Academic Journal
Swarm learning with weak supervision enables automatic breast cancer detection in magnetic resonance imaging
| Title: | Swarm learning with weak supervision enables automatic breast cancer detection in magnetic resonance imaging |
|---|---|
| Authors: | Oliver Lester Saldanha, Jiefu Zhu, Gustav Müller-Franzes, Zunamys I. Carrero, Nicholas R. Payne, Lorena Escudero Sánchez, Paul Christophe Varoutas, Sreenath Kyathanahally, Narmin Ghaffari Laleh, Kevin Pfeiffer, Marta Ligero, Jakob Behner, Kamarul A. Abdullah, Georgios Apostolakos, Chrysafoula Kolofousi, Antri Kleanthous, Michail Kalogeropoulos, Cristina Rossi, Sylwia Nowakowska, Alexandra Athanasiou, Raquel Perez-Lopez, Ritse Mann, Wouter Veldhuis, Julia Camps, Volkmar Schulz, Markus Wenzel, Sergey Morozov, Alexander Ciritsis, Christiane Kuhl, Fiona J. Gilbert, Daniel Truhn, Jakob Nikolas Kather |
| Contributors: | Institut Català de la Salut, [Saldanha OL] Else Kroener Fresenius Center for Digital Health, Medical Faculty Carl Gustav Carus, Technical University Dresden, Dresden, Germany. Department of Diagnostic and Interventional Radiology, University Hospital RWTH Aachen, Aachen, Germany. [Zhu J] Else Kroener Fresenius Center for Digital Health, Medical Faculty Carl Gustav Carus, Technical University Dresden, Dresden, Germany. [Müller-Franzes G, Carrero ZI] Department of Diagnostic and Interventional Radiology, University Hospital RWTH Aachen, Aachen, Germany. [Payn NR] Department of Radiology, Clinical School, Cambridge Biomedical Research Centre, University of Cambridge, Cambridge, UK. [Escudero Sánchez L] Department of Radiology, Clinical School, Cambridge Biomedical Research Centre, University of Cambridge, Cambridge, UK. Cancer Research UK Cambridge Centre, Cambridge, UK. [Perez-Lopez R] Radiomics Group, Vall d’Hebron Institute of Oncology (VHIO), Barcelona, Spain, Vall d'Hebron Barcelona Hospital Campus, MS Radiologie, Cancer, Circulatory Health, Apollo - University of Cambridge Repository |
| Source: | Commun Med (Lond) Scientia Scientia. Dipòsit d'Informació Digital del Departament de Salut instname Communications Medicine, Vol 5, Iss 1, Pp 1-12 (2025) Communications Medicine, 5, 1 |
| Publisher Information: | Springer Science and Business Media LLC, 2025. |
| Publication Year: | 2025 |
| Subject Terms: | Epidemiology, Medicine (miscellaneous), TÉCNICAS Y EQUIPOS ANALÍTICOS, DIAGNÓSTICOS Y TERAPÉUTICOS::diagnóstico::técnicas y procedimientos diagnósticos::diagnóstico por imagen::tomografía::imagen por resonancia magnética, 32 Biomedical and Clinical Sciences, Bioengineering, Assessment and Diagnosis, Article, 46 Information and Computing Sciences, Breast Cancer, Medical Imaging - Radboud University Medical Center, FENÓMENOS Y PROCESOS::conceptos matemáticos::algoritmos::inteligencia artificial::aprendizaje automático::aprendizaje profundo, Machine Learning and Artificial Intelligence, Internal Medicine, Cancer, PHENOMENA AND PROCESSES::Mathematical Concepts::Algorithms::Artificial Intelligence::Machine Learning::Deep Learning, Intel·ligència artificial - Aplicacions a la medicina, Data Science, Public Health, Environmental and Occupational Health, Otros calificadores::Otros calificadores::Otros calificadores::/diagnóstico por imagen, Other subheadings::Other subheadings::Other subheadings::/diagnostic imaging, 3211 Oncology and Carcinogenesis, Mama - Càncer - Imatgeria per ressonància magnètica, Networking and Information Technology R&D (NITRD), Biomedical Imaging, Women's Health, Medicine, ANALYTICAL, DIAGNOSTIC AND THERAPEUTIC TECHNIQUES, AND EQUIPMENT::Diagnosis::Diagnostic Techniques and Procedures::Diagnostic Imaging::Tomography::Magnetic Resonance Imaging, ENFERMEDADES::neoplasias::neoplasias por localización::neoplasias de la mama, DISEASES::Neoplasms::Neoplasms by Site::Breast Neoplasms, Aprenentatge profund |
| Description: | Background Over the next 5 years, new breast cancer screening guidelines recommending magnetic resonance imaging (MRI) for certain patients will significantly increase the volume of imaging data to be analyzed. While this increase poses challenges for radiologists, artificial intelligence (AI) offers potential solutions to manage this workload. However, the development of AI models is often hindered by manual annotation requirements and strict data-sharing regulations between institutions. Methods In this study, we present an integrated pipeline combining weakly supervised learning—reducing the need for detailed annotations—with local AI model training via swarm learning (SL), which circumvents centralized data sharing. We utilized three datasets comprising 1372 female bilateral breast MRI exams from institutions in three countries: the United States (US), Switzerland, and the United Kingdom (UK) to train models. These models were then validated on two external datasets consisting of 649 bilateral breast MRI exams from Germany and Greece. Results Upon systematically benchmarking various weakly supervised two-dimensional (2D) and three-dimensional (3D) deep learning (DL) methods, we find that the 3D-ResNet-101 demonstrates superior performance. By implementing a real-world SL setup across three international centers, we observe that these collaboratively trained models outperform those trained locally. Even with a smaller dataset, we demonstrate the practical feasibility of deploying SL internationally with on-site data processing, addressing challenges such as data privacy and annotation variability. Conclusions Combining weakly supervised learning with SL enhances inter-institutional collaboration, improving the utility of distributed datasets for medical AI training without requiring detailed annotations or centralized data sharing. |
| Document Type: | Article Other literature type |
| File Description: | application/pdf; application/zip; text/xml |
| Language: | English |
| ISSN: | 2730-664X |
| DOI: | 10.1038/s43856-024-00722-5 |
| Access URL: | https://pubmed.ncbi.nlm.nih.gov/39915630 http://hdl.handle.net/11351/12859 https://doaj.org/article/a1bcf5ae3c6b4dc7a9c39931cc3a78b4 https://hdl.handle.net/https://repository.ubn.ru.nl/handle/2066/317474 https://dspace.library.uu.nl/handle/1874/460712 https://repository.ubn.ru.nl//bitstream/handle/2066/317474/317474.pdf https://hdl.handle.net/2066/317474 |
| Rights: | CC BY |
| Accession Number: | edsair.doi.dedup.....9c3ebdd64aba722f33a52a6e78fb49fd |
| Database: | OpenAIRE |
| ISSN: | 2730664X |
|---|---|
| DOI: | 10.1038/s43856-024-00722-5 |