TY - JOUR
T1 - Exploratory Assessment of K-means Clustering to Classify 18F-Flutemetamol Brain PET as Positive or Negative
AU - Zukotynski, Katherine
AU - Black, Sandra E.
AU - Kuo, Phillip H.
AU - Bhan, Aparna
AU - Adamo, Sabrina
AU - Scott, Christopher J.M.
AU - Lam, Benjamin
AU - Masellis, Mario
AU - Kumar, Sanjeev
AU - Fischer, Corinne E.
AU - Tartaglia, Maria Carmela
AU - Lang, Anthony E.
AU - Tang-Wai, David F.
AU - Freedman, Morris
AU - Vasdev, Neil
AU - Gaudet, Vincent
N1 - Funding Information:
This is a multisite project of the Toronto Dementia Research Alliance (www.tdra.utoronto.ca) partly funded by Brain Canada, The Edward Foundation, the Canadian Institutes of Health Research (FDN 159910), the LC Campbell Cognitive Neurology Research Unit, Sunnybrook Research Institute, and the Dr Sandra Black Centre for Brain Resilience and Recovery. M.F. received support from the Saul A. Silverman Family Foundation as a Canada International Scientific Exchange Program and the Morris Kerzner Memorial Fund. We gratefully acknowledge GE Healthcare and the CAMH Brain Health Imaging Centre for manufacturing and supplying the ligand. We are also grateful to GE Healthcare for providing the software to calculate the brain region of interest SUV ratios. The study protocol, Brain Eye Amyloid Memory study (BEAM), is registered at https://clinicaltrials.gov/ct2/show/NCT02524405? term=beam+sandra+black&rank=1.
Funding Information:
Conflicts of interest and sources of funding: This is a multisite project of the Toronto Dementia Research Alliance partly funded by Brain Canada, The Edward Foundation, the Canadian Institutes of Health Research, the LC Campbell Cognitive Neurology Research Unit, Sunnybrook Research Institute, and the Dr Sandra Black Centre for Brain Resilience and Recovery. Phillip H. Kuo is a consultant for Novartis, Konica Minolta, and Bayer; is a consultant and speaker for Esai and General Electric Healthcare; and received a grant from Blue Earth Diagnostics. The other authors have no conflicts of interest to declare.
Publisher Copyright:
© Wolters Kluwer Health, Inc. All rights reserved.
PY - 2021
Y1 - 2021
N2 - Rationale We evaluated K-means clustering to classify amyloid brain PETs as positive or negative. Patients and Methods Sixty-six participants (31 men, 35 women; age range, 52-81 years) were recruited through a multicenter observational study: 19 cognitively normal, 25 mild cognitive impairment, and 22 dementia (11 Alzheimer disease, 3 subcortical vascular cognitive impairment, and 8 Parkinson-Lewy Body spectrum disorder). As part of the neurocognitive and imaging evaluation, each participant had an 18F-flutemetamol (Vizamyl, GE Healthcare) brain PET. All studies were processed using Cortex ID software (General Electric Company, Boston, MA) to calculate SUV ratios in 19 regions of interest and clinically interpreted by 2 dual-certified radiologists/nuclear medicine physicians, using MIM software (MIM Software Inc, Cleveland, OH), blinded to the quantitative analysis, with final interpretation based on consensus. K-means clustering was retrospectively used to classify the studies from the quantitative data. Results Based on clinical interpretation, 46 brain PETs were negative and 20 were positive for amyloid deposition. Of 19 cognitively normal participants, 1 (5%) had a positive 18F-flutemetamol brain PET. Of 25 participants with mild cognitive impairment, 9 (36%) had a positive 18F-flutemetamol brain PET. Of 22 participants with dementia, 10 (45%) had a positive 18F-flutemetamol brain PET; 7 of 11 participants with Alzheimer disease (64%), 1 of 3 participants with vascular cognitive impairment (33%), and 2 of 8 participants with Parkinson-Lewy Body spectrum disorder (25%) had a positive 18F-flutemetamol brain PET. Using clinical interpretation as the criterion standard, K-means clustering (K = 2) gave sensitivity of 95%, specificity of 98%, and accuracy of 97%. Conclusions K-means clustering may be a powerful algorithm for classifying amyloid brain PET.
AB - Rationale We evaluated K-means clustering to classify amyloid brain PETs as positive or negative. Patients and Methods Sixty-six participants (31 men, 35 women; age range, 52-81 years) were recruited through a multicenter observational study: 19 cognitively normal, 25 mild cognitive impairment, and 22 dementia (11 Alzheimer disease, 3 subcortical vascular cognitive impairment, and 8 Parkinson-Lewy Body spectrum disorder). As part of the neurocognitive and imaging evaluation, each participant had an 18F-flutemetamol (Vizamyl, GE Healthcare) brain PET. All studies were processed using Cortex ID software (General Electric Company, Boston, MA) to calculate SUV ratios in 19 regions of interest and clinically interpreted by 2 dual-certified radiologists/nuclear medicine physicians, using MIM software (MIM Software Inc, Cleveland, OH), blinded to the quantitative analysis, with final interpretation based on consensus. K-means clustering was retrospectively used to classify the studies from the quantitative data. Results Based on clinical interpretation, 46 brain PETs were negative and 20 were positive for amyloid deposition. Of 19 cognitively normal participants, 1 (5%) had a positive 18F-flutemetamol brain PET. Of 25 participants with mild cognitive impairment, 9 (36%) had a positive 18F-flutemetamol brain PET. Of 22 participants with dementia, 10 (45%) had a positive 18F-flutemetamol brain PET; 7 of 11 participants with Alzheimer disease (64%), 1 of 3 participants with vascular cognitive impairment (33%), and 2 of 8 participants with Parkinson-Lewy Body spectrum disorder (25%) had a positive 18F-flutemetamol brain PET. Using clinical interpretation as the criterion standard, K-means clustering (K = 2) gave sensitivity of 95%, specificity of 98%, and accuracy of 97%. Conclusions K-means clustering may be a powerful algorithm for classifying amyloid brain PET.
KW - K-means clustering
KW - brain imaging
KW - dementia
KW - machine learning
KW - unsupervised learning
UR - http://www.scopus.com/inward/record.url?scp=85110627723&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85110627723&partnerID=8YFLogxK
U2 - 10.1097/RLU.0000000000003668
DO - 10.1097/RLU.0000000000003668
M3 - Article
C2 - 33883495
AN - SCOPUS:85110627723
VL - 46
SP - 616
EP - 620
JO - Clinical Nuclear Medicine
JF - Clinical Nuclear Medicine
SN - 0363-9762
IS - 8
ER -