{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,24]],"date-time":"2026-09-24T01:01:47Z","timestamp":1790211707469,"version":"4.1.0"},"reference-count":26,"publisher":"SPIE-Intl Soc Optical Eng","issue":"01","funder":[{"DOI":"10.13039\/100000053","name":"HHS | NIH | National Eye Institute","doi-asserted-by":"publisher","award":["R21EY02949801"],"award-info":[{"award-number":["R21EY02949801"]}],"id":[{"id":"10.13039\/100000053","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100000053","name":"HHS | NIH | National Eye Institute","doi-asserted-by":"publisher","award":["PHS 5 T32 EB 7509-15"],"award-info":[{"award-number":["PHS 5 T32 EB 7509-15"]}],"id":[{"id":"10.13039\/100000053","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["J. Med. Imag."],"published-print":{"date-parts":[[2024,1,5]]},"abstract":"<jats:p>PurposeTo create Guided Correction Software for informed manual editing of automatically generated corneal endothelial cell (EC) segmentations and apply it to an active learning paradigm to analyze a diverse set of post-keratoplasty EC images.ApproachAn original U-Net model trained on 130 manually labeled post-Descemet stripping automated endothelial keratoplasty (EK) images was applied to 841 post-Descemet membrane EK images generating \u201cuncorrected\u201d cell border segmentations. Segmentations were then manually edited using the Guided Correction Software to create corrected labels. This dataset was split into 741 training and 100 testing EC images. U-Net and DeepLabV3+ were trained on the EC images and the corresponding uncorrected and corrected labels. Model performance was evaluated in a cell-by-cell analysis. Evaluation metrics included the number of over-segmentations, under-segmentations, correctly identified new cells, and endothelial cell density (ECD).ResultsUtilizing corrected segmentations for training U-Net and DeepLabV3+ improved their performance. The average number of over- and under-segmentations per image was reduced from 23 to 11 with the corrected training set. Predicted ECD values generated by networks trained on the corrected labels were not significantly different than the ground truth counterparts (p=0.02, paired t-test). These models also correctly segmented a larger percentage of newly identified cells. The proposed Guided Correction Software and semi-automated approach reduced the time to accurately segment EC images from 15 to 30 to 5\u00a0min, an \u223c80% decrease compared to manual editing.ConclusionsGuided Correction Software can efficiently label new training data for improved deep learning performance and generalization between EC datasets.<\/jats:p>","DOI":"10.1117\/1.jmi.11.1.014006","type":"journal-article","created":{"date-parts":[[2024,1,5]],"date-time":"2024-01-05T06:21:47Z","timestamp":1704435707000},"page":"1-14","source":"Crossref","is-referenced-by-count":3,"title":["Deep learning segmentation of endothelial cell images using an active learning paradigm with guided label corrections"],"prefix":"10.1117","volume":"11","author":[{"given":"Naomi","family":"Joseph","sequence":"first","affiliation":[{"name":"Case Western Reserve University"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ian","family":"Marshall","sequence":"additional","affiliation":[{"name":"Case Western Reserve University"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Elizabeth","family":"Fitzpatrick","sequence":"additional","affiliation":[{"name":"Case Western Reserve University"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Harry J.","family":"Menegay","sequence":"additional","affiliation":[{"name":"Case Western Reserve University"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jonathan H.","family":"Lass","sequence":"additional","affiliation":[{"name":"Case Western Reserve University"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Beth Ann M.","family":"Benetz","sequence":"additional","affiliation":[{"name":"Case Western Reserve