{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,4,15]],"date-time":"2025-04-15T04:06:33Z","timestamp":1744689993793,"version":"3.40.4"},"reference-count":50,"publisher":"Public Library of Science (PLoS)","issue":"4","license":[{"start":{"date-parts":[[2025,4,14]],"date-time":"2025-04-14T00:00:00Z","timestamp":1744588800000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":["www.plosone.org"],"crossmark-restriction":false},"short-container-title":["PLoS ONE"],"abstract":"<jats:p>In nephrology research, multi-glomerular segmentation in immunofluorescence images plays a crucial role in the early detection and diagnosis of chronic kidney disease. However, obtaining accurate segmentations often requires labor-intensive annotations and existing methods are hampered by low recall rates and limited accuracy. Recently, a general Segment Anything Model (SAM) has demonstrated promising performance in several segmentation tasks. In this paper, a SAM-based multi-glomerular segmentation model (GlomSAM) is introduced to employ SAM in the immunofluorescence pathology domain. The fusion encoder strategy utilizing the advantages of both convolution networks and transformer structures with prompts is conducted to facilitate SAM\u2019s transfer learning in applications of pathological analysis. Moreover, a rough mask generator is employed to generate preliminary glomerular segmentation masks, enabling automated input prompting and improving the final segmentation results. Extensive comparative experiments and ablation studies show its state-of-the-art performance surpassing other relevant research. We hope this report will provide insights to advance the field of glomerular segmentation and promote more interesting work in the future.<\/jats:p>","DOI":"10.1371\/journal.pone.0321096","type":"journal-article","created":{"date-parts":[[2025,4,14]],"date-time":"2025-04-14T20:12:35Z","timestamp":1744661555000},"page":"e0321096","update-policy":"https:\/\/doi.org\/10.1371\/journal.pone.corrections_policy","source":"Crossref","is-referenced-by-count":0,"title":["GlomSAM: Hybrid customized SAM for multi-glomerular detection and segmentation in immunofluorescence images"],"prefix":"10.1371","volume":"20","author":[{"given":"Shengyu","family":"Pan","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xuanli","family":"Tang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Bingxian","family":"Chen","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xiaobo","family":"Lai","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6290-4596","authenticated-orcid":true,"given":"Wei","family":"Jin","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"340","published-online":{"date-parts":[[2025,4,14]]},"reference":[{"issue":"10075","key":"pone.0321096.ref001","doi-asserted-by":"crossref","first-page":"1238","DOI":"10.1016\/S0140-6736(16)32064-5","article-title":"Chronic kidney disease","volume":"389","author":"AC Webster","year":"2017","journal-title":"Lancet"},{"issue":"13","key":"pone.0321096.ref002","doi-asserted-by":"crossref","first-page":"1294","DOI":"10.1001\/jama.2019.14745","article-title":"Chronic kidney disease diagnosis and management: A review","volume":"322","author":"TK Chen","year":"2019","journal-title":"JAMA"},{"issue":"12","key":"pone.0321096.ref003","doi-asserted-by":"crossref","first-page":"1555","DOI":"10.1038\/modpathol.3800239","article-title":"Practice guidelines for the renal biopsy","volume":"17","author":"PD Walker","year":"2004","journal-title":"Mod Pathol"},{"key":"pone.0321096.ref004","first-page":"1","article-title":"DGDI: A dataset for detecting glomeruli on renal direct immunofluorescence","author":"K Zhao","year":"2018","journal-title":"In: 2018 digital image computing: techniques and applications (DICTA)"},{"issue":"3","key":"pone.0321096.ref005","doi-asserted-by":"crossref","first-page":"609","DOI":"10.2215\/CJN.04160413","article-title":"Glomerular diseases: Membranous nephropathy\u2014A modern view","volume":"9","author":"C Ponticelli","year":"2014","journal-title":"Clin J Am Soc Nephrol"},{"key":"pone.0321096.ref006","doi-asserted-by":"crossref","first-page":"119168","DOI":"10.1016\/j.eswa.2022.119168","article-title":"Describe