{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,8]],"date-time":"2026-01-08T02:23:07Z","timestamp":1767838987175,"version":"3.49.0"},"reference-count":31,"publisher":"Wiley","issue":"1","license":[{"start":{"date-parts":[[2023,12,20]],"date-time":"2023-12-20T00:00:00Z","timestamp":1703030400000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/creativecommons.org\/licenses\/by-nc-nd\/4.0\/"}],"funder":[{"DOI":"10.13039\/501100003725","name":"National Research Foundation of Korea","doi-asserted-by":"publisher","award":["2023R1A2C2006223"],"award-info":[{"award-number":["2023R1A2C2006223"]}],"id":[{"id":"10.13039\/501100003725","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["pathsocjournals.onlinelibrary.wiley.com"],"crossmark-restriction":true},"short-container-title":["The Journal of Pathology CR"],"published-print":{"date-parts":[[2024,1]]},"abstract":"<jats:title>Abstract<\/jats:title><jats:p>Gastric cancer is a significant public health concern, emphasizing the need for accurate evaluation of lymphatic invasion (LI) for determining prognosis and treatment options. However, this task is time\u2010consuming, labor\u2010intensive, and prone to intra\u2010 and interobserver variability. Furthermore, the scarcity of annotated data presents a challenge, particularly in the field of digital pathology. Therefore, there is a demand for an accurate and objective method to detect LI using a small dataset, benefiting pathologists. In this study, we trained convolutional neural networks to classify LI using a four\u2010step training process: (1) weak model training, (2) identification of false positives, (3) hard negative mining in a weakly labeled dataset, and (4) strong model training. To overcome the lack of annotated datasets, we applied a hard negative mining approach in a weakly labeled dataset, which contained only final diagnostic information, resembling the typical data found in hospital databases, and improved classification performance. Ablation studies were performed to simulate the lack of datasets and severely unbalanced datasets, further confirming the effectiveness of our proposed approach. Notably, our results demonstrated that, despite the small number of annotated datasets, efficient training was achievable, with the potential to extend to other image classification approaches used in medicine.<\/jats:p>","DOI":"10.1002\/cjp2.355","type":"journal-article","created":{"date-parts":[[2023,12,20]],"date-time":"2023-12-20T05:44:43Z","timestamp":1703051083000},"update-policy":"https:\/\/doi.org\/10.1002\/crossmark_policy","source":"Crossref","is-referenced-by-count":3,"title":["A robust model training strategy using hard negative mining in a weakly labeled dataset for lymphatic invasion in gastric cancer"],"prefix":"10.1002","volume":"10","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-4528-5965","authenticated-orcid":false,"given":"Jonghyun","family":"Lee","sequence":"first","affiliation":[{"name":"Department of Medical and Digital Engineering Hanyang University College of Engineering  Seoul Republic of Korea"},{"name":"Department of Pathology Korea University Anam Hospital, Korea University College of Medicine  Seoul Republic of Korea"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Sangjeong","family":"Ahn","sequence":"additional","affiliation":[{"name":"Department of Pathology Korea University Anam Hospital, Korea University College of Medicine  Seoul Republic of Korea"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Hyun\u2010Soo","family":"Kim","sequence":"additional","affiliation":[{"name":"Department of Pathology and Translational Genomics Samsung Medical Center, Sungkyunkwan University School of Medicine  Seoul Republic of Korea"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jungsuk","family":"An","sequence":"additional","affiliation":[{"name":"Department of Pathology Korea University Anam Hospital, Korea University College of Medicine  Seoul Republic of Korea"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jongmin","family":"Sim","sequence":"additional","affiliation":[{"name":"Department of Pathology Korea University Anam Hospital, Korea University College of Medicine  Seoul Republic of Korea"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"311","published-online":{"date-parts":[[2023,12,20]]},"reference":[{"key":"e_1_2_8_2_1","doi-asserted-by":"publisher","DOI":"10.3322\/caac.21660"},{"key":"e_1_2_8_3_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.cell.2016.11.037"},{"key":"e_1_2_8_4_1","doi-asserted-by":"publisher","DOI":"10.3322\/caac.21388"},{"key":"e_1_2_8_5_1","doi-asserted-by":"publisher","DOI":"10.21873\/invivo.11942"},{"key":"e_1_2_8_6_1","first-page":"1589","article-title":"Lymphovascular invasion is an important predictor of lymph node metastasis in endoscopically resected early gastric cancers","volume":"25","author":"Kim H","year":"2011","journal-title":"Oncol Rep"},{"key":"e_1_2_8_7_1","doi-asserted-by":"publisher","DOI":"10.5230\/jgc.2020.20.e14"},{"key":"e_1_2_8_8_1","doi-asserted-by":"publisher","DOI":"10.1007\/s10120-008-0476-5"},{"key":"e_1_2_8_9_1","doi-asserted-by":"publisher","DOI":"10.3390\/cancers14215424"},{"key":"e_1_2_8_10_1","doi-asserted-by":"crossref","unstructured":"SrinidhiCL MartelAL.Improving self\u2010supervised learning with hardness\u2010aware dynamic curriculum learning: an application to digital pathology. InProceedings of the IEEE\/CVF International