{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,12,26]],"date-time":"2025-12-26T07:11:56Z","timestamp":1766733116469,"version":"3.40.3"},"publisher-location":"Singapore","reference-count":43,"publisher":"Springer Nature Singapore","isbn-type":[{"type":"print","value":"9789819609000"},{"type":"electronic","value":"9789819609017"}],"license":[{"start":{"date-parts":[[2024,12,8]],"date-time":"2024-12-08T00:00:00Z","timestamp":1733616000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2024,12,8]],"date-time":"2024-12-08T00:00:00Z","timestamp":1733616000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025]]},"DOI":"10.1007\/978-981-96-0901-7_9","type":"book-chapter","created":{"date-parts":[[2024,12,7]],"date-time":"2024-12-07T07:56:23Z","timestamp":1733558183000},"page":"142-158","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":2,"title":["Seeing Through Expert\u2019s Eyes: Leveraging Radiologist Eye Gaze and\u00a0Speech Report with\u00a0Graph Neural Networks for\u00a0Chest X-Ray Image Classification"],"prefix":"10.1007","author":[{"given":"Jamalia","family":"Sultana","sequence":"first","affiliation":[]},{"given":"Ruwen","family":"Qin","sequence":"additional","affiliation":[]},{"given":"Zhaozheng","family":"Yin","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2024,12,8]]},"reference":[{"issue":"1","key":"9_CR1","doi-asserted-by":"publisher","first-page":"4788","DOI":"10.1038\/s41598-023-30870-y","volume":"13","author":"J Albers","year":"2023","unstructured":"Albers, J., Wagner, W.L., Fiedler, M.O., Rothermel, A., W\u00fcnnemann, F., Di Lillo, F., Dreossi, D., Sodini, N., Baratella, E., Confalonieri, M., et al.: High resolution propagation-based lung imaging at clinically relevant x-ray dose levels. Sci. Rep. 13(1), 4788 (2023)","journal-title":"Sci. Rep."},{"key":"9_CR2","doi-asserted-by":"crossref","unstructured":"Alsentzer, E., Murphy, J.R., Boag, W., Weng, W.H., Jin, D., Naumann, T., McDermott, M.: Publicly available clinical bert embeddings. arXiv preprint arXiv:1904.03323 (2019)","DOI":"10.18653\/v1\/W19-1909"},{"issue":"1","key":"9_CR3","doi-asserted-by":"publisher","first-page":"62","DOI":"10.1080\/0142159X.2017.1391373","volume":"40","author":"H Ashraf","year":"2018","unstructured":"Ashraf, H., Sodergren, M.H., Merali, N., Mylonas, G., Singh, H., Darzi, A.: Eye-tracking technology in medical education: A systematic review. Med. Teach. 40(1), 62\u201369 (2018)","journal-title":"Med. Teach."},{"issue":"1","key":"9_CR4","doi-asserted-by":"publisher","first-page":"6381","DOI":"10.1038\/s41598-019-42294-8","volume":"9","author":"IM Baltruschat","year":"2019","unstructured":"Baltruschat, I.M., Nickisch, H., Grass, M., Knopp, T., Saalbach, A.: Comparison of deep learning approaches for multi-label chest x-ray classification. Sci. Rep. 9(1), 6381 (2019)","journal-title":"Sci. Rep."},{"key":"9_CR5","doi-asserted-by":"crossref","unstructured":"Bhattacharya, M., Jain, S., Prasanna, P.: Radiotransformer: a cascaded global-focal transformer for visual attention\u2013guided disease classification. In: European Conference on Computer Vision. pp. 679\u2013698. Springer (2022)","DOI":"10.1007\/978-3-031-19803-8_40"},{"key":"9_CR6","doi-asserted-by":"crossref","unstructured":"Boecking, B., Usuyama, N., Bannur, S., Castro, D.C., Schwaighofer, A., Hyland, S., Wetscherek, M., Naumann, T., Nori, A., Alvarez-Valle, J., et\u00a0al.: Making the most of text semantics to improve biomedical vision\u2013language processing. In: European conference on computer vision. pp. 1\u201321. Springer (2022)","DOI":"10.1007\/978-3-031-20059-5_1"},{"key":"9_CR7","unstructured":"Brody, S., Alon, U., Yahav, E.: How attentive are graph attention networks? arXiv preprint arXiv:2105.14491 (2021)"},{"key":"9_CR8","doi-asserted-by":"publisher","DOI":"10.1016\/j.media.2020.101797","volume":"66","author":"A Bustos","year":"2020","unstructured":"Bustos, A., Pertusa, A., Salinas, J.M., De La Iglesia-Vaya, M.: Padchest: A large chest x-ray image dataset with multi-label annotated reports. Med. Image Anal. 66, 101797 (2020)","journal-title":"Med. Image Anal."