731"},{"key":"ref81","first-page":"2127","article-title":"Attention-based deep multiple instance learning","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Ilse"},{"key":"ref82","doi-asserted-by":"publisher","DOI":"10.1109\/TMI.2020.2996256"},{"key":"ref83","doi-asserted-by":"publisher","DOI":"10.1109\/ICIP42928.2021.9506353"},{"key":"ref84","article-title":"COVID-19 detection in chest X-ray images using swin-transformer and transformer in transformer","author":"Jiang","year":"2021","journal-title":"arXiv:2110.08427"},{"key":"ref85","doi-asserted-by":"publisher","DOI":"10.1088\/1742-6596\/2010\/1\/012175"},{"key":"ref86","first-page":"1","article-title":"Federated split task-agnostic vision transformer for COVID-19 CXR diagnosis","volume-title":"Proc. Neural Inf. Process. Syst. Found. (NIPS)","author":"Park"},{"key":"ref87","article-title":"Visual transformer with statistical test for COVID-19 classification","author":"Hsu","year":"2021","journal-title":"arXiv:2107.05334"},{"key":"ref88","doi-asserted-by":"publisher","DOI":"10.1109\/ICCVW54120.2021.00063"},{"key":"ref89","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-24574-4_28"},{"key":"ref90","doi-asserted-by":"publisher","DOI":"10.1109\/JTEHM.2021.3134096"},{"key":"ref91","article-title":"COVID-VIT: Classification of COVID-19 from CT chest images based on vision transformer models","author":"Gao","year":"2021","journal-title":"arXiv:2107.01682"},{"key":"ref92","doi-asserted-by":"publisher","DOI":"10.3390\/ijerph182111086"},{"key":"ref93","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-86340-1_47"},{"key":"ref94","doi-asserted-by":"publisher","DOI":"10.1016\/j.media.2021.102299"},{"key":"ref95","first-page":"159","article-title":"SMILE: Sparse-attention based multiple instance contrastive learning for glioma sub-type classification using pathological images","volume-title":"Proc. MICCAI Workshop Comput. Pathol.","author":"Lu"},{"key":"ref96","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2022.108827"},{"key":"ref97","doi-asserted-by":"publisher","DOI":"10.1155\/2021\/7529893"},{"key":"ref98","article-title":"A deep learning based graph-transformer for whole slide image classification","author":"Zheng","journal-title":"medRxiv"},{"key":"ref99","doi-asserted-by":"publisher","DOI":"10.1007\/s12652-020-02727-z"},{"key":"ref100","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-87237-3_5"},{"key":"ref101","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01079"},{"key":"ref102","doi-asserted-by":"publisher","DOI":"10.1002\/mp.15312"},{"key":"ref103","doi-asserted-by":"publisher","DOI":"10.12688\/f1000research.73082.1"},{"key":"ref104","doi-asserted-by":"publisher","DOI":"10.1109\/ICNC52316.2021.9608181"},{"key":"ref105","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2021.108309"},{"key":"ref106","doi-asserted-by":"publisher","DOI":"10.1109\/EMBC46164.2021.9631000"},{"key":"ref107","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2020.10.015"},{"key":"ref108","doi-asserted-by":"publisher","DOI":"10.3390\/diagnostics11081384"},{"key":"ref109","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-87444-5_2"},{"key":"ref110","article-title":"Scopeformer: N-CNN-ViT hybrid model for intracranial hemorrhage classification","author":"Barhoumi","year":"2021","journal-title":"arXiv:2107.04575"},{"key":"ref111","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.195"},{"key":"ref112","doi-asserted-by":"publisher","DOI":"10.3390\/s21010220"},{"key":"ref113","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref114","doi-asserted-by":"publisher","DOI":"10.1109\/TMI.2018.2867261"},{"key":"ref115","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-87193-2_11"},{"key":"ref116","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-09002-8_1"},{"key":"ref117","article-title":"A robust volumetric transformer for accurate 3D tumor segmentation","author":"Peiris","year":"2021","journal-title":"arXiv:2111.13300"},{"key":"ref118","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-08999-2_22"},{"key":"ref119","article-title":"More than encoder: Introducing transformer decoder to