{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,16]],"date-time":"2026-09-16T16:12:27Z","timestamp":1789575147797,"version":"build-2803163510"},"reference-count":36,"publisher":"Springer Science and Business Media LLC","issue":"1","license":[{"start":{"date-parts":[[2023,1,21]],"date-time":"2023-01-21T00:00:00Z","timestamp":1674259200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"},{"start":{"date-parts":[[2023,1,21]],"date-time":"2023-01-21T00:00:00Z","timestamp":1674259200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"}],"funder":[{"DOI":"10.13039\/100000002","name":"National Institutes of Health","doi-asserted-by":"publisher","award":["S10-OD025081"],"award-info":[{"award-number":["S10-OD025081"]}],"id":[{"id":"10.13039\/100000002","id-type":"DOI","asserted-by":"publisher"}]},{"name":"National Institutes of Health,United States","award":["75N92020C00008"],"award-info":[{"award-number":["75N92020C00008"]}]},{"name":"National Institutes of Health,United States","award":["UL1TR000430"],"award-info":[{"award-number":["UL1TR000430"]}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Sci Rep"],"abstract":"<jats:title>Abstract<\/jats:title><jats:p>In addition to lung cancer, other thoracic abnormalities, such as emphysema, can be visualized within low-dose CT scans that were initially obtained in cancer screening programs, and thus, opportunistic evaluation of these diseases may be highly valuable. However, manual assessment for each scan is tedious and often subjective, thus we have developed an automatic, rapid computer-aided diagnosis system for emphysema using attention-based multiple instance deep learning and 865 LDCTs. In the task of determining if a CT scan presented with emphysema or not, our novel Transfer AMIL approach yielded an area under the ROC curve of 0.94\u00a0\u00b1\u00a00.04, which was a statistically significant improvement compared to other methods evaluated in our study following the Delong Test with correction for multiple comparisons. Further, from our novel attention weight curves, we found that the upper lung demonstrated a stronger influence in all scan classes, indicating that the model prioritized upper lobe information. Overall, our novel Transfer AMIL method yielded high performance and provided interpretable information by identifying slices that were most influential to the classification decision, thus demonstrating strong potential for clinical implementation.<\/jats:p>","DOI":"10.1038\/s41598-023-27549-9","type":"journal-article","created":{"date-parts":[[2023,1,21]],"date-time":"2023-01-21T11:02:49Z","timestamp":1674298969000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":12,"title":["Evaluation of emphysema on thoracic low-dose CTs through attention-based multiple instance deep learning"],"prefix":"10.1038","volume":"13","author":[{"given":"Jordan","family":"Fuhrman","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Rowena","family":"Yip","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yeqing","family":"Zhu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Artit C.","family":"Jirapatnakul","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Feng","family":"Li","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Claudia I.","family":"Henschke","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"David F.","family":"Yankelevitz","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Maryellen L.","family":"Giger","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2023,1,21]]},"reference":[{"key":"27549_CR1","doi-asserted-by":"publisher","first-page":"962","DOI":"10.1001\/jama.2021.1117","volume":"325","author":"US Preventive Services Task Force","year":"2021","unstructured":"US