Dataset Information

A systematic review and quality of reporting checklist for repeatability and reproducibility of radiomic features

ABSTRACT: Highlights • Main factors impacting feature stability: Image acquisition, reconstruction, tumor segmentation, and interpolation.• Textural features are less robust than morphological or statistical features.• A checklist is provided including items that should be reported in a radiomic study.

Purpose

Although quantitative image biomarkers (radiomics) show promising value for cancer diagnosis, prognosis, and treatment assessment, these biomarkers still lack reproducibility. In this systematic review, we aimed to assess the progress in radiomics reproducibility and repeatability in the recent years.

Methods and materials

Four hundred fifty-one abstracts were retrieved according to the original PubMed search pattern with the publication dates ranging from 2017/05/01 to 2020/12/01. Each abstract including the keywords was independently screened by four observers. Forty-two full-text articles were selected for further analysis. Patient population data, radiomic feature classes, feature extraction software, image preprocessing, and reproducibility results were extracted from each article. To support the community with a standardized reporting strategy, we propose a specific reporting checklist to evaluate the feasibility to reproduce each study.

Results

Many studies continue to under-report essential reproducibility information: all but one clinical and all but two phantom studies missed to report at least one important item reporting image acquisition. The studies included in this review indicate that all radiomic features are sensitive to image acquisition, reconstruction, tumor segmentation, and interpolation. However, the amount of sensitivity is feature dependent, for instance, textural features were, in general, less robust than statistical features.

Conclusions

Radiomics repeatability, reproducibility, and reporting quality can substantially be improved regarding feature extraction software and settings, image preprocessing and acquisition, cutoff values for stable feature selection. Our proposed radiomics reporting checklist can serve to simplify and improve the reporting and, eventually, guarantee the possibility to fully replicate and validate radiomic studies.

SUBMITTER: Pfaehler E

PROVIDER: S-EPMC8591412 | biostudies-literature |

REPOSITORIES: biostudies-literature

ACCESS DATA

Similar Datasets

Project description:PurposeAn ever-growing number of predictive models used to inform clinical decision making have included quantitative, computer-extracted imaging biomarkers, or "radiomic features." Broadly generalizable validity of radiomics-assisted models may be impeded by concerns about reproducibility. We offer a qualitative synthesis of 41 studies that specifically investigated the repeatability and reproducibility of radiomic features, derived from a systematic review of published peer-reviewed literature.Methods and materialsThe PubMed electronic database was searched using combinations of the broad Haynes and Ingui filters along with a set of text words specific to cancer, radiomics (including texture analyses), reproducibility, and repeatability. This review has been reported in compliance with Preferred Reporting Items for Systematic Reviews and Meta-Analyses guidelines. From each full-text article, information was extracted regarding cancer type, class of radiomic feature examined, reporting quality of key processing steps, and statistical metric used to segregate stable features.ResultsAmong 624 unique records, 41 full-text articles were subjected to review. The studies primarily addressed non-small cell lung cancer and oropharyngeal cancer. Only 7 studies addressed in detail every methodologic aspect related to image acquisition, preprocessing, and feature extraction. The repeatability and reproducibility of radiomic features are sensitive at various degrees to processing details such as image acquisition settings, image reconstruction algorithm, digital image preprocessing, and software used to extract radiomic features. First-order features were overall more reproducible than shape metrics and textural features. Entropy was consistently reported as one of the most stable first-order features. There was no emergent consensus regarding either shape metrics or textural features; however, coarseness and contrast appeared among the least reproducible.ConclusionsInvestigations of feature repeatability and reproducibility are currently limited to a small number of cancer types. Reporting quality could be improved regarding details of feature extraction software, digital image manipulation (preprocessing), and the cutoff value used to distinguish stable features.

