{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,12]],"date-time":"2026-09-12T17:36:00Z","timestamp":1789234560814,"version":"build-2803163510"},"reference-count":52,"publisher":"Springer Science and Business Media LLC","issue":"1","license":[{"start":{"date-parts":[[2025,11,22]],"date-time":"2025-11-22T00:00:00Z","timestamp":1763769600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"},{"start":{"date-parts":[[2025,11,22]],"date-time":"2025-11-22T00:00:00Z","timestamp":1763769600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"}],"funder":[{"name":"PMRF"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Sci Rep"],"abstract":"<jats:title>Abstract<\/jats:title>\n                  <jats:p>\n                    Cell segmentation in histopathological images is vital for diagnosis, and treatment of several diseases. Annotating data is tedious, and requires medical expertise, making it difficult to employ supervised learning. Instead, we study a weakly supervised setting, where only bounding box supervision is available, and present the use of Segment Anything (SAM) for this without any finetuning, i.e., directly utilizing the pre-trained model. We propose BoxCell, a cell segmentation framework that utilizes SAM\u2019s capability to interpret bounding boxes as prompts,\n                    <jats:italic>both<\/jats:italic>\n                    at train and test times. At train time, gold bounding boxes given to SAM produce (pseudo-)masks, which are used to train a standalone segmenter. At test time, BoxCell generates two segmentation masks: (1) generated by this standalone segmenter, and (2) a trained object detector outputs bounding boxes, which are given as prompts to SAM to produce another mask. Recognizing complementary strengths, we reconcile the two segmentation masks using a novel integer programming formulation with intensity and spatial constraints. We experiment on three publicly available cell segmentation datasets namely, CoNSep, MoNuSeg, and TNBC, and find that BoxCell significantly outperforms existing box supervised image segmentation models, obtaining 6-10 point Dice gains.\n                  <\/jats:p>","DOI":"10.1038\/s41598-025-26789-1","type":"journal-article","created":{"date-parts":[[2025,11,22]],"date-time":"2025-11-22T19:33:27Z","timestamp":1763840007000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":2,"title":["BoxCell: Leveraging SAM for Cell Segmentation with Box Supervision"],"prefix":"10.1038","volume":"15","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-3615-7283","authenticated-orcid":false,"given":"Aayush Kumar","family":"Tyagi","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Vaibhav","family":"Mishra","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8699-5760","authenticated-orcid":false,"given":"Prathosh","family":"A.P.","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4088-4296","authenticated-orcid":false,"family":"Mausam","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2025,11,22]]},"reference":[{"key":"26789_CR1","doi-asserted-by":"publisher","first-page":"1438","DOI":"10.1038\/s41374-018-0095-7","volume":"98","author":"C Lu","year":"2018","unstructured":"Lu, C. et al. Nuclear shape and orientation features from h &e images predict survival in early-stage estrogen receptor-positive breast cancers. Lab. Invest. 98, 1438\u20131448 (2018).","journal-title":"Lab. Invest."},{"key":"26789_CR2","doi-asserted-by":"publisher","first-page":"67","DOI":"10.1111\/j.0022-2720.2004.01338.x","volume":"215","author":"C W\u00e4hlby","year":"2004","unstructured":"W\u00e4hlby, C., Sintorn, I.-M., Erlandsson, F., Borgefors, G. & Bengtsson, E. Combining intensity, edge and shape information for 2d and 3d segmentation of cell nuclei in tissue sections. J. Microsc. 