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.

How to access this content:

For one year after publication, abstracts and videos are only open to registrants of this annual meeting. Registrants should use their existing login information. Non-registrant access can be purchased via the ISMRM E-Library.

After one year, current ISMRM & ISMRT members get free access to both the abstracts and videos. Non-members and non-registrants must purchase access via the ISMRM E-Library.

After two years, the meeting proceedings (abstracts) are opened to the public and require no login information. Videos remain behind password for access by members, registrants and E-Library customers.

Click here for more information on becoming a member.