{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,9]],"date-time":"2026-03-09T06:33:36Z","timestamp":1773038016647,"version":"3.50.1"},"reference-count":29,"publisher":"Springer Science and Business Media LLC","issue":"1","license":[{"start":{"date-parts":[[2021,3,11]],"date-time":"2021-03-11T00:00:00Z","timestamp":1615420800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"},{"start":{"date-parts":[[2021,3,11]],"date-time":"2021-03-11T00:00:00Z","timestamp":1615420800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"}],"funder":[{"name":"Medical Synergy Science and Technology Innovation Research"},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["U1830107"],"award-info":[{"award-number":["U1830107"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["81700813"],"award-info":[{"award-number":["81700813"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Beijing Municipal Administration of Hospitals' Youth Programme"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["npj Digit. Med."],"abstract":"<jats:title>Abstract<\/jats:title><jats:p>The application of deep learning algorithms for medical diagnosis in the real world faces challenges with transparency and interpretability. The labeling of large-scale samples leads to costly investment in developing deep learning algorithms. The application of human prior knowledge is an effective way to solve these problems. Previously, we developed a deep learning system for glaucoma diagnosis based on a large number of samples that had high sensitivity and specificity. However, it is a black box and the specific analytic methods cannot be elucidated. Here, we establish a hierarchical deep learning system based on a small number of samples that comprehensively simulates the diagnostic thinking of human experts. This system can extract the anatomical characteristics of the fundus images, including the optic disc, optic cup, and appearance of the retinal nerve fiber layer to realize automatic diagnosis of glaucoma. In addition, this system is transparent and interpretable, and the intermediate process of prediction can be visualized. Applying this system to three validation datasets of fundus images, we demonstrate performance comparable to that of human experts in diagnosing glaucoma. Moreover, it markedly improves the diagnostic accuracy of ophthalmologists. This system may expedite the screening and diagnosis of glaucoma, resulting in improved clinical outcomes.<\/jats:p>","DOI":"10.1038\/s41746-021-00417-4","type":"journal-article","created":{"date-parts":[[2021,3,11]],"date-time":"2021-03-11T11:03:49Z","timestamp":1615460629000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":40,"title":["A hierarchical deep learning approach with transparency and interpretability based on small samples for glaucoma diagnosis"],"prefix":"10.1038","volume":"4","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-9625-3410","authenticated-orcid":false,"given":"Yongli","family":"Xu","sequence":"first","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0350-4071","authenticated-orcid":false,"given":"Man","family":"Hu","sequence":"additional","affiliation":[]},{"given":"Hanruo","family":"Liu","sequence":"additional","affiliation":[]},{"given":"Hao","family":"Yang","sequence":"additional","affiliation":[]},{"given":"Huaizhou","family":"Wang","sequence":"additional","affiliation":[]},{"given":"Shuai","family":"Lu","sequence":"additional","affiliation":[]},{"given":"Tianwei","family":"Liang","sequence":"additional","affiliation":[]},{"given":"Xiaoxing","family":"Li","sequence":"additional","affiliation":[]},{"given":"Mai","family":"Xu","sequence":"additional","affiliation":[]},{"given":"Liu","family":"Li","sequence":"additional","affiliation":[]},{"given":"Huiqi","family":"Li","sequence":"additional","affiliation":[]},{"given":"Xin","family":"Ji","sequence":"additional","affiliation":[]},{"given":"Zhijun","family":"Wang","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5585-743X","authenticated-orcid":false,"given":"Li","family":"Li","sequence":"additional","affiliation":[]},{"given":"Robert