Project description:ObjectivesWe aimed to investigate the influence of magnetic resonance fingerprinting (MRF) dictionary design on radiomic features using in vivo human brain scans.MethodsScan-rescans of three-dimensional MRF and conventional T1-weighted imaging were performed on 21 healthy volunteers (9 males and 12 females; mean age, 41.3 ± 14.6 years; age range, 22-72 years). Five patients with multiple sclerosis (3 males and 2 females; mean age, 41.2 ± 7.3 years; age range, 32-53 years) were also included. MRF data were reconstructed using various dictionaries with different step sizes. First- and second-order radiomic features were extracted from each dataset. Intra-dictionary repeatability and inter-dictionary reproducibility were evaluated using intraclass correlation coefficients (ICCs). Features with ICCs > 0.90 were considered acceptable. Relative changes were calculated to assess inter-dictionary biases.ResultsThe overall scan-rescan ICCs of MRF-based radiomics ranged from 0.86 to 0.95, depending on dictionary step size. No significant differences were observed in the overall scan-rescan repeatability of MRF-based radiomic features and conventional T1-weighted imaging (p = 1.00). Intra-dictionary repeatability was insensitive to dictionary step size differences. MRF-based radiomic features varied among dictionaries (overall ICC for inter-dictionary reproducibility, 0.62-0.99), especially when step sizes were large. First-order and gray level co-occurrence matrix features were the most reproducible feature classes among different step size dictionaries. T1 map-derived radiomic features provided higher repeatability and reproducibility among dictionaries than those obtained with T2 maps.ConclusionMRF-based radiomic features are highly repeatable in various dictionary step sizes. Caution is warranted when performing MRF-based radiomics using datasets containing maps generated from different dictionaries.Key points• MRF-based radiomic features are highly repeatable in various dictionary step sizes. • Use of different MRF dictionaries may result in variable radiomic features, even when the same MRF acquisition data are used. • Caution is needed when performing radiomic analysis using data reconstructed from different dictionaries.

Project description:BackgroundIn January 2003, STAndards for the Reporting of Diagnostic accuracy studies (STARD) were published in a number of journals, to improve the quality of reporting in diagnostic accuracy studies. We designed a study to investigate the inter-assessment reproducibility, and intra- and inter-observer reproducibility of the items in the STARD statement.MethodsThirty-two diagnostic accuracy studies published in 2000 in medical journals with an impact factor of at least 4 were included. Two reviewers independently evaluated the quality of reporting of these studies using the 25 items of the STARD statement. A consensus evaluation was obtained by discussing and resolving disagreements between reviewers. Almost two years later, the same studies were evaluated by the same reviewers. For each item, percentages agreement and Cohen's kappa between first and second consensus assessments (inter-assessment) were calculated. Intraclass Correlation coefficients (ICC) were calculated to evaluate its reliability.ResultsThe overall inter-assessment agreement for all items of the STARD statement was 85% (Cohen's kappa 0.70) and varied from 63% to 100% for individual items. The largest differences between the two assessments were found for the reporting of the rationale of the reference standard (kappa 0.37), number of included participants that underwent tests (kappa 0.28), distribution of the severity of the disease (kappa 0.23), a cross tabulation of the results of the index test by the results of the reference standard (kappa 0.33) and how indeterminate results, missing data and outliers were handled (kappa 0.25). Within and between reviewers, also large differences were observed for these items. The inter-assessment reliability of the STARD checklist was satisfactory (ICC = 0.79 [95% CI: 0.62 to 0.89]).ConclusionAlthough the overall reproducibility of the quality of reporting on diagnostic accuracy studies using the STARD statement was found to be good, substantial disagreements were found for specific items. These disagreements were not so much caused by differences in interpretation of the items by the reviewers but rather by difficulties in assessing the reporting of these items due to lack of clarity within the articles. Including a flow diagram in all reports on diagnostic accuracy studies would be very helpful in reducing confusion between readers and among reviewers.

Project description:PurposeTo investigate reproducibility of myocardial radiomic features with cardiac MRI.Materials and methodsTest-retest studies were performed with a 3-T MRI system using commonly used cardiac MRI sequences of cine balanced steady-state free precession (cine bSSFP), T1-weighted and T2-weighted imaging, and quantitative T1 and T2 mapping in phantom experiments and 10 healthy participants (mean ± standard deviation age, 29 years ± 13). In addition, this study assessed repeatability in 51 patients (56 years ± 14) who underwent imaging twice during the same session. Three readers independently delineated the myocardium to investigate inter- and intraobserver reproducibility of radiomic features. A total of 1023 radiomic features were extracted by using PyRadiomics (https://pyradiomics.readthedocs.io/) with 11 image filters and six feature families. The intraclass correlation coefficient (ICC) was estimated to assess reproducibility and repeatability, and features with ICCs greater than or equal to 0.8 were considered reproducible.ResultsDifferent reproducibility patterns were observed among sequences in in vivo test-retest studies. In cine bSSFP, the gray-level run-length matrix was the most reproducible feature family, and the wavelet low-pass filter applied horizontally and vertically was the most reproducible image filter. In T1 and T2 maps, intensity-based statistics (first-order) and gray-level co-occurrence matrix features were the most reproducible feature families, without a dominant reproducible image filter. Across all sequences, gray-level nonuniformity was the most frequently identified reproducible feature name. In inter- and intraobserver reproducibility studies, respectively, only 32%-47% and 61%-73% of features were identified as reproducible.ConclusionOnly a small subset of myocardial radiomic features was reproducible, and these reproducible radiomic features varied among different sequences. Supplemental material is available for this article. © RSNA, 2020See also the commentary by Leiner in this issue.