like a pathologist: Glomerular immunofluorescence image caption based on hierarchical feature fusion attention network","volume":"213","author":"H Liu","year":"2023","journal-title":"Expert Syst Applic"},{"key":"pone.0321096.ref007","doi-asserted-by":"crossref","first-page":"16001","DOI":"10.1038\/nrdp.2016.1","article-title":"IgA nephropathy","volume":"2","author":"KN Lai","year":"2016","journal-title":"Nat Rev Dis Primers"},{"issue":"9","key":"pone.0321096.ref008","doi-asserted-by":"crossref","first-page":"876","DOI":"10.1038\/ki.2009.54","article-title":"Tissue proteomics: A new investigative tool for renal biopsy analysis","volume":"75","author":"JR Sedor","year":"2009","journal-title":"Kidney Int"},{"key":"pone.0321096.ref009"},{"issue":"5","key":"pone.0321096.ref010","doi-asserted-by":"crossref","first-page":"e253","DOI":"10.1016\/S1470-2045(19)30154-8","article-title":"Digital pathology and artificial intelligence","volume":"20","author":"M Niazi","year":"2019","journal-title":"Lancet Oncol."},{"issue":"2","key":"pone.0321096.ref011","doi-asserted-by":"crossref","first-page":"225","DOI":"10.1007\/s11548-024-03154-7","article-title":"Unsupervised stain augmentation enhanced glomerular instance segmentation on pathology images","volume":"20","author":"F Yang","year":"2025","journal-title":"Int J Comput Assist Radiol Surg"},{"issue":"9","key":"pone.0321096.ref012","doi-asserted-by":"crossref","first-page":"1077","DOI":"10.1038\/s42256-024-00889-5","article-title":"Accelerating histopathology workflows with generative AI-based virtually multiplexed tumour profiling","volume":"6","author":"P Pati","year":"2024","journal-title":"Nat Mach Intell"},{"issue":"1","key":"pone.0321096.ref013","doi-asserted-by":"crossref","first-page":"397","DOI":"10.1186\/s12967-024-05221-8","article-title":"Artificial intelligence assists identification and pathologic classification of glomerular lesions in patients with diabetic nephropathy","volume":"22","author":"Q Lei","year":"2024","journal-title":"J Transl Med"},{"key":"pone.0321096.ref014","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1109\/DICTA47822.2019.8945813","article-title":"To what extent does downsampling, compression, and data scarcity impact renal image analysis?","volume-title":"In: 2019 digital image computing: techniques and applications (DICTA)","author":"C Peng","year":"2019"},{"issue":"24","key":"pone.0321096.ref015","doi-asserted-by":"crossref","first-page":"22565","DOI":"10.1007\/s00521-022-07676-6","article-title":"HFANet: hierarchical feature fusion attention network for classification of glomerular immunofluorescence images","volume":"34","author":"H Liu","year":"2022","journal-title":"Neural Comput Applic"},{"key":"pone.0321096.ref016","first-page":"297","article-title":"Glomerular detection and segmentation from multimodal microscopy images using a Butterworth band-pass filter","volume":"10581","author":"D Govind","year":"2018","journal-title":"In: Medical imaging 2018: Digital pathology"},{"key":"pone.0321096.ref017","first-page":"4015","article-title":"Segment anything","volume-title":"In: Proceedings of the IEEE\/CVF international conference on computer vision","author":"A Kirillov","year":"2023"},{"key":"pone.0321096.ref018","article-title":"Sam 2: Segment anything in images and videos","author":"N Ravi","year":"2024","journal-title":"arXiv preprint"},{"issue":"5","key":"pone.0321096.ref019","first-page":"052408","article-title":"Glo-In-One: Holistic glomerular detection, segmentation, and lesion characterization with large-scale web image mining","volume":"9","author":"T Yao","year":"2022","journal-title":"J Med Imaging (Bellingham)"},{"issue":"1","key":"pone.0321096.ref020","first-page":"20","article-title":"Automated quantitative image analysis of glomerular desmin immunostaining as a sensitive injury marker in spontaneously diabetic torii rats","volume":"1","author":"Y Hirohashi","year":"2014","journal-title":"J Biomed Image Process."