Fig 2 - uploaded by Junshen Xu
Content may be subject to copyright.
Source publication
Fetal brain MRI is useful for diagnosing brain abnormalities but is challenged by fetal motion. The current protocol for T2-weighted fetal brain MRI is not robust to motion so image volumes are degraded by inter- and intra- slice motion artifacts. Besides, manual annotation for fetal MR image quality assessment are usually time-consuming. Therefore...
Contexts in source publication
Context 1
... set of 11223 images from 42 subjects are selected as labeled set and classified into three categories: diagnostic (D), non-diagnostic (N) and images without brain region of interest (W). Diagnostic images were characterized by sharp brain boundaries while non-diagnostic images were characterized by artifacts that occlude such features (Fig. 2). Motion artifacts manifest as signal void and blurring over the brain region. Other artifacts manifest as aliasing or the fetus not being in the field of view. A research assistant trained under radiologists labeled the dataset. The labeled dataset is divided into training (7717 images), validation (1782 images), and test (1724 images) ...
Context 2
... set of 11223 images from 42 subjects are selected as labeled set and classified into three categories: diagnostic (D), non-diagnostic (N) and images without brain region of interest (W). Diagnostic images were characterized by sharp brain boundaries while non-diagnostic images were characterized by artifacts that occlude such features (Fig. 2). Motion artifacts manifest as signal void and blurring over the brain region. Other artifacts manifest as aliasing or the fetus not being in the field of view. A research assistant trained under radiologists labeled the dataset. The labeled dataset is divided into training (7717 images), validation (1782 images), and test (1724 images) ...
