{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,11,1]],"date-time":"2025-11-01T02:52:03Z","timestamp":1761965523387,"version":"3.41.0"},"reference-count":25,"publisher":"Springer Science and Business Media LLC","issue":"3","license":[{"start":{"date-parts":[[2025,4,22]],"date-time":"2025-04-22T00:00:00Z","timestamp":1745280000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"},{"start":{"date-parts":[[2025,4,22]],"date-time":"2025-04-22T00:00:00Z","timestamp":1745280000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"}],"funder":[{"name":"Mines Paris - PSL"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["J Math Imaging Vis"],"published-print":{"date-parts":[[2025,6]]},"abstract":"<jats:title>Abstract<\/jats:title>\n          <jats:p>Bright objects on a dark background, such as cells in microscopy images, can sometimes be modeled as maxima of sufficient dynamic, called <jats:italic>h<\/jats:italic>-maxima. Such a model could be sufficient to count these objects in images, provided we know the dynamic threshold that tells apart actual objects from irrelevant maxima. In a previous study we introduced a neural architecture that includes a morphological pipeline counting the number of <jats:italic>h<\/jats:italic>-maxima in an image, preceded by a classical  which estimates the dynamic <jats:italic>h<\/jats:italic> yielding the right number of objects. This was made possible by geodesic reconstruction layers, and a new module counting connected components. The resulting architecture could be trained end-to-end to count cells by minimizing a loss function focusing mainly on an intermediate image and very marginally on the counting errors. In the present paper, we extend that work with a detailed theoretical analysis of the derivability of such pipeline, and with more cell counting experiments on different datasets. Our analysis explains why it is difficult to train the proposed pipeline when penalizing counting errors, and ends up with a solution to that challenge. Our experiments show that our approach can obtain results comparable to the state of the art with much fewer parameters and an increased interpretability of the model.<\/jats:p>","DOI":"10.1007\/s10851-025-01243-z","type":"journal-article","created":{"date-parts":[[2025,4,22]],"date-time":"2025-04-22T15:14:40Z","timestamp":1745334880000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":1,"title":["Cell Counting with Trainable h-Maxima and Connected Component Layers"],"prefix":"10.1007","volume":"67","author":[{"given":"Samy","family":"Blusseau","sequence":"first","affiliation":[]},{"given":"Xiaohu","family":"Liu","sequence":"additional","affiliation":[]},{"given":"Santiago","family":"Velasco-Forero","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2025,4,22]]},"reference":[{"issue":"4","key":"1243_CR1","doi-asserted-by":"publisher","first-page":"982","DOI":"10.1364\/OSAC.388082","volume":"3","author":"Y Kong","year":"2020","unstructured":"Kong, Y., Li, H., Ren, Y., Genchev, G.Z., Wang, X., Zhao, H., Xie, Z., Lu, H.: Automated yeast cells segmentation and counting using a parallel U-Net based two-stage framework. OSA Contin. 3(4), 982\u2013992 (2020)","journal-title":"OSA Contin."},{"key":"1243_CR2","doi-asserted-by":"publisher","DOI":"10.1016\/j.media.2020.101892","volume":"68","author":"S He","year":"2021","unstructured":"He, S., Minn, K.T., Solnica-Krezel, L., Anastasio, M.A., Li, H.: Deeply-supervised density regression for automatic cell counting in microscopy images. Med. Image Anal. 68, 101892 (2021)","journal-title":"Med. Image Anal."},{"issue":"3","key":"1243_CR3","first-page":"171","volume":"41","author":"T Lazard","year":"2022","unstructured":"Lazard, T., Blusseau, S., Velasco-Forero, S., Decenci\u00e8re, \u00c9., Flouret, V., Cohen, C., Baldeweck, T.: Applying deep learning to melanocyte counting on fluorescent TRP1 labelled images of in vitro skin model. Image Anal. Stereol. 41(3), 171\u201380 (2022)","journal-title":"Image Anal. Stereol."