{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,30]],"date-time":"2026-03-30T20:26:24Z","timestamp":1774902384817,"version":"3.50.1"},"reference-count":37,"publisher":"Frontiers Media SA","license":[{"start":{"date-parts":[[2022,12,5]],"date-time":"2022-12-05T00:00:00Z","timestamp":1670198400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":["frontiersin.org"],"crossmark-restriction":true},"short-container-title":["Front. Cell Dev. Biol."],"abstract":"<jats:p>Meibomian gland dysfunction (MGD) is caused by abnormalities of the meibomian glands (MG) and is one of the causes of evaporative dry eye (DED). Precise MG segmentation is crucial for MGD-related DED diagnosis because the morphological parameters of MG are of importance. Deep learning has achieved state-of-the-art performance in medical image segmentation tasks, especially when training and test data come from the same distribution. But in practice, MG images can be acquired from different devices or hospitals. When testing image data from different distributions, deep learning models that have been trained on a specific distribution are prone to poor performance. Histogram specification (HS) has been reported as an effective method for contrast enhancement and improving model performance on images of different modalities. Additionally, contrast limited adaptive histogram equalization (CLAHE) will be used as a preprocessing method to enhance the contrast of MG images. In this study, we developed and evaluated the automatic segmentation method of the eyelid area and the MG area based on CNN and automatically calculated MG loss rate. This method is evaluated in the internal and external testing sets from two meibography devices. In addition, to assess whether HS and CLAHE improve segmentation results, we trained the network model using images from one device (internal testing set) and tested on images from another device (external testing set). High DSC (0.84 for MG region, 0.92 for eyelid region) for the internal test set was obtained, while for the external testing set, lower DSC (0.69\u20130.71 for MG region, 0.89\u20130.91 for eyelid region) was obtained. Also, HS and CLAHE were reported to have no statistical improvement in the segmentation results of MG in this experiment.<\/jats:p>","DOI":"10.3389\/fcell.2022.1067914","type":"journal-article","created":{"date-parts":[[2022,12,5]],"date-time":"2022-12-05T07:21:58Z","timestamp":1670224918000},"update-policy":"https:\/\/doi.org\/10.3389\/crossmark-policy","source":"Crossref","is-referenced-by-count":6,"title":["Is histogram manipulation always beneficial when trying to improve model performance across devices? Experiments using a Meibomian gland segmentation model"],"prefix":"10.3389","volume":"10","author":[{"given":"Xianyu","family":"Deng","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Lei","family":"Tian","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yinghuai","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ao","family":"Li","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Shangyu","family":"Cai","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yongjin","family":"Zhou","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ying","family":"Jie","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"1965","published-online":{"date-parts":[[2022,12,5]]},"reference":[{"key":"B1","doi-asserted-by":"publisher","first-page":"911","DOI":"10.1016\/j.ophtha.2007.06.031","article-title":"Noncontact infrared meibography to document age-related changes of the meibomian glands in a normal population","volume":"115","author":"Arita","year":"2008","journal-title":"Ophthalmology"},{"key":"B2","doi-asserted-by":"publisher","first-page":"746","DOI":"10.1136\/bjophthalmol-2012-303014","article-title":"Objective image analysis of the meibomian gland area","volume":"98","author":"Arita","year":"2014","journal-title":"Br. J. Ophthalmol."},{"key":"B3","doi-asserted-by":"publisher","first-page":"194","DOI":"10.1016\/j.optom.2013.09.001","article-title":"Bioimage informatics approach to automated meibomian gland analysis in infrared images of meibography","volume":"6","author":"Celik","year":"2013","journal-title":"J. Optometry"},{"key":"B4","doi-asserted-by":"publisher","first-page":"103906","DOI":"10.1016\/j.compbiomed.2020.103906","article-title":"Kidney segmentation from computed tomography images using deep neural network","volume":"123","author":"da Cruz","year":"2020","journal-title":"Comput. Biol. Med."