{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,5]],"date-time":"2026-08-05T07:47:26Z","timestamp":1785916046499,"version":"3.56.0"},"reference-count":27,"publisher":"Wiley","license":[{"start":{"date-parts":[[2026,8,5]],"date-time":"2026-08-05T00:00:00Z","timestamp":1785888000000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/creativecommons.org\/licenses\/by\/4.0\/"},{"start":{"date-parts":[[2026,8,5]],"date-time":"2026-08-05T00:00:00Z","timestamp":1785888000000},"content-version":"tdm","delay-in-days":0,"URL":"http:\/\/doi.wiley.com\/10.1002\/tdm_license_1.1"}],"funder":[{"DOI":"10.13039\/501100007937","name":"Peking University","doi-asserted-by":"publisher","award":["JG2024126"],"award-info":[{"award-number":["JG2024126"]}],"id":[{"id":"10.13039\/501100007937","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100014892","name":"Aerospace Center Hospital","doi-asserted-by":"publisher","award":["YN202413"],"award-info":[{"award-number":["YN202413"]}],"id":[{"id":"10.13039\/501100014892","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["onlinelibrary.wiley.com"],"crossmark-restriction":true},"short-container-title":["Int J Lab Hematology"],"abstract":"<jats:title>ABSTRACT<\/jats:title>\n                  <jats:sec>\n                    <jats:title>Background<\/jats:title>\n                    <jats:p>Schistocytes are critical morphological markers for thrombotic microangiopathy (TMA) diagnosis. Manual identification is hampered by inconsistent standards and high interobserver variability, compromising accuracy. Although AI has advanced in hematology, AI\u2010enabled schistocyte classification remains under\u2010studied, creating a clinical gap.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Methods<\/jats:title>\n                    <jats:p>\n                      We constructed a two\u2010stage AI system for segmentation and classification. Three segmentation models (U\u2010Net, ENet, and R2U\u2010Net) were assessed on 25\u2009067 RBCs from 183 patients. ResNet\u201050 and Xception were trained on 28\u2009586 RBCs, including 13\u2009125 ICSH\u2010classified schistocytes, using grayscale and RGB images. Clinical validation was performed on 156\u2009784 RBCs from 219 patients. Performance was evaluated using recall, specificity, precision, and\n                      <jats:italic>F<\/jats:italic>\n                      <jats:sub>1<\/jats:sub>\n                      score.\n                    <\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Results<\/jats:title>\n                    <jats:p>\n                      R2U\u2010Net achieved the best segmentation (recall\u2009=\u20090.868,\n                      <jats:italic>F<\/jats:italic>\n                      <jats:sub>1<\/jats:sub>\n                      \u2009=\u20090.881, mIoU\u2009=\u20090.807). The Xception\u2010RGB model performed best in classification (weighted\n                      <jats:italic>F<\/jats:italic>\n                      <jats:sub>1<\/jats:sub>\n                      \u2009=\u20090.957), with high precision and recall for schistocyte subtypes. Clinical validation showed excellent reliability with all weighted metrics at 0.998.\n                    <\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Conclusions<\/jats:title>\n                    <jats:p>This two\u2010stage framework enables accurate schistocyte analysis with better feature representation using RGB images and Xception. It improves diagnostic accuracy and reproducibility, supporting TMA auxiliary diagnosis and clinical decision\u2010making.<\/jats:p>\n                  <\/jats:sec>","DOI":"10.1111\/ijlh.70209","type":"journal-article","created":{"date-parts":[[2026,8,5]],"date-time":"2026-08-05T07:06:02Z","timestamp":1785913562000},"update-policy":"https:\/\/doi.org\/10.1002\/crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["<scp>AI<\/scp>\n                    \u2010Enabled Automated Schistocyte Classification in Peripheral Blood for\n                    <scp>TMA<\/scp>\n                    Auxiliary Diagnosis"],"prefix":"10.1111","author":[{"ORCID":"https:\/\/orcid.org\/0009-0002-7724-8330","authenticated-orcid":false,"given":"Lei","family":"Shang","sequence":"first","affiliation":[{"name":"Department of Clinical Laboratory Aerospace Center Hospital  Beijing China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Chao","family":"Fang","sequence":"additional","affiliation":[{"name":"Faculty of Engineering and Design University of Auckland  Auckland New Zealand"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Dongshuo","family":"Li","sequence":"additional","affiliation":[{"name":"Department of Clinical Laboratory Aerospace Center Hospital  Beijing China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xuesong","family":"Wang","sequence":"additional","affiliation":[{"name":"School of Science, Beijing Jiaotong University  Beijing