{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,1,11]],"date-time":"2025-01-11T03:10:26Z","timestamp":1736565026964,"version":"3.32.0"},"reference-count":36,"publisher":"Springer Science and Business Media LLC","issue":"1","license":[{"start":{"date-parts":[[2025,1,11]],"date-time":"2025-01-11T00:00:00Z","timestamp":1736553600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"},{"start":{"date-parts":[[2025,1,11]],"date-time":"2025-01-11T00:00:00Z","timestamp":1736553600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["BMC Bioinformatics"],"abstract":"<jats:title>Abstract<\/jats:title><jats:sec>\n                <jats:title>Background<\/jats:title>\n                <jats:p>Deep learning (DL) has set new standards in cancer diagnosis, significantly enhancing the accuracy of automated classification of whole slide images (WSIs) derived from biopsied tissue samples. To enable DL models to process these large images, WSIs are typically divided into thousands of smaller tiles, each containing 10\u201350 cells. Multiple Instance Learning (MIL) is a commonly used approach, where WSIs are treated as bags comprising numerous tiles (instances) and only bag-level labels are provided during training. The model learns from these broad labels to extract more detailed, instance-level insights. However, biopsied sections often exhibit high intra- and inter-phenotypic heterogeneity, presenting a significant challenge for classification. To address this, many graph-based methods have been proposed, where each WSI is represented as a graph with tiles as nodes and edges defined by specific spatial relationships.<\/jats:p>\n              <\/jats:sec><jats:sec>\n                <jats:title>Results<\/jats:title>\n                <jats:p>In this study, we investigate how different graph configurations, varying in connectivity and neighborhood structure, affect the performance of MIL models. We developed a novel pipeline, K-MIL, to evaluate the impact of contextual information on cell classification performance. By incorporating neighboring tiles into the analysis, we examined whether contextual information improves or impairs the network\u2019s ability to identify patterns and features critical for accurate classification. Our experiments were conducted on two datasets: COLON cancer and UCSB datasets.<\/jats:p>\n              <\/jats:sec><jats:sec>\n                <jats:title>Conclusions<\/jats:title>\n                <jats:p>Our results indicate that while incorporating more spatial context information generally improves model accuracy at both the bag and tile levels, the improvement at the tile level is not linear. In some instances, increasing spatial context leads to misclassification, suggesting that more context is not always beneficial. This finding highlights the need for careful consideration when incorporating spatial context information in digital pathology classification tasks.<\/jats:p>\n              <\/jats:sec>","DOI":"10.1186\/s12859-024-06007-x","type":"journal-article","created":{"date-parts":[[2025,1,11]],"date-time":"2025-01-11T01:59:11Z","timestamp":1736560751000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Not seeing the trees for the forest. The impact of neighbours on graph-based configurations in histopathology"],"prefix":"10.1186","volume":"26","author":[{"given":"Olga","family":"Fourkioti","sequence":"first","affiliation":[]},{"given":"Matt","family":"De Vries","sequence":"additional","affiliation":[]},{"given":"Reed","family":"Naidoo","sequence":"additional","affiliation":[]},{"given":"Chris","family":"Bakal","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2025,1,11]]},"reference":[{"issue":"5","key":"6007_CR1","doi-asserted-by":"publisher","DOI":"10.1016\/j.modpat.2023.100118","volume":"36","author":"A Khan","year":"2023","unstructured":"Khan A, Brouwer N, Blank A, M\u00fcller F, Soldini D, Noske A, Gaus E, Brandt S, Nagtegaal I, Dawson H, et al. Computer-assisted diagnosis of lymph node metastases in colorectal cancers using transfer learning with an ensemble model. Mod Pathol. 