Preventive Services Task Force. Screening for lung cancer: US preventive services task force recommendation statement. JAMA 325, 962\u2013970 (2021).","journal-title":"JAMA"},{"key":"27549_CR2","doi-asserted-by":"publisher","first-page":"99","DOI":"10.1016\/S0140-6736(99)06093-6","volume":"354","author":"CI Henschke","year":"1999","unstructured":"Henschke, C. I. et al. Early lung cancer action project: Overall design and findings from baseline screening. Lancet 354, 99\u2013105 (1999).","journal-title":"Lancet"},{"key":"27549_CR3","doi-asserted-by":"publisher","first-page":"395","DOI":"10.1056\/NEJMoa1102873","volume":"365","author":"The National Lung Screening Trial Research Team","year":"2011","unstructured":"The National Lung Screening Trial Research Team. Reduced lung-cancer mortality with low-dose computed tomographic screening. N. Engl. J. Med. 365, 395\u2013409 (2011).","journal-title":"N. Engl. J. Med."},{"key":"27549_CR4","doi-asserted-by":"publisher","first-page":"241","DOI":"10.1148\/radiol.211561","volume":"303","author":"PJ Pickhardt","year":"2022","unstructured":"Pickhardt, P. J. Value-added opportunistic CT screening: State of the art. Radiology 303, 241\u2013254 (2022).","journal-title":"Radiology"},{"key":"27549_CR5","doi-asserted-by":"publisher","first-page":"1141","DOI":"10.21037\/tlcr-20-746","volume":"10","author":"R Yip","year":"2021","unstructured":"Yip, R. et al. Added benefits of early detection of other diseases on low-dose CT screening. Transl. Lung Cancer Res. 10, 1141\u20131153 (2021).","journal-title":"Transl. Lung Cancer Res."},{"key":"27549_CR6","doi-asserted-by":"publisher","first-page":"136","DOI":"10.1016\/j.clinimag.2021.03.012","volume":"78","author":"D Steiger","year":"2021","unstructured":"Steiger, D. et al. The importance of low-dose CT screening to identify emphysema in asymptomatic participants with and without a prior diagnosis of COPD. Clin. Imaging 78, 136\u2013141 (2021).","journal-title":"Clin. Imaging"},{"key":"27549_CR7","doi-asserted-by":"publisher","DOI":"10.1371\/journal.pone.0219187","volume":"14","author":"J Gonz\u00e1lez","year":"2019","unstructured":"Gonz\u00e1lez, J. et al. Emphysema phenotypes and lung cancer risk. PLoS ONE 14, e0219187 (2019).","journal-title":"PLoS ONE"},{"key":"27549_CR8","doi-asserted-by":"publisher","first-page":"858","DOI":"10.1136\/thoraxjnl-2018-212457","volume":"74","author":"PC Yong","year":"2019","unstructured":"Yong, P. C. et al. The effect of radiographic emphysema in assessing lung cancer risk. Thorax 74, 858\u2013864 (2019).","journal-title":"Thorax"},{"key":"27549_CR9","doi-asserted-by":"publisher","first-page":"1812","DOI":"10.1016\/j.chest.2020.12.004","volume":"159","author":"WW Labaki","year":"2021","unstructured":"Labaki, W. W. et al. Quantitative emphysema on low-dose CT imaging of the chest and risk of lung cancer and airflow obstruction: An analysis of the national lung screening Trial. Chest 159, 1812\u20131820 (2021).","journal-title":"Chest"},{"key":"27549_CR10","doi-asserted-by":"publisher","first-page":"240","DOI":"10.1016\/j.canlet.2016.09.002","volume":"382","author":"C Mouronte-Roib\u00e1s","year":"2016","unstructured":"Mouronte-Roib\u00e1s, C. et al. COPD, emphysema and the onset of lung cancer: A systematic review. Cancer Lett. 382, 240\u2013244 (2016).","journal-title":"Cancer Lett."