Philips decision support software assists in FDG-PET scan interpretations
Philips Research reported it has successfully concluded a usability and feasibility study of its decision support software tool for the automatic evaluation of dementia using PET image data.
The software has been evaluated in collaboration with the University Medical Center Hamburg-Eppendorf in Hamburg, Germany, and Austin Hospital in Melbourne, Australia.
Currently, an effective way of diagnosing dementia in its earlier stages is by performing a PET brain scan with FDG. The decision support software has shown positive results in retrospective studies using libraries of FDG-PET brain scan images that had already been independently interpreted by an expert, Philips said.
In a study based on a University Medical Center Hamburg-Eppendorf library of FDG-PET scans from 83 patients, the software achieved more than 98 percent correspondence with the expert physician’s interpretation when programmed to differentiate between brain scans showing no signs of dementia, brain scans characteristic of Alzheimer’s disease and those characteristic of frontotemporal dementia, according to Philips.
In a similar 48-patient study using FDG-PET images provided by the Austin Hospital, the software achieved more than 80 percent accuracy in differentiating between the scans of un-diseased patients, those suffering from Alzheimer’s, those suffering from frontotemporal dementia and those suffering from Lewy body dementia, the company said.
The Philips software analyses PET brain-scan images, and combines them with MRI scans, to detect the characteristic patterns of brain diseases, and then quantifies the degree to which they resemble reference images of known dementia sufferers, Philips said. The University Medical Center Hamburg-Eppendorf in Germany, co-developer of the system, has been using the software alongside its existing diagnostic procedures for the last year to evaluate its feasibility and usability in a clinical setting, the company added.
The software has been evaluated in collaboration with the University Medical Center Hamburg-Eppendorf in Hamburg, Germany, and Austin Hospital in Melbourne, Australia.
Currently, an effective way of diagnosing dementia in its earlier stages is by performing a PET brain scan with FDG. The decision support software has shown positive results in retrospective studies using libraries of FDG-PET brain scan images that had already been independently interpreted by an expert, Philips said.
In a study based on a University Medical Center Hamburg-Eppendorf library of FDG-PET scans from 83 patients, the software achieved more than 98 percent correspondence with the expert physician’s interpretation when programmed to differentiate between brain scans showing no signs of dementia, brain scans characteristic of Alzheimer’s disease and those characteristic of frontotemporal dementia, according to Philips.
In a similar 48-patient study using FDG-PET images provided by the Austin Hospital, the software achieved more than 80 percent accuracy in differentiating between the scans of un-diseased patients, those suffering from Alzheimer’s, those suffering from frontotemporal dementia and those suffering from Lewy body dementia, the company said.
The Philips software analyses PET brain-scan images, and combines them with MRI scans, to detect the characteristic patterns of brain diseases, and then quantifies the degree to which they resemble reference images of known dementia sufferers, Philips said. The University Medical Center Hamburg-Eppendorf in Germany, co-developer of the system, has been using the software alongside its existing diagnostic procedures for the last year to evaluate its feasibility and usability in a clinical setting, the company added.