},{"issue":"1","key":"1243_CR4","doi-asserted-by":"publisher","first-page":"22920","DOI":"10.1038\/s41598-021-01929-5","volume":"11","author":"R Morelli","year":"2021","unstructured":"Morelli, R., Clissa, L., Amici, R., Cerri, M., Hitrec, T., Luppi, M., Rinaldi, L., Squarcio, F., Zoccoli, A.: Automating cell counting in fluorescent microscopy through deep learning with c-resunet. Sci. Rep. 11(1), 22920 (2021)","journal-title":"Sci. Rep."},{"issue":"4","key":"1243_CR5","doi-asserted-by":"publisher","first-page":"103","DOI":"10.1049\/htl.2018.5098","volume":"6","author":"MM Alam","year":"2019","unstructured":"Alam, M.M., Islam, M.T.: Machine learning approach of automatic identification and counting of blood cells. Healthc. Technol. Lett. 6(4), 103\u2013108 (2019)","journal-title":"Healthc. Technol. Lett."},{"key":"1243_CR6","doi-asserted-by":"crossref","unstructured":"Xia, T., Jiang, R., Fu, Y.Q., Jin, N.: Automated blood cell detection and counting via deep learning for microfluidic point-of-care medical devices. In: IOP Conference Series: Materials Science and Engineering, vol. 646, p. 012048. IOP Publishing (2019)","DOI":"10.1088\/1757-899X\/646\/1\/012048"},{"key":"1243_CR7","doi-asserted-by":"publisher","DOI":"10.1016\/j.bspc.2021.102495","volume":"66","author":"A Shakarami","year":"2021","unstructured":"Shakarami, A., Menhaj, M.B., Mahdavi-Hormat, A., Tarrah, H.: A fast and yet efficient yolov3 for blood cell detection. Biomed. Signal Process. Control 66, 102495 (2021)","journal-title":"Biomed. Signal Process. Control"},{"key":"1243_CR8","doi-asserted-by":"crossref","unstructured":"Liu, X., Blusseau, S., Velasco-Forero, S.: Counting melanocytes with trainable h-maxima and connected component layers. In: International Conference on Discrete Geometry and Mathematical Morphology, pp. 417\u2013430. Springer, Berlin (2024)","DOI":"10.1007\/978-3-031-57793-2_32"},{"key":"1243_CR9","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-662-03939-7","volume-title":"Morphological Image Analysis: Principles and Applications","author":"P Soille","year":"1999","unstructured":"Soille, P.: Morphological Image Analysis: Principles and Applications, vol. 2. Springer, Berlin (1999)"},{"issue":"1","key":"1243_CR10","doi-asserted-by":"publisher","first-page":"23","DOI":"10.1137\/21M1417867","volume":"15","author":"S Velasco-Forero","year":"2022","unstructured":"Velasco-Forero, S., Pag\u00e8s, R., Angulo, J.: Learnable empirical mode decomposition based on mathematical morphology. SIAM J. Imag. Sci. 15(1), 23\u201344 (2022)","journal-title":"SIAM J. Imag. Sci."},{"key":"1243_CR11","unstructured":"Velasco-Forero, S., Rhim, A., Angulo, J.: Fixed point layers for geodesic morphological operations. In: British Machine Vision Conference, pp. 1\u201311 (2022)"},{"volume-title":"Mathematical Morphology: from Theory to Applications","year":"2013","key":"1243_CR12","unstructured":"Najman, L., Talbot, H. (eds.): Mathematical Morphology: from Theory to Applications. John Wiley & Sons, Oxford (2013)"},{"issue":"2","key":"1243_CR13","doi-asserted-by":"publisher","first-page":"176","DOI":"10.1109\/83.217222","volume":"2","author":"L Vincent","year":"1993","unstructured":"Vincent, L.: Morphological grayscale reconstruction in image analysis: applications and efficient algorithms. IEEE Trans. Image Process. 2(2), 176\u2013201 (1993)","journal-title":"IEEE Trans. Image Process."},{"key":"1243_CR14","doi-asserted-by":"crossref","unstructured":"Grimaud, M.: New measure of contrast: the dynamics. In: Image Algebra and Morphological Image Processing III, vol. 1769, pp. 292\u2013305. SPIE (1992)","DOI":"10.1117\/12.60650"},{"key":"1243_CR15","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1051\/cocv:2002069","volume":"9","author":"C Ballester","year":"2003","unstructured":"Ballester, C., Caselles, V., Monasse, P.: The tree of shapes of an image. ESAIM Control Optim. Calcul. Var. 9, 1\u201318 (2003)","journal-title":"ESAIM Control Optim. Calcul. Var."},{"issue":"2","key":"1243_CR16","doi-asserted-by":"publisher","first-page":"146","DOI":"10.1137\/0201010","volume":"1","author":"R Tarjan","year":"1972","unstructured":"Tarjan, R.: Depth-first search and linear graph algorithms. SIAM J. Comput. 1(2), 146\u2013160 (1972)","journal-title":"SIAM J. Comput."