215, 67\u201376 (2004).","journal-title":"J. Microsc."},{"key":"26789_CR3","doi-asserted-by":"crossref","unstructured":"Tyagi, A.\u00a0K. et al. Degpr: Deep guided posterior regularization for multi-class cell detection and counting. In Proc. IEEE\/CVF Conference on Computer Vision and Pattern Recognition, 23913\u201323923 (2023).","DOI":"10.1109\/CVPR52729.2023.02290"},{"key":"26789_CR4","doi-asserted-by":"crossref","unstructured":"Ahn, J., Cho, S. & Kwak, S. Weakly supervised learning of instance segmentation with inter-pixel relations. In Proc. IEEE\/CVF conference on computer vision and pattern recognition, 2209\u20132218 (2019).","DOI":"10.1109\/CVPR.2019.00231"},{"key":"26789_CR5","doi-asserted-by":"crossref","unstructured":"Lin, D., Dai, J., Jia, J., He, K. & Sun, J. Scribblesup: Scribble-supervised convolutional networks for semantic segmentation. In Proc. IEEE conference on computer vision and pattern recognition, 3159\u20133167 (2016).","DOI":"10.1109\/CVPR.2016.344"},{"key":"26789_CR6","doi-asserted-by":"crossref","unstructured":"Bearman, A., Russakovsky, O., Ferrari, V. & Fei-Fei, L. What\u2019s the point: Semantic segmentation with point supervision. In European conference on computer vision, 549\u2013565 (Springer, 2016).","DOI":"10.1007\/978-3-319-46478-7_34"},{"key":"26789_CR7","doi-asserted-by":"crossref","unstructured":"Cheng, T., Wang, X., Chen, S., Zhang, Q. & Liu, W. Boxteacher: Exploring high-quality pseudo labels for weakly supervised instance segmentation. In Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, 3145\u20133154 (2023).","DOI":"10.1109\/CVPR52729.2023.00307"},{"key":"26789_CR8","doi-asserted-by":"crossref","unstructured":"Wang, J. & Xia, B. Bounding box tightness prior for weakly supervised image segmentation. In International conference on medical image computing and computer-assisted intervention, 526\u2013536 (Springer, 2021).","DOI":"10.1007\/978-3-030-87196-3_49"},{"key":"26789_CR9","doi-asserted-by":"crossref","unstructured":"Tian, Z., Shen, C., Wang, X. & Chen, H. Boxinst: High-performance instance segmentation with box annotations. In Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, 5443\u20135452 (2021).","DOI":"10.1109\/CVPR46437.2021.00540"},{"key":"26789_CR10","doi-asserted-by":"crossref","unstructured":"Mahani, G.\u00a0K. et al. Bounding box based weakly supervised deep convolutional neural network for medical image segmentation using an uncertainty guided and spatially constrained loss. In 2022 IEEE 19th International Symposium on Biomedical Imaging (ISBI), 1\u20135 (IEEE, 2022).","DOI":"10.1109\/ISBI52829.2022.9761558"},{"key":"26789_CR11","doi-asserted-by":"crossref","unstructured":"Yang, R., Song, L., Ge, Y. & Li, X. Boxsnake: Polygonal instance segmentation with box supervision. arXiv preprint arXiv:2303.11630 (2023).","DOI":"10.1109\/ICCV51070.2023.00077"},{"key":"26789_CR12","unstructured":"Liu, Y. et al. Box2seg: Learning semantics of 3d point clouds with box-level supervision. arXiv preprint arXiv:2201.02963 (2022)."},{"key":"26789_CR13","unstructured":"Kirillov, A. et al. Segment anything. arXiv preprint arXiv:2304.02643 (2023)."},{"key":"26789_CR14","doi-asserted-by":"crossref","unstructured":"Lou, A., Guan, S., Ko, H. & Loew, M.\u00a0H. Caranet: Context axial reverse attention network for segmentation of small medical objects. In Medical Imaging 2022: Image Processing, vol. 12032, 81\u201392 (SPIE, 2022).","DOI":"10.1117\/12.2611802"},{"key":"26789_CR15","unstructured":"Jocher, G., Chaurasia, A. & Qiu, J. YOLO by Ultralytics (2023)."