دورية أكاديمية
Application of convolutional neural networks to breast biopsies to delineate tissue correlates of mammographic breast density.
العنوان: | Application of convolutional neural networks to breast biopsies to delineate tissue correlates of mammographic breast density. |
---|---|
المؤلفون: | Mullooly M; 1Division of Population Health Sciences, Royal College of Surgeons in Ireland, Dublin, Ireland.; 2Division of Cancer Epidemiology and Genetics, National Cancer Institute, Bethesda, MD USA., Ehteshami Bejnordi B; 3Department of Pathology, Radboud University Medical Center Nijmegen, Nijmegen, the Netherlands.; 4Beth Israel Deaconess Medical Center, Harvard Medical School, Boston, MA USA., Pfeiffer RM; 2Division of Cancer Epidemiology and Genetics, National Cancer Institute, Bethesda, MD USA., Fan S; 2Division of Cancer Epidemiology and Genetics, National Cancer Institute, Bethesda, MD USA., Palakal M; 2Division of Cancer Epidemiology and Genetics, National Cancer Institute, Bethesda, MD USA., Hada M; 2Division of Cancer Epidemiology and Genetics, National Cancer Institute, Bethesda, MD USA., Vacek PM; 5University of Vermont and University of Vermont Cancer Center, Burlington, VT USA., Weaver DL; 5University of Vermont and University of Vermont Cancer Center, Burlington, VT USA., Shepherd JA; 6University of California, San Francisco, San Francisco, CA USA.; 7University of Hawaii Cancer Center, Honolulu, HI USA., Fan B; 6University of California, San Francisco, San Francisco, CA USA., Mahmoudzadeh AP; 6University of California, San Francisco, San Francisco, CA USA., Wang J; 8Department of Radiation Medicine, Hokkaido University Graduate School of Medicine, Sapporo, Hokkaido, Japan., Malkov S; 6University of California, San Francisco, San Francisco, CA USA., Johnson JM; 9The University of Texas MD Anderson Cancer Center, Houston, TX USA., Herschorn SD; 5University of Vermont and University of Vermont Cancer Center, Burlington, VT USA., Sprague BL; 5University of Vermont and University of Vermont Cancer Center, Burlington, VT USA., Hewitt S; 10Center for Cancer Research, National Cancer Institute, Bethesda, MD USA., Brinton LA; 2Division of Cancer Epidemiology and Genetics, National Cancer Institute, Bethesda, MD USA., Karssemeijer N; 3Department of Pathology, Radboud University Medical Center Nijmegen, Nijmegen, the Netherlands., van der Laak J; 3Department of Pathology, Radboud University Medical Center Nijmegen, Nijmegen, the Netherlands., Beck A; 4Beth Israel Deaconess Medical Center, Harvard Medical School, Boston, MA USA., Sherman ME; 11Mayo Clinic, Jacksonville, FL USA., Gierach GL; 2Division of Cancer Epidemiology and Genetics, National Cancer Institute, Bethesda, MD USA. |
المصدر: | NPJ breast cancer [NPJ Breast Cancer] 2019 Nov 19; Vol. 5, pp. 43. Date of Electronic Publication: 2019 Nov 19 (Print Publication: 2019). |
نوع المنشور: | Journal Article |
اللغة: | English |
بيانات الدورية: | Publisher: Breast Cancer Research Foundation Country of Publication: United States NLM ID: 101674891 Publication Model: eCollection Cited Medium: Print ISSN: 2374-4677 (Print) Linking ISSN: 23744677 NLM ISO Abbreviation: NPJ Breast Cancer Subsets: PubMed not MEDLINE |
أسماء مطبوعة: | Original Publication: New York, NY : Breast Cancer Research Foundation : Nature Publishing Group, [2015]- |
مستخلص: | Breast density, a breast cancer risk factor, is a radiologic feature that reflects fibroglandular tissue content relative to breast area or volume. Its histology is incompletely characterized. Here we use deep learning approaches to identify histologic correlates in radiologically-guided biopsies that may underlie breast density and distinguish cancer among women with elevated and low density. We evaluated hematoxylin and eosin (H&E)-stained digitized images from image-guided breast biopsies ( n = 852 patients). Breast density was assessed as global and localized fibroglandular volume (%). A convolutional neural network characterized H&E composition. In total 37 features were extracted from the network output, describing tissue quantities and morphological structure. A random forest regression model was trained to identify correlates most predictive of fibroglandular volume ( n = 588). Correlations between