A preliminary PET radiomics study of brain metastases using a fully automatic segmentation method

Abstract

Background Positron Emission Tomography (PET) is increasingly utilized in radiomics studies for treatment evaluation purposes. Nevertheless, lesion volume identification in PET images is a critical and still challenging step in the process of radiomics, due to the low spatial resolution and high noise level of PET images. Currently, the biological target volume (BTV) is manually contoured by nuclear physicians, with a time expensive and operator-dependent procedure. This study aims to obtain BTVs from cerebral metastases in patients who underwent L-[11C]methionine (11C-MET) PET, using a fully automatic procedure and to use these BTVs to extract radiomics features to stratify between patients who respond to treatment or not. For these purposes, 31 brain metastases, for predictive evaluation, and 25 ones, for follow-up evaluation after treatment, were delineated using the proposed method. Successively, 11C-MET PET studies and related volumetric segmentations were used to extract 108 features to investigate the potential application of radiomics analysis in patients with brain metastases. A novel statistical system has been implemented for feature reduction and selection, while discriminant analysis was used as a method for feature classification. Results For predictive evaluation, 3 features (asphericity, low-intensity run emphasis, and complexity) were able to discriminate between responder and non-responder patients, after feature reduction and selection. Best performance in patient discrimination was obtained using the combination of the three selected features (sensitivity 81.23%, specificity 73.97%, and accuracy 78.27%) compared to the use of all features. Secondly, for follow-up evaluation, 8 features (SUVmean, SULpeak, SUVmin, SULpeak prod-surface-area, SUVmean prod-sphericity, surface mean SUV 3, SULpeak prod-sphericity, and second angular moment) were selected with optimal performance in discriminant analysis classification (sensitivity 86.28%, specificity 87.75%, and accuracy 86.57%) outperforming the use of all features. Conclusions The proposed system is able i) to extract 108 features for each automatically segmented lesion and ii) to select a sub-panel of 11C-MET PET features (3 and 8 in the case of predictive and follow-up evaluation), with valuable association with patient outcome. We believe that our model can be useful to improve treatment response and prognosis evaluation, potentially allowing the personalization of cancer treatment plans.

A Systematic Review of PET Textural Analysis and Radiomics in Cancer

“…We collected 17 publications [ 225 , 241 , 242 , 243 , 244 , 245 , 246 , 247 , 248 , 249 , 250 , 251 , 252 , 253 , 254 , 255 , 256 ] focusing on the evaluation of brain tumors, most of them gliomas (71%). The average number of patients was 71 (median = 70, range, 20–127) and the average number of evaluated textures was 40 (median = 33, range, 2–75), extracted mainly from the GLCM (94%), the GLZSM (65%), and the GLRLM (65%).…”

Deep Learning-Based Methods for Prostate Segmentation in Magnetic Resonance Imaging

“…In the biomedical imaging field, target delineation is routinely used as the first step in any automatized disease diagnosis system (i.e., radiotherapy system) and, in the last few years, in radiomics studies [ 1 , 2 ] to obtain a multitude of quantitative parameters from biomedical images [ 3 , 4 ]. These parameters are then used as imaging biomarkers to identify any possible associations with patient outcome.…”

Reproducibility of Baseline Tumour Metabolic Volume Measurements in Diffuse Large B-Cell Lymphoma: Is There a Superior Method?

“…In addition, it should also be carried out as quickly as possible to be usable in everyday life, implying the use of automatic, or at the very least, semi-automatic segmentation methods. Recently, automatic delineation using artificial intelligence have been proposed [19][20][21]. From a theoretical point of view, this approach allows a neural network to learn key imaging features in patient and extract tumours automatically while removing physiological uptakes.…”