Browsing by Author "Djuričić, Goran J. (59157834100)"

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 <0.05. Results: 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° and 97° 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. © 2022 International Society for Magnetic Resonance in Medicine.

The prediction of induction chemotherapy response at the time of diagnosis may improve outcomes in osteosarcoma by allowing for personalized tailoring of therapy. The aim of this study was thus to investigate the predictive potential of the so far unexploited computational analysis of osteosarcoma magnetic resonance (MR) images. Fractal and gray level cooccurrence matrix (GLCM) algorithms were employed in retrospective analysis of MR images of primary osteosarcoma localized in distal femur prior to the OsteoSa induction chemotherapy. The predicted and actual chemotherapy response outcomes were then compared by means of receiver operating characteristic (ROC) analysis and accuracy calculation. Dbin, λ, and SCN were the standard fractal and GLCM features which significantly associated with the chemotherapy outcome, but only in one of the analyzed planes. Our newly developed normalized fractal dimension, called the space-filling ratio (SFR) exerted an independent and much better predictive value with the prediction significance accomplished in two of the three imaging planes, with accuracy of 82% and area under the ROC curve of 0.20 (95% confidence interval 0-0.41). In conclusion, SFR as the newly designed fractal coefficient provided superior predictive performance in comparison to standard image analysis features, presumably by compensating for the tumor size variation in MR images. © 2017 Djuricic, Radulovic, Sopta, Nikitovic and Miloševic.

The prediction of induction chemotherapy response at the time of diagnosis may improve outcomes in osteosarcoma by allowing for personalized tailoring of therapy. The aim of this study was thus to investigate the predictive potential of the so far unexploited computational analysis of osteosarcoma magnetic resonance (MR) images. Fractal and gray level cooccurrence matrix (GLCM) algorithms were employed in retrospective analysis of MR images of primary osteosarcoma localized in distal femur prior to the OsteoSa induction chemotherapy. The predicted and actual chemotherapy response outcomes were then compared by means of receiver operating characteristic (ROC) analysis and accuracy calculation. Dbin, λ, and SCN were the standard fractal and GLCM features which significantly associated with the chemotherapy outcome, but only in one of the analyzed planes. Our newly developed normalized fractal dimension, called the space-filling ratio (SFR) exerted an independent and much better predictive value with the prediction significance accomplished in two of the three imaging planes, with accuracy of 82% and area under the ROC curve of 0.20 (95% confidence interval 0-0.41). In conclusion, SFR as the newly designed fractal coefficient provided superior predictive performance in comparison to standard image analysis features, presumably by compensating for the tumor size variation in MR images. © 2017 Djuricic, Radulovic, Sopta, Nikitovic and Miloševic.

Background: Due to the high level of cytogenetic heterogeneity in osteosarcoma, personalized treatment is the promising strategy for the improvement in outcomes. This is currently not possible due to the absence of targeted therapies and reliable predictors for response to induction chemotherapy. Objectives: To investigate the predictive value of computational analysis of osteosarcoma magnetic resonance (MR) images. Patients and Methods: Multifractal analysis was performed on MR images of primary osteosarcoma of long tubular bones prior to OsteoSa induction chemotherapy. A total of 900 images derived from 67 good and poor responder patients were classified and compared to the actual retrospective outcome. Results: Among the six calculated multifractal features, Dqmax exerted the highest predictive value with the prediction accuracy of 74.3%, sensitivity of 72.4% and specificity of 76.2%. The obtained classification accuracy was validated by a ten V-fold split sample cross validation. The area under the curve (AUC) value for the best-performing multifractal Dqmax feature was 0.82 (95% confidence interval, 0.70-0.91). Conclusion: These results suggest for the first time that measuring tumor structure by using multifractal geometry can predict an individual patient response to neoadjuvant cytotoxic therapy. Therefore, it potentially allows precise implementation of alternative treatment options. This predictive approach made use of digital data that is routinely collected but currently still underexploited. © 2018, Iranian Journal of Radiology.