},{"key":"26789_CR16","doi-asserted-by":"publisher","DOI":"10.1016\/j.media.2019.101563","volume":"58","author":"S Graham","year":"2019","unstructured":"Graham, S. et al. Hover-net: Simultaneous segmentation and classification of nuclei in multi-tissue histology images. Med. Image Anal. 58, 101563 (2019).","journal-title":"Med. Image Anal."},{"key":"26789_CR17","first-page":"8","volume":"39","author":"R Verma","year":"2020","unstructured":"Verma, R. et al. Multi-organ nuclei segmentation and classification challenge 2020. IEEE Trans. Med. Imaging 39, 8 (2020).","journal-title":"IEEE Trans. Med. Imaging"},{"key":"26789_CR18","doi-asserted-by":"publisher","first-page":"448","DOI":"10.1109\/TMI.2018.2865709","volume":"38","author":"P Naylor","year":"2018","unstructured":"Naylor, P., La\u00e9, M., Reyal, F. & Walter, T. Segmentation of nuclei in histopathology images by deep regression of the distance map. IEEE Trans. Med. Imaging 38, 448\u2013459 (2018).","journal-title":"IEEE Trans. Med. Imaging"},{"key":"26789_CR19","doi-asserted-by":"crossref","unstructured":"Ji, W. et al. Segment anything is not always perfect: An investigation of sam on different real-world applications (2024).","DOI":"10.1007\/s11633-023-1385-0"},{"key":"26789_CR20","unstructured":"He, C. et al. Weakly-supervised concealed object segmentation with sam-based pseudo labeling and multi-scale feature grouping. arXiv preprint arXiv:2305.11003 (2023)."},{"key":"26789_CR21","unstructured":"Qiao, Y. et al. Robustness of sam: Segment anything under corruptions and beyond. arXiv preprint arXiv:2306.07713 (2023)."},{"key":"26789_CR22","unstructured":"Hu, C. & Li, X. When sam meets medical images: An investigation of segment anything model (sam) on multi-phase liver tumor segmentation. arXiv preprint arXiv:2304.08506 (2023)."},{"key":"26789_CR23","unstructured":"Mohapatra, S., Gosai, A. & Schlaug, G. Sam vs bet: A comparative study for brain extraction and segmentation of magnetic resonance images using deep learning. arXiv preprint arXiv:2304.047382, 4 (2023)."},{"key":"26789_CR24","doi-asserted-by":"crossref","unstructured":"R.\u00a0D. et al. Segment anything model (sam) for digital pathology: Assess zero-shot segmentation on whole slide imaging. In IS &T International Symposium on Electronic Imaging, vol.\u00a037, COIMG\u2013132 (2025).","DOI":"10.2352\/EI.2025.37.14.COIMG-132"},{"key":"26789_CR25","doi-asserted-by":"crossref","unstructured":"Na, S., Guo, Y., Jiang, F., Ma, H. & Huang, J. Segment any cell: A sam-based auto-prompting fine-tuning framework for nuclei segmentation. arXiv preprint arXiv:2401.13220 (2024).","DOI":"10.1109\/TNNLS.2025.3611322"},{"key":"26789_CR26","doi-asserted-by":"crossref","unstructured":"Israel, U. et al. A foundation model for cell segmentation. bioRxiv 2023\u201311 (2024).","DOI":"10.1101\/2023.11.17.567630"},{"key":"26789_CR27","doi-asserted-by":"publisher","DOI":"10.1016\/j.media.2023.102918","volume":"89","author":"MA Mazurowski","year":"2023","unstructured":"Mazurowski, M. A. et al. Segment anything model for medical image analysis: an experimental study. Med. Image Anal. 89, 102918 (2023).","journal-title":"Med. Image Anal."},{"key":"26789_CR28","doi-asserted-by":"crossref","unstructured":"Archit, A. et al. Segment anything for microscopy. bioRxiv 2023\u201308 (2023).","DOI":"10.1101\/2023.08.21.554208"},{"key":"26789_CR29","doi-asserted-by":"crossref","unstructured":"Chen, J., Huang, W., Zhang, J., Debattista, K. & Han, J. Addressing inconsistent labeling with cross image matching for scribble-based medical image segmentation. IEEE Transactions on Image Processing (2025).","DOI":"10.1109\/TIP.2025.3530787"},{"key":"26789_CR30","doi-asserted-by":"crossref","unstructured":"Chen, J., Li, W., Li, H. & Zhang, J. Deep class-specific affinity-guided convolutional network for multimodal unpaired image segmentation. In International Conference on Medical Image Computing and Computer-Assisted Intervention, 187\u2013196 (Springer, 2020).","DOI":"10.1007\/978-3-030-59719-1_19"},{"key":"26789_CR31","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2023.109881","volume":"145","author":"J Chen","year":"2024","unstructured":"Chen, J. et al. Dynamic contrastive learning guided by class confidence and confusion degree for medical image segmentation. Pattern Recogn. 