},{"issue":"3","key":"9_CR9","doi-asserted-by":"publisher","first-page":"2291","DOI":"10.1007\/s00521-022-07953-4","volume":"35","author":"P Celard","year":"2023","unstructured":"Celard, P., Iglesias, E.L., Sorribes-Fdez, J.M., Romero, R., Vieira, A.S., Borrajo, L.: A survey on deep learning applied to medical images: from simple artificial neural networks to generative models. Neural Comput. Appl. 35(3), 2291\u20132323 (2023)","journal-title":"Neural Comput. Appl."},{"issue":"2","key":"9_CR10","doi-asserted-by":"publisher","first-page":"304","DOI":"10.1093\/jamia\/ocv080","volume":"23","author":"D Demner-Fushman","year":"2016","unstructured":"Demner-Fushman, D., Kohli, M.D., Rosenman, M.B., Shooshan, S.E., Rodriguez, L., Antani, S., Thoma, G.R., McDonald, C.J.: Preparing a collection of radiology examinations for distribution and retrieval. J. Am. Med. Inform. Assoc. 23(2), 304\u2013310 (2016)","journal-title":"J. Am. Med. Inform. Assoc."},{"issue":"1","key":"9_CR11","doi-asserted-by":"publisher","first-page":"68","DOI":"10.1109\/TTS.2023.3234203","volume":"4","author":"T Dhar","year":"2023","unstructured":"Dhar, T., Dey, N., Borra, S., Sherratt, R.S.: Challenges of deep learning in medical image analysis\u2013improving explainability and trust. IEEE Transactions on Technology and Society 4(1), 68\u201375 (2023)","journal-title":"IEEE Transactions on Technology and Society"},{"key":"9_CR12","first-page":"8291","volume":"35","author":"K Han","year":"2022","unstructured":"Han, K., Wang, Y., Guo, J., Tang, Y., Wu, E.: Vision gnn: An image is worth graph of nodes. Adv. Neural. Inf. Process. Syst. 35, 8291\u20138303 (2022)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"9_CR13","doi-asserted-by":"crossref","unstructured":"He, K., Zhang, X., Ren, S., Sun, J.: Deep residual learning for image recognition. In: Proceedings of the IEEE conference on computer vision and pattern recognition. pp. 770\u2013778 (2016)","DOI":"10.1109\/CVPR.2016.90"},{"key":"9_CR14","doi-asserted-by":"crossref","unstructured":"Hsieh, J.: Spatial and temporal motion characterization for x-ray ct. Medical Physics (2024)","DOI":"10.1002\/mp.17075"},{"key":"9_CR15","doi-asserted-by":"crossref","unstructured":"Huang, G., Liu, Z., Van Der\u00a0Maaten, L., Weinberger, K.Q.: Densely connected convolutional networks. In: Proceedings of the IEEE conference on computer vision and pattern recognition. pp. 4700\u20134708 (2017)","DOI":"10.1109\/CVPR.2017.243"},{"key":"9_CR16","doi-asserted-by":"crossref","unstructured":"Huang, S.C., Shen, L., Lungren, M.P., Yeung, S.: Gloria: A multimodal global-local representation learning framework for label-efficient medical image recognition. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision. pp. 3942\u20133951 (2021)","DOI":"10.1109\/ICCV48922.2021.00391"},{"issue":"9","key":"9_CR17","doi-asserted-by":"publisher","first-page":"2307","DOI":"10.1038\/s41591-023-02504-3","volume":"29","author":"Z Huang","year":"2023","unstructured":"Huang, Z., Bianchi, F., Yuksekgonul, M., Montine, T.J., Zou, J.: A visual-language foundation model for pathology image analysis using medical twitter. Nat. Med. 29(9), 2307\u20132316 (2023)","journal-title":"Nat. Med."