},{"key":"B5","doi-asserted-by":"publisher","first-page":"23083","DOI":"10.1109\/ACCESS.2021.3056234","article-title":"A novel meibomian gland morphology analytic system based on a convolutional neural network","volume":"9","author":"Dai","year":"2021","journal-title":"IEEE Access"},{"key":"B6","doi-asserted-by":"publisher","first-page":"1930","DOI":"10.1167\/iovs.10-6997b","article-title":"The international workshop on meibomian gland dysfunction: Report of the definition and classification subcommittee","volume":"52","author":"Den","year":"2011","journal-title":"Invest. Ophthalmol. Vis. Sci."},{"key":"B7","first-page":"17","article-title":"Ocular surface disease","volume-title":"Update in the diagnosis and management of meibomian gland dysfunction","author":"Djalilian","year":"2018"},{"key":"B8","doi-asserted-by":"publisher","first-page":"343","DOI":"10.1016\/s0039-6257(96)80064-6","article-title":"Meibomian gland dysfunction","volume":"40","author":"Driver","year":"1996","journal-title":"Surv. Ophthalmol."},{"key":"B9","doi-asserted-by":"publisher","first-page":"1938","DOI":"10.1167\/iovs.10-6997c","article-title":"The international workshop on meibomian gland dysfunction: Report of the subcommittee on anatomy, physiology, and pathophysiology of the meibomian gland","volume":"52","author":"Erich","year":"2011","journal-title":"Invest. Ophthalmol. Vis. Sci."},{"key":"B10","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1021\/ci0342472","article-title":"The problem of overfitting","volume":"44","author":"Hawkins","year":"2004","journal-title":"J. Chem. Inf. Comput. Sci."},{"key":"B11","first-page":"770","article-title":"Deep residual learning for image recognition","author":"He","year":"2016"},{"key":"B12","doi-asserted-by":"publisher","first-page":"201","DOI":"10.1016\/j.jtos.2020.08.012","article-title":"A novel transillumination meibography device for in vivo imaging of mouse meibomian glands","volume":"19","author":"Hwang","year":"2021","journal-title":"Ocul. Surf."},{"key":"B13","doi-asserted-by":"crossref","DOI":"10.1109\/CIBCB48159.2020.9277638","article-title":"A survey of loss functions for semantic segmentation","author":"Jadon","year":"2020"},{"key":"B14","article-title":"Measuring the tendency of cnns to learn surface statistical regularities","author":"Jo","year":"2017"},{"key":"B15","doi-asserted-by":"publisher","first-page":"82","DOI":"10.1186\/s12938-017-0373-4","article-title":"A clinical utility assessment of the automatic measurement method of the quality of Meibomian glands","volume":"16","author":"Koprowski","year":"2017","journal-title":"Biomed. Eng. Online"},{"key":"B16","doi-asserted-by":"publisher","first-page":"130","DOI":"10.1016\/j.compbiomed.2016.06.001","article-title":"A quantitative method for assessing the quality of meibomian glands","volume":"75","author":"Koprowski","year":"2016","journal-title":"Comput. Biol. Med."},{"key":"B17","doi-asserted-by":"publisher","first-page":"192","DOI":"10.3390\/app7020192","article-title":"Recognition algorithm based on improved FCM and rough sets for meibomian gland morphology","volume":"7","author":"Liang","year":"2017","journal-title":"Appl. Sci."},{"key":"B18","doi-asserted-by":"publisher","first-page":"17","DOI":"10.1167\/tvst.8.4.17","article-title":"A novel automated approach for infrared-based assessment of meibomian gland morphology","volume":"8","author":"Llorens-Quintana","year":"2019","journal-title":"Trans. Vis. Sci. Tech."},{"key":"B19","doi-asserted-by":"publisher","first-page":"144","DOI":"10.1016\/j.jtos.2015.11.002","article-title":"Economic and humanistic burden of dry eye disease in europe, north America, and asia: A systematic literature review","volume":"14","author":"McDonald","year":"2016","journal-title":"Ocul. Surf."},{"key":"B20","doi-asserted-by":"publisher","first-page":"118154","DOI":"10.1109\/ACCESS.2021.3107473","article-title":"Cross-modality guided contrast enhancement for improved liver tumor image segmentation","volume":"9","author":"Naseem","year":"2021","journal-title":"IEEE Access"},{"key":"B21","doi-asserted-by":"publisher","first-page":"1922","DOI":"10.1167\/iovs.10-6997a","article-title":"The international workshop on meibomian gland dysfunction: Executive summary","volume":"52","author":"Nichols","year":"2011","journal-title":"Invest. Ophthalmol. Vis. Sci."