},{"key":"1243_CR17","doi-asserted-by":"crossref","unstructured":"Guan, S., Loew, M.: Understanding the ability of deep neural networks to count connected components in images. In: 2020 IEEE Applied Imagery Pattern Recognition Workshop (AIPR), pp. 1\u20137. IEEE (2020)","DOI":"10.1109\/AIPR50011.2020.9425331"},{"key":"1243_CR18","doi-asserted-by":"publisher","DOI":"10.1007\/3-540-10861-0","volume-title":"Automatic Differentiation: Techniques and Applications","author":"LB Rall","year":"1981","unstructured":"Rall, L.B.: Automatic Differentiation: Techniques and Applications. Springer, Berlin (1981)"},{"key":"1243_CR19","doi-asserted-by":"crossref","unstructured":"Duval, C., Cohen, C., Chagnoleau, C., Flouret, V., Bourreau, E., Bernerd, F.: Key regulatory role of dermal fibroblasts in pigmentation as demonstrated using a reconstructed skin model: impact of photo-aging. PLoS ONE 9(12), 114182 (2014)","DOI":"10.1371\/journal.pone.0114182"},{"key":"1243_CR20","doi-asserted-by":"crossref","unstructured":"Stringer, C., Wang, T., Michaelos, M., Pachitariu, M.: Cellpose: a generalist algorithm for cellular segmentation. Nat. Methods 18(1), 100\u2013106 (2021)","DOI":"10.1038\/s41592-020-01018-x"},{"issue":"2","key":"1243_CR21","first-page":"26","volume":"4","author":"T Tieleman","year":"2012","unstructured":"Tieleman, T., Hinton, G., et al.: Lecture 6.5-RMSPROP: divide the gradient by a running average of its recent magnitude. COURSERA Neural Netw. Mach. Learn. 4(2), 26\u201331 (2012)","journal-title":"COURSERA Neural Netw. Mach. Learn."},{"key":"1243_CR22","doi-asserted-by":"crossref","unstructured":"Ronneberger, O., Fischer, P., Brox, T.: U-net: convolutional networks for biomedical image segmentation. In: Medical Image Computing and Computer-assisted intervention\u2013MICCAI 2015: 18th International Conference, Munich, Germany, October 5\u20139, 2015, Proceedings, Part III 18, pp. 234\u2013241. Springer, Berlin (2015)","DOI":"10.1007\/978-3-319-24574-4_28"},{"key":"1243_CR23","unstructured":"Chierchia, G., Perret, B.: Ultrametric fitting by gradient descent. Adv. Neural Inf. Process. Syst. 32 (2019)"},{"key":"1243_CR24","doi-asserted-by":"crossref","unstructured":"Charisopoulos, V., Maragos, P.: Morphological perceptrons: geometry and training algorithms. In: ISMM 2017, pp. 3\u201315. Springer, Berlin (2017)","DOI":"10.1007\/978-3-319-57240-6_1"},{"key":"1243_CR25","doi-asserted-by":"crossref","unstructured":"Blusseau, S.: Training morphological neural networks with gradient descent: some theoretical insights. In: DGMM Proceedings. Springer, Berlin (2024)","DOI":"10.1007\/978-3-031-57793-2_18"}],"container-title":["Journal of Mathematical Imaging and Vision"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s10851-025-01243-z.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s10851-025-01243-z\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s10851-025-01243-z.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,7,3]],"date-time":"2025-07-03T09:44:35Z","timestamp":1751535875000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s10851-025-01243-z"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,4,22]]},"references-count":25,"journal-issue":{"issue":"3","published-print":{"date-parts":[[2025,6]]}},"alternative-id":["1243"],"URL":"https:\/\/doi.org\/10.1007\/s10851-025-01243-z","relation":{},"ISSN":["0924-9907","1573-7683"],"issn-type":[{"type":"print","value":"0924-9907"},{"type":"electronic","value":"1573-7683"}],"subject":[],"published":{"date-parts":[[2025,4,22]]},"assertion":[{"value":"13 September 2024","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"24 March 2025","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"22 April 2025","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"1 May 2025","order":4,"name":"change_date","label":"Change Date","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"Update","order":5,"name":"change_type","label":"Change Type","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"In this article in footnote 4, at the bottom of page 12. Indeed, the full stop at the end of the footnote was included in the link, which makes the latter wrong and it is corrected now.","order":6,"name":"change_details","label":"Change Details","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":"Conflict of interest"}}],"article-number":"27"}}