Conference on Computer Vision 2021; 562\u2013571.","DOI":"10.1109\/ICCVW54120.2021.00069"},{"key":"e_1_2_8_11_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.media.2020.101859"},{"key":"e_1_2_8_12_1","doi-asserted-by":"crossref","unstructured":"LiM WuL WiliemA et al.Deep instance\u2010level hard negative mining model for histopathology images. InMedical Image Computing and Computer Assisted Intervention\u2013MICCAI 2019: 22nd International Conference Shenzhen China October 13\u201317 2019 Proceedings Part I 22. Springer 2019; 514\u2013522.","DOI":"10.1007\/978-3-030-32239-7_57"},{"key":"e_1_2_8_13_1","doi-asserted-by":"publisher","DOI":"10.3390\/cancers13061325"},{"key":"e_1_2_8_14_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.humpath.2022.11.007"},{"key":"e_1_2_8_15_1","unstructured":"RenS HeK GirshickR et al.Faster r\u2010cnn: towards real\u2010time object detection with region proposal networks. InNIPS'15: Proceedings of the 28th International Conference on Neural Information Processing Systems \u2010 Volume 1 2015;91\u201399.https:\/\/dl.acm.org\/doi\/10.5555\/2969239.2969250"},{"key":"e_1_2_8_16_1","doi-asserted-by":"publisher","DOI":"10.3390\/cancers14133174"},{"key":"e_1_2_8_17_1","doi-asserted-by":"crossref","unstructured":"TangH KimDR XieX.Automated pulmonary nodule detection using 3D deep convolutional neural networks. In2018 IEEE 15th International Symposium on Biomedical Imaging(ISBI 2018). IEEE 2018; 523\u2013526.","DOI":"10.1109\/ISBI.2018.8363630"},{"key":"e_1_2_8_18_1","doi-asserted-by":"crossref","unstructured":"QinY ZhengH ZhuY\u2010M et al.Simultaneous accurate detection of pulmonary nodules and false positive reduction using 3D CNNs. In2018 IEEE International Conference on Acoustics Speech and Signal Processing(ICASSP). IEEE 2018; 1005\u20131009.","DOI":"10.1109\/ICASSP.2018.8462546"},{"key":"e_1_2_8_19_1","doi-asserted-by":"publisher","DOI":"10.1007\/s11548-019-01979-1"},{"key":"e_1_2_8_20_1","doi-asserted-by":"publisher","DOI":"10.1038\/s41746-019-0112-2"},{"key":"e_1_2_8_21_1","doi-asserted-by":"crossref","unstructured":"Guti\u00e9rrezY ArevaloJ Mart\u00e1nezF.Multimodal contrastive supervised learning to classify clinical significance MRI regions on prostate cancer. In2022 44th Annual International Conference of the IEEE Engineering in Medicine & Biology Society(EMBC). IEEE 2022; 1682\u20131685.","DOI":"10.1109\/EMBC48229.2022.9871243"},{"key":"e_1_2_8_22_1","doi-asserted-by":"crossref","unstructured":"XueC DouQ ShiX et al.Robust learning at noisy labeled medical images: applied to skin lesion classification. In2019 IEEE 16th International Symposium on Biomedical Imaging(ISBI 2019). IEEE 2019; 1280\u20131283.","DOI":"10.1109\/ISBI.2019.8759203"},{"key":"e_1_2_8_23_1","doi-asserted-by":"publisher","DOI":"10.1111\/odi.13735"},{"key":"e_1_2_8_24_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.compbiomed.2020.103735"},{"key":"e_1_2_8_25_1","doi-asserted-by":"publisher","DOI":"10.1111\/his.13975"},{"key":"e_1_2_8_26_1","doi-asserted-by":"publisher","DOI":"10.1038\/sj.bjc.6602739"},{"key":"e_1_2_8_27_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.humpath.2006.04.014"},{"key":"e_1_2_8_28_1","first-page":"2579","article-title":"Visualizing data using t\u2010SNE","volume":"9","author":"Maaten L","year":"2008","journal-title":"J Mach Learn Res"},{"key":"e_1_2_8_29_1","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-019-01228-7"},{"key":"e_1_2_8_30_1","doi-asserted-by":"crossref","unstructured":"ChenZ TianZ ZhuJ et al.C\u2010CAM: causal CAM for weakly supervised semantic segmentation on medical image. In2022 IEEE\/CVF Conference on Computer Vision and Pattern Recognition(CVPR). New Orleans LA: IEEE 2022; 11666\u201311675.","DOI":"10.1109\/CVPR52688.2022.01138"},{"key":"e_1_2_8_31_1","doi-asserted-by":"crossref","unstructured":"ZhouT ZhangM ZhaoF et al.Regional semantic contrast and aggregation for weakly supervised semantic segmentation. In2022 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR). New Orleans LA: IEEE 2022; 4299\u20134309.","DOI":"10.1109\/CVPR52688.2022.00426"},{"key":"e_1_2_8_32_1","doi-asserted-by":"publisher","DOI":"10.1038\/s41551-022-00929-8"}],"container-title":["The Journal of Pathology: Clinical Research"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/pathsocjournals.onlinelibrary.wiley.com\/doi\/pdf\/10.1002\/cjp2.355","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,12]],"date-time":"2025-10-12T17:41:45Z","timestamp":1760290905000},"score":1,"resource":{"primary":{"URL":"https:\/\/pathsocjournals.onlinelibrary.wiley.com\/doi\/10.1002\/cjp2.355"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,12,20]]},"references-count":31,"journal-issue":{"issue":"1","published-print":{"date-parts":[[2024,1]]}},"alternative-id":["10.1002\/cjp2.355"],"URL":"https:\/\/doi.org\/10.1002\/cjp2.355","archive":["Portico"],"relation":{},"ISSN":["2056-4538","2056-4538"],"issn-type":[{"value":"2056-4538","type":"print"},{"value":"2056-4538","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023,12,20]]},"assertion":[{"value":"2023-06-11","order":0,"name":"received","label":"Received","group":{"name":"publication_history","label":"Publication History"}},{"value":"2023-11-22","order":2,"name":"accepted","label":"Accepted","group":{"name":"publication_history","label":"Publication History"}},{"value":"2023-12-20","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}],"article-number":"e355"}}