{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,17]],"date-time":"2026-10-17T06:36:45Z","timestamp":1792219005645,"version":"4.4.0"},"reference-count":37,"publisher":"Springer Science and Business Media LLC","issue":"1","license":[{"start":{"date-parts":[[2023,6,2]],"date-time":"2023-06-02T00:00:00Z","timestamp":1685664000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"},{"start":{"date-parts":[[2023,6,2]],"date-time":"2023-06-02T00:00:00Z","timestamp":1685664000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Sci Rep"],"abstract":"<jats:title>Abstract<\/jats:title><jats:p>Infectious keratitis refers to a group of corneal disorders in which corneal tissues suffer inflammation and damage caused by pathogenic infections. Among these disorders, fungal keratitis (FK) and acanthamoeba keratitis (AK) are particularly severe and can cause permanent blindness if not diagnosed early and accurately. In Vivo Confocal Microscopy (IVCM) allows for imaging of different corneal layers and provides an important tool for an early and accurate diagnosis. In this paper, we introduce the IVCM-Keratitis dataset, which comprises of a total of 4001 sample images of AK and FK, as well as non-specific keratitis (NSK) and healthy corneas classes. We use this dataset to develop multiple deep-learning models based on Convolutional Neural Networks (CNNs) to provide automated assistance in enhancing the diagnostic accuracy of confocal microscopy in infectious keratitis. Densenet161 had the best performance among these models, with an accuracy, precision, recall, and F1 score of 93.55%, 92.52%, 94.77%, and 96.93%, respectively. Our study highlights the potential of deep learning models to provide automated diagnostic assistance for infectious keratitis via confocal microscopy images, particularly in the early detection of AK and FK. The proposed model can provide valuable support to both experienced and inexperienced eye-care practitioners in confocal microscopy image analysis, by suggesting the most likely diagnosis. We further demonstrate that these models can highlight the areas of infection in the IVCM images and explain the reasons behind their diagnosis by utilizing saliency maps, a technique used in eXplainable Artificial Intelligence (XAI) to interpret these models.<\/jats:p>","DOI":"10.1038\/s41598-023-35085-9","type":"journal-article","created":{"date-parts":[[2023,6,2]],"date-time":"2023-06-02T10:05:33Z","timestamp":1685700333000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":52,"title":["Interpretable deep learning for diagnosis of fungal and acanthamoeba keratitis using in vivo confocal microscopy images"],"prefix":"10.1038","volume":"13","author":[{"given":"Mahmoud","family":"Essalat","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Mohammad","family":"Abolhosseini","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Thanh Huy","family":"Le","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Seyed Mohamadmehdi","family":"Moshtaghion","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Mozhgan Rezaei","family":"Kanavi","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2023,6,2]]},"reference":[{"key":"35085_CR1","unstructured":"Goldstein, E. B. & Brockmole, J. Sensation & perception. (10th ed). In Cengage Learning, 75\u201377 (2016)"},{"issue":"6 Pt 2","key":"35085_CR2","doi-asserted-by":"publisher","first-page":"346","DOI":"10.1097\/ICL.0b013e318157c49d","volume":"33","author":"L