Multicenter study demonstrates radiomic features derived from magnetic resonance perfusion images identify pseudoprogression in glioblastoma

Abstract

Pseudoprogression (PsP) is a diagnostic clinical dilemma in cancer. In this study, we retrospectively analyse glioblastoma patients, and using their dynamic susceptibility contrast and dynamic contrast-enhanced perfusion MRI images we build a classifier using radiomic features obtained from both Ktrans and rCBV maps coupled with support vector machines. We achieve an accuracy of 90.82% (area under the curve (AUC) = 89.10%, sensitivity = 91.36%, 67 specificity = 88.24%, p = 0.017) in differentiating between pseudoprogression (PsP) and progressive disease (PD). The diagnostic performances of the models built using radiomic features from Ktrans and rCBV separately were equally high (Ktrans: AUC = 94%, 69 p = 0.012; rCBV: AUC = 89.8%, p = 0.004). Thus, this MR perfusion-based radiomic model demonstrates high accuracy, sensitivity and specificity in discriminating PsP from PD, thus provides a reliable alternative for noninvasive identification of PsP versus PD at the time of clinical/radiologic question. This study also illustrates the successful application of radiomic analysis as an advanced processing step on different MR perfusion maps.

Repeatability of radiomic features in magnetic resonance imaging of glioblastoma: Test–retest and image registration analyses

“…65,66 On the other hand, there are several variations in the clinical definitions of pseudo-progression based on the imaging reports which require higher precision quantitative imaging. 67 Some radiomics studies have shown the feasibility of MR image radiomic features to discriminate between pseudo-progression compared to true progression [68][69][70] and genomic mutation prediction 8-11,71,72 and treatment response assessments. 5,6 In the present image biomarker discovery era, our results would be important, wherein radiomic features with greatest robustness to image registration between images may be more beneficial in clinical studies.…”

Artificial intelligence for clinical decision support in neurology

“…Accurate identification of these target labels requires clinical knowledge, and we are dependent on people with extensive clinical experience and expertise to provide reliable outcome measures in our patients. Humans and machines need to work together to ensure that the outputs of AI models are robust enough for clinical prediction ( Elshafeey et al , 2019 ).…”

Swarm Learning as a privacy-preserving machine learning approach for disease classification

“…This will not be restricted to omics data as exemplified here, but will extend to other large medical data such as medical imaging data 55,56 . Particularly in oncology, great successes applying machine learning have already been reported for tumor detection 47,55,57,58 , subtyping 59,60 , grading 61 , genomic characterization 62 , or outcome prediction 63 , yet progress is hindered by too small datasets at any given institution 26 with current privacy regulations 8 (hhs.gov, https://www.hhs.gov/hipaa/index.html, 2020; Intersoft Consulting, General Data Protection Regulation, https://gdpr-info.ee) making it less appealing to develop centralized AI systems. We introduce Swarm Learning as a decentralized learning system with access to data stored locally that can replace the current paradigm of data sharing and centralized storage while preserving data privacy in cross-institutional research in a wide spectrum of biomedical disciplines.…”