China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jiani","family":"Yu","sequence":"additional","affiliation":[{"name":"School of Public Health, Xiamen University  Xiamen China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yunchu","family":"Cui","sequence":"additional","affiliation":[{"name":"School of Public Health, Xiamen University  Xiamen China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jingliang","family":"Chen","sequence":"additional","affiliation":[{"name":"Department of Clinical Laboratory Aerospace Center Hospital  Beijing China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xuekai","family":"Liu","sequence":"additional","affiliation":[{"name":"Department of Clinical Laboratory Aerospace Center Hospital  Beijing China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"311","published-online":{"date-parts":[[2026,8,5]]},"reference":[{"issue":"5","key":"e_1_2_13_2_1","doi-asserted-by":"crossref","first-page":"e798","DOI":"10.1212\/CPJ.0000000000001067","article-title":"Thrombotic Thrombocytopenic Purpura Without Schistocytes: Beware of Misdiagnosis","volume":"11","author":"Decker P.","year":"2021","journal-title":"Neurology Clinical Practice"},{"issue":"362","key":"e_1_2_13_3_1","doi-asserted-by":"crossref","DOI":"10.1016\/j.morpho.2024.100777","article-title":"The Importance of Schistocytes in a Patient in VA\u2010ECMO","volume":"108","author":"Barros Pinto M. P.","year":"2024","journal-title":"Morphologie"},{"issue":"2","key":"e_1_2_13_4_1","doi-asserted-by":"crossref","first-page":"145","DOI":"10.1111\/ijlh.13130","article-title":"Peripheral Blood Schistocytes in the Acute Phase After Allogeneic or Autologous Stem Cell Transplantation Assessed by Digital Microscopy","volume":"42","author":"Karakioulaki M.","year":"2020","journal-title":"International Journal of Laboratory Hematology"},{"issue":"2","key":"e_1_2_13_5_1","doi-asserted-by":"crossref","first-page":"149","DOI":"10.1111\/j.1751-553X.2006.00829.x","article-title":"Laboratory Measurement of Schistocytes","volume":"29","author":"Lesesve J. F.","year":"2007","journal-title":"International Journal of Laboratory Hematology"},{"issue":"2","key":"e_1_2_13_6_1","first-page":"135","article-title":"Spherocytes, Irregularly Contracted Cells or \u2026 Schistocytes?","volume":"24","author":"Lesesve J. F.","year":"2002","journal-title":"Clinical and Laboratory Haematology"},{"issue":"2","key":"e_1_2_13_7_1","doi-asserted-by":"crossref","first-page":"107","DOI":"10.1111\/j.1751-553X.2011.01380.x","article-title":"ICSH Recommendations for Identification, Diagnostic Value, and Quantitation of Schistocytes","volume":"34","author":"Zini G.","year":"2012","journal-title":"International Journal of Laboratory Hematology"},{"issue":"6","key":"e_1_2_13_8_1","doi-asserted-by":"crossref","first-page":"1264","DOI":"10.1111\/ijlh.13682","article-title":"2021 Update of the 2012 ICSH Recommendations for Identification, Diagnostic Value, and Quantitation of Schistocytes: Impact and Revisions","volume":"43","author":"Zini G.","year":"2021","journal-title":"International Journal of Laboratory Hematology"},{"key":"e_1_2_13_9_1","volume-title":"Schistocyte Morphological Standardization Guidelines","author":"The Japanese Society for Laboratory Hematology","year":"2025"},{"issue":"5","key":"e_1_2_13_10_1","first-page":"605","article-title":"\u00c9valuation de recommandations concernant l'identification et la num\u00e9ration des schizocytes: une enqu\u00eate du Groupe francophone d'h\u00e9matologie cellulaire","volume":"70","author":"Lesesve J. F.","year":"2012","journal-title":"Annales de Biologie Clinique"},{"issue":"13","key":"e_1_2_13_11_1","doi-asserted-by":"crossref","DOI":"10.3390\/cells12131755","article-title":"Artificial Intelligence\u2010Assisted Diagnostic Cytology and Genomic Testing for Hematologic Disorders","volume":"12","author":"Gedefaw L.","year":"2023","journal-title":"Cells"},{"issue":"4","key":"e_1_2_13_12_1","doi-asserted-by":"crossref","DOI":"10.3390\/diagnostics14040420","article-title":"Validation of Artificial Intelligence (AI)\u2010Assisted Flow Cytometry Analysis for Immunological Disorders","volume":"14","author":"Lu Z.","year":"2024","journal-title":"Diagnostics"},{"issue":"1","key":"e_1_2_13_13_1","doi-asserted-by":"crossref","DOI":"10.1038\/s41598-023-29331-3","article-title":"A Deep Learning Model for Detection of Leukocytes Under Various Interference Factors","volume":"13","author":"Li M.","year":"2023","journal-title":"Scientific Reports"},{"key":"e_1_2_13_14_1","doi-asserted-by":"publisher","DOI":"10.1155\/2022\/4189781"},{"issue":"20","key":"e_1_2_13_15_1","doi-asserted-by":"crossref","first-page":"17723","DOI":"10.1007\/s00521-022-07419-7","article-title":"R2U++: A Multiscale Recurrent Residual U\u2010Net With Dense Skip Connections for Medical Image Segmentation","volume":"34","author":"Mubashar