upsample","author":"Li","year":"2021","journal-title":"arXiv:2106.10637"},{"key":"ref120","article-title":"TransAttUnet: Multi-level attention-guided U-Net with transformer for medical image segmentation","author":"Chen","year":"2021","journal-title":"arXiv:2107.05274"},{"key":"ref121","doi-asserted-by":"publisher","DOI":"10.1007\/978-981-99-8543-2_4"},{"key":"ref122","doi-asserted-by":"publisher","DOI":"10.1016\/j.media.2021.102327"},{"key":"ref123","article-title":"Attention U-Net: Learning where to look for the pancreas","author":"Oktay","year":"2018","journal-title":"arXiv:1804.03999"},{"key":"ref124","doi-asserted-by":"publisher","DOI":"10.1016\/j.ultrasmedbio.2020.06.015"},{"key":"ref125","article-title":"Region aware transformer for automatic breast ultrasound tumor segmentation","volume-title":"Medical Imaging With Deep Learning","author":"Zhu"},{"key":"ref126","doi-asserted-by":"publisher","DOI":"10.1109\/EMBC46164.2021.9629523"},{"key":"ref127","doi-asserted-by":"publisher","DOI":"10.1109\/BIBM49941.2020.9313305"},{"key":"ref128","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-87193-2_10"},{"key":"ref129","first-page":"2136","article-title":"TransMIL: Transformer based correlated multiple instance learning for whole slide image classification","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"34","author":"Shao"},{"key":"ref130","doi-asserted-by":"publisher","DOI":"10.1117\/12.2611177"},{"key":"ref131","article-title":"SpecTr: Spectral transformer for hyperspectral pathology image segmentation","author":"Yun","year":"2021","journal-title":"arXiv:2103.03604"},{"key":"ref132","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-68107-4_30"},{"key":"ref133","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-68107-4_29"},{"key":"ref134","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.244"},{"key":"ref135","doi-asserted-by":"publisher","DOI":"10.1109\/TMI.2021.3090082"},{"key":"ref136","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-87583-1_7"},{"key":"ref137","article-title":"TransUNet: Transformers make strong encoders for medical image segmentation","author":"Chen","year":"2021","journal-title":"arXiv:2102.04306"},{"key":"ref138","article-title":"MISSFormer: An effective medical image segmentation transformer","author":"Huang","year":"2021","journal-title":"arXiv:2109.07162"},{"key":"ref139","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-93049-3_6"},{"key":"ref140","article-title":"TransClaw U-Net: Claw U-Net with transformers for medical image segmentation","author":"Chang","year":"2021","journal-title":"arXiv:2107.05188"},{"key":"ref141","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-87199-4_16"},{"key":"ref142","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-98385-7_1"},{"key":"ref143","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-87193-2_2"},{"key":"ref144","article-title":"Self-supervised pre-training of swin transformers for 3D medical image analysis","author":"Tang","year":"2021","journal-title":"arXiv:2111.14791"},{"key":"ref145","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-87193-2_8"},{"key":"ref146","article-title":"Swin-Unet: Unet-like pure transformer for medical image segmentation","author":"Cao","year":"2021","journal-title":"arXiv:2105.05537"},{"key":"ref147","article-title":"AG-CUResNeSt: A novel method for colon polyp segmentation","author":"Viet Sang","year":"2021","journal-title":"arXiv:2105.00402"},{"key":"ref148","first-page":"305","article-title":"CU-Net: Coupled U-Nets","volume-title":"Proc. Brit. Mach. Vis. Conf.","author":"Tang"},{"key":"ref149","article-title":"Pyramid medical transformer for medical image segmentation","author":"Zhang","year":"2021","journal-title":"arXiv:2104.14702"},{"key":"ref150","doi-asserted-by":"publisher","DOI":"10.1109\/TIM.2022.3178991"},{"key":"ref151","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2021\/112"},{"key":"ref152","doi-asserted-by":"publisher","DOI":"10.1038\/s41598-021-90428-8"},{"key":"ref153","article-title":"Study of attention mechanisms and ensemble methods for medical image semantic