},{"key":"B22","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1016\/j.neuroimage.2019.03.026","article-title":"Unsupervised domain adaptation for medical imaging segmentation with self-ensembling","volume":"194","author":"Perone","year":"2019","journal-title":"NeuroImage"},{"key":"B23","doi-asserted-by":"publisher","first-page":"101776","DOI":"10.1016\/j.bspc.2019.101776","article-title":"Deep learning segmentation and quantification of Meibomian glands","volume":"57","author":"Prabhu","year":"2020","journal-title":"Biomed. Signal Process. Control"},{"key":"B24","doi-asserted-by":"publisher","first-page":"E760","DOI":"10.1097\/OPX.0b013e3182512ac1","article-title":"A review of meibography","volume":"89","author":"Pult","year":"2012","journal-title":"Optom. Vis. Sci."},{"key":"B25","doi-asserted-by":"publisher","first-page":"22","DOI":"10.1016\/j.clae.2012.10.074","article-title":"Comparison of subjective grading and objective assessment in meibography","volume":"36","author":"Pult","year":"2013","journal-title":"Cont. Lens Anterior Eye"},{"key":"B26","doi-asserted-by":"publisher","first-page":"77","DOI":"10.1016\/j.clae.2011.08.003","article-title":"Non-contact meibography: Keep it simple but effective","volume":"35","author":"Pult","year":"2012","journal-title":"Cont. Lens Anterior Eye"},{"key":"B27","first-page":"234","article-title":"U-net: Convolutional networks for biomedical image segmentation","author":"Ronneberger","year":"2015"},{"key":"B28","doi-asserted-by":"publisher","DOI":"10.15406\/aovs.2018.08.00295","article-title":"Meibomian gland dysfunction: An overlooked eyelid disease","volume":"8","author":"Turgut","year":"2018","journal-title":"Adv. Ophthalmol. Vis. Syst."},{"key":"B29","doi-asserted-by":"publisher","first-page":"33","DOI":"10.1007\/s10994-011-5273-4","article-title":"Visualizing non-metric similarities in multiple maps","volume":"9","author":"Van der Maaten","year":"2008","journal-title":"Mach. Learn."},{"key":"B30","doi-asserted-by":"publisher","first-page":"37","DOI":"10.1167\/tvst.8.6.37","article-title":"A deep learning approach for meibomian gland atrophy evaluation in meibography images","volume":"8","author":"Wang","year":"2019","journal-title":"Trans. Vis. Sci. Tech."},{"key":"B31","doi-asserted-by":"publisher","first-page":"311","DOI":"10.1016\/j.clae.2018.10.014","article-title":"Comparison of meibomian gland dropout using two infrared imaging devices","volume":"42","author":"Wong","year":"2019","journal-title":"Cont. Lens Anterior Eye"},{"key":"B32","doi-asserted-by":"publisher","first-page":"2798","DOI":"10.1016\/j.neucom.2017.11.057","article-title":"Brightness and contrast controllable image enhancement based on histogram specification","volume":"275","author":"Xiao","year":"2018","journal-title":"Neurocomputing"},{"key":"B33","doi-asserted-by":"publisher","first-page":"160","DOI":"10.1016\/j.ajo.2019.09.005","article-title":"Functional and morphological evaluation of meibomian glands in the assessment of meibomian gland dysfunction subtype and severity","volume":"209","author":"Xiao","year":"2020","journal-title":"Am. J. Ophthalmol."},{"key":"B34","doi-asserted-by":"publisher","first-page":"1586","DOI":"10.21037\/qims-20-611","article-title":"An automated and multiparametric algorithm for objective analysis of meibography images","volume":"11","author":"Xiao","year":"2021","journal-title":"Quant. Imaging Med. Surg."},{"key":"B35","first-page":"623","article-title":"The domain shift problem of medical image segmentation and vendor-adaptation by unet-GAN","volume-title":"Medical image computing and computer assisted intervention \u2013 MICCAI 2019, lecture notes in computer science","author":"Yan","year":"2019"},{"key":"B36","article-title":"CE-Net: Context encoder network for 2D medical image segmentation","author":"Zaiwang","year":"2019"},{"key":"B37","first-page":"2223","article-title":"Unpaired image-to-image translation using cycle-consistent adversarial networks","author":"Zhu","year":"2017"}],"container-title":["Frontiers in Cell and Developmental Biology"],"original-title":[],"link":[{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fcell.2022.1067914\/full","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,12,5]],"date-time":"2022-12-05T07:22:01Z","timestamp":1670224921000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fcell.2022.1067914\/full"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,12,5]]},"references-count":37,"alternative-id":["10.3389\/fcell.2022.1067914"],"URL":"https:\/\/doi.org\/10.3389\/fcell.2022.1067914","relation":{},"ISSN":["2296-634X"],"issn-type":[{"value":"2296-634X","type":"electronic"}],"subject":[],"published":{"date-parts":[[2022,12,5]]},"article-number":"1067914"}}