Meeting Banner
Abstract #4078

MRI-based radiomic features and machine learning for differentiating myelodysplastic syndrome and aplastic anemia

Miyuki Takasu1, Makoto Iida1, Yasutaka Baba2, Yuji Akiyama1, Yuji Takahashi1, Takashi Abe3, and Kazuo Awai1
1Department of Diagnostic Radiology, Hiroshima University Hospital, Hiroshima, Japan, 2Department of Radiology, International Medical Center, Saitama Medical University, Saitama, Japan, 3Department of Radiology, Nagoya University Hospital, Aichi, Japan, Nagoya, Japan

We assessed the feasibility of a method of radiomic analysis based on machine learning (ML) and lumbar MRI to differentiate between MDS and aplastic anemia (AA). Regions of interest were drawn in the L3 vertebral body on the mid-sagittal images of sagittal T1-weighted and STIR images of patients with MDS (n=62) or AA (n=78) from six institutions. The model of ML with logistic regression resulted in the best performance for differentiating MDS from AA when using T1-weighted images. The model was not predictive for STIR or concatenated images. The radiomics-based ML model enabled the differentiation of MDS and AA.

This abstract and the presentation materials are available to members only; a login is required.

Join Here