segmentation","author":"Ribeiro","year":"2019"},{"key":"ref154","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-87589-3_28"},{"key":"ref155","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-87193-2_20"},{"key":"ref156","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-87589-3_40"},{"key":"ref157","doi-asserted-by":"publisher","DOI":"10.1109\/JBHI.2021.3129245"},{"key":"ref158","doi-asserted-by":"publisher","DOI":"10.1109\/ICPR48806.2021.9413346"},{"key":"ref159","doi-asserted-by":"publisher","DOI":"10.1109\/DICTA52665.2021.9647299"},{"key":"ref160","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-63830-6_43"},{"key":"ref161","doi-asserted-by":"publisher","DOI":"10.1088\/1361-6560\/ac1c4c"},{"key":"ref162","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.660"},{"key":"ref163","doi-asserted-by":"publisher","DOI":"10.1155\/2022\/8111883"},{"key":"ref164","doi-asserted-by":"publisher","DOI":"10.3390\/app12073676"},{"key":"ref165","doi-asserted-by":"publisher","DOI":"10.3389\/fbioe.2020.00670"},{"key":"ref166","doi-asserted-by":"publisher","DOI":"10.3389\/fbioe.2020.605132"},{"key":"ref167","article-title":"Automatic segmentation of head and neck tumor: How powerful transformers are?","volume-title":"Medical Image With Deep Learning","author":"Sobirov"},{"key":"ref168","doi-asserted-by":"publisher","DOI":"10.1109\/WACV51458.2022.00333"},{"key":"ref169","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P18-1240"},{"key":"ref170","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-32692-0_77"},{"key":"ref171","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.findings-emnlp.110"},{"key":"ref172","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-69541-5_36"},{"key":"ref173","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.naacl-main.416"},{"key":"ref174","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.emnlp-main.112"},{"key":"ref175","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.findings-acl.23"},{"key":"ref176","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-87199-4_59"},{"key":"ref177","doi-asserted-by":"publisher","DOI":"10.1016\/j.imu.2021.100557"},{"key":"ref178","article-title":"CheXNet: Radiologist-level pneumonia detection on chest X-rays with deep learning","author":"Rajpurkar","year":"2017","journal-title":"arXiv:1711.05225"},{"issue":"8","key":"ref179","first-page":"9","article-title":"Language models are unsupervised multitask learners","volume":"1","author":"Radford","year":"2019","journal-title":"OpenAI Blog"},{"key":"ref180","doi-asserted-by":"publisher","DOI":"10.1109\/ICDS53782.2021.9626725"},{"key":"ref181","doi-asserted-by":"publisher","DOI":"10.1145\/3516367"},{"key":"ref182","article-title":"Trust it or not: Confidence-guided automatic radiology report generation","volume-title":"arXiv:2106.10887","author":"Wang","year":"2021"},{"key":"ref183","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01354"},{"key":"ref184","first-page":"1","article-title":"Auto-encoding knowledge graph for unsupervised medical report generation","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"34","author":"Liu"},{"key":"ref185","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.emnlp-main.288"},{"key":"ref186","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-87199-4_7"},{"key":"ref187","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-87234-2_28"},{"key":"ref188","doi-asserted-by":"publisher","DOI":"10.1038\/s42256-021-00425-9"},{"key":"ref189","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-87202-1_28"},{"key":"ref190","article-title":"Self-supervised image-text pre-training with mixed data in chest X-rays","author":"Wang","year":"2021","journal-title":"arXiv:2103. 