Implications of reconstruction protocol for histo-biological characterisation of breast cancers using FDG-PET radiomics

Abstract

BackgroundThe aim of this study is to determine if the choice of the 18F-FDG-PET protocol, especially matrix size and reconstruction algorithm, is of importance to discriminate between immunohistochemical subtypes (luminal versus non-luminal) in breast cancer with textural features (TFs).ProceduresForty-seven patients referred for breast cancer staging in the framework of a prospective study were reviewed as part of an ancillary study. In addition to standard PET imaging (PSFWholeBody), a high-resolution breast acquisition was performed and reconstructed with OSEM and PSF (OSEMbreast/PSFbreast). PET standard metrics and TFs were extracted. For each reconstruction protocol, a prediction model for tumour classification was built using a random forests method. Spearman coefficients were used to seek correlation between PET metrics.ResultsPSFWholeBody showed lower numbers of voxels within VOIs than OSEMbreast and PSFbreast with median (interquartile range) equal to 130 (43–271), 316 (167–1042), 367 (107–1221), respectively (p < 0.0001). Therefore, using LifeX software, 28 (59%), 46 (98%) and 42 (89%) patients were exploitable with PSFWholeBody, OSEMbreast and PSFbreast, respectively.On matched comparisons, PSFbreast reconstruction presented better abilities than PSFwholeBody and OSEMbreast for the classification of luminal versus non-luminal breast tumours with an accuracy reaching 85.7% as compared to 67.8% for PSFwholeBody and 73.8% for OSEMbreast. PSFbreast accuracy, sensitivity, specificity, PPV and NPV were equal to 85.7%, 94.3%, 42.9%, 89.2%, 60.0%, respectively. Coarseness and ZLNU were found to be main variables of importance, appearing in all three prediction models. Coarseness was correlated with SUVmax on PSFwholeBody images (ρ = − 0.526, p = 0.005), whereas it was not on OSEMbreast (ρ = − 0.183, p = 0.244) and PSFbreast (ρ = − 0.244, p = 0.119) images. Moreover, the range of its values was higher on PSFbreast images as compared to OSEMbreast, especially in small lesions (MTV < 3 ml).ConclusionsHigh-resolution breast PET acquisitions, applying both small-voxel matrix and PSF modelling, appeared to improve the characterisation of breast tumours.Electronic supplementary materialThe online version of this article (10.1186/s13550-018-0466-5) contains supplementary material, which is available to authorized users.

Experimental Multicenter and Multivendor Evaluation of the Performance of PET Radiomic Features Using 3-Dimensionally Printed Phantom Inserts

“…Nonetheless, because a high ICC also indicates that features can differentiate well between inserts, our results suggest that EARLcompliant reconstructions also result in more meaningful features, especially when using the EARL2 settings. This is in line with the findings of Aide et al, who showed that images reconstructed with higher-resolution reconstructions improved the characterization of breast tumors when compared with EARL1 (22).…”

A Systematic Review of PET Textural Analysis and Radiomics in Cancer

“…Finally, we found 44 papers evaluating technical factors [ 53 , 60 , 61 , 62 , 64 , 154 , 303 , 304 , 305 , 306 , 307 , 308 , 309 , 310 , 311 , 312 , 313 , 314 , 315 , 316 , 317 , 318 , 319 , 320 , 321 , 322 , 323 , 324 , 325 , 326 , 327 , 328 , 329 , 330 , 331 , 332 , 333 , 334 , 335 , 336 , 337 , 338 , 339 ], without pursuing a clinical objective. Of these, 30% evaluated the impact of different tumor segmentation methods.…”

Texture Analysis in the Diagnosis of Primary Breast Cancer: Comparison of High-Resolution Dedicated Breast Positron Emission Tomography (dbPET) and Whole-Body PET/CT

“…The effect of the image reconstruction methods on the texture analysis of dbPET should also be clarified in the future. High-resolution reconstruction of PET/CT images has been reported to change the textural features compared to standard reconstructed clinical PET images (11,25). It is necessary to assess how the texture features of dbPET change compared to that of the whole-body PET/CT image due to the differences in the reconstruction method.…”

“…In the past few years, research on radiomics has focused particularly on texture analysis using various imaging modalities, including BC studies utilizing MRI and US (7,8). Some studies reported that PET images' texture features are associated with BC subtypes and prognosis (9)(10)(11). Texture analysis, which assesses intra-tumoral heterogeneity to compute image-specific information, is highly reproducible, has little variation among diagnostic radiologists, and will help mitigate the shortage of said radiologists who are excellent at diagnosing BC imaging.…”