دورية أكاديمية
Semi-Supervised Learning to Automate Tumor Bud Detection in Cytokeratin-Stained Whole-Slide Images of Colorectal Cancer.
العنوان: | Semi-Supervised Learning to Automate Tumor Bud Detection in Cytokeratin-Stained Whole-Slide Images of Colorectal Cancer. |
---|---|
المؤلفون: | Bokhorst JM; Department of Pathology, Radboud University Medical Center, 6525 GA Nijmegen, The Netherlands., Nagtegaal ID; Department of Pathology, Radboud University Medical Center, 6525 GA Nijmegen, The Netherlands., Zlobec I; Institute of Tissue Medicine and Pathology, University of Bern, 3008 Bern, Switzerland., Dawson H; Institute of Tissue Medicine and Pathology, University of Bern, 3008 Bern, Switzerland., Sheahan K; UCD School of Medicine, St. Vincent's University Hospital, D04 T6F4 Dublin, Ireland., Simmer F; Department of Pathology, Radboud University Medical Center, 6525 GA Nijmegen, The Netherlands., Kirsch R; Division of Pathology and Lab Medicine, University of Toronto, Toronto, ON M5S 1X5, Canada., Vieth M; Klinikum Bayreuth, Friedrich-Alexander-University Erlangen-Nuremberg, 91054 Bayreuth, Germany., Lugli A; Institute of Tissue Medicine and Pathology, University of Bern, 3008 Bern, Switzerland., van der Laak J; Department of Pathology, Radboud University Medical Center, 6525 GA Nijmegen, The Netherlands.; Center for Medical Image Science and Visualization, Linköping University, 581 83 Linköping, Sweden., Ciompi F; Department of Pathology, Radboud University Medical Center, 6525 GA Nijmegen, The Netherlands. |
المصدر: | Cancers [Cancers (Basel)] 2023 Mar 30; Vol. 15 (7). Date of Electronic Publication: 2023 Mar 30. |
نوع المنشور: | Journal Article |
اللغة: | English |
بيانات الدورية: | Publisher: MDPI Country of Publication: Switzerland NLM ID: 101526829 Publication Model: Electronic Cited Medium: Print ISSN: 2072-6694 (Print) Linking ISSN: 20726694 NLM ISO Abbreviation: Cancers (Basel) Subsets: PubMed not MEDLINE |
أسماء مطبوعة: | Original Publication: Basel, Switzerland : MDPI |
مستخلص: | Tumor budding is a histopathological biomarker associated with metastases and adverse survival outcomes in colorectal carcinoma (CRC) patients. It is characterized by the presence of single tumor cells or small clusters of cells within the tumor or at the tumor-invasion front. In order to obtain a tumor budding score for a patient, the region with the highest tumor bud density must first be visually identified by a pathologist, after which buds will be counted in the chosen hotspot field. The automation of this process will expectedly increase efficiency and reproducibility. Here, we present a deep learning convolutional neural network model that automates the above procedure. For model training, we used a semi-supervised learning method, to maximize the detection performance despite the limited amount of labeled training data. The model was tested on an independent dataset in which human- and machine-selected hotspots were mapped in relation to each other and manual and machine detected tumor bud numbers in the manually selected fields were compared. We report the results of the proposed method in comparison with visual assessment by pathologists. We show that the automated tumor bud count achieves a prognostic value comparable with visual estimation, while based on an objective and reproducible quantification. We also explore novel metrics to quantify buds such as density and dispersion and report their prognostic value. We have made the model available for research use on the grand-challenge platform. |
References: | Nat Rev Clin Oncol. 2021 Feb;18(2):101-115. (PMID: 32901132) Mod Pathol. 2018 Jun;31(6):862-872. (PMID: 29403085) Inform Med Unlocked. 2020;20:100405. (PMID: 32835082) Anal Quant Cytol Histol. 2001 Aug;23(4):291-9. (PMID: 11531144) Diagn Pathol. 2018 Aug 28;13(1):64. (PMID: 30153844) Med Image Anal. 2019 Dec;58:101544. (PMID: 31466046) J Med Syst. 2019 Dec 18;44(2):38. (PMID: 31853654) Mod Pathol. 2020 May;33(5):825-833. (PMID: 31844269) Histopathology. 2021 Sep;79(3):391-405. (PMID: 33590485) J Clin Med. 2020 Mar 10;9(3):. (PMID: 32164298) Histopathology. 2021 Mar;78(4):476-484. (PMID: 33001500) Histopathology. 2022 Feb;80(3):485-500. (PMID: 34580909) Mod Pathol. 2017 Sep;30(9):1299-1311. (PMID: 28548122) Virchows Arch. 2021 Sep;479(3):459-469. (PMID: 33650042) |
معلومات مُعتمدة: | 10602/2016-2 Dutch Cancer Society; KFS-4427-02-2018 Swiss cancer Research foundation; KUN 2014-7032 Dutch Cancer Society; 825292 European Union's Horizon 2020 research and innovation programme |
فهرسة مساهمة: | Keywords: colorectal carcinoma; computational pathology; deep learning; object detection; tumor budding |
تواريخ الأحداث: | Date Created: 20230413 Latest Revision: 20230415 |
رمز التحديث: | 20230415 |
مُعرف محوري في PubMed: | PMC10093661 |
DOI: | 10.3390/cancers15072079 |
PMID: | 37046742 |
قاعدة البيانات: | MEDLINE |
تدمد: | 2072-6694 |
---|---|
DOI: | 10.3390/cancers15072079 |