N.","family":"Weinreb","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8933-4482","authenticated-orcid":false,"given":"Ningli","family":"Wang","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2021,3,11]]},"reference":[{"key":"417_CR1","doi-asserted-by":"publisher","first-page":"2402","DOI":"10.1001\/jama.2016.17216","volume":"316","author":"V Gulshan","year":"2016","unstructured":"Gulshan, V. et al. Development and validation of a deep learning algorithm for detection of diabetic retinopathy in retinal fundus photographs. JAMA 316, 2402\u20132410 (2016).","journal-title":"JAMA"},{"key":"417_CR2","doi-asserted-by":"publisher","first-page":"1122","DOI":"10.1016\/j.cell.2018.02.010","volume":"172","author":"DS Kermany","year":"2018","unstructured":"Kermany, D. S. et al. Identifying medical diagnoses and treatable diseases by image-based deep learning. Cell 172, 1122\u20131131 (2018). e9.","journal-title":"Cell"},{"key":"417_CR3","doi-asserted-by":"publisher","first-page":"115","DOI":"10.1038\/nature21056","volume":"542","author":"A Esteva","year":"2017","unstructured":"Esteva, A. et al. Dermatologist-level classification of skin cancer with deep neural networks. Nature 542, 115\u2013118 (2017).","journal-title":"Nature"},{"key":"417_CR4","doi-asserted-by":"publisher","DOI":"10.1038\/srep24454","volume":"6","author":"JZ Cheng","year":"2016","unstructured":"Cheng, J. Z. et al. Computer-aided diagnosis with deep learning architecture: applications to breast lesions in US images and pulmonary nodules in CT scans. Sci. Rep. 6, 24454 (2016).","journal-title":"Sci. Rep."},{"key":"417_CR5","doi-asserted-by":"publisher","first-page":"1337","DOI":"10.1038\/s41591-018-0147-y","volume":"24","author":"JJ Titano","year":"2018","unstructured":"Titano, J. J. et al. Automated deep-neural-network surveillance of cranial images for acute neurologic events. Nat. Med. 24, 1337\u20131341 (2018).","journal-title":"Nat. Med."},{"key":"417_CR6","doi-asserted-by":"publisher","first-page":"357","DOI":"10.7326\/M18-0249","volume":"169","author":"Y Mori","year":"2018","unstructured":"Mori, Y. et al. Real-time use of artificial intelligence in identification of diminutive polyps during colonoscopy: a prospective study. Ann. Intern. Med. 169, 357\u2013366 (2018).","journal-title":"Ann. Intern. Med"},{"key":"417_CR7","doi-asserted-by":"publisher","first-page":"2199","DOI":"10.1001\/jama.2017.14585","volume":"318","author":"BB Ehteshami","year":"2017","unstructured":"Ehteshami, B. B. et al. Diagnostic assessment of deep learning algorithms for detection of lymph node metastases in women with breast cancer. JAMA 318, 2199\u20132210 (2017).","journal-title":"JAMA"},{"key":"417_CR8","doi-asserted-by":"publisher","first-page":"30","DOI":"10.1038\/s41591-018-0307-0","volume":"25","author":"J He","year":"2019","unstructured":"He, J. et al. The practical implementation of artificial intelligence technologies in medicine. Nat. Med. 25, 30\u201336 (2019).","journal-title":"Nat. Med."},{"key":"417_CR9","doi-asserted-by":"publisher","DOI":"10.1017\/S0140525X17000255","volume":"40","author":"PM Patrzyk","year":"2017","unstructured":"Patrzyk, P. M., Link, D. & Marewski, J. N. Human-like machines: transparency and comprehensibility. Behav. Brain Sci. 40, e276 (2017).","journal-title":"Behav. Brain Sci."},{"key":"417_CR10","doi-asserted-by":"publisher","first-page":"626","DOI":"10.1162\/NECO_a_00409","volume":"25","author":"D Sussillo","year":"2013","unstructured":"Sussillo, D. & Barak, O. Opening the black box: low-dimensional dynamics in high-dimensional recurrent neural networks. Neural Comput. 25, 626\u2013649 (2013).","journal-title":"Neural Comput."