predicted and radiologically quantified fibroglandular volume were assessed in 264 independent patients. A second random forest classifier was trained to predict diagnosis (invasive vs. benign); performance was assessed using area under receiver-operating characteristics curves (AUC). Using extracted features, regression models predicted global ( r = 0.94) and localized ( r = 0.93) fibroglandular volume, with fat and non-fatty stromal content representing the strongest correlates, followed by epithelial organization rather than quantity. For predicting cancer among high and low fibroglandular volume, the classifier achieved AUCs of 0.92 and 0.84, respectively, with epithelial organizational features ranking most important. These results suggest non-fatty stroma, fat tissue quantities and epithelial region organization predict fibroglandular volume. The model holds promise for identifying histological correlates of cancer risk in patients with high and low density and warrants further evaluation. Competing Interests: Competing interestsThe following authors have competing interests to disclose: Dr. Andrew Beck is an employee and equity holder of PathAI. Dr. Sally D. Herschorn is on the Medical Advisory Board of DenseBreast-Info.org, an education coalition about breast density. Dr. Jeroen van der Laak is member of the scientific advisory board of Philips, the Netherlands, is a member of the scientific advisory board of ContextVision, Sweden, has received research funding from Philips, the Netherlands and research funding from Sectra, Sweden. Dr Nico Karssemeijer reported receiving holding shares in Volpara Solutions, QView Medical, and ScreenPoint Medical BV; consulting fees from QView Medical; and being an employee of ScreenPoint Medical BV. Remaining authors have no competing interests. (© This is a U.S. government work and not under copyright protection in the U.S.; foreign copyright protection may apply 2019.) |
References: | Sci Rep. 2016 May 23;6:26286. (PMID: 27212078) Nature. 2015 May 28;521(7553):436-44. (PMID: 26017442) Med Phys. 2009 Dec;36(12):5525-36. (PMID: 20095265) J Med Imaging (Bellingham). 2017 Oct;4(4):044504. (PMID: 29285517) Breast Cancer Res. 2005;7(5):R605-8. (PMID: 16168104) J Natl Cancer Inst. 2020 Mar 1;112(3):278-285. (PMID: 31165158) Cancer Epidemiol Biomarkers Prev. 2011 Aug;20(8):1718-25. (PMID: 21693627) Sci Rep. 2017 Apr 18;7:46450. (PMID: 28418027) BMC Bioinformatics. 2011 Mar 17;12:77. (PMID: 21414208) PLoS One. 2014 Dec 09;9(12):e114885. (PMID: 25490766) Acad Radiol. 2018 Aug;25(8):977-984. (PMID: 29395798) PLoS One. 2017 Jun 1;12(6):e0177544. (PMID: 28570557) CA Cancer J Clin. 2018 Nov;68(6):394-424. (PMID: 30207593) J Natl Cancer Inst. 2014 Sep 12;106(10):. (PMID: 25217577) Cancer Epidemiol Biomarkers Prev. 2005 Feb;14(2):343-9. (PMID: 15734956) Breast Cancer Res. 2016 Jan 08;18(1):5. (PMID: 26747277) Cancer Epidemiol Biomarkers Prev. 2014 Nov;23(11):2338-48. (PMID: 25139935) NPJ Breast Cancer. 2019 Nov 19;5:43. (PMID: 31754628) JAMA. 2017 Dec 12;318(22):2199-2210. (PMID: 29234806) Mod Pathol. 2018 Oct;31(10):1502-1512. (PMID: 29899550) Clin Cancer Res. 2013 Sep 15;19(18):4972-4982. (PMID: 23918601) Breast Cancer Res. 2016 Aug 23;18(1):88. (PMID: 27552842) J Natl Cancer Inst. 2014 May 10;106(5):. (PMID: 24816206) Cancer Epidemiol Biomarkers Prev. 2006 Jun;15(6):1159-69. (PMID: 16775176) Lab Invest. 2015 Apr;95(4):377-84. (PMID: 25599534) Cancer Prev Res (Phila). 2016 Feb;9(2):149-58. (PMID: 26645278) Med Image Anal. 2017 Dec;42:60-88. (PMID: 28778026) Nat Rev Cancer. 2009 Feb;9(2):108-22. (PMID: 19165226) J Clin Oncol. 2015 Oct 1;33(28):3137-43. (PMID: 26282663) Sci Transl Med. 2011 Nov 9;3(108):108ra113. (PMID: 22072638) Cancer Epidemiol Biomarkers Prev. 2011 Jul;20(7):1473-82. (PMID: 21610220) Breast Cancer Res Treat. 2014 Apr;144(3):479-502. (PMID: 24615497) |
معلومات مُعتمدة: | U01 CA196383 United States CA NCI NIH HHS |
فهرسة مساهمة: | Keywords: Cancer epidemiology; Cancer prevention |
تواريخ الأحداث: | Date Created: 20191123 Latest Revision: 20240722 |
رمز التحديث: | 20240722 |
مُعرف محوري في PubMed: | PMC6864056 |
DOI: | 10.1038/s41523-019-0134-6 |
PMID: | 31754628 |
قاعدة البيانات: | MEDLINE |
تدمد: | 2374-4677 |
---|---|
DOI: | 10.1038/s41523-019-0134-6 |