Multiple Instance Learning for Lymph Node Metastasis Prediction from Cervical Cancer MRI
Jin, S., Xu, H., Dong, Y., Hao, X., Qin, F., Wang, R., & Cong, F. (2023). Multiple Instance Learning for Lymph Node Metastasis Prediction from Cervical Cancer MRI. In 2023 IEEE 20th International Symposium on Biomedical Imaging (ISBI). IEEE. International Symposium on Biomedical Imaging. https://doi.org/10.1109/isbi53787.2023.10230666
Published in
International Symposium on Biomedical ImagingAuthors
Date
2023Discipline
Secure Communications Engineering and Signal ProcessingTekniikkaTietotekniikkaSecure Communications Engineering and Signal ProcessingEngineeringMathematical Information TechnologyAccess restrictions
Embargoed until: 2025-04-18Request copy from author
Copyright
© 2023, IEEE
Lymph node metastasis (LNM) is an important prognostic factor for recurrence and overall survival of cancer patients. The current LNM diagnosis is based on histopathologic examination after surgical lymphadenectomy, but an accurate and noninvasive method for LNM diagnosis is essential in selecting reasonable surgical operations and treatment plans. This paper presents an attention based multiple instance learning (MIL) model to diagnose LNM from cervical cancer multimodal MRI. The proposed MIL model adopts convolutional neural network (CNN) to extract features from multimodal MRI and attention-based pooling to make patient-level LNM status prediction. By incorporating the MIL and attention mechanism, the top rank MRI slice with informative regions in each LNM positive patient is visualized to provide the interpretability for LNM diagnosis. Experiments evaluated on a cohort of 241 cervical cancer patients show improvements in LNM status prediction compared with existing comparative models, which indicates the advantages of our designed model.
...
Publisher
IEEEParent publication ISBN
978-1-6654-7359-0Conference
IEEE International Symposium on Biomedical ImagingIs part of publication
2023 IEEE 20th International Symposium on Biomedical Imaging (ISBI)ISSN Search the Publication Forum
1945-7928Keywords
Publication in research information system
https://converis.jyu.fi/converis/portal/detail/Publication/184618753
Metadata
Show full item recordCollections
Additional information about funding
This work was supported by the National Key Research and Development Program of China (2022YFC3902100) and the Fundamental Research Funds for the Central Universities (DUT21YG135).License
Related items
Showing items with similar title or keywords.
-
Tertiary lymphoid structures in pulmonary metastases of microsatellite stable colorectal cancer
Karjula, Topias; Niskakangas, Anne; Mustonen, Olli; Puro, Iiris; Elomaa, Hanna; Ahtiainen, Maarit; Kuopio, Teijo; Mecklin, Jukka-Pekka; Seppälä, Toni T.; Wirta, Erkki-Ville; Sihvo, Eero; Yannopoulos, Fredrik; Helminen, Olli; Väyrynen, Juha P. (Springer, 2023)Tertiary lymphoid structures (TLSs) are ectopic lymphoid aggregates located at sites of chronic inflammation and recognized as prognosticators in several cancers. We aimed to analyse the prognostic effect of TLSs in ... -
Resectability, conversion, metastasectomy and outcome according to RAS and BRAF status for metastatic colorectal cancer in the prospective RAXO study
Uutela, Aki; Osterlund, Emerik; Halonen, Päivi; Kallio, Raija; Ålgars, Annika; Salminen, Tapio; Lamminmäki, Annamarja; Soveri, Leena-Maija; Ristamäki, Raija; Lehtomäki, Kaisa; Stedt, Hanna; Heervä, Eetu; Muhonen, Timo; Kononen, Juha; Nordin, Arno; Ovissi, Ali; Kytölä, Soili; Keinänen, Mauri; Sundström, Jari; Nieminen, Lasse; Mäkinen, Markus J.; Kuopio, Teijo; Ristimäki, Ari; Isoniemi, Helena; Osterlund, Pia (Nature Publishing Group, 2022)Background Outcomes after metastasectomy for metastatic colorectal cancer (mCRC) vary with RAS and BRAF mutational status, but their effects on resectability and conversion rates have not been extensively studied. Me ... -
Robustness, Stability, and Fidelity of Explanations for a Deep Skin Cancer Classification Model
Saarela, Mirka; Geogieva, Lilia (MDPI AG, 2022)Skin cancer is one of the most prevalent of all cancers. Because of its being widespread and externally observable, there is a potential that machine learning models integrated into artificial intelligence systems will ... -
Lack of association between screening interval and cancer stage in Lynch syndrome may be accounted for by over-diagnosis; a prospective Lynch syndrome database report
Seppälä, Toni T.; Ahadova, Aysel; Dominguez-Valentin, Mev; Macrae, Finlay; Evans, D. Gareth; Therkildsen, Christina; Sampson, Julian; Scott, Rodney; Burn, John; Möslein, Gabriela; Bernstein, Inge; Holinski-Feder, Elke; Pylvänäinen, Kirsi; Renkonen-Sinisalo, Laura; Lepistö, Anna; Lautrup, Charlotte Kvist; Lindblom, Annika; Plazzer, John-Paul; Winship, Ingrid; Tjandra, Douglas; Katz, Lior H.; Aretz, Stefan; Hüneburg, Robert; Holzapfel, Stefanie; Heinimann, Karl; Valle, Adriana Della; Neffa, Florencia; Gluck, Nathan; Cappel, Wouter H. de Vos tot Nederveen; Vasen, Hans; Morak, Monika; Steinke-Lange, Verena; Engel, Christoph; Rahner, Nils; Schmiegel, Wolff; Vangala, Deepak; Thomas, Huw; Green, Kate; Lalloo, Fiona; Crosbie, Emma J.; Hill, James; Capella, Gabriel; Pineda, Marta; Navarro, Matilde; Blanco, Ignacio; Broeke, Sanne ten; Nielsen, Maartje; Ljungmann, Ken; Nakken, Sigve; Lindor, Noralane; Frayling, Ian; Hovig, Eivind; Sunde, Lone; Kloor, Matthias; Mecklin, Jukka-Pekka; Kalager, Mette; Møller, Pål (BioMed Central Ltd., 2019)Background Recent epidemiological evidence shows that colorectal cancer (CRC) continues to occur in carriers of pathogenic mismatch repair (path_MMR) variants despite frequent colonoscopy surveillance in expert centres. ... -
MIHIC: a multiplex IHC histopathological image classification dataset for lung cancer immune microenvironment quantification
Wang, Ranran; Qiu, Yusong; Wang, Tong; Wang, Mingkang; Jin, Shan; Cong, Fengyu; Zhang, Yong; Xu, Hongming (Frontiers Media, 2024)Background: Immunohistochemistry (IHC) is a widely used laboratory technique for cancer diagnosis, which selectively binds specific antibodies to target proteins in tissue samples and then makes the bound proteins visible ...