结合深度学习和手工制造的放射学来对对比度增强的乳房图进行可疑病变的分类

Manon P L Beuque1, Marc B I Lobbes1, Yvonka van Wijk1

  • 1From the Department of Precision Medicine (M.P.L.B., Y.v.W., Y.W., S.P., H.C.W., P.L.) and Department of Radiology and Nuclear Medicine (M.B.I.L.), GROW School for Oncology and Reproduction, Maastricht University, Universiteitssingel 40, 6229 ER Maastricht, the Netherlands; Department of Radiology and Nuclear Medicine, Maastricht University Medical Center, Maastricht, the Netherlands (M.B.I.L., H.C.W., P.L.); Department of Medical Imaging, Zuyderland Medical Center, Sittard-Geleen, the Netherlands (M.B.I.L.); Department of Imaging, Institut Gustave Roussy, Université Paris Saclay, Villejuif, France (M.M., C.B.); and Biomaps, UMR1281 INSERM, CEA, CNRS, Université Paris-Saclay, Villejuif, France (C.B.).

Radiology
|June 20, 2023
PubMed
概括

一个新的深度学习 (DL) 工具准确地识别和细分对比度增强乳房扫描 (CEM) 图像上的乳房病变. 将DL与手工制作的放射学相结合,可显著提高诊断性能,用于分类恶性与良性病变.