2023;36(5): 100118.","journal-title":"Mod Pathol."},{"issue":"1","key":"6007_CR2","doi-asserted-by":"publisher","first-page":"80","DOI":"10.1186\/s12916-021-01953-2","volume":"19","author":"H Yang","year":"2021","unstructured":"Yang H, Chen L, Cheng Z, Yang M, Wang J, Lin C, Wang Y, Huang L, Chen Y, Peng S, et al. Deep learning-based six-type classifier for lung cancer and mimics from histopathological whole slide images: a retrospective study. BMC Med. 2021;19(1):80.","journal-title":"BMC Med."},{"issue":"16","key":"6007_CR3","doi-asserted-by":"publisher","first-page":"4373","DOI":"10.3390\/s20164373","volume":"20","author":"Z Hameed","year":"2020","unstructured":"Hameed Z, Zahia S, Garcia-Zapirain B, Javier Aguirre JA. Breast cancer histopathology image classification using an ensemble of deep learning models. Sensors (Basel). 2020;20(16):4373.","journal-title":"Sensors (Basel)"},{"issue":"12","key":"6007_CR4","doi-asserted-by":"publisher","first-page":"1983","DOI":"10.1038\/s41379-022-01146-z","volume":"35","author":"H Farahani","year":"2022","unstructured":"Farahani H, Boschman J, Farnell D, Darbandsari A, Zhang A, Ahmadvand P, Jones SJM, Huntsman D, K\u00f6bel M, Gilks CB, et al. Deep learning-based histotype diagnosis of ovarian carcinoma whole-slide pathology images. Modern Pathol. 2022;35(12):1983\u201390.","journal-title":"Modern Pathol."},{"key":"6007_CR5","doi-asserted-by":"publisher","DOI":"10.3390\/diagnostics13010103","author":"MMK Sarker","year":"2023","unstructured":"Sarker MMK, Akram F, Alsharid M, Singh VK, Yasrab R, Elyan E. Efficient breast cancer classification network with dual squeeze and excitation in histopathological images. Diagnostics. 2023. https:\/\/doi.org\/10.3390\/diagnostics13010103.","journal-title":"Diagnostics"},{"issue":"1","key":"6007_CR6","doi-asserted-by":"publisher","first-page":"15600","DOI":"10.1038\/s41598-022-19278-2","volume":"12","author":"Z Hameed","year":"2022","unstructured":"Hameed Z, Garcia-Zapirain B, Aguirre JJ, Isaza-Ruget MA. Multiclass classification of breast cancer histopathology images using multilevel features of deep convolutional neural network. Sci Rep. 2022;12(1):15600.","journal-title":"Sci Rep."},{"key":"6007_CR7","doi-asserted-by":"crossref","unstructured":"Wu Z, Wang L, Li C, Cai Y, Liang Y, Mo X, Lu Q, Dong L, Liu Y. \u201cDeepLRHE: A deep convolutional neural network framework to evaluate the risk of lung cancer recurrence and metastasis from histopathology images\u201d. In: Front. Genet. 11. (2020)","DOI":"10.3389\/fgene.2020.00768"},{"issue":"1","key":"6007_CR8","doi-asserted-by":"publisher","first-page":"16605","DOI":"10.1038\/s41598-021-95747-4","volume":"11","author":"A Sadhwani","year":"2021","unstructured":"Sadhwani A, Chang H-W, Behrooz A, Brown T, Auvigne-Flament I, Patel H, Findlater R, Velez V, Tan F, Tekiela K, et al. Comparative analysis of machine learning approaches to classify tumor mutation burden in lung adenocarcinoma using histopathology images. Sci Rep. 2021;11(1):16605.","journal-title":"Sci Rep."},{"key":"6007_CR9","doi-asserted-by":"crossref","unstructured":"Zormpas-Petridis K, Noguera R, Ivankovic DK, Roxanis I, Jamin Y, Yuan Y. \u201cSuperHistopath: A deep learning pipeline for mapping tumor heterogeneity on low-resolution whole-slide digital histopathology images\u201d. In: Front. Oncol. 2021;10.","DOI":"10.3389\/fonc.2020.586292"},{"issue":"1","key":"6007_CR10","doi-asserted-by":"publisher","first-page":"1830","DOI":"10.1038\/s41598-022-05709-7","volume":"12","author":"JW Yang","year":"2022","unstructured":"Yang JW, Song DH, An HJ, Seo SB. Classification of subtypes including LCNEC in lung cancer biopsy slides using convolutional neural network from scratch. Sci Rep. 2022;12(1):1830.","journal-title":"Sci Rep."