Published July 8, 2021 | Version v.1
Journal article Open

Computational analysis of MRIs predicts osteosarcoma chemoresponsiveness

Authors/Creators

  • 1. Department of Radiology, University Children's Hospital, School of Medicine, University of Belgrade, Belgrade, 11000, Serbia
  • 2. Department of Biophysics, School of Medicine, University of Belgrade, Belgrade, 11000, Serbia
  • 3. Institute of Pathology, School of Medicine, University of Belgrade, Belgrade, 11000, Serbia
  • 4. St. Catherine Specialty Hospital, Zagreb, 10000, Croatia
  • 5. Department of Orthopaedic, Institute for Orthopaedic Surgery, "Banjica", Belgrade, 11040, Serbia
  • 6. Department of Experimental Oncology, Institute for Oncology & Radiology of Serbia, Belgrade, 11000, Serbia email: marko@radulovic.net

Description

Aim: This study aimed to improve osteosarcoma chemoresponsiveness prediction by optimization of computational analysis of MRIs. Patients & methods: Our retrospective predictive model involved osteosarcoma patients with MRI scans performed before OsteoSa MAP neoadjuvant cytotoxic chemotherapy. Results: We found that several monofractal and multifractal algorithms were able to classify tumors according to their chemoresponsiveness. The predictive clues were defined as morphological complexity, homogeneity and fractality. The monofractal feature CV for (G) provided the best predictive association (area under the ROC curve = 0.88; p <0.001), followed by Y-axis intersection of the regression line for box fractal dimension, r2 for FDM and tumor circularity. Conclusion: This is the first full-scale study to indicate that computational analysis of pretreatment MRIs could provide imaging biomarkers for the classification of osteosarcoma according to their chemoresponsiveness.

Tweetable abstract: Fractal analysis of MRI scans was shown to predict the chemosensitivity of osteosarcoma. These findings may eventually lead to improved patient survival by enabling personalized cytotoxic chemotherapy prescription

Notes

This work was supported by the Ministry of Education, Science and Technological Development of the Republic of Serbia, grant number 451-03-9/2021-14/200043. The funding source was not involved in study design, in the collection, analysis and interpretation of data, in the writing of the report, and in the decision to submit the article for publication.

Files

Djuricic et al. revised Computational .. (2).pdf

Files (1.6 MB)

Additional details

Related works

Is derived from
https://www.futuremedicine.com/doi/pdfplus/10.2217/bmm-2020-0876 (URL)
Is part of
1752-0363 (ISSN)