Keay","year":"2007","unstructured":"Keay, L., Stapleton, F. & Schein, O. Epidemiology of contact lens-related inflammation and microbial keratitis: A 20-year perspective. Eye Contact Lens 33(6 Pt 2), 346\u2013363 (2007).","journal-title":"Eye Contact Lens"},{"issue":"11","key":"35085_CR3","doi-asserted-by":"publisher","first-page":"1678","DOI":"10.1016\/j.ophtha.2017.05.012","volume":"124","author":"A Austin","year":"2017","unstructured":"Austin, A., Lietman, T. & Rose-Nussbaumer, J. Update on the management of infectious keratitis. Ophthalmology 124(11), 1678\u20131689 (2017).","journal-title":"Ophthalmology"},{"issue":"14","key":"35085_CR4","doi-asserted-by":"publisher","first-page":"6367","DOI":"10.1167\/iovs.16-20110","volume":"57","author":"JM Alshehri","year":"2016","unstructured":"Alshehri, J. M. et al. Evaluation of corneal cross-linking for treatment of fungal keratitis: Using confocal laser scanning microscopy on an ex vivo human corneal model. Investig. Ophthalmol. Vis. Sci. 57(14), 6367\u20136373 (2016).","journal-title":"Investig. Ophthalmol. Vis. Sci."},{"issue":"2","key":"35085_CR5","doi-asserted-by":"publisher","first-page":"e0007964","DOI":"10.1371\/journal.pntd.0007964","volume":"14","author":"ML Rodrigues","year":"2020","unstructured":"Rodrigues, M. L. & Nosanchuk, J. D. Fungal diseases as neglected pathogens: A wake-up call to public health officials. PLoS Negl. Trop. Dis. 14(2), e0007964 (2020).","journal-title":"PLoS Negl. Trop. Dis."},{"issue":"1","key":"35085_CR6","doi-asserted-by":"publisher","first-page":"109","DOI":"10.1016\/j.ophtha.2005.08.013","volume":"113","author":"L Keay","year":"2006","unstructured":"Keay, L. et al. Microbial keratitis predisposing factors and morbidity. Ophthalmology 113(1), 109\u2013116 (2006).","journal-title":"Ophthalmology"},{"key":"35085_CR7","doi-asserted-by":"publisher","first-page":"10","DOI":"10.1051\/parasite\/2015010","volume":"22","author":"J Lorenzo-Morales","year":"2015","unstructured":"Lorenzo-Morales, J., Khan, N. A. & Walochnik, J. An update on Acanthamoeba keratitis: Diagnosis, pathogenesis and treatment. Parasite 22, 10 (2015).","journal-title":"Parasite"},{"issue":"2","key":"35085_CR8","doi-asserted-by":"publisher","first-page":"225","DOI":"10.1136\/bjo.87.2.225","volume":"87","author":"I Jalbert","year":"2003","unstructured":"Jalbert, I., Stapleton, F., Papas, E., Sweeney, D. F. & Coroneo, M. In vivo confocal microscopy of the human cornea. Br. J. Ophthalmol. 87(2), 225\u2013236 (2003).","journal-title":"Br. J. Ophthalmol."},{"issue":"8","key":"35085_CR9","doi-asserted-by":"publisher","first-page":"982","DOI":"10.1136\/bjo.2009.175083","volume":"94","author":"SC Hau","year":"2010","unstructured":"Hau, S. C. et al. Diagnostic accuracy of microbial keratitis with in vivo scanning laser confocal microscopy. Br. J. Ophthalmol. 94(8), 982\u2013987 (2010).","journal-title":"Br. J. Ophthalmol."},{"issue":"3\u20134","key":"35085_CR10","doi-asserted-by":"publisher","first-page":"197","DOI":"10.1561\/2000000039","volume":"7","author":"L Deng","year":"2014","unstructured":"Deng, L. & Dong, Y. Deep learning: Methods and applications. Found. Trends Signal Process. 7(3\u20134), 197\u2013387. https:\/\/doi.org\/10.1561\/2000000039 (2014).","journal-title":"Found. Trends Signal Process."