Project description:PurposeTo assess the contribution of a generative adversarial network (GAN) to improve intermanufacturer reproducibility of radiomic features (RFs).Materials and methodsThe authors retrospectively developed a cycle-GAN to translate texture information from chest radiographs acquired using one manufacturer (Siemens) to chest radiographs acquired using another (Philips), producing fake chest radiographs with different textures. The authors prospectively evaluated the ability of this texture-translation cycle-GAN to reduce the intermanufacturer variability of RFs extracted from the lung parenchyma. This study assessed the cycle-GAN's ability to fool several machine learning (ML) classifiers tasked with recognizing the manufacturer on the basis of chest radiography inputs. The authors also evaluated the cycle-GAN's ability to mislead radiologists who were asked to perform the same recognition task. Finally, the authors tested whether the cycle-GAN had an impact on radiomic diagnostic accuracy for chest radiography in patients with congestive heart failure (CHF).ResultsRFs, extracted from chest radiographs after the cycle-GAN's texture translation (fake chest radiographs), showed decreased intermanufacturer RF variability. Using cycle-GAN-generated chest radiographs as inputs, ML classifiers categorized the fake chest radiographs as belonging to the target manufacturer rather than to a native one. Moreover, cycle-GAN fooled two experienced radiologists who identified fake chest radiographs as belonging to a target manufacturer class. Finally, reducing intermanufacturer RF variability with cycle-GAN improved the discriminative power of RFs for patients without CHF versus patients with CHF (from 55% to 73.5%, P < .001).ConclusionBoth ML classifiers and radiologists had difficulty recognizing the chest radiographs' manufacturer. The cycle-GAN improved RF intermanufacturer reproducibility and discriminative power for identifying patients with CHF. This deep learning approach may help counteract the sensitivity of RFs to differences in acquisition.Supplemental material is available for this article.© RSNA, 2020See also the commentary by Alderson in this issue.

Project description:ObjectivesTo examine the quality of reporting of harms in systematic reviews, and to determine the need for a reporting guideline specific for reviews of harms.DesignSystematic review.Data sourcesCochrane Database of Systematic Reviews (CDSR) and Database of Abstracts of Reviews of Effects (DARE).Review methodsDatabases were searched for systematic reviews having an adverse event as the main outcome, published from January 2008 to April 2011. Adverse events included an adverse reaction, harms, or complications associated with any healthcare intervention. Articles with a primary aim to investigate the complete safety profile of an intervention were also included. We developed a list of 37 items to measure the quality of reporting on harms in each review; data were collected as dichotomous outcomes ("yes" or "no" for each item).ResultsOf 4644 reviews identified, 309 were systematic reviews or meta-analyses primarily assessing harms (13 from CDSR; 296 from DARE). Despite a short time interval, the comparison between the years of 2008 and 2010-11 showed no difference on the quality of reporting over time (P=0.079). Titles in fewer than half the reviews (proportion of reviews 0.46 (95% confidence interval 0.40 to 0.52)) did not mention any harm related terms. Almost one third of DARE reviews (0.26 (0.22 to 0.31)) did not clearly define the adverse events reviewed, nor did they specify the study designs selected for inclusion in their methods section. Almost half of reviews (n=170) did not consider patient risk factors or length of follow-up when reviewing harms of an intervention. Of 67 reviews of complications related to surgery or other procedures, only four (0.05 (0.01 to 0.14)) reported professional qualifications of the individuals involved. The overall, unweighted, proportion of reviews with good reporting was 0.56 (0.55 to 0.57); corresponding proportions were 0.55 (0.53 to 0.57) in 2008, 0.55 (0.54 to 0.57) in 2009, and 0.57 (0.55 to 0.58) in 2010-11.ConclusionSystematic reviews compound the poor reporting of harms data in primary studies by failing to report on harms or doing so inadequately. Improving reporting of adverse events in systematic reviews is an important step towards a balanced assessment of an intervention.