},{"issue":"2","key":"pone.0321096.ref021","doi-asserted-by":"crossref","first-page":"171","DOI":"10.1016\/j.etp.2014.11.007","article-title":"Quantitative analysis of markers of podocyte injury in the rat puromycin aminonucleoside nephropathy model","volume":"67","author":"T Kakimoto","year":"2015","journal-title":"Exp Toxicol Pathol"},{"key":"pone.0321096.ref022","first-page":"144","article-title":"A training algorithm for optimal margin classifiers","author":"BE Boser","year":"1992","journal-title":"In: Proceedings of the fifth annual workshop on computational learning theory"},{"key":"pone.0321096.ref023","first-page":"310","article-title":"Multi-scale multi-site renal microvascular structures segmentation for whole slide imaging in renal pathology","volume-title":"In: Medical imaging 2024: Digital and computational pathology","author":"F Hu","year":"2024"},{"issue":"2","key":"pone.0321096.ref024","first-page":"399","article-title":"Accurate kidney pathological image classification method based on deep learning and multi-modal fusion method with application to membranous nephropathy","volume":"13","author":"F Hao","year":"2023","journal-title":"Life (Basel)"},{"key":"pone.0321096.ref025","doi-asserted-by":"crossref","first-page":"105637","DOI":"10.1016\/j.engappai.2022.105637","article-title":"Ada-CCFNet: Classification of multimodal direct immunofluorescence images for membranous nephropathy via adaptive weighted confidence calibration fusion network","volume":"117","author":"R Wang","year":"2023","journal-title":"Eng Applic Artif Intell"},{"key":"pone.0321096.ref026","doi-asserted-by":"crossref","first-page":"107747","DOI":"10.1016\/j.cmpb.2023.107747","article-title":"Deep multi-task learning for nephropathy diagnosis on immunofluorescence images","volume":"241","author":"Y Fu","year":"2023","journal-title":"Comput Methods Programs Biomed"},{"key":"pone.0321096.ref027","article-title":"Adapting mouse pathological model to human glomerular lesion segmentation","author":"L Yu","year":"2024"},{"issue":"12","key":"pone.0321096.ref028","doi-asserted-by":"crossref","first-page":"2503","DOI":"10.1093\/ckj\/sfad153","article-title":"Development of a multiple convolutional neural network-facilitated diagnostic screening program for immunofluorescence images of IgA nephropathy and idiopathic membranous nephropathy","volume":"16","author":"P Xia","year":"2023","journal-title":"Clin Kidney J"},{"key":"pone.0321096.ref029"},{"issue":"11","key":"pone.0321096.ref030","doi-asserted-by":"crossref","first-page":"14013","DOI":"10.1007\/s13369-022-06608-9","article-title":"Glomerulus semantic segmentation using ensemble of deep learning models","volume":"47","author":"Y Gu","year":"2022","journal-title":"Arab J Sci Eng"},{"issue":"19","key":"pone.0321096.ref031","doi-asserted-by":"crossref","first-page":"3152","DOI":"10.3390\/diagnostics13193152","article-title":"Automatic identification of glomerular in whole-slide images using a modified UNet model","volume":"13","author":"G Kaur","year":"2023","journal-title":"Diagnostics (Basel)"},{"key":"pone.0321096.ref032","article-title":"Skinsam: Empowering skin cancer segmentation with segment anything model","author":"M Hu","year":"2023","journal-title":"arXiv preprint"},{"issue":"1","key":"pone.0321096.ref033","doi-asserted-by":"crossref","first-page":"654","DOI":"10.1038\/s41467-024-44824-z","article-title":"Segment anything in medical images","volume":"15","author":"J Ma","year":"2024","journal-title":"Nat Commun"},{"key":"pone.0321096.ref034","article-title":"SamLP: A customized segment anything model for license plate detection","author":"H Ding","year":"2024","journal-title":"arXiv preprint"},{"key":"pone.0321096.ref035","doi-asserted-by":"crossref","first-page":"759","DOI":"10.1117\/12.3006809","article-title":"Polyp-sam: Transfer sam for polyp segmentation","volume-title":"In: Medical imaging 2024: Computer-aided diagnosis","author":"Y Li","year":"2024"},{"issue":"20","key":"pone.0321096.ref036","doi-asserted-by":"crossref","first-page":"22520","DOI":"10.1609\/aaai.v38i20.30260","article-title":"UV-SAM: Adapting segment anything model for urban village identification","volume":"38","author":"X Zhang","year":"2024","journal-title":"AAAI"},{"key":"pone.0321096.ref037","article-title":"Medical sam adapter: Adapting segment anything model for medical image segmentation","author":"J Wu","year":"2023","journal-title":"arXiv preprint"},{"key":"pone.0321096.ref038","first-page":"14541","article-title":"Fast vision transformers with hilo attention","volume":"35","author":"Z Pan","year":"2022","journal-title":"Adv Neural Inform Process Syst."