},{"key":"27549_CR11","doi-asserted-by":"publisher","first-page":"1932","DOI":"10.1378\/chest.07-1490","volume":"132","author":"JP de Torres","year":"2007","unstructured":"de Torres, J. P. et al. Assessing the relationship between lung cancer risk and emphysema detected on low-dose CT of the chest. Chest 132, 1932\u20131938 (2007).","journal-title":"Chest"},{"key":"27549_CR12","doi-asserted-by":"publisher","first-page":"424","DOI":"10.1378\/chest.06-1040","volume":"131","author":"CP Hersh","year":"2007","unstructured":"Hersh, C. P. et al. Interobserver variability in the determination of upper lobe-predominant emphysema. Chest 131, 424\u2013431 (2007).","journal-title":"Chest"},{"key":"27549_CR13","doi-asserted-by":"publisher","DOI":"10.1016\/j.ejrad.2021.109561","volume":"136","author":"JE Hartman","year":"2021","unstructured":"Hartman, J. E. et al. HRCT characteristics of severe emphysema patients: Interobserver variability among expert readers and comparison with quantitative software. Eur. J. Radiol. 136, 109561 (2021).","journal-title":"Eur. J. Radiol."},{"key":"27549_CR14","doi-asserted-by":"publisher","first-page":"329","DOI":"10.1016\/j.patcog.2017.10.009","volume":"77","author":"M-A Carbonneau","year":"2018","unstructured":"Carbonneau, M.-A., Cheplygina, V., Granger, E. & Gagnon, G. Multiple instance learning: A survey of problem characteristics and applications. Pattern Recogn. 77, 329\u2013353 (2018).","journal-title":"Pattern Recogn."},{"key":"27549_CR15","doi-asserted-by":"publisher","first-page":"15","DOI":"10.1016\/j.patcog.2017.08.026","volume":"74","author":"X Wang","year":"2018","unstructured":"Wang, X., Yan, Y., Tang, P., Bai, X. & Liu, W. Revisiting multiple instance neural networks. Pattern Recogn. 74, 15\u201324 (2018).","journal-title":"Pattern Recogn."},{"key":"27549_CR16","unstructured":"Ilse, M., Tomczak, J. & Welling, M. Attention-based deep multiple instance learning. in International Conference on Machine Learning 2127\u20132136 (PMLR, 2018)."},{"key":"27549_CR17","doi-asserted-by":"publisher","first-page":"434","DOI":"10.1148\/radiol.2019191022","volume":"294","author":"SM Humphries","year":"2020","unstructured":"Humphries, S. M. et al. Deep learning enables automatic classification of emphysema pattern at CT. Radiology 294, 434\u2013444 (2020).","journal-title":"Radiology"},{"key":"27549_CR18","doi-asserted-by":"publisher","first-page":"213054","DOI":"10.1148\/radiol.213054","volume":"304","author":"AS Oh","year":"2022","unstructured":"Oh, A. S. et al. Emphysema progression at CT by deep learning predicts functional impairment and mortality: Results from the COPD gene study. Radiology 304, 213054. https:\/\/doi.org\/10.1148\/radiol.213054 (2022).","journal-title":"Radiology"},{"key":"27549_CR19","doi-asserted-by":"publisher","unstructured":"Negahdar, M., Coy, A. & Beymer, D. An end-to-end deep learning pipeline for emphysema quantification using multi-label learning. in 2019 41st Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC) 929\u2013932 (2019). https:\/\/doi.org\/10.1109\/EMBC.2019.8857392.","DOI":"10.1109\/EMBC.2019.8857392"},{"key":"27549_CR20","doi-asserted-by":"publisher","unstructured":"Cheplygina, V. et al. Classification of COPD with multiple instance learning. in 2014 22nd International Conference on Pattern Recognition 1508\u20131513 (2014). https:\/\/doi.org\/10.1109\/ICPR.2014.268.","DOI":"10.1109\/ICPR.2014.268"},{"key":"27549_CR21","doi-asserted-by":"publisher","unstructured":"\u00d8rting, S. N., Petersen, J., Thomsen, L. H., Wille, M. M. W. & Bruijne, M. de. Detecting emphysema with multiple instance learning. in 2018 IEEE 15th International Symposium on Biomedical Imaging (ISBI 2018) 510\u2013513 (2018). https:\/\/doi.org\/10.1109\/ISBI.2018.8363627.","DOI":"10.1109\/ISBI.2018.8363627"},{"key":"27549_CR22","doi-asserted-by":"publisher","first-page":"854","DOI":"10.1109\/TMI.2019.2936244","volume":"39","author":"R Tennakoon","year":"2020","unstructured":"Tennakoon, R. et al. Classification of volumetric images using multi-instance learning and extreme value theorem. IEEE Trans. Med. Imaging 