Nikita V Orlov1, Sokratis Makrogiannis2, Luigi Ferrucci3, Ilya G Goldberg3. 1. National Institute on Aging, National Institute of Health, 251 Bayview Blvd, BRC, Ste 100, Baltimore, MD 21224-6825, USA. Electronic address: norlov@nih.gov. 2. National Institute on Aging, National Institute of Health, Baltimore, Maryland. 3. National Institute on Aging, National Institute of Health, 251 Bayview Blvd, BRC, Ste 100, Baltimore, MD 21224-6825, USA.
Abstract
RATIONALE AND OBJECTIVES: Changes in the composition of body tissues are major aging phenotypes, but they have been difficult to study in depth. Here we describe age-related change in abdominal tissues observable in computed tomography (CT) scans. We used pattern recognition and machine learning to detect and quantify these changes in a model-agnostic fashion. MATERIALS AND METHODS: CT scans of abdominal L4 sections were obtained from Baltimore Longitudinal Study of Aging (BLSA) participants. Age-related change in the constituent tissues were determined by training machine classifiers to differentiate age groups within male and female strata ("Younger" at 50-70 years old vs "Older" at 80-99 years old). The accuracy achieved by the classifiers in differentiating the age cohorts was used as a surrogate measure of the aging signal in the different tissues. RESULTS: The highest accuracy for discriminating age differences was 0.76 and 0.72 for males and females, respectively. The classification accuracy was 0.79 and 0.71 for adipose tissue, 0.70 and 0.68 for soft tissue, and 0.65 and 0.64 for bone. CONCLUSIONS: Using image data from a large sample of well-characterized pool of participants dispersed over a wide age range, we explored age-related differences in gross morphology and texture of abdominal tissues. This technology is advantageous for tracking effects of biological aging and predicting adverse outcomes when compared to the traditional use of specific molecular biomarkers. Application of pattern recognition and machine learning as a tool for analyzing medical images may provide much needed insight into tissue changes occurring with aging and, further, connect these changes with their metabolic and functional consequences. Published by Elsevier Inc.
RATIONALE AND OBJECTIVES: Changes in the composition of body tissues are major aging phenotypes, but they have been difficult to study in depth. Here we describe age-related change in abdominal tissues observable in computed tomography (CT) scans. We used pattern recognition and machine learning to detect and quantify these changes in a model-agnostic fashion. MATERIALS AND METHODS: CT scans of abdominal L4 sections were obtained from Baltimore Longitudinal Study of Aging (BLSA) participants. Age-related change in the constituent tissues were determined by training machine classifiers to differentiate age groups within male and female strata ("Younger" at 50-70 years old vs "Older" at 80-99 years old). The accuracy achieved by the classifiers in differentiating the age cohorts was used as a surrogate measure of the aging signal in the different tissues. RESULTS: The highest accuracy for discriminating age differences was 0.76 and 0.72 for males and females, respectively. The classification accuracy was 0.79 and 0.71 for adipose tissue, 0.70 and 0.68 for soft tissue, and 0.65 and 0.64 for bone. CONCLUSIONS: Using image data from a large sample of well-characterized pool of participants dispersed over a wide age range, we explored age-related differences in gross morphology and texture of abdominal tissues. This technology is advantageous for tracking effects of biological aging and predicting adverse outcomes when compared to the traditional use of specific molecular biomarkers. Application of pattern recognition and machine learning as a tool for analyzing medical images may provide much needed insight into tissue changes occurring with aging and, further, connect these changes with their metabolic and functional consequences. Published by Elsevier Inc.
Entities:
Keywords:
Abdominal CT scans; age discrimination; differential aging; pattern recognition
Authors: Nikita Orlov; Lior Shamir; Tomasz Macura; Josiah Johnston; D Mark Eckley; Ilya G Goldberg Journal: Pattern Recognit Lett Date: 2008-01 Impact factor: 3.756
Authors: Nhat Trung Doan; Sanneke van Rooden; Maarten J Versluis; Mathijs Buijs; Andrew G Webb; Jeroen van der Grond; Mark A van Buchem; Johan H C Reiber; Julien Milles Journal: Magn Reson Med Date: 2014-08-07 Impact factor: 4.668
Authors: Manuel López-Alcaraz; Pedro Manuel Garamendi González; Inmaculada Alemán Aguilera; Miguel Botella López Journal: Int J Legal Med Date: 2014-07-02 Impact factor: 2.686
Authors: P Lee; R J Brychta; M T Collins; J Linderman; S Smith; P Herscovitch; C Millo; K Y Chen; F S Celi Journal: Osteoporos Int Date: 2012-08-14 Impact factor: 4.507
Authors: Nikita V Orlov; Ashani T Weeraratna; Stephen M Hewitt; Christopher E Coletta; John D Delaney; D Mark Eckley; Lior Shamir; Ilya G Goldberg Journal: Cytometry A Date: 2012-03-29 Impact factor: 4.355
Authors: Iva Miljkovic; Jane A Cauley; Patty Y Wang; Kathleen F Holton; Christine G Lee; Yahtyng Sheu; Elizabeth Barrett-Connor; Andrew R Hoffman; Cora B Lewis; Eric S Orwoll; Marcia L Stefanick; Elsa S Strotmeyer; Lynn M Marshall Journal: Obesity (Silver Spring) Date: 2013-05-29 Impact factor: 5.002
Authors: Adam J Santanasto; Bret H Goodpaster; Stephen B Kritchevsky; Iva Miljkovic; Suzanne Satterfield; Ann V Schwartz; Steven R Cummings; Robert M Boudreau; Tamara B Harris; Anne B Newman Journal: J Gerontol A Biol Sci Med Sci Date: 2017-04-01 Impact factor: 6.053