},{"issue":"1","key":"6007_CR11","doi-asserted-by":"publisher","first-page":"44","DOI":"10.1093\/nsr\/nwx106","volume":"5","author":"Z-H Zhou","year":"2017","unstructured":"Zhou Z-H. A brief introduction to weakly supervised learning. Nat Sci Rev. 2017;5(1):44\u201353.","journal-title":"Nat Sci Rev."},{"key":"6007_CR12","doi-asserted-by":"publisher","unstructured":"Hezi H, Gelber M, Balabanov A, Maruvka YE, Freiman M (2024) \u201cCIMIL-CRC: a clinically-informed multiple instance learning framework for patient-level colorectal cancer molecular subtypes classification from H & E stained images\u201d. In: CoRR abs\/2401.16131. https:\/\/doi.org\/10.48550\/ARXIV.2401.16131. arXiv:2401.16131.","DOI":"10.48550\/ARXIV.2401.16131"},{"key":"6007_CR13","doi-asserted-by":"publisher","first-page":"329","DOI":"10.1016\/J.PATCOG.2017.10.009","volume":"77","author":"M Carbonneau","year":"2018","unstructured":"Carbonneau M, Cheplygina V, Granger E, Gagnon G. Multiple instance learning: A survey of problem characteristics and applications. Pattern Recognit. 2018;77:329\u201353. https:\/\/doi.org\/10.1016\/J.PATCOG.2017.10.009.","journal-title":"Pattern Recognit."},{"issue":"1","key":"6007_CR14","doi-asserted-by":"publisher","first-page":"211","DOI":"10.1177\/0300985813503570","volume":"51","author":"JD Webster","year":"2014","unstructured":"Webster JD, Dunstan RW. Whole-slide imaging and automated image analysis. Vet Pathol. 2014;51(1):211\u201323.","journal-title":"Vet Pathol."},{"issue":"12","key":"6007_CR15","doi-asserted-by":"publisher","first-page":"3952","DOI":"10.1109\/TMI.2022.3202759","volume":"41","author":"Z Wang","year":"2022","unstructured":"Wang Z, Saoud C, Wangsiricharoen S, James AW, Popel AS, Sulam J. Label cleaning multiple instance learning: refining coarse annotations on single whole-slide images. IEEE Trans Med Imaging. 2022;41(12):3952\u201368. https:\/\/doi.org\/10.1109\/TMI.2022.3202759.","journal-title":"IEEE Trans Med Imaging"},{"key":"6007_CR16","unstructured":"Sharma Y, Shrivastava A, Ehsan L, Moskaluk CA, Syed S, Brown DE. \u201cCluster-to-Conquer: A Framework for End-to-End Multi-Instance Learning for Whole Slide Image Classification\u201d. In: Medical Imaging with Deep Learning, 7-9 July 2021, L \u00fc beck, Germany. Ed. by M.P. Heinrich, Q. Dou, M. de Bruijne, J. Lellmann, A. Schlaefer, and F. Ernst. Vol.143. Proceedings of Machine Learning Research. PMLR, 2021;682\u2013698."},{"key":"6007_CR17","doi-asserted-by":"publisher","DOI":"10.1016\/J.MEDIA.2022.102462","volume":"79","author":"Z Su","year":"2022","unstructured":"Su Z, Tavolara TE, Carreno-Galeano G, Lee SJ, Gurcan MN, Niazi MKK. Attention2majority: Weak multiple instance learning for regenerative kidney grading on whole slide images. Med Image Anal. 2022;79: 102462. https:\/\/doi.org\/10.1016\/J.MEDIA.2022.102462.","journal-title":"Med Image Anal."},{"key":"6007_CR18","doi-asserted-by":"publisher","first-page":"103","DOI":"10.1016\/j.eswa.2018.09.049","volume":"117","author":"PJ Sudharshan","year":"2019","unstructured":"Sudharshan PJ, Petitjean C, Spanhol FA, de Oliveira LES, Heutte L, Honeine P. Multiple instance learning for histopathological breast cancer image classification. Expert Syst Appl. 2019;117:103\u201311. https:\/\/doi.org\/10.1016\/j.eswa.2018.09.049.","journal-title":"Expert Syst. Appl."},{"issue":"1","key":"6007_CR19","doi-asserted-by":"publisher","first-page":"20317","DOI":"10.1038\/s41598-021-99246-4","volume":"11","author":"A Teramoto","year":"2021","unstructured":"Teramoto A, Kiriyama Y, Tsukamoto T, Sakurai E, Michiba A, Imaizumi K, Saito K, Fujita H. Weakly supervised learning for classification of lung cytological images using attention-based multiple instance learning. Sci Rep. 2021;11(1):20317.","journal-title":"Sci Rep."