Quantitative diagnosis of breast tumors by morphometric classification of microenvironmental myoepithelial cells using a machine learning approach

• Verfasst von: Yamamoto, Yoichiro [VerfasserIn]
• Verfasst von: Rojas-Moraleda, Rodrigo [VerfasserIn]
• Verfasst von: Eils, Roland [VerfasserIn]
• Verfasst von: Grabe, Niels [VerfasserIn]
• Titel: Quantitative diagnosis of breast tumors by morphometric classification of microenvironmental myoepithelial cells using a machine learning approach
• Verf.angabe: Yoichiro Yamamoto, Akira Saito, Ayako Tateishi, Hisashi Shimojo, Hiroyuki Kanno, Shinichi Tsuchiya, Ken-ichi Ito, Eric Cosatto, Hans Peter Graf, Rodrigo R. Moraleda, Roland Eils & Niels Grabe
• E-Jahr: 2017
• Jahr: 25 April 2017
• Umfang: 12 S.
• Teil: volume:7
• Teil: year:2017
• Teil: elocationid:46732
• Teil: extent:12
• Fussnoten: Gesehen am 22.10.2018
• Titel Quelle: Enthalten in: Scientific reports
• Ort Quelle: [London] : Macmillan Publishers Limited, part of Springer Nature, 2011
• Jahr Quelle: 2017
• Band/Heft Quelle: 7(2017), Artikel-ID 46732
• ISSN Quelle: 2045-2322
• DOI: doi:10.1038/srep46732
• Datenträger: Online-Ressource
• Sprache: eng
• K10plus-PPN: 1582174466

Abstract

Machine learning systems have recently received increased attention for their broad applications in several fields. In this study, we show for the first time that histological types of breast tumors can be classified using subtle morphological differences of microenvironmental myoepithelial cell nuclei without any direct information about neoplastic tumor cells. We quantitatively measured 11661 nuclei on the four histological types: normal cases, usual ductal hyperplasia and low/high grade ductal carcinoma in situ (DCIS). Using a machine learning system, we succeeded in classifying the four histological types with 90.9% accuracy. Electron microscopy observations suggested that the activity of typical myoepithelial cells in DCIS was lowered. Through these observations as well as meta-analytic database analyses, we developed a paracrine cross-talk-based biological mechanism of DCIS progressing to invasive cancer. Our observations support novel approaches in clinical computational diagnostics as well as in therapy development against progression.