Deep Learning-Based Quantification of Visceral Fat Volumes Predicts Posttransplant Diabetes Mellitus in Kidney Transplant Recipients

被引:5
|
作者
Kim, Ji Eun [1 ]
Park, Sang Joon [2 ]
Kim, Yong Chul [3 ]
Min, Sang-Il [4 ]
Ha, Jongwon [4 ]
Kim, Yon Su [3 ]
Yoon, Soon Ho [2 ,5 ]
Han, Seung Seok [3 ]
机构
[1] Korea Univ, Dept Internal Med, Guro Hosp, Seoul, South Korea
[2] Seoul Natl Univ, Dept Radiol, Coll Med, Seoul, South Korea
[3] Seoul Natl Univ, Dept Internal Med, Coll Med, Seoul, South Korea
[4] Seoul Natl Univ, Coll Med, Dept Surg, Seoul, South Korea
[5] UMass Mem Med Ctr, Dept Radiol, Worcester, MA 01655 USA
关键词
artificial intelligence; body mass index; fat; deep learning; kidney transplantation; post-transplant diabetes mellitus; COMPARING ROC CURVES; BODY-MASS INDEX; ADIPOSE-TISSUE; RENAL-TRANSPLANTATION; ARTIFICIAL-INTELLIGENCE; ANALYTIC MORPHOMICS; GLUCOSE-METABOLISM; PERMUTATION TEST; RISK; CYCLOSPORINE;
D O I
10.3389/fmed.2021.632097
中图分类号
R5 [内科学];
学科分类号
1002 ; 100201 ;
摘要
Background: Because obesity is associated with the risk of posttransplant diabetes mellitus (PTDM), the precise estimation of visceral fat mass before transplantation may be helpful. Herein, we addressed whether a deep-learning based volumetric fat quantification on pretransplant computed tomographic images predicted the risk of PTDM more precisely than body mass index (BMI). Methods: We retrospectively included a total of 718 nondiabetic kidney recipients who underwent pretransplant abdominal computed tomography. The 2D (waist) and 3D (waist or abdominal) volumes of visceral, subcutaneous, and total fat masses were automatically quantified using the deep neural network. The predictability of the PTDM risk was estimated using a multivariate Cox model and compared among the fat parameters using the areas under the receiver operating characteristic curves (AUROCs). Results: PTDM occurred in 179 patients (24.9%) during the median follow-up period of 5 years (interquartile range, 2.5-8.6 years). All the fat parameters predicted the risk of PTDM, but the visceral and total fat volumes from 2D and 3D evaluations had higher AUROC values than BMI did, and the best predictor of PTDM was the 3D abdominal visceral fat volumes [AUROC, 0.688 (0.636-0.741)]. The addition of the 3D abdominal VF volume to the model with clinical risk factors increased the predictability of PTDM, but BMI did not. Conclusions: A deep-learning based quantification of visceral fat volumes on computed tomographic images better predicts the risk of PTDM after kidney transplantation than BMI.
引用
收藏
页数:8
相关论文
共 49 条
  • [1] Posttransplant diabetes mellitus in kidney transplant recipients
    Prokopenko, Elena
    Scherbakova, Eugenia
    Vatazin, Andrey
    Gulimova, Svetlana
    Matyuhin, Igor
    NEPHROLOGY DIALYSIS TRANSPLANTATION, 2006, 21 : 278 - 278
  • [2] Analysis of posttransplant diabetes mellitus prevalence in a population of kidney transplant recipients
    Bonato, V.
    Barni, R.
    Cataldo, D.
    Collini, A.
    Ruggieri, G.
    De Bartolomeis, C.
    Dotta, F.
    Carmellini, M.
    TRANSPLANTATION PROCEEDINGS, 2008, 40 (06) : 1888 - 1890
  • [3] Posttransplant diabetes mellitus in kidney transplant recipients under tacrolimus immunosuppression
    Khoury, N
    Kriaa, F
    Hiesse, C
    Von Ey, F
    Durbach, A
    Ammor, M
    Hafi, A
    Djeffal, R
    Boubenider, S
    Droupy, S
    Hammoudi, Y
    Eschwege, P
    Benoît, G
    Charpentier, B
    TRANSPLANTATION PROCEEDINGS, 2000, 32 (08) : 2763 - 2764
  • [4] Microvascular Complications of Posttransplant Diabetes Mellitus in Kidney Transplant Recipients: A Longitudinal Study
    Londero, Thiza Massaia
    Giaretta, Luana Seminotti
    Farenzena, Luisa Penso
    Manfro, Roberto Ceratti
    Canani, Luis Henrique
    Lavinsky, Daniel
    Leitao, Cristiane Bauermann
    Bauer, Andrea Carla
    JOURNAL OF CLINICAL ENDOCRINOLOGY & METABOLISM, 2019, 104 (02): : 557 - 567
  • [5] Risk Factors and Outcomes Associated With Posttransplant Diabetes Mellitus in Kidney Transplant Recipients
    Siraj, E. S.
    Abacan, C.
    Chinnappa, P.
    Wojtowicz, J.
    Braun, W.
    TRANSPLANTATION PROCEEDINGS, 2010, 42 (05) : 1685 - 1689
  • [6] CLINICAL CHARACTERISTICS OF KIDNEY-TRANSPLANT RECIPIENTS WITH POSTTRANSPLANT DIABETES-MELLITUS
    GERO, L
    FOLDES, K
    HEMAANGSHU, P
    SANDIL, A
    SZEPLAKI, P
    BEKEFFY, M
    SPITZER, N
    PANCZEL, P
    DIABETOLOGIA, 1995, 38 : A14 - A14
  • [7] Posttransplant diabetes mellitus in kidney transplant recipients receiving calcineurin or mTOR inhibitor drugs
    Araki, M
    Flechner, SM
    Ismail, HR
    Flechner, LM
    Zhou, LM
    Derweesh, IH
    Goldfarb, D
    Modlin, C
    Novick, AC
    Faiman, C
    TRANSPLANTATION, 2006, 81 (03) : 335 - 341
  • [8] Conversion From Steroid to Everolimus in Maintenance Kidney Transplant Recipients With Posttransplant Diabetes Mellitus
    Nanmoku, Koji
    Kurosawa, Akira
    Kubo, Taro
    Shinzato, Takahiro
    Shimizu, Toshihiro
    Kimura, Takaaki
    Yagisawa, Takashi
    EXPERIMENTAL AND CLINICAL TRANSPLANTATION, 2019, 17 (01) : 47 - 51
  • [9] Incidence of posttransplant diabetes mellitus in kidney transplant recipients immunosuppressed with sirolimus in combination with cyclosporine
    Romagnoli, J.
    Citterio, F.
    Nanni, G.
    Favi, E.
    Tondolo, V.
    Spagnoletti, G.
    Salerno, M. Paola
    Castagneto, M.
    TRANSPLANTATION PROCEEDINGS, 2006, 38 (04) : 1034 - 1036
  • [10] Deep Learning-based Quantification of Abdominal Subcutaneous and Visceral Fat Volume on CT Images
    Grainger, Andrew T.
    Krishnaraj, Arun
    Quinones, Michael H.
    Tustison, Nicholas J.
    Epstein, Samantha
    Fuller, Daniela
    Jha, Aakash
    Allman, Kevin L.
    Shi, Weibin
    ACADEMIC RADIOLOGY, 2021, 28 (11) : 1481 - 1487