Advertisement

Identifying How the Next Generation of Radiologists Will Increase the Value of Imaging and our Impact on Patient Outcomes: The Added Potential of CT Radiomics and AI Analysis

Published:April 06, 2022DOI:https://doi.org/10.1016/j.acra.2022.03.010
      In the study, “Prediction of the Acuity of Vertebral Compression Fractions on CT using Radiologic and Radiomic Features,” A. Yeon Kim and colleagues developed a program using radiomics to evaluate and assist in differentiating the acuity of vertebral compression fractures (
      • Kim AY
      • Yoon MA
      • Ham SJ
      • et al.
      Prediction of the acuity of vertebral compression fractures on CT using radiologic and radiomic features.
      ). The authors’ analysis centered on the creation of a radiomic score for each compression fracture studied through a careful 4 step process and using discrete reproducible features or guidelines outlined from the image biomarker standardization initiative (IBSI) (
      • Zwanenburg A
      • Vallieres M
      • Abdalah MA
      • et al.
      The image biomarker standardization initiative: standardized quantitative radiomics for high throughput image-based phenotyping.
      ). This incorporated 280 radiomic features extracted from non-enhanced CT images. The resulting radiologic model was generated and then validated against an independent test cohort, in both direct comparison and by comparing a new combined integrated score created by this primary method in addition to the radiomic score associated with its respective case. The study then compared the differences between the training cohort and the independent test group, showing similar validation. By comparing the radiologic image information only model to the combined integrated model using both the combined radiomic score and CT findings, amplified the potential differences. The process was again validated using an internal test cohort methodology.
      To read this article in full you will need to make a payment

      Purchase one-time access:

      Academic & Personal: 24 hour online accessCorporate R&D Professionals: 24 hour online access
      One-time access price info
      • For academic or personal research use, select 'Academic and Personal'
      • For corporate R&D use, select 'Corporate R&D Professionals'

      Subscribe:

      Subscribe to Academic Radiology
      Already a print subscriber? Claim online access
      Already an online subscriber? Sign in
      Institutional Access: Sign in to ScienceDirect

      References

        • Kim AY
        • Yoon MA
        • Ham SJ
        • et al.
        Prediction of the acuity of vertebral compression fractures on CT using radiologic and radiomic features.
        Acad Radiol. 2022; (S1076-6332(21)00573-0)https://doi.org/10.1016/j.acra.2021.12.008
        • Zwanenburg A
        • Vallieres M
        • Abdalah MA
        • et al.
        The image biomarker standardization initiative: standardized quantitative radiomics for high throughput image-based phenotyping.
        Radiology. 2020; 295: 328-338
        • Chang M-Y
        • Lee SH
        • Ha JW
        • et al.
        Change predicting bone marrow edema and fracture age in vertebral fragility fractures using MDCT.
        Am J Roentgenol. 2020; 215: 970-977https://doi.org/10.2214/AJR.19.22606
        • Ikeda T
        • Suzuki T
        • Takagi M
        • et al.
        Effect of early rehabilitation treatment on activities of daily living in patients receiving conservative treatment for vertebral compression fracture.
        Prog Rehabil Med. 2021; 620210049https://doi.org/10.2490/prm.20210049
        • Graffy P
        • Lee SJ
        • Ziemlewicz TJ
        • et al.
        Prevalence of vertebral compression fractures on routine CT scans according to L1 trabecular attenuation: determining relevant thresholds for opportunistic osteoporosis screening.
        Am J Roentgenol. 2017; 209: 491-496https://doi.org/10.2214/AJR.17.17853
        • Ahmed H
        • Parmar C
        • Quackenbush J
        • et al.
        Artificial intelligence in radiology.
        Nat Rev Cancer. 2018; 18: 500-510