16022"},{"key":"ref191","doi-asserted-by":"publisher","DOI":"10.1109\/ICCC54389.2021.9674267"},{"key":"ref192","article-title":"Transformer for polyp detection","author":"Liu","year":"2021","journal-title":"arXiv:2111.07918"},{"key":"ref193","doi-asserted-by":"publisher","DOI":"10.1117\/12.2613273"},{"key":"ref194","doi-asserted-by":"publisher","DOI":"10.1109\/TMI.2021.3120913"},{"key":"ref195","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46723-8_49"},{"key":"ref196","article-title":"Self-supervised answer retrieval on clinical notes","author":"Grundmann","year":"2021","journal-title":"arXiv:2108.00775"},{"key":"ref197","first-page":"196","article-title":"Read, attend, and code: Pushing the limits of medical codes prediction from clinical notes by machines","volume-title":"Proc. 6th Mach. Learn. Healthcare Conf.","volume":"149","author":"Kim"},{"key":"ref198","article-title":"AGMB-transformer: Anatomy-guided multi-branch transformer network for automated evaluation of root canal therapy","author":"Li","year":"2021","journal-title":"arXiv:2105.00381"},{"key":"ref199","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-87231-1_50"},{"key":"ref200","doi-asserted-by":"publisher","DOI":"10.3390\/make1010019"},{"key":"ref201","doi-asserted-by":"publisher","DOI":"10.1002\/prot.25819"},{"key":"ref202","doi-asserted-by":"publisher","DOI":"10.1002\/prot.25792"},{"key":"ref203","doi-asserted-by":"publisher","DOI":"10.1002\/prot.25697"},{"key":"ref204","doi-asserted-by":"publisher","DOI":"10.1038\/s41586-019-1923-7"},{"key":"ref205","first-page":"1","article-title":"Pre-training protein language models with label-agnostic binding pairs enhances performance in downstream tasks","volume-title":"Proc. Mach. Learn. Struct. Biol. Workshop (NeurIPS)","author":"Filipavicius"},{"key":"ref206","doi-asserted-by":"publisher","DOI":"10.1002\/prot.26052"},{"key":"ref207","doi-asserted-by":"publisher","DOI":"10.1093\/bib\/bbab390"},{"key":"ref208","article-title":"Gene transformer: Transformers for the gene expression-based classification of lung cancer subtypes","author":"Khan","year":"2021","journal-title":"arXiv:2108.11833"},{"key":"ref209","doi-asserted-by":"publisher","DOI":"10.1038\/s41597-021-00815-z"},{"key":"ref210","doi-asserted-by":"publisher","DOI":"10.1038\/s41597-019-0322-0"},{"key":"ref211","doi-asserted-by":"publisher","DOI":"10.5555\/3454287.3455008"},{"key":"ref212","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.243"},{"key":"ref213","first-page":"3145","article-title":"Learning important features through propagating activation differences","volume-title":"Proc. 34th Int. Conf. Mach. Learn.","author":"Shrikumar"},{"key":"ref214","doi-asserted-by":"publisher","DOI":"10.1371\/journal.pone.0130140"},{"key":"ref215","article-title":"Captum: A unified and generic model interpretability library for PyTorch","author":"Kokhlikyan","year":"2020","journal-title":"arXiv:2009.07896"},{"key":"ref216","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00084"},{"key":"ref217","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"ref218","doi-asserted-by":"publisher","DOI":"10.1109\/MCSE.2007.55"},{"key":"ref219","first-page":"1","article-title":"On the relationship between self-attention and convolutional layers","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Cordonnier"},{"key":"ref220","doi-asserted-by":"publisher","DOI":"10.1145\/3236386.3241340"},{"key":"ref221","first-page":"1","article-title":"Sanity checks for saliency maps","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"31","author":"Adebayo"},{"key":"ref222","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-28954-6_14"},{"key":"ref223","first-page":"1","article-title":"A benchmark for interpretability methods in deep neural networks","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"32","author":"Hooker"},{"key":"ref224","doi-asserted-by":"publisher","DOI":"10.1038\/s42256-019-0048-x"},{"key":"ref225","doi-asserted-by":"publisher","DOI":"10.1145\/3313831.3376219"}],"container-title":["IEEE Access"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6287639\/9668973\/09889720.pdf?arnumber=9889720","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,1,22]],"date-time":"2024-01-22T21:09:57Z","timestamp":1705957797000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9889720\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022]]},"references-count":225,"URL":"https:\/\/doi.org\/10.1109\/access.2022.3206449","relation":{},"ISSN":["2169-3536"],"issn-type":[{"value":"2169-3536","type":"electronic"}],"subject":[],"published":{"date-parts":[[2022]]}}}