39, 854\u2013865 (2020).","journal-title":"IEEE Trans. Med. Imaging"},{"key":"27549_CR23","doi-asserted-by":"publisher","first-page":"1216","DOI":"10.1378\/chest.11-0101","volume":"141","author":"JJ Zulueta","year":"2012","unstructured":"Zulueta, J. J. et al. Emphysema scores predict death from COPD and lung cancer. Chest 141, 1216\u20131223 (2012).","journal-title":"Chest"},{"key":"27549_CR24","doi-asserted-by":"publisher","first-page":"192","DOI":"10.1148\/radiol.2015141579","volume":"277","author":"DA Lynch","year":"2015","unstructured":"Lynch, D. A. et al. CT-definable subtypes of chronic obstructive pulmonary disease: A statement of the Fleischner society. Radiology 277, 192\u2013205 (2015).","journal-title":"Radiology"},{"key":"27549_CR25","unstructured":"Shao, Z. et al. TransMIL: Transformer based Correlated Multiple Instance Learning for Whole Slide Image Classification. http:\/\/arxiv.org\/abs\/2106.00908 (2021)."},{"key":"27549_CR26","unstructured":"Simonyan, K., Vedaldi, A. & Zisserman, A. Deep Inside Convolutional Networks: Visualising Image Classification Models and Saliency Maps. http:\/\/arxiv.org\/abs\/1312.6034 (2013)."},{"key":"27549_CR27","doi-asserted-by":"publisher","first-page":"512","DOI":"10.1016\/j.jacr.2017.12.028","volume":"15","author":"ML Giger","year":"2018","unstructured":"Giger, M. L. Machine learning in medical imaging. J. Am. Coll. Radiol. 15, 512\u2013520 (2018).","journal-title":"J. Am. Coll. Radiol."},{"key":"27549_CR28","doi-asserted-by":"publisher","first-page":"e1","DOI":"10.1002\/mp.13264","volume":"46","author":"B Sahiner","year":"2019","unstructured":"Sahiner, B. et al. Deep learning in medical imaging and radiation therapy. Med. Phys. 46, e1\u2013e36 (2019).","journal-title":"Med. Phys."},{"key":"27549_CR29","doi-asserted-by":"publisher","first-page":"60","DOI":"10.1016\/j.media.2017.07.005","volume":"42","author":"G Litjens","year":"2017","unstructured":"Litjens, G. et al. A survey on deep learning in medical image analysis. Med. Image Anal. 42, 60\u201388 (2017).","journal-title":"Med. Image Anal."},{"key":"27549_CR30","doi-asserted-by":"publisher","first-page":"5162","DOI":"10.1002\/mp.12453","volume":"44","author":"N Antropova","year":"2017","unstructured":"Antropova, N., Huynh, B. Q. & Giger, M. L. A deep feature fusion methodology for breast cancer diagnosis demonstrated on three imaging modality datasets. Med. Phys. 44, 5162\u20135171 (2017).","journal-title":"Med. Phys."},{"key":"27549_CR31","doi-asserted-by":"publisher","first-page":"48","DOI":"10.1016\/j.neucom.2021.03.091","volume":"452","author":"Z Niu","year":"2021","unstructured":"Niu, Z., Zhong, G. & Yu, H. A review on the attention mechanism of deep learning. Neurocomputing 452, 48\u201362 (2021).","journal-title":"Neurocomputing"},{"key":"27549_CR32","doi-asserted-by":"publisher","first-page":"837","DOI":"10.2307\/2531595","volume":"44","author":"ER DeLong","year":"1988","unstructured":"DeLong, E. R., DeLong, D. M. & Clarke-Pearson, D. L. Comparing the areas under two or more correlated receiver operating characteristic curves: A nonparametric approach. Biometrics 44, 837\u2013845 (1988).","journal-title":"Biometrics"},{"key":"27549_CR33","doi-asserted-by":"publisher","first-page":"1413","DOI":"10.1016\/j.ejrad.2015.03.010","volume":"84","author":"T Araki","year":"2015","unstructured":"Araki, T. et al. Paraseptal emphysema: Prevalence and distribution on CT and association with interstitial lung abnormalities. Eur. J. Radiol. 84, 1413\u20131418 (2015).","journal-title":"Eur. J. Radiol."