145, 109881 (2024).","journal-title":"Pattern Recogn."},{"key":"26789_CR32","doi-asserted-by":"publisher","first-page":"594","DOI":"10.1109\/TMI.2022.3213372","volume":"42","author":"J Chen","year":"2022","unstructured":"Chen, J., Zhang, J., Debattista, K. & Han, J. Semi-supervised unpaired medical image segmentation through task-affinity consistency. IEEE Trans. Med. Imaging 42, 594\u2013605 (2022).","journal-title":"IEEE Trans. Med. Imaging"},{"key":"26789_CR33","unstructured":"Kervadec, H., Dolz, J., Wang, S., Granger, E. & Ayed, I.\u00a0B. Bounding boxes for weakly supervised segmentation: Global constraints get close to full supervision. In Medical imaging with deep learning, 365\u2013381 (PMLR, 2020)."},{"key":"26789_CR34","doi-asserted-by":"crossref","unstructured":"Liu, W., He, Q. & He, X. Weakly supervised nuclei segmentation via instance learning. In 2022 IEEE 19th International Symposium on Biomedical Imaging (ISBI), 1\u20135 (IEEE, 2022).","DOI":"10.1109\/ISBI52829.2022.9761644"},{"key":"26789_CR35","doi-asserted-by":"crossref","unstructured":"Chen, Z., Tian, Z., Zhu, J., Li, C. & Du, S. C-cam: Causal cam for weakly supervised semantic segmentation on medical image. In Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, 11676\u201311685 (2022).","DOI":"10.1109\/CVPR52688.2022.01138"},{"key":"26789_CR36","doi-asserted-by":"crossref","unstructured":"Ma, T. et al. Ensembling low precision models for binary biomedical image segmentation. In Proceedings of the IEEE\/CVF Winter Conference on Applications of Computer Vision, 325\u2013334 (2021).","DOI":"10.1109\/WACV48630.2021.00037"},{"key":"26789_CR37","unstructured":"Dai, H. et al. Samaug: Point prompt augmentation for segment anything model. arXiv preprint arXiv:2307.01187 (2023)."},{"key":"26789_CR38","doi-asserted-by":"publisher","first-page":"1966","DOI":"10.1109\/TPAMI.2011.280","volume":"34","author":"A Alush","year":"2012","unstructured":"Alush, A. & Goldberger, J. Ensemble segmentation using efficient integer linear programming. IEEE Trans. Pattern Anal. Mach. Intell. 34, 1966\u20131977 (2012).","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"26789_CR39","doi-asserted-by":"publisher","first-page":"309","DOI":"10.1145\/1015706.1015720","volume":"23","author":"C Rother","year":"2004","unstructured":"Rother, C., Kolmogorov, V. & Blake, A. \u201cGrabcut\u2019\u2019 interactive foreground extraction using iterated graph cuts. ACM Trans. Graph. (TOG) 23, 309\u2013314 (2004).","journal-title":"ACM Trans. Graph. (TOG)"},{"key":"26789_CR40","unstructured":"Triggs, B. & Verbeek, J. Scene segmentation with crfs learned from partially labeled images. Advances in neural information processing systems20 (2007)."},{"key":"26789_CR41","doi-asserted-by":"crossref","unstructured":"Plath, N., Toussaint, M. & Nakajima, S. Multi-class image segmentation using conditional random fields and global classification. In Proceedings of the 26th annual international conference on machine learning, 817\u2013824 (2009).","DOI":"10.1145\/1553374.1553479"},{"key":"26789_CR42","unstructured":"Kr\u00e4henb\u00fchl, P. & Koltun, V. Efficient inference in fully connected crfs with gaussian edge potentials. Advances in neural information processing systems24 (2011)."