},{"issue":"5","key":"6007_CR20","doi-asserted-by":"publisher","first-page":"323","DOI":"10.1038\/nrc3261","volume":"12","author":"A Marusyk","year":"2012","unstructured":"Marusyk A, Almendro V, Polyak K. Intra-tumour heterogeneity: A looking glass for cancer? Nat Rev Cancer. 2012;12(5):323\u201334.","journal-title":"Nat Rev Cancer."},{"issue":"7","key":"6007_CR21","doi-asserted-by":"publisher","first-page":"66","DOI":"10.1038\/s41389-020-00250-6","volume":"9","author":"JY Buikhuisen","year":"2020","unstructured":"Buikhuisen JY, Torang A, Medema JP. Exploring and modelling colon cancer inter-tumour heterogeneity: Opportunities and challenges. Oncogenesis. 2020;9(7):66.","journal-title":"Oncogenesis"},{"key":"6007_CR22","doi-asserted-by":"publisher","DOI":"10.1016\/J.COMPMEDIMAG.2021.102027","volume":"95","author":"D Ahmedt-Aristizabal","year":"2022","unstructured":"Ahmedt-Aristizabal D, Armin MA, Denman S, Fookes C, Petersson L. A survey on graph-based deep learning for computational histopathology. Comput Med Imaging Graph. 2022;95: 102027. https:\/\/doi.org\/10.1016\/J.COMPMEDIMAG.2021.102027.","journal-title":"Comput Med Imaging Graph."},{"issue":"11","key":"6007_CR23","doi-asserted-by":"publisher","first-page":"3003","DOI":"10.1109\/TMI.2022.3176598","volume":"41","author":"Y Zheng","year":"2022","unstructured":"Zheng Y, Gindra RH, Green EJ, Burks EJ, Betke M, Beane JE, Kolachalama VB. A graph-transformer for whole slide image classification. IEEE Trans Med Imaging. 2022;41(11):3003\u201315. https:\/\/doi.org\/10.1109\/TMI.2022.3176598.","journal-title":"IEEE Trans Med Imaging."},{"issue":"1","key":"6007_CR24","doi-asserted-by":"publisher","first-page":"7555","DOI":"10.1038\/s41598-023-33863-z","volume":"13","author":"F Yacob","year":"2023","unstructured":"Yacob F, Siarov J, Villiamsson K, Suvilehto JT, Sj\u00f6blom L, Kjellberg M, Neittaanm\u00e4ki N. Weakly supervised detection and classification of basal cell carcinoma using graph-transformer on whole slide images. Sci Rep. 2023;13(1):7555.","journal-title":"Sci Rep."},{"key":"6007_CR25","doi-asserted-by":"publisher","first-page":"15","DOI":"10.1016\/j.patcog.2017.08.026","volume":"74","author":"X Wang","year":"2018","unstructured":"Wang X, Yan Y, Tang P, Bai X, Liu W. Revisiting multiple instance neural networks. Pattern Recognit. 2018;74:15\u201324. https:\/\/doi.org\/10.1016\/j.patcog.2017.08.026.","journal-title":"Pattern Recognit."},{"issue":"3","key":"6007_CR26","doi-asserted-by":"publisher","first-page":"591","DOI":"10.1016\/j.media.2014.01.010","volume":"18","author":"Y Xu","year":"2014","unstructured":"Xu Y, Zhu J, Chang EI, Lai M, Tu Z. Weakly supervised histopathology cancer image segmentation and classification. Med Image Anal. 2014;18(3):591\u2013604. https:\/\/doi.org\/10.1016\/j.media.2014.01.010.","journal-title":"Med Image Anal."},{"key":"6007_CR27","unstructured":"Velickovic P, Cucurull G, Casanova A, Romero A, Li\u00f2 P, Bengio Y (2018) \u201cGraph Attention Networks\u201d. In: 6th International Conference on Learning Representations, ICLR 2018, Vancouver, BC, Canada, April 30 - May 3, 2018, Conference Track Proceedings. OpenReview.net."},{"key":"6007_CR28","doi-asserted-by":"crossref","unstructured":"Nandy A, Haldar S, Banerjee S, Mitra S. \u201cA Survey on Applications of Siamese Neural Networks in Computer Vision\u201d. In: 2020 International Conference for Emerging Technology (INCET), 2020;1\u20135.","DOI":"10.1109\/INCET49848.2020.9153977"},{"key":"6007_CR29","unstructured":"Shaham U, Stanton K, Li H, Nadler B, Basri R, Kluger Y. SpectralNet: Spectral Clustering using Deep Neural Networks. cite arxiv:1801.01587Comment: Added demo of semisupervised learning. Accepted to ICLR 2018. (2018)"},{"key":"6007_CR30","unstructured":"Ilse M, Tomczak JM, Welling M. \u201cAttention-based Deep Multiple Instance Learning\u201d. In: Proceedings of the 35th International Conference on Machine Learning, ICML 2018, Stockholmsm \u00e4 ssan, Stockholm, Sweden, July 10-15, 2018. Ed. by J.G. Dy and A. Krause. Vol.80. Proceedings of Machine Learning Research, 2018;2132\u20132141."