},{"key":"27549_CR34","doi-asserted-by":"publisher","first-page":"239","DOI":"10.1378\/chest.41.3.239","volume":"41","author":"JP Wyatt","year":"1962","unstructured":"Wyatt, J. P., Fischer, V. W. & Sweet, H. C. Panlobular emphysema: Anatomy and pathodynamics. Dis. Chest 41, 239\u2013259 (1962).","journal-title":"Dis. Chest"},{"key":"27549_CR35","doi-asserted-by":"publisher","first-page":"547","DOI":"10.1136\/thx.28.5.547","volume":"28","author":"AE Anderson","year":"1973","unstructured":"Anderson, A. E. & Foraker, A. G. Centrilobular emphysema and panlobular emphysema: Two different diseases. Thorax 28, 547\u2013550 (1973).","journal-title":"Thorax"},{"key":"27549_CR36","doi-asserted-by":"publisher","first-page":"27","DOI":"10.1148\/radiology.159.1.3952318","volume":"159","author":"WL Foster","year":"1986","unstructured":"Foster, W. L. et al. Centrilobular emphysema: CT-pathologic correlation. Radiology 159, 27\u201332 (1986).","journal-title":"Radiology"}],"container-title":["Scientific Reports"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.nature.com\/articles\/s41598-023-27549-9.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/www.nature.com\/articles\/s41598-023-27549-9","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/www.nature.com\/articles\/s41598-023-27549-9.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,1,21]],"date-time":"2023-01-21T11:08:09Z","timestamp":1674299289000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.nature.com\/articles\/s41598-023-27549-9"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,1,21]]},"references-count":36,"journal-issue":{"issue":"1","published-online":{"date-parts":[[2023,12]]}},"alternative-id":["27549"],"URL":"https:\/\/doi.org\/10.1038\/s41598-023-27549-9","relation":{},"ISSN":["2045-2322"],"issn-type":[{"value":"2045-2322","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023,1,21]]},"assertion":[{"value":"15 August 2022","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"4 January 2023","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"21 January 2023","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"Dr. David Yankelevitz is a named inventor on a number of patents and patent applications relating to the evaluation of diseases of the chest including measurement of nodules. Some of these, which are owned by Cornell Research Foundation (CRF) are non-exclusively licensed to General Electric. As an inventor of these patents, Dr. Yankelevitz is entitled to a share of any compensation which CRF may receive from its commercialization of these patents. Consultant and shareholder for Accumetra LLC. Advisory Board and shareholder HeartLung Technologies. Advisory Board Median Technologies. Dr. Henschke is the President and serves on the board of the Early Diagnosis and Treatment Research Foundation. She receives no compensation from the Foundation. The Foundation is established to provide grants for projects, conferences, and public databases for research on early diagnosis and treatment of diseases. Dr. Claudia Henschke is also a named inventor on a number of patents and patent applications relating to the evaluation of pulmonary nodules on CT scans of the chest which are owned by Cornell Research Foundation (CRF). Since 2009, Dr. Henschke does not accept any financial benefit from these patents including royalties and any other proceeds related to the patents or patent applications owned by CRF. Maryellen L. Giger: Stockholder and receives royalties, Hologic, Inc.; Equity holder and co-founder, Quantitative Insights, Inc (now Qlarity Imaging).; Shareholder, QView Medical, Inc.; Royalties, General Electric Company, MEDIAN Technologies, Riverain Technologies, LLC, Mitsubishi, and Toshiba. Other authors declare no competing interests.","order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Competing interests"}}],"article-number":"1187"}}