University"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9763-1463","authenticated-orcid":false,"given":"David L.","family":"Wilson","sequence":"additional","affiliation":[{"name":"Case Western Reserve University"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"189","reference":[{"key":"r1","doi-asserted-by":"publisher","DOI":"10.1016\/S0161-6420(82)34746-6"},{"key":"r2","doi-asserted-by":"publisher","DOI":"10.1097\/00003226-200005000-00002"},{"key":"r3","doi-asserted-by":"publisher","DOI":"10.1016\/j.ajo.2018.01.018"},{"key":"r4","doi-asserted-by":"publisher","DOI":"10.17077\/omia.1023"},{"key":"r5","first-page":"163","article-title":"Perte de cellules endoth\u00e9liales apr\u00e8s une k\u00e9ratoplastie (Endothelial cell loss after keratoplasty)","author":"Lass","year":"2020"},{"key":"r6","first-page":"160","article-title":"Specular microscopy","author":"Benetz","year":"2016"},{"key":"r7","doi-asserted-by":"publisher","DOI":"10.1117\/12.2582171"},{"key":"r8","first-page":"323","article-title":"Automatic segmentation of corneal endothelium images with convolutional neural network","author":"Nurzynska","year":"2018"},{"key":"r9","doi-asserted-by":"publisher","DOI":"10.1038\/s41598-019-41034-2"},{"key":"r10","doi-asserted-by":"publisher","DOI":"10.1117\/1.JMI.7.1.014503"},{"key":"r11","doi-asserted-by":"publisher","DOI":"10.1016\/j.artmed.2018.04.004"},{"key":"r12","doi-asserted-by":"publisher","DOI":"10.1016\/j.bspc.2021.102805"},{"key":"r13","doi-asserted-by":"publisher","DOI":"10.1186\/s42490-019-0003-2"},{"key":"r14","doi-asserted-by":"publisher","DOI":"10.1167\/tvst.9.2.49"},{"key":"r15","article-title":"Rotaflip: a new CNN layer for regularization and rotational invariance in medical images","author":"Vigueras-Guill\u00e9n","year":"2021"},{"key":"r16","doi-asserted-by":"crossref","DOI":"10.1038\/s41598-022-18180-1","article-title":"DenseUNets with feedback non-local attention for the segmentation of specular microscopy images of the corneal endothelium with Guttae","author":"Vigueras-Guill\u00e9n","year":"2022"},{"key":"r17","doi-asserted-by":"publisher","DOI":"10.1016\/j.media.2021.102062"},{"key":"r18","doi-asserted-by":"publisher","DOI":"10.1038\/s41598-019-57242-9"},{"key":"r19","doi-asserted-by":"publisher","DOI":"10.3389\/frai.2022.939967"},{"key":"r20","doi-asserted-by":"publisher","DOI":"10.1016\/j.compmedimag.2020.101752"},{"key":"r21","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2021.3058890"},{"key":"r22","doi-asserted-by":"publisher","DOI":"10.1007\/s10462-022-10152-1"},{"key":"r23","doi-asserted-by":"publisher","DOI":"10.1109\/TCBB.2021.3085608"},{"key":"r24","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-24574-4_28"},{"key":"r25","doi-asserted-by":"crossref","DOI":"10.1007\/978-3-030-01234-2_49","article-title":"Encoder-decoder with atrous separable convolution for semantic image segmentation","author":"Chen","year":"2018"},{"key":"r26","doi-asserted-by":"publisher","DOI":"10.1109\/ISBI52829.2022.9761467"}],"container-title":["Journal of Medical Imaging"],"original-title":[],"link":[{"URL":"https:\/\/www.spiedigitallibrary.org\/journals\/journal-of-medical-imaging\/volume-11\/issue-01\/014006\/Deep-learning-segmentation-of-endothelial-cell-images-using-an-active\/10.1117\/1.JMI.11.1.014006.full","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,9,24]],"date-time":"2026-09-24T00:17:56Z","timestamp":1790209076000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.spiedigitallibrary.org\/journals\/journal-of-medical-imaging\/volume-11\/issue-01\/014006\/Deep-learning-segmentation-of-endothelial-cell-images-using-an-active\/10.1117\/1.JMI.11.1.014006.full"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,1,5]]},"references-count":26,"journal-issue":{"issue":"01","published-online":{"date-parts":[[2024,1,1]]}},"URL":"https:\/\/doi.org\/10.1117\/1.jmi.11.1.014006","relation":{},"ISSN":["2329-4302","2329-4310"],"issn-type":[{"value":"2329-4302","type":"print"},{"value":"2329-4310","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,1,5]]}}}