M.","year":"2022","journal-title":"Neural Computing and Applications"},{"key":"e_1_2_13_16_1","doi-asserted-by":"crossref","DOI":"10.1155\/2023\/6965259","article-title":"An ENet Semantic Segmentation Method Combined With Attention Mechanism","volume":"2023","author":"Bai W.","year":"2023","journal-title":"Computational Intelligence and Neuroscience"},{"issue":"8","key":"e_1_2_13_17_1","doi-asserted-by":"crossref","first-page":"5162","DOI":"10.1097\/JS9.0000000000002639","article-title":"Integrating Computational Pathology and Multi\u2010Transcriptomics to Characterize Lung Adenocarcinoma Heterogeneity and Prognostic Modeling","volume":"111","author":"Li Z.","year":"2025","journal-title":"International Journal of Surgery"},{"issue":"19","key":"e_1_2_13_18_1","doi-asserted-by":"crossref","DOI":"10.1088\/1361-6560\/ac8f11","article-title":"Diagnosis of Rectal Cancer Based on the Xception\u2010MS Network","volume":"67","author":"Yi S.","year":"2022","journal-title":"Physics in Medicine and Biology"},{"key":"e_1_2_13_19_1","first-page":"937","article-title":"YOLO\u2010Stutter: End\u2010to\u2010End Region\u2010Wise Speech Dysfluency Detection","volume":"2024","author":"Zhou X.","year":"2024","journal-title":"Interspeech"},{"key":"e_1_2_13_20_1","doi-asserted-by":"crossref","DOI":"10.7717\/peerj-cs.1813","article-title":"Blood Cell Image Segmentation and Classification: A Systematic Review","volume":"10","author":"Shahzad M.","year":"2024","journal-title":"PeerJ Computer Science"},{"issue":"1","key":"e_1_2_13_21_1","article-title":"Recurrent Residual U\u2010Net for Medical Image Segmentation","volume":"6","author":"Alom M. Z.","year":"2019","journal-title":"Journal of Medical Imaging"},{"issue":"24","key":"e_1_2_13_22_1","doi-asserted-by":"crossref","DOI":"10.3390\/s20247253","article-title":"High\u2010Capacity Image Steganography Based on Improved Xception","volume":"20","author":"Duan X.","year":"2020","journal-title":"Sensors"},{"key":"e_1_2_13_23_1","doi-asserted-by":"publisher","DOI":"10.1111\/ijlh.12364"},{"issue":"8","key":"e_1_2_13_24_1","article-title":"Reference Range for the Automated Fragmented Red Cell Parameter and Its Diagnostic Utility in Red Blood Cell (RBC) Fragment Quantification: A Prospective Study","volume":"17","author":"Bharti G.","year":"2025","journal-title":"Cureus"},{"key":"e_1_2_13_25_1","doi-asserted-by":"crossref","DOI":"10.1016\/j.artmed.2022.102462","article-title":"ReCasNet: Improving Consistency Within the Two\u2010Stage Mitosis Detection Framework","volume":"135","author":"Piansaddhayanaon C.","year":"2023","journal-title":"Artificial Intelligence in Medicine"},{"key":"e_1_2_13_26_1","doi-asserted-by":"crossref","DOI":"10.1016\/j.compbiomed.2024.109616","article-title":"Two\u2010Stage CNN\u2010Based Framework for Leukocytes Classification","volume":"187","author":"Khan S.","year":"2025","journal-title":"Computers in Biology and Medicine"},{"key":"e_1_2_13_27_1","doi-asserted-by":"crossref","DOI":"10.1016\/j.compbiomed.2024.109220","article-title":"Two\u2010Stage Deep Learning Framework for Occlusal Crown Depth Image Generation","volume":"183","author":"Roh J.","year":"2024","journal-title":"Computers in Biology and Medicine"},{"issue":"4","key":"e_1_2_13_28_1","article-title":"Two\u2010Stage Training Framework Using Multicontrast MRI Radiomics for IDH Mutation Status Prediction in Glioma","volume":"6","author":"Truong N. C. D.","year":"2024","journal-title":"Radiology: Artificial Intelligence"}],"container-title":["International Journal of Laboratory Hematology"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/onlinelibrary.wiley.com\/doi\/pdf\/10.1111\/ijlh.70209","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/onlinelibrary.wiley.com\/doi\/full-xml\/10.1111\/ijlh.70209","content-type":"application\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/onlinelibrary.wiley.com\/doi\/pdf\/10.1111\/ijlh.70209","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,8,5]],"date-time":"2026-08-05T07:06:09Z","timestamp":1785913569000},"score":1,"resource":{"primary":{"URL":"https:\/\/onlinelibrary.wiley.com\/doi\/10.1111\/ijlh.70209"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,8,5]]},"references-count":27,"alternative-id":["10.1111\/ijlh.70209"],"URL":"https:\/\/doi.org\/10.1111\/ijlh.70209","archive":["Portico"],"relation":{},"ISSN":["1751-5521","1751-553X"],"issn-type":[{"value":"1751-5521","type":"print"},{"value":"1751-553X","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,8,5]]},"assertion":[{"value":"2026-04-20","order":0,"name":"received","label":"Received","group":{"name":"publication_history","label":"Publication History"}},{"value":"2026-07-17","order":2,"name":"accepted","label":"Accepted","group":{"name":"publication_history","label":"Publication History"}},{"value":"2026-08-05","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}],"article-number":"ijlh.70209"}}