},{"key":"6007_CR31","doi-asserted-by":"publisher","unstructured":"Andersson A, Koriakina N, Sladoje N, Lindblad J. \u201cEnd-to-end Multiple Instance Learning with Gradient Accumulation\u201d. In: 2022 IEEE International Conference on Big Data (Big Data). Los Alamitos, CA, USA: IEEE Computer Society, 2022;2742\u20132746. https:\/\/doi.org\/10.1109\/BigData55660.2022.10020801.","DOI":"10.1109\/BigData55660.2022.10020801"},{"key":"6007_CR32","doi-asserted-by":"publisher","unstructured":"Sirinukunwattana K, e Ahmed Raza S, Tsang Y, Snead DRJ, Cree IA, Rajpoot NM. \u201cLocality Sensitive Deep Learning for Detection and Classification of Nuclei in Routine Colon Cancer Histology Images\u201d. IEEE Trans. Med. Imaging 2016;35.5,1196\u20131206. https:\/\/doi.org\/10.1109\/TMI.2016.2525803.","DOI":"10.1109\/TMI.2016.2525803"},{"issue":"7123","key":"6007_CR33","doi-asserted-by":"publisher","first-page":"111","DOI":"10.1038\/nature05384","volume":"445","author":"L Ricci-Vitiani","year":"2007","unstructured":"Ricci-Vitiani L, Lombardi DG, Pilozzi E, Biffoni M, Todaro M, Peschle C, De Maria R. Identification and expansion of human colon-cancer-initiating cells. Nature. 2007;445(7123):111\u20135.","journal-title":"Nature"},{"key":"6007_CR34","doi-asserted-by":"publisher","unstructured":"Gelasca ED, Byun J, Obara B, Manjunath BS. \u201cEvaluation and benchmark for biological image segmentation\u201d. In: Proceedings of the International Conference on Image Processing, ICIP 2008, October 12-15, 2008, San Diego, California, USA. IEEE, 2008;1816\u20131819. https:\/\/doi.org\/10.1109\/ICIP.2008.4712130.","DOI":"10.1109\/ICIP.2008.4712130"},{"key":"6007_CR35","unstructured":"Kingma DP, Ba J. \u201cAdam: A Method for Stochastic Optimization\u201d. In: 3rd International Conference on Learning Representations, ICLR 2015, San Diego, CA, USA, May 7-9, 2015, Conference Track Proceedings. Ed. by Y. Bengio and Y. LeCun. (2015)"},{"issue":"5","key":"6007_CR36","doi-asserted-by":"publisher","first-page":"34","DOI":"10.1109\/38.946629","volume":"21","author":"E Reinhard","year":"2001","unstructured":"Reinhard E, Ashikhmin M, Gooch B, Shirley P. Color transfer between images. IEEE Comput Graph Appl. 2001;21(5):34\u201341. https:\/\/doi.org\/10.1109\/38.946629.","journal-title":"IEEE Comput Graph Appl."}],"container-title":["BMC Bioinformatics"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1186\/s12859-024-06007-x.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1186\/s12859-024-06007-x\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1186\/s12859-024-06007-x.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,1,11]],"date-time":"2025-01-11T02:02:04Z","timestamp":1736560924000},"score":1,"resource":{"primary":{"URL":"https:\/\/bmcbioinformatics.biomedcentral.com\/articles\/10.1186\/s12859-024-06007-x"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,1,11]]},"references-count":36,"journal-issue":{"issue":"1","published-online":{"date-parts":[[2025,12]]}},"alternative-id":["6007"],"URL":"https:\/\/doi.org\/10.1186\/s12859-024-06007-x","relation":{},"ISSN":["1471-2105"],"issn-type":[{"value":"1471-2105","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,1,11]]},"assertion":[{"value":"31 May 2024","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"5 December 2024","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"11 January 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":"Not applicable.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Ethics approval and consent to participate"}},{"value":"Not applicable.","order":3,"name":"Ethics","group":{"name":"EthicsHeading","label":"Consent for publication"}},{"value":"The authors declare that they have no Conflict of interest.","order":4,"name":"Ethics","group":{"name":"EthicsHeading","label":"Competing interests"}}],"article-number":"9"}}