Detection Of Neurological Conditions And White Matter Pathologies by Delphitm

Brain tumor segmentation using Magnetic Resonance (MR) Imaging technology plays a significant role in computer-aided brain tumor diagnosis. However, when applying classic segmentation methods, limitations such as inhomogeneous intensity, complex physiological structure and blurred tissues boundaries in brain MR images usually lead to unsatisfactory results. DELPHITM is an active system for the visualization of brain health. It is a proprietary acquisition and analysis AI based algorithm that interfaces with available â??Off-the-Shelfâ?? hardware to enable direct stimulation and monitoring of the brain (TMS-EEG). DELPHIâ??soutput measures, which areindicative for several electrophysiological features were significantly different between age defined groups as well as mild Dementia patients and age matched healthy controls. In a multidimensional approach the DELPHIoutput measures ability in identification of brain white matter fibres connectivity damage in stroke and traumatic brain injury (TBI) was tested. DELPHI output measures were able to classify healthy from unhealthy with a balanced accuracy of 0.81±0.02and AUC of 0.88±0.01. additionally, DELPHI output measures, differentiated successfully, between cerebral small vessle disease (cSVD) diagnosed subjects and age matched healthy controls, with AUC of 0.88 (p<0.0001), sensitivity of 0.83 and specificity of 0.75. These results indicate DELPHI as a possible aid for early detection of white matter integrity and pathologies.
Author(s): Dolev Iftach

Abstract | PDF

Share This Article