Impact Factor 4.137 | CiteScore 4.28
More on impact ›

Original Research ARTICLE Provisionally accepted The full-text will be published soon. Notify me

Front. Oncol. | doi: 10.3389/fonc.2019.00941

Supervised machine-learning enables segmentation and evaluation of heterogeneous post-treatment changes in multi-parametric MRI of soft-tissue sarcoma

 Matthew D. Blackledge1, 2,  Jessica M. Winfield2, Veronica Morgan1, Khin Thway1, Dirk Strauss1, David Collins2,  Martin O. Leach2, Dow-Mu Koh1, 2, Aisha Miah1 and  Christina Messiou1, 2*
  • 1Royal Marsden Hospital, United Kingdom
  • 2Institute of Cancer Research (ICR), United Kingdom

Background
Multi-parametric MRI provides non-invasive methods for response assessment of soft-tissue sarcoma (STS) from non-surgical treatments. However, evaluation of MRI parameters over the whole tumour volume may not reveal the full extent of post-treatment changes as STS tumours are often highly heterogeneous, including cellular tumour, fat, necrosis, and cystic tissue compartments. In this pilot study, we investigate the use of machine-learning approaches to automatically delineate tissue compartments in STS, and use this approach to monitor post-radiotherapy changes.
Methods
Eighteen patients with retroperitoneal sarcoma were imaged using multi-parametric MRI; 8/18 received a follow-up imaging study 2-4 weeks after pre-operative radiotherapy. Eight commonly-used supervised machine-learning techniques were optimized for classifying pixels into one of five tissue sub-types using an exhaustive cross-validation approach and expert-defined regions of interest as a gold standard. Final pixel classification was smoothed using a Markov Random Field (MRF) prior distribution on the final machine-learning models.
Findings
5/8 machine-learning techniques demonstrated high median cross-validation accuracies (82.2%, range 80.5-82.5%) with no significant difference between these five methods. One technique was selected (Naïve-Bayes) due to its relatively short training and class-prediction times (median 0.73ms and 0.69ms respectively on a 3.5GHz personal machine). When combined with the MRF-prior, this approach was successfully applied in all eight post-radiotherapy imaging studies and provided visualisation and quantification of changes to independent STS sub-regions following radiotherapy for heterogeneous response assessment.
Interpretation
Supervised machine-learning approaches to tissue classification in multi-parametric MRI of soft-tissue sarcomas provide quantitative evaluation of heterogeneous tissue changes following radiotherapy.

Keywords: Magnetic Resonance Imaging, Soft-tissue sarcoma, artificial intelligence, cancer heterogeneity, Radiotherapy, imaging biomarkers

Received: 23 Apr 2019; Accepted: 06 Sep 2019.

Copyright: © 2019 Blackledge, Winfield, Morgan, Thway, Strauss, Collins, Leach, Koh, Miah and Messiou. This is an open-access article distributed under the terms of the Creative Commons Attribution License (CC BY). The use, distribution or reproduction in other forums is permitted, provided the original author(s) and the copyright owner(s) are credited and that the original publication in this journal is cited, in accordance with accepted academic practice. No use, distribution or reproduction is permitted which does not comply with these terms.

* Correspondence: MD. Christina Messiou, Royal Marsden Hospital, London, United Kingdom, christina.messiou@icr.ac.uk