},{"key":"pone.0321096.ref039","first-page":"118","article-title":"Asps: Augmented segment anything model for polyp segmentation","volume-title":"In: Proceedings of the international conference on medical image computing and computer-assisted intervention","author":"H Li","year":"2024"},{"key":"pone.0321096.ref040","first-page":"24","article-title":"Beyond adapting SAM: Towards end-to-end ultrasound image segmentation via auto prompting","volume-title":"In: Proceedings of the international conference on medical image computing and computer-assisted intervention","author":"X Lin","year":"2024"},{"key":"pone.0321096.ref041","first-page":"108","article-title":"CC-SAM: SAM with cross-feature attention and context for ultrasound image segmentation. In: European Conference on Computer Vision","author":"S Gowda","year":"2025"},{"key":"pone.0321096.ref042","first-page":"292","article-title":"Boundary difference over union loss for medical image segmentation","author":"F Sun","year":"2023","journal-title":"In: Proceedings of the international conference on medical image computing and computer-assisted intervention"},{"key":"pone.0321096.ref043","first-page":"234","article-title":"U-net: Convolutional networks for biomedical image segmentation","author":"O Ronneberger","year":"2015","journal-title":"In: Medical image computing and computer-assisted intervention\u2014MICCAI 2015:18th international conference, Munich, Germany, October 5-9, 2015, proceedings, part III 18"},{"key":"pone.0321096.ref044","first-page":"3","article-title":"Unet++: A nested u-net architecture for medical image segmentation. In: Deep learning in medical image analysis and multimodal learning for clinical decision support: 4th international workshop, DLMIA 2018, and 8th international workshop, ML-CDS 2018, held in conjunction with MICCAI 2018","author":"Z Zhou","year":"2018"},{"key":"pone.0321096.ref045","first-page":"205","article-title":"Swin-unet: Unet-like pure transformer for medical image segmentation. In: European conference on computer vision. Springer","author":"H Cao","year":"2022"},{"key":"pone.0321096.ref046","article-title":"Transunet: Transformers make strong encoders for medical image segmentation","author":"J Chen","year":"2021","journal-title":"arXiv preprint"},{"issue":"12","key":"pone.0321096.ref047","doi-asserted-by":"crossref","first-page":"2481","DOI":"10.1109\/TPAMI.2016.2644615","article-title":"SegNet: A deep convolutional encoder-decoder architecture for image segmentation","volume":"39","author":"V Badrinarayanan","year":"2017","journal-title":"IEEE Trans Pattern Anal Mach Intell"},{"key":"pone.0321096.ref048","article-title":"Ultralytics YOLO","author":"G Jocher","year":"2023"},{"key":"pone.0321096.ref049","first-page":"9157","article-title":"Yolact: Real-time instance segmentation. In: Proceedings of the IEEE\/CVF international conference on computer vision","author":"D Bolya","year":"2019"},{"key":"pone.0321096.ref050","first-page":"2961","article-title":"Mask r-cnn. In: Proceedings of the IEEE international conference on computer vision","author":"K He","year":"2017"}],"container-title":["PLOS ONE"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/dx.plos.org\/10.1371\/journal.pone.0321096","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,4,14]],"date-time":"2025-04-14T20:12:47Z","timestamp":1744661567000},"score":1,"resource":{"primary":{"URL":"https:\/\/dx.plos.org\/10.1371\/journal.pone.0321096"}},"subtitle":[],"editor":[{"given":"Xu","family":"Yanwu","sequence":"first","affiliation":[],"role":[{"role":"editor","vocabulary":"crossref"}]}],"short-title":[],"issued":{"date-parts":[[2025,4,14]]},"references-count":50,"journal-issue":{"issue":"4","published-online":{"date-parts":[[2025,4,14]]}},"URL":"https:\/\/doi.org\/10.1371\/journal.pone.0321096","relation":{},"ISSN":["1932-6203"],"issn-type":[{"value":"1932-6203","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,4,14]]}}}