Directionally Sensitive Fractal Radiomics Compatible With Irregularly Shaped Magnetic Resonance Tumor Regions of Interest: Association With Osteosarcoma Chemoresistance

被引:4
作者
Djuricic, Goran J. [1 ]
Ahammer, Helmut [2 ]
Rajkovic, Stanislav [3 ]
Kovac, Jelena Djokic [4 ]
Milosevic, Zorica [5 ]
Sopta, Jelena P. [6 ]
Radulovic, Marko [7 ]
机构
[1] Univ Belgrade, Fac Med, Dept Radiol, Univ Childrens Hosp, Belgrade, Serbia
[2] Med Univ Graz, Div Biophys, GSRC, Graz, Austria
[3] Univ Belgrade, Fac Med, Inst Orthopaed Banjica, Belgrade, Serbia
[4] Univ Belgrade, Fac Med, Ctr Radiol, Clin Ctr Serbia, Belgrade, Serbia
[5] Univ Belgrade, Fac Med, Inst Oncol & Radiol Serbia, Clin Radiat Oncol & Radiol, Belgrade, Serbia
[6] Univ Belgrade, Fac Med, Inst Pathol, Belgrade, Serbia
[7] Inst Oncol & Radiol Serbia, Dept Expt Oncol, Belgrade, Serbia
关键词
cancer; chemotherapy; osteosarcoma; prediction; radiomics; Higuchi dimension; TEXTURE FEATURES; IMAGES; BIOMARKERS; LESIONS;
D O I
10.1002/jmri.28232
中图分类号
R8 [特种医学]; R445 [影像诊断学];
学科分类号
1002 ; 100207 ; 1009 ;
摘要
Background Computational analysis of routinely acquired MRI has potential to improve the tumor chemoresistance prediction and to provide decision support in precision medicine, which may extend patient survival. Most radiomic analytical methods are compatible only with rectangular regions of interest (ROIs) and irregular tumor shape is therefore an important limitation. Furthermore, the currently used analytical methods are not directionally sensitive. Purpose To implement a tumor analysis that is directionally sensitive and compatible with irregularly shaped ROIs. Study Type Retrospective. Subjects A total of 54 patients with histopathologic diagnosis of primary osteosarcoma on tubular long bones and with prechemotherapy MRI. Field Strength/Sequence A 1.5 T, T2-weighted-short-tau-inversion-recovery-fast-spin-echo. Assessment A model to explore associations with osteosarcoma chemo-responsiveness included MRI data obtained before OsteoSa MAP neoadjuvant cytotoxic chemotherapy. Osteosarcoma morphology was analyzed in the MRI data by calculation of the nondirectional two-dimensional (2D) and directional and nondirectional one-dimensional (1D) Higuchi dimensions (Dh). MAP chemotherapy response was assessed by histopathological necrosis. Statistical Tests The area under the receiver operating characteristic (ROC) curve (AUC) evaluated the association of the calculated features with the actual chemoresponsiveness, using tumor histopathological necrosis (95%) as the endpoint. Least absolute shrinkage and selection operator (LASSO) machine learning and multivariable regression were used for feature selection. Significance was set at The nondirectional 1D Dh reached an AUC of 0.88 in association with the 95% tumor necrosis, while the directional 1D analysis along 180 radial lines significantly improved this association according to the Hanley/McNeil test, reaching an AUC of 0.95. The model defined by variable selection using LASSO reached an AUC of 0.98. The directional analysis showed an optimal predictive range between 90 degrees and 97 degrees and revealed structural osteosarcoma anisotropy manifested by its directionally dependent textural properties. Data Conclusion Directionally sensitive radiomics had superior predictive performance in comparison to the standard nondirectional image analysis algorithms with AUCs reaching 0.95 and full compatibility with irregularly shaped ROIs. Evidence Level 3 Technical Efficacy Stage 1
引用
收藏
页码:248 / 258
页数:11
相关论文
共 41 条
  • [1] Is a two-dimensional generalization of the Higuchi algorithm really necessary?
    Ahammer, Helmut
    Sabathiel, Nikolaus
    Reiss, Martin A.
    [J]. CHAOS, 2015, 25 (07)
  • [2] Higuchi Dimension of Digital Images
    Ahammer, Helmut
    [J]. PLOS ONE, 2011, 6 (09):
  • [3] Volumetric texture analysis of breast lesions on contrast-enhanced magnetic resonance images
    Chen, Weijie
    Giger, Maryellen L.
    Li, Hui
    Bick, Ulrich
    Newstead, Gillian M.
    [J]. MAGNETIC RESONANCE IN MEDICINE, 2007, 58 (03) : 562 - 571
  • [4] Micro-Computed Tomography Derived Anisotropy Detects Tumor Provoked Deviations in Bone in an Orthotopic Osteosarcoma Murine Model
    Cole, Heather A.
    Ohba, Tetsuro
    Ichikawa, Jiro
    Nyman, Jeffry S.
    Cates, Justin M. M.
    Haro, Hirotaka
    Schwartz, Herbert S.
    Schoenecker, Jonathan G.
    [J]. PLOS ONE, 2014, 9 (06):
  • [5] Nonlinear analysis of EEG complexity in episode and remission phase of recurrent depression
    Cukic, Milena
    Stokic, Miodrag
    Radenkovic, Slavoljub
    Ljubisavljevic, Milos
    Simic, Slobodan
    Savic, Danka
    [J]. INTERNATIONAL JOURNAL OF METHODS IN PSYCHIATRIC RESEARCH, 2020, 29 (02)
  • [6] Rotation Invariance and Directional Sensitivity: Spherical Harmonics versus Radiomics Features
    Depeursinge, Adrien
    Fageot, Julien
    Andrearczyk, Vincent
    Ward, John Paul
    Unser, Michael
    [J]. MACHINE LEARNING IN MEDICAL IMAGING: 9TH INTERNATIONAL WORKSHOP, MLMI 2018, 2018, 11046 : 107 - 115
  • [7] Computational analysis of MRIs predicts osteosarcoma chemoresponsiveness
    Djuricic, Goran J.
    Rajkovic, Nemanja
    Milosevic, Nebojsa
    Sopta, Jelena P.
    Boric, Igor
    Ducic, Sinisa
    Apostolovic, Milan
    Radulovic, Marko
    [J]. BIOMARKERS IN MEDICINE, 2021, 15 (12) : 929 - 940
  • [8] Fractal and Gray Level Cooccurrence Matrix Computational Analysis of Primary Osteosarcoma Magnetic Resonance Images Predicts the Chemotherapy Response
    Djuricic, Goran J.
    Radulovic, Marko
    Sopta, Jelena P.
    Nikitovic, Marina
    Milosevic, Nebojsa T.
    [J]. FRONTIERS IN ONCOLOGY, 2017, 7
  • [9] Multifractal Properties of a Closed Contour: A Peek beyond the Shape Analysis
    Duarte-Neto, Paulo
    Stosic, Borko
    Stosic, Tatijana
    Lessa, Rosangela
    Milosevic, Milorad V.
    Stanley, H. Eugene
    [J]. PLOS ONE, 2014, 9 (12):
  • [10] 1977 RIETZ LECTURE - BOOTSTRAP METHODS - ANOTHER LOOK AT THE JACKKNIFE
    EFRON, B
    [J]. ANNALS OF STATISTICS, 1979, 7 (01) : 1 - 26