Machine learning for filtering out false positive grey matter atrophies in single subject voxel based morphometry: A simulation based study

JOURNAL OF THE NEUROLOGICAL SCIENCES

卷:420

Article

Kulsgaard, Hernan C.¹  Orlando, Jose I.¹  Bendersky, Mariana^2,4  Princich, Juan P.²  Manzanera, Luis S. R.³  Vargas, Alberto³  Kochen, Silvia²  Larrabide, Ignacio¹ 

[1] Consejo Nacl Invest Cient & Tecn, Pladema Inst UNICEN, Buenos Aires, DF, Argentina

[2] Consejo Nacl Invest Cient & Tecn, ENyS UNAJ, Buenos Aires, DF, Argentina

[3] Hosp Clin Barcelona, Barcelona, Spain

[4] Univ Buenos Aires, Sch Med, Normal Anat Dept 3, Buenos Aires, DF, Argentina

关键词: Voxel based morphometry;    Magnetic resonance imaging;    Grey matter atrophies;    Machine learning;   

DOI  :  10.1016/j.jns.2020.117220

来源: Elsevier

【 摘 要 】

Single subject VBM (SS-VBM), has been used as an alternative tool to standard VBM for single case studies. However, it has the disadvantage of producing an excessively large number of false positive detections. In this study we propose a machine learning technique widely used for automated data classification, namely Support Vector Machine (SVM), to refine the findings produced by SS-VBM. A controlled set of experiments was conducted to evaluate the proposed approach using three-dimensional T1 MRI scans from control subjects collected from the publicly available IXI dataset. The scans were artificially atrophied at different locations and with different sizes to mimic the behavior of neurological disorders. Results empirically demonstrated that the proposed method is able to significantly reduce the amount of false positive clusters (p < 0.05), with no statistical differences in the true positive findings (p > 0.05). This evidence was observed to be consistent for different atrophied areas and sizes of atrophies. This approach could be potentially be applied to alleviate the intensive manual analysis that radiologists and clinicians have to perform to filter out miss-detections of SS-VBM, increasing its usability for image reading.

【 授权许可】

Free