},{"key":"26789_CR43","doi-asserted-by":"publisher","first-page":"1380","DOI":"10.1109\/TMI.2019.2947628","volume":"39","author":"N Kumar","year":"2019","unstructured":"Kumar, N. et al. A multi-organ nucleus segmentation challenge. IEEE Trans. Med. Imaging 39, 1380\u20131391 (2019).","journal-title":"IEEE Trans. Med. Imaging"},{"key":"26789_CR44","unstructured":"Csurka, G., Larlus, D., Perronnin, F. & Meylan, F. What is a good evaluation measure for semantic segmentation?. In Bmvc, vol.\u00a027, 10\u20135244 (Bristol, 2013)."},{"key":"26789_CR45","first-page":"12077","volume":"34","author":"E Xie","year":"2021","unstructured":"Xie, E. et al. Segformer: Simple and efficient design for semantic segmentation with transformers. Adv. Neural. Inf. Process. Syst. 34, 12077\u201312090 (2021).","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"26789_CR46","doi-asserted-by":"publisher","first-page":"1084778","DOI":"10.3389\/fpls.2023.1084778","volume":"14","author":"A Das","year":"2023","unstructured":"Das, A., Das Choudhury, S., Das, A. K., Samal, A. & Awada, T. Emergenet: A novel deep-learning based ensemble segmentation model for emergence timing detection of coleoptile. Front. Plant Sci. 14, 1084778 (2023).","journal-title":"Front. Plant Sci."},{"key":"26789_CR47","unstructured":"Gurobi Optimization, LLC. Gurobi Optimizer Reference Manual (2023)."},{"key":"26789_CR48","unstructured":"Hsu, C.-C., Hsu, K.-J., Tsai, C.-C., Lin, Y.-Y. & Chuang, Y.-Y. Weakly supervised instance segmentation using the bounding box tightness prior. Advances in Neural Information Processing Systems32 (2019)."},{"key":"26789_CR49","unstructured":"Ravi, N. et al. Sam 2: Segment anything in images and videos. arXiv preprint (2024)."},{"key":"26789_CR50","doi-asserted-by":"publisher","first-page":"654","DOI":"10.1038\/s41467-024-44824-z","volume":"15","author":"J Ma","year":"2024","unstructured":"Ma, J. et al. Segment anything in medical images. Nat. Commun. 15, 654 (2024).","journal-title":"Nat. Commun."},{"key":"26789_CR51","doi-asserted-by":"crossref","unstructured":"Ma, J. & Wang, B. Segment anything in medical images. arXiv preprint arXiv:2304.12306 (2023).","DOI":"10.1038\/s41467-024-44824-z"},{"key":"26789_CR52","doi-asserted-by":"publisher","first-page":"579","DOI":"10.1038\/s41592-024-02580-4","volume":"22","author":"A Archit","year":"2025","unstructured":"Archit, A. et al. Segment anything for microscopy. Nat. Methods 22, 579\u2013591 (2025).","journal-title":"Nat. Methods"}],"container-title":["Scientific Reports"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.nature.com\/articles\/s41598-025-26789-1.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/www.nature.com\/articles\/s41598-025-26789-1","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/www.nature.com\/articles\/s41598-025-26789-1.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,11,28]],"date-time":"2025-11-28T10:24:37Z","timestamp":1764325477000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.nature.com\/articles\/s41598-025-26789-1"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,11,22]]},"references-count":52,"journal-issue":{"issue":"1","published-online":{"date-parts":[[2025,12]]}},"alternative-id":["26789"],"URL":"https:\/\/doi.org\/10.1038\/s41598-025-26789-1","relation":{},"ISSN":["2045-2322"],"issn-type":[{"value":"2045-2322","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,11,22]]},"assertion":[{"value":"23 May 2025","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"30 October 2025","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"22 November 2025","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"The authors declare no competing interests.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Competing interests"}}],"article-number":"42652"}}