},{"key":"417_CR11","doi-asserted-by":"publisher","first-page":"44","DOI":"10.1038\/s41591-018-0300-7","volume":"25","author":"EJ Topol","year":"2019","unstructured":"Topol, E. J. High-performance medicine: the convergence of human and artificial intelligence. Nat. Med. 25, 44\u201356 (2019).","journal-title":"Nat. Med"},{"key":"417_CR12","doi-asserted-by":"publisher","first-page":"70","DOI":"10.1097\/SLA.0000000000002693","volume":"268","author":"DA Hashimoto","year":"2018","unstructured":"Hashimoto, D. A., Rosman, G., Rus, D. & Meireles, O. R. Artificial intelligence in surgery: promises and perils. Ann. Surg. 268, 70\u201376 (2018).","journal-title":"Ann. Surg."},{"key":"417_CR13","doi-asserted-by":"publisher","first-page":"2366","DOI":"10.1001\/jama.2016.17563","volume":"316","author":"TY Wong","year":"2016","unstructured":"Wong, T. Y. & Bressler, N. M. Artificial intelligence with deep learning technology looks into diabetic retinopathy screening. JAMA 316, 2366\u20132367 (2016).","journal-title":"JAMA"},{"key":"417_CR14","doi-asserted-by":"publisher","first-page":"1170","DOI":"10.1001\/jamaophthalmol.2017.3782","volume":"135","author":"PM Burlina","year":"2017","unstructured":"Burlina, P. M. et al. Automated grading of age-related macular degeneration from color fundus images using deep convolutional neural networks. JAMA Ophthalmol. 135, 1170\u20131176 (2017).","journal-title":"JAMA Ophthalmol."},{"key":"417_CR15","doi-asserted-by":"publisher","first-page":"2211","DOI":"10.1001\/jama.2017.18152","volume":"318","author":"D Ting","year":"2017","unstructured":"Ting, D. et al. Development and validation of a deep learning system for diabetic retinopathy and related eye diseases using retinal images from multiethnic populations with diabetes. JAMA 318, 2211\u20132223 (2017).","journal-title":"JAMA"},{"key":"417_CR16","doi-asserted-by":"publisher","first-page":"1410","DOI":"10.1016\/j.ophtha.2018.02.037","volume":"125","author":"F Grassmann","year":"2018","unstructured":"Grassmann, F. et al. A deep learning algorithm for prediction of age-related eye disease study severity scale for age-related macular degeneration from color fundus photography. Ophthalmology 125, 1410\u20131420 (2018).","journal-title":"Ophthalmology"},{"key":"417_CR17","doi-asserted-by":"publisher","first-page":"158","DOI":"10.1038\/s41551-018-0195-0","volume":"2","author":"R Poplin","year":"2018","unstructured":"Poplin, R. et al. Prediction of cardiovascular risk factors from retinal fundus photographs via deep learning. Nat. Biomed. Eng. 2, 158\u2013164 (2018).","journal-title":"Nat. Biomed. Eng."},{"key":"417_CR18","doi-asserted-by":"publisher","first-page":"1199","DOI":"10.1016\/j.ophtha.2018.01.023","volume":"125","author":"Z Li","year":"2018","unstructured":"Li, Z. et al. Efficacy of a deep learning system for detecting glaucomatous optic neuropathy based on color fundus photographs. Ophthalmology 125, 1199\u20131206 (2018).","journal-title":"Ophthalmology"},{"key":"417_CR19","doi-asserted-by":"publisher","first-page":"1353","DOI":"10.1001\/jamaophthalmol.2019.3501","volume":"137","author":"H Liu","year":"2019","unstructured":"Liu, H. et al. Development and validation of a deep learning system to detect glaucomatous optic neuropathy using fundus photographs. JAMA Ophthalmol. 137, 1353\u20131360 (2019).","journal-title":"JAMA Ophthalmol."},{"key":"417_CR20","doi-asserted-by":"publisher","DOI":"10.1038\/s41598-018-35044-9","volume":"8","author":"M Christopher","year":"2018","unstructured":"Christopher, M. et al. Performance of deep learning architectures and transfer learning for detecting glaucomatous optic neuropathy in fundus photographs. Sci. Rep. 8, 16685 (2018).","journal-title":"Sci. Rep."