Combined Use of Texture Features and Morphological Classification Based on Dynamic Contrast-enhanced MR Imaging: Differentiating Benign and Malignant Breast Masses with High Negative Predictive Value

• Published in: Magnetic Resonance in Medical Sciences Vol. 21; no. 3; pp. 485 - 498
• Main Authors: Xiao, Qilin, Tozaki, Mitsuhiro, Sasaki, Michiro, Fujisawa, Yasuko, Chiba, Hisae, Sagara, Yoshiaki, Ohyu, Shigeharu
• Format: Journal Article
• Language: English
• Published: Tokyo Japanese Society for Magnetic Resonance in Medicine 01.07.2022; Japan Science and Technology Agency
• Subjects: Benign; benign mass; Breast cancer; Diagnosis; diagnostic performance; Lesions; Magnetic resonance imaging; Major Paper; Texture; texture feature; Thresholds; Training

Purpose: We evaluated the diagnostic performance of the texture features of dynamic contrast-enhanced (DCE) MRI for breast cancer diagnosis in which the discriminator was optimized, so that the specificity was maximized via the restriction of the negative predictive value (NPV) to greater than 98%.M...