TY - GEN
T1 - Image processing approach provides robust feature extraction for classification with small sample sizes
AU - Zhakubayev, Alibek
AU - Andersen, Thomas
AU - Vesterby, Annie
AU - Boel, Lene Warner Thorup
AU - Grant, Kathleen
AU - Iwaniec, Urszula
AU - Turner, Russell
AU - Baker, Erich
AU - Benton, Mary Lauren
N1 - Publisher Copyright:
© 2023 ACM.
PY - 2023/5/10
Y1 - 2023/5/10
N2 - Understanding the effects of chronic alcohol consumption on bone architecture is of great clinical importance due to its influence on skeletal health. Medical images contain valuable information for machine learning approaches to classify features relevant to alcohol use; however, the sample sizes are too small for traditional approaches. In this work, we develop a novel image feature extraction technique designed for small image datasets and apply it to analyze the effects of intrinsic (e.g., age, sex) and extrinsic (e.g., alcohol consumption patterns) factors on bone architecture. We train our models using images ascertained from microcomputed tomography on bone samples from humans and non-human primates. We achieve the best performance in both species when distinguishing bones from males and females (72% in macaque, 65.5% in human). We are able to distinguish between drinking and non-drinking individuals with an accuracy of 68% in macaques and 65% in humans, suggesting that our image processing approach is able to capture general biological features across species. Although the effects of alcohol on bone architecture are subtle, we find that they are detectable directly from imaging data.
AB - Understanding the effects of chronic alcohol consumption on bone architecture is of great clinical importance due to its influence on skeletal health. Medical images contain valuable information for machine learning approaches to classify features relevant to alcohol use; however, the sample sizes are too small for traditional approaches. In this work, we develop a novel image feature extraction technique designed for small image datasets and apply it to analyze the effects of intrinsic (e.g., age, sex) and extrinsic (e.g., alcohol consumption patterns) factors on bone architecture. We train our models using images ascertained from microcomputed tomography on bone samples from humans and non-human primates. We achieve the best performance in both species when distinguishing bones from males and females (72% in macaque, 65.5% in human). We are able to distinguish between drinking and non-drinking individuals with an accuracy of 68% in macaques and 65% in humans, suggesting that our image processing approach is able to capture general biological features across species. Although the effects of alcohol on bone architecture are subtle, we find that they are detectable directly from imaging data.
KW - alcohol
KW - bone
KW - machine learning
KW - microcomputed tomography
KW - rhesus macaque
UR - http://www.scopus.com/inward/record.url?scp=85175399951&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85175399951&partnerID=8YFLogxK
U2 - 10.1145/3603765.3603777
DO - 10.1145/3603765.3603777
M3 - Conference contribution
AN - SCOPUS:85175399951
T3 - ACM International Conference Proceeding Series
SP - 82
EP - 89
BT - ICISDM 2023 - 7th International Conference on Information System and Data Mining
PB - Association for Computing Machinery
T2 - 7th International Conference on Information System and Data Mining, ICISDM 2023
Y2 - 10 May 2023 through 12 May 2023
ER -