},{"issue":"7553","key":"35085_CR11","doi-asserted-by":"publisher","first-page":"436","DOI":"10.1038\/nature14539","volume":"521","author":"Y LeCun","year":"2015","unstructured":"LeCun, Y., Bengio, Y. & Hinton, G. Deep learning. Nature 521(7553), 436\u2013444 (2015).","journal-title":"Nature"},{"key":"35085_CR12","doi-asserted-by":"publisher","first-page":"221","DOI":"10.1146\/annurev-bioeng-071516-044442","volume":"19","author":"D Shen","year":"2017","unstructured":"Shen, D., Wu, G. & Suk, H. I. Deep learning in medical image analysis. Annu. Rev. Biomed. Eng. 19, 221\u2013248 (2017).","journal-title":"Annu. Rev. Biomed. Eng."},{"issue":"9","key":"35085_CR13","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(9), 1410\u20131420 (2018).","journal-title":"Ophthalmology"},{"key":"35085_CR14","doi-asserted-by":"publisher","unstructured":"Chen, X., Xu, Y., Yan, S., Wong, D. W. K., Wong, T. Y. & Liu, J. Automatic feature learning for glaucoma detection based on deep learning. In Medical Image Computing and Computer-Assisted Intervention\u2013MICCAI 2015. MICCAI 2015, vol 9351 https:\/\/doi.org\/10.1007\/978-3-319-24574-4_80 (Springer, 2015).","DOI":"10.1007\/978-3-319-24574-4_80"},{"issue":"5","key":"35085_CR15","doi-asserted-by":"publisher","first-page":"e0177726","DOI":"10.1371\/journal.pone.0177726","volume":"12","author":"SJ Kim","year":"2017","unstructured":"Kim, S. J., Cho, K. J. & Oh, S. Development of machine learning models for diagnosis of glaucoma. PLoS ONE 12(5), e0177726 (2017).","journal-title":"PLoS ONE"},{"issue":"5","key":"35085_CR16","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(5), 1122-1131.e9 (2018).","journal-title":"Cell"},{"issue":"6","key":"35085_CR17","doi-asserted-by":"publisher","first-page":"720","DOI":"10.1097\/ICO.0000000000002279","volume":"39","author":"S Maruoka","year":"2020","unstructured":"Maruoka, S. et al. Deep neural network-based method for detecting obstructive meibomian gland dysfunction with in vivo laser confocal microscopy. Cornea 39(6), 720\u2013725 (2020).","journal-title":"Cornea"},{"issue":"11","key":"35085_CR18","doi-asserted-by":"publisher","first-page":"706","DOI":"10.21037\/atm.2020.03.134","volume":"8","author":"J Lv","year":"2020","unstructured":"Lv, J. et al. Deep learning-based automated diagnosis of fungal keratitis with in vivo confocal microscopy images. Ann. Transl. Med. 8(11), 706 (2020).","journal-title":"Ann. Transl. Med."},{"key":"35085_CR19","doi-asserted-by":"publisher","unstructured":"Zhang, X. Deep learning for three types of keratitis classification based on confocal microscopy images. In Proceedings of the 2020 3rd International Conference on Signal Processing and Machine Learning (SPML 2020), 91\u201397 https:\/\/doi.org\/10.1145\/3432291.3432310, (Association for Computing Machinery, 2020).","DOI":"10.1145\/3432291.3432310"},{"issue":"37","key":"35085_CR20","doi-asserted-by":"publisher","first-page":"7120","DOI":"10.1126\/scirobotics.aay7120","volume":"4","author":"D Gunning","year":"2019","unstructured":"Gunning, D. et al. XAI-explainable artificial intelligence. Sci. Robot. 4(37), 7120 (2019).","journal-title":"Sci. Robot."},{"key":"35085_CR21","doi-asserted-by":"publisher","unstructured":"Simonyan, K., Vedaldi, A. & Zisserman, A. Deep inside convolutional networks: Visualising image classification models and saliency maps. arXiv preprint 1312.6034 https:\/\/doi.org\/10.48550\/ARXIV.1312.6034 (2013).","DOI":"10.48550\/ARXIV.1312.6034"},{"issue":"3","key":"35085_CR22","doi-asserted-by":"publisher","first-page":"333","DOI":"10.1080\/08164622.2021.1932430","volume":"105","author":"M Abolhosseini","year":"2022","unstructured":"Abolhosseini, M., Moshtaghion, S. M., Rezaei Kanavi, M. & Hosseini, S. B. A triad of microscopes for rapid and proper diagnosis of infectious keratitis. Clin. Exp. Optom. 