A Postreconstruction Harmonization Method for Multicenter Radiomic Studies in PET

Abstract

Several reports have shown that radiomic features are affected by acquisition and reconstruction parameters, thus hampering multicenter studies. We propose a method that, by removing the center effect while preserving patient-specific effects, standardizes features measured from PET images obtained using different imaging protocols. PretreatmentF-FDG PET images of patients with breast cancer were included. In one nuclear medicine department (department A), 63 patients were scanned on a time-of-flight PET/CT scanner, and 16 lesions were triple-negative (TN). In another nuclear medicine department (department B), 74 patients underwent PET/CT on a different brand of scanner and a different reconstruction protocol, and 15 lesions were TN. The images from department A were smoothed using a gaussian filter to mimic data from a third department (department A-S). The primary lesion was segmented to obtain a lesion volume of interest (VOI), and a spheric VOI was set in healthy liver tissue. Three SUVs and 6 textural features were computed in all VOIs. A harmonization method initially described for genomic data was used to estimate the department effect based on the observed feature values. Feature distributions in each department were compared before and after harmonization. In healthy liver tissue, the distributions significantly differed for 4 of 9 features between departments A and B and for 6 of 9 between departments A and A-S ( < 0.05, Wilcoxon test). After harmonization, none of the 9 feature distributions significantly differed between 2 departments ( > 0.1). The same trend was observed in lesions, with a realignment of feature distributions between the departments after harmonization. Identification of TN lesions was largely enhanced after harmonization when the cutoffs were determined on data from one department and applied to data from the other department. The proposed harmonization method is efficient at removing the multicenter effect for textural features and SUVs. The method is easy to use, retains biologic variations not related to a center effect, and does not require any feature recalculation. Such harmonization allows for multicenter studies and for external validation of radiomic models or cutoffs and should facilitate the use of radiomic models in clinical practice.

Personalizing Medicine Through Hybrid Imaging and Medical Big Data Analysis

“…As an example, while numerous studies utilized a fixed number of bins for textural analysis, recent studies suggested that a fixed bin size with variable number of bins per lesion provides better comparability and reproducibility of textural features [10,55,184]. Furthermore, image resolution normalization [228], or normalization of already extracted radiomic features in the feature space [229] have been proposed. In addition, guidelines are available focusing on imaging, feature extraction, analysis and cross-validation standardization of radiomic studies [230][231][232].…”

LIFEx: A Freeware for Radiomic Feature Calculation in Multimodality Imaging to Accelerate Advances in the Characterization of Tumor Heterogeneity

“…Last, the use of RF in the clinics is hampered by the unavailability of widely validated radiomic models. The identification of robust radiomic models is complicated by the variability of feature values as a function of the acquisition device and acquisition protocols (5)(6)(7)(8), although harmonization methods have recently been described (9).…”

Radiomics robustness assessment and classification evaluation: A two‐stage method demonstrated on multivendor FFDM

“…Classification performance of the RACE method proposed in this paper was compared to the ComBat harmonization method used in previous studies . The results, summarized in Fig.…”

“…While the approach to handling heterogeneous feature data in this paper focuses on limiting feature selection to robust features through a two‐stage analysis (RACE), other groups have approached the same issue by harmonizing (or standardizing) feature data across different imaging conditions. One such example is the ComBat harmonization method, originally developed to correct for the “batch effect” in the genomics field, and later applied to Positron Emission Tomography (PET) radiomics studies . In a study by Orlhac et al., the ComBat harmonization method was applied to standardize radiomic features extracted from PET images of breast cancer patients acquired in two different institutions in order to identify triple negative (TN) lesions …”

“…One such example is the ComBat harmonization method, originally developed to correct for the “batch effect” in the genomics field, and later applied to Positron Emission Tomography (PET) radiomics studies . In a study by Orlhac et al., the ComBat harmonization method was applied to standardize radiomic features extracted from PET images of breast cancer patients acquired in two different institutions in order to identify triple negative (TN) lesions …”