TY - JOUR
T1 - Radiomics-based machine learning (ML) classifier for detection of type 2 diabetes on standard-of-care abdomen CTs
T2 - a proof-of-concept study
AU - Wright, Darryl E.
AU - Mukherjee, Sovanlal
AU - Patra, Anurima
AU - Khasawneh, Hala
AU - Korfiatis, Panagiotis
AU - Suman, Garima
AU - Chari, Suresh T.
AU - Kudva, Yogish C.
AU - Kline, Timothy L.
AU - Goenka, Ajit H.
N1 - Publisher Copyright:
© 2022, The Author(s), under exclusive licence to Springer Science+Business Media, LLC, part of Springer Nature.
PY - 2022/11
Y1 - 2022/11
N2 - Purpose: To determine if pancreas radiomics-based AI model can detect the CT imaging signature of type 2 diabetes (T2D). Methods: Total 107 radiomic features were extracted from volumetrically segmented normal pancreas in 422 T2D patients and 456 age-matched controls. Dataset was randomly split into training (300 T2D, 300 control CTs) and test subsets (122 T2D, 156 control CTs). An XGBoost model trained on 10 features selected through top-K-based selection method and optimized through threefold cross-validation on training subset was evaluated on test subset. Results: Model correctly classified 73 (60%) T2D patients and 96 (62%) controls yielding F1-score, sensitivity, specificity, precision, and AUC of 0.57, 0.62, 0.61, 0.55, and 0.65, respectively. Model’s performance was equivalent across gender, CT slice thicknesses, and CT vendors (p values > 0.05). There was no difference between correctly classified versus misclassified patients in the mean (range) T2D duration [4.5 (0–15.4) versus 4.8 (0–15.7) years, p = 0.8], antidiabetic treatment [insulin (22% versus 18%), oral antidiabetics (10% versus 18%), both (41% versus 39%) (p > 0.05)], and treatment duration [5.4 (0–15) versus 5 (0–13) years, p = 0.4]. Conclusion: Pancreas radiomics-based AI model can detect the imaging signature of T2D. Further refinement and validation are needed to evaluate its potential for opportunistic T2D detection on millions of CTs that are performed annually.
AB - Purpose: To determine if pancreas radiomics-based AI model can detect the CT imaging signature of type 2 diabetes (T2D). Methods: Total 107 radiomic features were extracted from volumetrically segmented normal pancreas in 422 T2D patients and 456 age-matched controls. Dataset was randomly split into training (300 T2D, 300 control CTs) and test subsets (122 T2D, 156 control CTs). An XGBoost model trained on 10 features selected through top-K-based selection method and optimized through threefold cross-validation on training subset was evaluated on test subset. Results: Model correctly classified 73 (60%) T2D patients and 96 (62%) controls yielding F1-score, sensitivity, specificity, precision, and AUC of 0.57, 0.62, 0.61, 0.55, and 0.65, respectively. Model’s performance was equivalent across gender, CT slice thicknesses, and CT vendors (p values > 0.05). There was no difference between correctly classified versus misclassified patients in the mean (range) T2D duration [4.5 (0–15.4) versus 4.8 (0–15.7) years, p = 0.8], antidiabetic treatment [insulin (22% versus 18%), oral antidiabetics (10% versus 18%), both (41% versus 39%) (p > 0.05)], and treatment duration [5.4 (0–15) versus 5 (0–13) years, p = 0.4]. Conclusion: Pancreas radiomics-based AI model can detect the imaging signature of T2D. Further refinement and validation are needed to evaluate its potential for opportunistic T2D detection on millions of CTs that are performed annually.
KW - Artificial intelligence
KW - Pancreas
KW - Type 2 diabetes mellitus
KW - X-ray computed tomography
UR - http://www.scopus.com/inward/record.url?scp=85137819728&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85137819728&partnerID=8YFLogxK
U2 - 10.1007/s00261-022-03668-1
DO - 10.1007/s00261-022-03668-1
M3 - Article
C2 - 36085379
AN - SCOPUS:85137819728
SN - 2366-004X
VL - 47
SP - 3806
EP - 3816
JO - Abdominal Radiology
JF - Abdominal Radiology
IS - 11
ER -