105(3), 333\u2013335 (2022).","journal-title":"Clin. Exp. Optom."},{"key":"35085_CR23","doi-asserted-by":"crossref","unstructured":"Essalat, M., Abolhosseini, M., Le, T. H., Moshtaghion, S. M. & Kanavi, M. R. An interpretable deep learning approach for automatic diagnosis of fungal keratitis and acanthamoeba keratitis based on an introduced database of in vivo confocal microscopic images (Version 1.0.0), https:\/\/figshare.com\/articles\/dataset\/Dataset\/19838083 (2022).","DOI":"10.2139\/ssrn.4119213"},{"key":"35085_CR24","doi-asserted-by":"publisher","unstructured":"Miko\u0142ajczyk, A. & Grochowski, M. Data augmentation for improving deep learning in image classification problem. In 2018 International Interdisciplinary PhD Workshop (IIPhDW 2018), 117\u2013122, https:\/\/doi.org\/10.1109\/IIPHDW.2018.8388338 (IEEE, 2018)","DOI":"10.1109\/IIPHDW.2018.8388338"},{"key":"35085_CR25","doi-asserted-by":"publisher","unstructured":"Huang, G., Liu, Z., Van Der Maaten, L. & Weinberger, K. Q. Densely connected convolutional networks. In 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2261\u20132269, https:\/\/doi.org\/10.1109\/CVPR.2017.243 (IEEE, 2017)","DOI":"10.1109\/CVPR.2017.243"},{"key":"35085_CR26","doi-asserted-by":"publisher","unstructured":"He, K., Zhang, X., Ren, S. & Sun, J. Deep residual learning for image recognition. In 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR 2016), 770\u2013778, https:\/\/doi.org\/10.1109\/CVPR.2016.90 (IEEE,2016)","DOI":"10.1109\/CVPR.2016.90"},{"key":"35085_CR27","doi-asserted-by":"publisher","unstructured":"Wang, C. Y. et al. CSPNet: A new backbone that can enhance learning capability of CNN. In Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition Workshops. arXiv preprint; 1911.11929. https:\/\/doi.org\/10.48550\/ARXIV.1911.11929 (2019).","DOI":"10.48550\/ARXIV.1911.11929"},{"key":"35085_CR28","doi-asserted-by":"publisher","unstructured":"Xie, S., Girshick, R., Doll\u00e1r, P. & Tu, Z. Aggregated residual transformations for deep neural networks. In 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR 2017), 5987\u20135995, https:\/\/doi.org\/10.1109\/CVPR.2017.634 (IEEE,2017)","DOI":"10.1109\/CVPR.2017.634"},{"key":"35085_CR29","doi-asserted-by":"publisher","unstructured":"Simonyan, K. & Zisserman, A. Very deep convolutional networks for large-scale image recognition. arXiv preprint 1409.1556. https:\/\/doi.org\/10.48550\/arxiv.1409.1556. (2014).","DOI":"10.48550\/arxiv.1409.1556"},{"key":"35085_CR30","unstructured":"Glorot, X. & Bengio, Y. Understanding the difficulty of training deep feedforward neural networks. Proceedings of the Thirteenth International Conference on Artificial Intelligence and Statistics, In Proceedings of Machine Learning Research (PMLR) vol. 9, 249\u2013256. https:\/\/proceedings.mlr.press\/v9\/glorot10a (2010)."},{"key":"35085_CR31","doi-asserted-by":"publisher","DOI":"10.1007\/978-0-387-39940-9_565","volume-title":"Encyclopedia of Database Systems","author":"P Refaeilzadeh","year":"2009","unstructured":"Refaeilzadeh, P., Tang, L. & Liu, H. Cross-validation. In Encyclopedia of Database Systems (eds Liu, L. & \u00d6zsu, M. T.) (Springer, 2009). https:\/\/doi.org\/10.1007\/978-0-387-39940-9_565."