},{"key":"9_CR18","doi-asserted-by":"crossref","unstructured":"Huff, D.T., Weisman, A.J., Jeraj, R.: Interpretation and visualization techniques for deep learning models in medical imaging. Physics in Medicine & Biology 66(4), 04TR01 (2021)","DOI":"10.1088\/1361-6560\/abcd17"},{"key":"9_CR19","doi-asserted-by":"publisher","first-page":"1423051","DOI":"10.3389\/fncom.2024.1423051","volume":"18","author":"S Iqbal","year":"2024","unstructured":"Iqbal, S., Qureshi, A.N., Alhussein, M., Aurangzeb, K., Choudhry, I.A., Anwar, M.S.: Hybrid deep spatial and statistical feature fusion for accurate mri brain tumor classification. Front. Comput. Neurosci. 18, 1423051 (2024)","journal-title":"Front. Comput. Neurosci."},{"key":"9_CR20","doi-asserted-by":"crossref","unstructured":"Johnson, A.E., Pollard, T.J., Berkowitz, S.J., Greenbaum, N.R., Lungren, M.P., Deng, C.y., Mark, R.G., Horng, S.: Mimic-cxr, a de-identified publicly available database of chest radiographs with free-text reports. Scientific data 6(1), 317 (2019)","DOI":"10.1038\/s41597-019-0322-0"},{"issue":"1","key":"9_CR21","doi-asserted-by":"publisher","first-page":"92","DOI":"10.1038\/s41597-021-00863-5","volume":"8","author":"A Karargyris","year":"2021","unstructured":"Karargyris, A., Kashyap, S., Lourentzou, I., Wu, J.T., Sharma, A., Tong, M., Abedin, S., Beymer, D., Mukherjee, V., Krupinski, E.A., et al.: Creation and validation of a chest x-ray dataset with eye-tracking and report dictation for ai development. Scientific data 8(1), 92 (2021)","journal-title":"Scientific data"},{"key":"9_CR22","doi-asserted-by":"crossref","unstructured":"Kaushal, S., Sun, Y., Zukerman, R., Chen, R.W., Thakoor, K.A.: Detecting eye disease using vision transformers informed by ophthalmology resident gaze data. In: 2023 45th Annual International Conference of the IEEE Engineering in Medicine & Biology Society (EMBC). pp.\u00a01\u20134. IEEE (2023)","DOI":"10.1109\/EMBC40787.2023.10340746"},{"issue":"5","key":"9_CR23","doi-asserted-by":"publisher","first-page":"11878","DOI":"10.48084\/etasr.6335","volume":"13","author":"NC Kundur","year":"2023","unstructured":"Kundur, N.C., Anil, B.C., Dhulavvagol, P.M., Ganiger, R., Ramadoss, B.: Pneumonia detection in chest x-rays using transfer learning and tpus. Engineering, Technology & Applied Science Research 13(5), 11878\u201311883 (2023)","journal-title":"Engineering, Technology & Applied Science Research"},{"key":"9_CR24","unstructured":"Lanfredi, R.B., Zhang, M., Auffermann, W., Chan, J., Duong, P.A., Srikumar, V., Drew, T., Schroeder, J., Tasdizen, T.: Reflacx: Reports and eye-tracking data for localization of abnormalities in chest x-rays (2021)"},{"key":"9_CR25","doi-asserted-by":"crossref","unstructured":"Li, G., Muller, M., Thabet, A., Ghanem, B.: Deepgcns: Can gcns go as deep as cnns? In: Proceedings of the IEEE\/CVF international conference on computer vision. pp. 9267\u20139276 (2019)","DOI":"10.1109\/ICCV.2019.00936"},{"key":"9_CR26","doi-asserted-by":"crossref","unstructured":"Neves, J., Hsieh, C., Nobre, I.B., Sousa, S.C., Ouyang, C., Maciel, A., Duchowski, A., Jorge, J., Moreira, C.: Shedding light on ai in radiology: A systematic review and taxonomy of eye gaze-driven interpretability in deep learning. European Journal of Radiology p. 111341 (2024)","DOI":"10.1016\/j.ejrad.2024.111341"},{"issue":"1","key":"9_CR27","doi-asserted-by":"publisher","DOI":"10.2196\/58342","volume":"3","author":"M