},{"key":"417_CR21","doi-asserted-by":"publisher","first-page":"1597","DOI":"10.1109\/TMI.2018.2791488","volume":"37","author":"H Fu","year":"2018","unstructured":"Fu, H. et al. Joint optic disc and cup segmentation based on multi-label deep network and polar transformation. IEEE Trans. Med Imaging 37, 1597\u20131605 (2018).","journal-title":"IEEE Trans. Med Imaging"},{"key":"417_CR22","doi-asserted-by":"crossref","unstructured":"Sammut, C. & Webb, G. I. Encyclopedia of Machine Learning, (Springer US, 2010).","DOI":"10.1007\/978-0-387-30164-8"},{"key":"417_CR23","doi-asserted-by":"publisher","first-page":"54","DOI":"10.1016\/j.knosys.2016.05.055","volume":"107","author":"Z Qi","year":"2016","unstructured":"Qi, Z., Wang, B., Tian, Y. & Zhang, P. When ensemble learning meets deep learning: A new deep support vector machine for classification. Knowl.-Based Syst. 107, 54\u201360 (2016).","journal-title":"Knowl.-Based Syst."},{"key":"417_CR24","doi-asserted-by":"publisher","first-page":"878","DOI":"10.15252\/msb.20156651","volume":"12","author":"C Angermueller","year":"2016","unstructured":"Angermueller, C., P\u00e4rnamaa, T., Parts, L. & Stegle, O. Deep learning for computational biology. Mol. Syst. Biol. 12, 878 (2016).","journal-title":"Mol. Syst. Biol."},{"key":"417_CR25","doi-asserted-by":"crossref","unstructured":"Szegedy, C., Vanhoucke, V., Ioffe, S., Shlens, J. & Wojna, Z. Rethinking the inception architecture for computer vision. in 2016 IEEE Conference on Computer Vision and Pattern Recognition (2016).","DOI":"10.1109\/CVPR.2016.308"},{"key":"417_CR26","doi-asserted-by":"crossref","unstructured":"Ronneberger, O., Fischer, P. & Brox, T. U-Net: Convolutional networks for biomedical image segmentation. in International Conference on Medical Image Computing and Computer-Assisted Intervention (2015).","DOI":"10.1007\/978-3-319-24574-4_28"},{"key":"417_CR27","doi-asserted-by":"publisher","first-page":"1579","DOI":"10.1001\/archopht.124.11.1579","volume":"124","author":"N Harizman","year":"2006","unstructured":"Harizman, N. et al. The ISNT rule and differentiation of normal from glaucomatous eyes. Arch. Ophthalmol. 124, 1579\u20131583 (2006).","journal-title":"Arch. Ophthalmol."},{"key":"417_CR28","first-page":"273","volume":"20","author":"C Cortes","year":"1995","unstructured":"Cortes, C. & Vapnik, V. N. Support vector networks. Mach. Learn. 20, 273\u2013297 (1995).","journal-title":"Mach. Learn."},{"key":"417_CR29","doi-asserted-by":"publisher","first-page":"660","DOI":"10.1109\/21.97458","volume":"21","author":"SR Safavian","year":"2002","unstructured":"Safavian, S. R. & Landgrebe, D. A survey of decision tree classifier methodology. IEEE Trans. Syst. Man Cybern. 21, 660\u2013674 (2002).","journal-title":"IEEE Trans. Syst. Man Cybern."}],"container-title":["npj Digital Medicine"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.nature.com\/articles\/s41746-021-00417-4.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/www.nature.com\/articles\/s41746-021-00417-4","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/www.nature.com\/articles\/s41746-021-00417-4.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,12,3]],"date-time":"2022-12-03T18:46:59Z","timestamp":1670093219000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.nature.com\/articles\/s41746-021-00417-4"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,3,11]]},"references-count":29,"journal-issue":{"issue":"1","published-online":{"date-parts":[[2021,12]]}},"alternative-id":["417"],"URL":"https:\/\/doi.org\/10.1038\/s41746-021-00417-4","relation":{},"ISSN":["2398-6352"],"issn-type":[{"value":"2398-6352","type":"electronic"}],"subject":[],"published":{"date-parts":[[2021,3,11]]},"assertion":[{"value":"9 June 2020","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"8 February 2021","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"11 March 2021","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"The authors declare no competing interests.","order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Competing interests"}}],"article-number":"48"}}