},{"issue":"1","key":"35085_CR32","doi-asserted-by":"publisher","first-page":"14424","DOI":"10.1038\/s41598-020-71425-9","volume":"10","author":"MT Kuo","year":"2020","unstructured":"Kuo, M. T. et al. A deep learning approach in diagnosing fungal keratitis based on corneal photographs. Sci. Rep. 10(1), 14424 (2020).","journal-title":"Sci. Rep."},{"issue":"1","key":"35085_CR33","doi-asserted-by":"publisher","first-page":"30","DOI":"10.1016\/j.preteyeres.2009.11.001","volume":"29","author":"RL Niederer","year":"2010","unstructured":"Niederer, R. L. & McGhee, C. N. Clinical in vivo confocal microscopy of the human cornea in health and disease. Prog. Retin. Eye Res. 29(1), 30\u201358 (2010).","journal-title":"Prog. Retin. Eye Res."},{"issue":"5","key":"35085_CR34","doi-asserted-by":"publisher","first-page":"466","DOI":"10.1016\/j.survophthal.2012.12.003","volume":"58","author":"DV Patel","year":"2013","unstructured":"Patel, D. V. & McGhee, C. N. Quantitative analysis of in vivo confocal microscopy images: A review. Surv. Ophthalmol. 58(5), 466\u2013475 (2013).","journal-title":"Surv. Ophthalmol."},{"key":"35085_CR35","doi-asserted-by":"publisher","first-page":"81","DOI":"10.1016\/j.ajo.2017.04.011","volume":"179","author":"A Kheirkhah","year":"2017","unstructured":"Kheirkhah, A. et al. Sensitivity and specificity of laser-scanning in vivo confocal microscopy for filamentous fungal keratitis: Role of observer experience. Am. J. Ophthalmol. 179, 81\u201389. https:\/\/doi.org\/10.1016\/j.ajo.2017.04.011 (2017) (Epub 2017 Apr 23).","journal-title":"Am. J. Ophthalmol."},{"issue":"7","key":"35085_CR36","doi-asserted-by":"publisher","first-page":"818","DOI":"10.1097\/ICO.0000000000001507","volume":"37","author":"A Kheirkhah","year":"2018","unstructured":"Kheirkhah, A. et al. Factors influencing the diagnostic accuracy of laser-scanning in vivo confocal microscopy for acanthamoeba keratitis. Cornea 37(7), 818\u2013823. https:\/\/doi.org\/10.1097\/ICO.0000000000001507 (2018).","journal-title":"Cornea"},{"issue":"8","key":"35085_CR37","doi-asserted-by":"publisher","first-page":"5136","DOI":"10.1167\/iovs.10-7048","volume":"52","author":"A Cruzat","year":"2011","unstructured":"Cruzat, A. et al. Inflammation and the nervous system: The connection in the cornea in patients with infectious keratitis. Investig. Ophthalmol. Vis. Sci. 52(8), 5136\u20135143. https:\/\/doi.org\/10.1167\/iovs.10-7048 (2011).","journal-title":"Investig. Ophthalmol. Vis. Sci."}],"container-title":["Scientific Reports"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.nature.com\/articles\/s41598-023-35085-9.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/www.nature.com\/articles\/s41598-023-35085-9","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/www.nature.com\/articles\/s41598-023-35085-9.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,6,2]],"date-time":"2023-06-02T10:10:05Z","timestamp":1685700605000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.nature.com\/articles\/s41598-023-35085-9"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,6,2]]},"references-count":37,"journal-issue":{"issue":"1","published-online":{"date-parts":[[2023,12]]}},"alternative-id":["35085"],"URL":"https:\/\/doi.org\/10.1038\/s41598-023-35085-9","relation":{},"ISSN":["2045-2322"],"issn-type":[{"value":"2045-2322","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023,6,2]]},"assertion":[{"value":"2 November 2022","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"12 May 2023","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"2 June 2023","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":"8953"}}