Cluster analysis of autoencoder-extracted FDG PET/CT features identifies multiple myeloma patients with poor prognosis

• Published in: Scientific reports Vol. 13; no. 1; pp. 7881 - 12
• Main Authors: Lee, Hyunjong, Hyun, Seung Hyup, Cho, Young Seok, Moon, Seung Hwan, Choi, Joon Young, Kim, Kihyun, Lee, Kyung-Han
• Format: Journal Article
• Language: English
• Published: London Nature Publishing Group UK 15.05.2023; Nature Publishing Group; Nature Portfolio
• Subjects: 692/4028; 692/4028/67/1990; 692/4028/67/2321; Algorithms; Artificial Intelligence; Cluster Analysis; Computed tomography; Fluorodeoxyglucose F18; Humanities and Social Sciences; Humans; Medical prognosis; multidisciplinary; Multiple myeloma; Multiple Myeloma - diagnostic imaging; Multiple Myeloma - metabolism; Positron emission tomography; Positron Emission Tomography Computed Tomography - methods; Prognosis; Radiopharmaceuticals; Regression analysis; Retrospective Studies; Science; Science (multidisciplinary); Survival; Tomography; Tumor Burden
• ISSN: 2045-2322; 2045-2322
• DOI: 10.1038/s41598-023-34653-3

F-18 fluorodeoxyglucose positron emission tomography/computed tomography (FDG PET/CT) is a robust imaging modality used for staging multiple myeloma (MM) and assessing treatment responses. Herein, we extracted features from the FDG PET/CT images of MM patients using an artificial intelligence autoencoder algorithm that constructs a compressed representation of input data. We then evaluated the prognostic value of the image-feature clusters thus extracted. Conventional image parameters including metabolic tumor volume (MTV) were measured on volumes-of-interests (VOIs) covering only the bones. Features were extracted with the autoencoder algorithm on bone-covering VOIs. Supervised and unsupervised clustering were performed on image features. Survival analyses for progression-free survival (PFS) were performed for conventional parameters and clusters. In result, supervised and unsupervised clustering of the image features grouped the subjects into three clusters (A, B, and C). In multivariable Cox regression analysis, unsupervised cluster C, supervised cluster C, and high MTV were significant independent predictors of worse PFS. Supervised and unsupervised cluster analyses of image features extracted from FDG PET/CT scans of MM patients by an autoencoder allowed significant and independent prediction of worse PFS. Therefore, artificial intelligence algorithm–based cluster analyses of FDG PET/CT images could be useful for MM risk stratification.