Noda","year":"2024","unstructured":"Noda, M., Yoshimura, H., Okubo, T., Koshu, R., Uchiyama, Y., Nomura, A., Ito, M., Takumi, Y., et al.: Feasibility of multimodal artificial intelligence using gpt-4 vision for the classification of middle ear disease: Qualitative study and validation. JMIR AI 3(1), e58342 (2024)","journal-title":"JMIR AI"},{"key":"9_CR28","unstructured":"Rajpurkar, P., Irvin, J., Zhu, K., Yang, B., Mehta, H., Duan, T., Ding, D., Bagul, A., Langlotz, C., Shpanskaya, K., et\u00a0al.: Chexnet: Radiologist-level pneumonia detection on chest x-rays with deep learning. arXiv preprint arXiv:1711.05225 (2017)"},{"key":"9_CR29","unstructured":"Rubin, J., Sanghavi, D., Zhao, C., Lee, K., Qadir, A., Xu-Wilson, M.: Large scale automated reading of frontal and lateral chest x-rays using dual convolutional neural networks. arXiv preprint arXiv:1804.07839 (2018)"},{"key":"9_CR30","doi-asserted-by":"crossref","unstructured":"Saab, K., Hooper, S.M., Sohoni, N.S., Parmar, J., Pogatchnik, B., Wu, S., Dunnmon, J.A., Zhang, H.R., Rubin, D., R\u00e9, C.: Observational supervision for medical image classification using gaze data. In: Medical Image Computing and Computer Assisted Intervention\u2013MICCAI 2021: 24th International Conference, Strasbourg, France, September 27\u2013October 1, 2021, Proceedings, Part II 24. pp. 603\u2013614. Springer (2021)","DOI":"10.1007\/978-3-030-87196-3_56"},{"issue":"1","key":"9_CR31","doi-asserted-by":"publisher","first-page":"36","DOI":"10.1016\/j.medcle.2020.03.004","volume":"155","author":"R S\u00e1nchez-Oro","year":"2020","unstructured":"S\u00e1nchez-Oro, R., Nuez, J.T., Mart\u00ednez-Sanz, G.: Radiological findings for diagnosis of sars-cov-2 pneumonia (covid-19). Medicina Cl\u00ednica (English Edition) 155(1), 36\u201340 (2020)","journal-title":"Medicina Cl\u00ednica (English Edition)"},{"key":"9_CR32","doi-asserted-by":"crossref","unstructured":"Selvaraju, R.R., Cogswell, M., Das, A., Vedantam, R., Parikh, D., Batra, D.: Grad-cam: Visual explanations from deep networks via gradient-based localization. In: Proceedings of the IEEE international conference on computer vision. pp. 618\u2013626 (2017)","DOI":"10.1109\/ICCV.2017.74"},{"key":"9_CR33","doi-asserted-by":"crossref","unstructured":"van Sonsbeek, T., Zhen, X., Mahapatra, D., Worring, M.: Probabilistic integration of object level annotations in chest x-ray classification. In: Proceedings of the IEEE\/CVF Winter Conference on Applications of Computer Vision. pp. 3630\u20133640 (2023)","DOI":"10.1109\/WACV56688.2023.00362"},{"key":"9_CR34","doi-asserted-by":"publisher","first-page":"1253001","DOI":"10.3389\/fmedt.2023.1253001","volume":"5","author":"M Tahri Sqalli","year":"2023","unstructured":"Tahri Sqalli, M., Aslonov, B., Gafurov, M., Mukhammadiev, N., Sqalli Houssaini, Y.: Eye tracking technology in medical practice: a perspective on its diverse applications. Frontiers in Medical Technology 5, 1253001 (2023)","journal-title":"Frontiers in Medical Technology"},{"key":"9_CR35","doi-asserted-by":"crossref","unstructured":"Wang, B., Aboah, A., Zhang, Z., Bagci, U.: Gazesam: What you see is what you segment. arXiv preprint arXiv:2304.13844 (2023)","DOI":"10.3724\/2096-1715.2023.007.003.109"},{"key":"9_CR36","doi-asserted-by":"crossref","unstructured":"Wang, B., Pan, H., Aboah, A., Zhang, Z., Keles, E., Torigian, D., Turkbey, B., Krupinski, E., Udupa, J., Bagci, U.: Gazegnn: A gaze-guided graph neural network for chest x-ray classification. In: Proceedings of the IEEE\/CVF Winter Conference on Applications of Computer Vision. pp. 2194\u20132203 (2024)","DOI":"10.1109\/WACV57701.2024.00219"},{"issue":"7","key":"9_CR37","doi-asserted-by":"publisher","first-page":"1688","DOI":"10.1109\/TMI.2022.3146973","volume":"41","author":"S Wang","year":"2022","unstructured":"Wang, S., Ouyang, X., Liu, T., Wang, Q., Shen, D.: Follow my eye: Using gaze to supervise computer-aided diagnosis. IEEE Trans. Med. Imaging 41(7), 1688\u20131698 (2022)","journal-title":"IEEE Trans. Med. Imaging"},{"issue":"3","key":"9_CR38","doi-asserted-by":"publisher","first-page":"415","DOI":"10.1007\/s41095-022-0274-8","volume":"8","author":"W Wang","year":"2022","unstructured":"Wang, W., Xie, E., Li, X., Fan, D.P., Song, K., Liang, D., Lu, T., Luo, P., Shao, L.: Pvt v2: Improved baselines with pyramid vision transformer. Computational Visual Media 8(3), 415\u2013424 (2022)","journal-title":"Computational Visual Media"},{"key":"9_CR39","doi-asserted-by":"crossref","unstructured":"Wang, Z., Wu, Z., Agarwal, D., Sun, J.: Medclip: Contrastive learning from unpaired medical images and text. arXiv preprint arXiv:2210.10163 (2022)","DOI":"10.18653\/v1\/2022.emnlp-main.256"},{"key":"9_CR40","doi-asserted-by":"publisher","DOI":"10.3389\/fradi.2022.991683","volume":"2","author":"A Watanabe","year":"2022","unstructured":"Watanabe, A., Ketabi, S., Namdar, K., Khalvati, F.: Improving disease classification performance and explainability of deep learning models in radiology with heatmap generators. Frontiers in radiology 2, 991683 (2022)","journal-title":"Frontiers in radiology"},{"key":"9_CR41","unstructured":"Xie, Y., Yang, B., Guan, Q., Zhang, J., Wu, Q., Xia, Y.: Attention mechanisms in medical image segmentation: A survey. arXiv preprint arXiv:2305.17937 (2023)"},{"key":"9_CR42","doi-asserted-by":"crossref","unstructured":"You, K., Gu, J., Ham, J., Park, B., Kim, J., Hong, E.K., Baek, W., Roh, B.: Cxr-clip: Toward large scale chest x-ray language-image pre-training. In: International Conference on Medical Image Computing and Computer-Assisted Intervention. pp. 101\u2013111. Springer (2023)","DOI":"10.1007\/978-3-031-43895-0_10"},{"key":"9_CR43","doi-asserted-by":"crossref","unstructured":"Zhang, J., Huang, J., Jin, S., Lu, S.: Vision-language models for vision tasks: A survey. IEEE Transactions on Pattern Analysis and Machine Intelligence (2024)","DOI":"10.1109\/TPAMI.2024.3369699"}],"container-title":["Lecture Notes in Computer Science","Computer Vision \u2013 ACCV 2024"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-981-96-0901-7_9","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,12,7]],"date-time":"2024-12-07T08:08:33Z","timestamp":1733558913000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-981-96-0901-7_9"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,12,8]]},"ISBN":["9789819609000","9789819609017"],"references-count":43,"URL":"https:\/\/doi.org\/10.1007\/978-981-96-0901-7_9","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2024,12,8]]},"assertion":[{"value":"8 December 2024","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"ACCV","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Asian Conference on Computer Vision","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Hanoi","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Vietnam","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2024","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"8 December 2024","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"12 December 2024","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"17","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"accv2024","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}