دورية أكاديمية
A deep learning image-based intrinsic molecular subtype classifier of breast tumors reveals tumor heterogeneity that may affect survival.
العنوان: | A deep learning image-based intrinsic molecular subtype classifier of breast tumors reveals tumor heterogeneity that may affect survival. |
---|---|
المؤلفون: | Jaber MI; NantOmics LLC, 9920 Jefferson Blvd., Culver City, CA, 90232, USA., Song B; ImmunityBio, 9920 Jefferson Blvd., Culver City, CA, 90232, USA., Taylor C; Department of Pathology, Keck School of Medicine, University of Southern California, HMR 2011 Zonal Ave., Health Sciences Campus, Los Angeles, CA, 90033, USA., Vaske CJ; ImmunityBio, 2901 Mission St. Ext., Santa Cruz, CA, 95066, USA., Benz SC; ImmunityBio, 2901 Mission St. Ext., Santa Cruz, CA, 95066, USA., Rabizadeh S; NantOmics LLC, 9920 Jefferson Blvd., Culver City, CA, 90232, USA.; ImmunityBio, 9920 Jefferson Blvd., Culver City, CA, 90232, USA., Soon-Shiong P; ImmunityBio, 9920 Jefferson Blvd., Culver City, CA, 90232, USA., Szeto CW; ImmunityBio, 2901 Mission St. Ext., Santa Cruz, CA, 95066, USA. Christopher.Szeto@ImmunityBio.com. |
المصدر: | Breast cancer research : BCR [Breast Cancer Res] 2020 Jan 28; Vol. 22 (1), pp. 12. Date of Electronic Publication: 2020 Jan 28. |
نوع المنشور: | Journal Article |
اللغة: | English |
بيانات الدورية: | Publisher: BioMed Central Ltd Country of Publication: England NLM ID: 100927353 Publication Model: Electronic Cited Medium: Internet ISSN: 1465-542X (Electronic) Linking ISSN: 14655411 NLM ISO Abbreviation: Breast Cancer Res Subsets: MEDLINE |
أسماء مطبوعة: | Publication: London, UK : BioMed Central Ltd Original Publication: London, UK : Current Science, c1999- |
مواضيع طبية MeSH: | Deep Learning* , Gene Expression Regulation, Neoplastic*, Biomarkers, Tumor/*genetics , Breast Neoplasms/*mortality , Breast Neoplasms/*pathology , Image Processing, Computer-Assisted/*methods , Molecular Typing/*methods, Breast Neoplasms/classification ; Breast Neoplasms/genetics ; Female ; Humans ; Neoplasm Grading ; Receptor, ErbB-2/metabolism ; Survival Rate |
مستخلص: | Background: Breast cancer intrinsic molecular subtype (IMS) as classified by the expression-based PAM50 assay is considered a strong prognostic feature, even when controlled for by standard clinicopathological features such as age, grade, and nodal status, yet the molecular testing required to elucidate these subtypes is not routinely performed. Furthermore, when such bulk assays as RNA sequencing are performed, intratumoral heterogeneity that may affect prognosis and therapeutic decision-making can be missed. Methods: As a more facile and readily available method for determining IMS in breast cancer, we developed a deep learning approach for approximating PAM50 intrinsic subtyping using only whole-slide images of H&E-stained breast biopsy tissue sections. This algorithm was trained on images from 443 tumors that had previously undergone PAM50 subtyping to classify small patches of the images into four major molecular subtypes-Basal-like, HER2-enriched, Luminal A, and Luminal B-as well as Basal vs. non-Basal. The algorithm was subsequently used for subtype classification of a held-out set of 222 tumors. Results: This deep learning image-based classifier correctly subtyped the majority of samples in the held-out set of tumors. However, in many cases, significant heterogeneity was observed in assigned subtypes across patches from within a single whole-slide image. We performed further analysis of heterogeneity, focusing on contrasting Luminal A and Basal-like subtypes because classifications from our deep learning algorithm-similar to PAM50-are associated with significant differences in survival between these two subtypes. Patients with tumors classified as heterogeneous were found to have survival intermediate between Luminal A and Basal patients, as well as more varied levels of hormone receptor expression patterns. Conclusions: Here, we present a method for minimizing manual work required to identify cancer-rich patches among all multiscale patches in H&E-stained WSIs that can be generalized to any indication. These results suggest that advanced deep machine learning methods that use only routinely collected whole-slide images can approximate RNA-seq-based molecular tests such as PAM50 and, importantly, may increase detection of heterogeneous tumors that may require more detailed subtype analysis. |
References: | IEEE Rev Biomed Eng. 2009;2:147-71. (PMID: 20671804) N Engl J Med. 2016 Sep 22;375(12):1109-12. (PMID: 27653561) Nat Commun. 2016 Aug 16;7:12474. (PMID: 27527408) EBioMedicine. 2018 Jan;27:317-328. (PMID: 29292031) Front Genet. 2019 Feb 19;10:80. (PMID: 30838023) J Pathol. 2019 Apr;247(5):552-562. (PMID: 30426489) Sci Rep. 2017 Apr 18;7:46450. (PMID: 28418027) NPJ Breast Cancer. 2018 Sep 3;4:30. (PMID: 30182055) Clin Cancer Res. 2010 Nov 1;16(21):5222-32. (PMID: 20837693) Nat Commun. 2018 Sep 4;9(1):3588. (PMID: 30181541) Cell. 2015 Oct 8;163(2):506-19. (PMID: 26451490) Clin Cancer Res. 2012 Aug 15;18(16):4465-72. (PMID: 22711706) Arch Pathol Lab Med. 2016 Aug;140(8):815-24. (PMID: 27472240) Brief Bioinform. 2017 Sep 1;18(5):851-869. (PMID: 27473064) Stat Med. 2014 Mar 15;33(6):985-1000. (PMID: 24123069) J Med Imaging (Bellingham). 2017 Oct;4(4):044504. (PMID: 29285517) Nat Med. 2017 Oct 6;23(10):1124-1134. (PMID: 28985214) Womens Health (Lond). 2016 Jan;12(1):103-19. (PMID: 26756229) J Digit Imaging. 2016 Aug;29(4):496-506. (PMID: 26961982) BMC Med Genomics. 2015 Aug 22;8:54. (PMID: 26297356) NPJ Precis Oncol. 2017 Jun 19;1(1):22. (PMID: 29872706) Sci Rep. 2016 Jun 02;6:25696. (PMID: 27254731) Ann Surg Oncol. 2012 Oct;19(10):3257-63. (PMID: 22965266) J Pathol Inform. 2016 Jul 26;7:29. (PMID: 27563488) PLoS One. 2019 Mar 29;14(3):e0214587. (PMID: 30925170) |
فهرسة مساهمة: | Keywords: Breast cancer; Deep learning algorithm; Intrinsic molecular subtype (IMS); Whole-slide imaging (WSI) |
المشرفين على المادة: | 0 (Biomarkers, Tumor) EC 2.7.10.1 (ERBB2 protein, human) EC 2.7.10.1 (Receptor, ErbB-2) |
تواريخ الأحداث: | Date Created: 20200130 Date Completed: 20201001 Latest Revision: 20231113 |
رمز التحديث: | 20231215 |
مُعرف محوري في PubMed: | PMC6988279 |
DOI: | 10.1186/s13058-020-1248-3 |
PMID: | 31992350 |
قاعدة البيانات: | MEDLINE |
تدمد: | 1465-542X |
---|---|
DOI: | 10.1186/s13058-020-1248-3 |