La radiologia medica, Journal Year: 2024, Volume and Issue: 129(11), P. 1559 - 1574
Published: Oct. 16, 2024
Language: Английский
Published: Jan. 1, 2025
Language: Английский
Citations
5
European Radiology, Journal Year: 2025, Volume and Issue: unknown
Published: Jan. 9, 2025
Abstract Objectives To investigate how studies determine the sample size when developing radiomics prediction models for binary outcomes, and whether meets estimates obtained by using established criteria. Methods We identified that were published from 01 January 2023 to 31 December in seven leading peer-reviewed radiological journals. reviewed justification methods, actual used. calculated compared used three criteria proposed Riley et al. investigated which characteristics factors associated with sufficient Results included 116 studies. Eleven out of one hundred sixteen justified size, 6/11 performed a priori calculation. The median (first third quartile, Q1, Q3) total is 223 (130, 463), those training are 150 (90, 288). (Q1, difference between minimum according −100 (−216, 183), differences more restrictive approach based on −268 (−427, −157). presence external testing specialty topic size. Conclusion Radiomics often designed without justification, whose may be too small avoid overfitting. Sample encouraged model. Key Points Question critical help minimize overfitting model, but overlooked underpowered research . Findings Few justified, calculated, or reported their most them did not meet recent formal Clinical relevance justification. Consequently, many It should justify, perform, report considerations
Language: Английский
Citations
2
European Radiology, Journal Year: 2024, Volume and Issue: unknown
Published: July 24, 2024
To evaluate the robustness of radiomics features among photon-counting detector CT (PCD-CT) and dual-energy (DECT) systems.
Language: Английский
Citations
7
European Radiology, Journal Year: 2025, Volume and Issue: unknown
Published: Jan. 31, 2025
To assess the impact of acquisition and reconstruction factors on robustness radiomics within photon-counting detector CT (PCD-CT). A phantom with twenty-eight texture materials was scanned different including reposition, scan mode (standard vs high-pitch), tube voltage (120 kVp 140 kVp), slice thickness (1.0 mm 0.4 mm), radiation dose level (0.5 mGy, 1.0 3.0 5.0 10.0 mGy), quantum iterative (0/4, 2/4, 4/4), kernel (Qr40, Qr44, Qr48). Thirteen sets virtual monochromatic images at 70-keV were reconstructed. The regions interest drawn rigid registrations. Ninety-three features extracted from each material. reproducibility evaluated using intraclass correlation coefficient (ICC) concordance (CCC). variability assessed by variation (CV) quartile dispersion (QCD). percentage ICC > 0.90 CCC high when repositioned (88.2% 88.2%) changed (87.1% 87.1%), but none high-pitch used. CV < 10% QCD (47.3% 68.8%) (64.2% 71.0%), that low between standard scans (16.1% 26.9%) (19.4% 29.0%). PCD-CT robust to voltage, dose, strength level, kernel, brittle thickness. Question stability against should be fully determined before academic research clinical application. Findings are Clinical relevance influence voxel size set careful attention PCD-CT, allow a higher implementation analysis in routine.
Language: Английский
Citations
1
European Radiology, Journal Year: 2023, Volume and Issue: 34(4), P. 2805 - 2815
Published: Sept. 22, 2023
Language: Английский
Citations
15
Journal of Magnetic Resonance Imaging, Journal Year: 2024, Volume and Issue: unknown
Published: May 11, 2024
Background Radiomics models trained on data from one center typically show a decline of performance when applied to external centers, hindering their introduction into large‐scale clinical practice. Current expert recommendations suggest use only reproducible radiomics features isolated by multiscanner test–retest experiments, which might help overcome the problem limited generalizability data. Purpose To evaluate influence using subset robust features, defined in prior vivo multi‐MRI‐scanner test–retest‐study, and models. Study Type Retrospective. Population Patients with monoclonal plasma cell disorders. Training set (117 MRIs 1); internal test (42 (143 2–8). Field Strength/Sequence 1.5T 3.0T; T1‐weighted turbo spin echo. Assessment The task for was predict infiltration, determined bone marrow biopsy, noninvasively MRI. machine learning models, including linear regressor, support vector regressor (SVR), random forest (RFR), were 1, either all or features. Models tested an (center 1) multicentric Statistical Tests Pearson correlation coefficient r mean absolute error (MAE) between predicted actual infiltration. Fisher's z‐transformation, Wilcoxon signed‐rank test, rank‐sum test; significance level P < 0.05. Results When compared SVR significantly improved ( = 0.43 vs. 0.18 MAE 22.6 28.2). For RFR, deteriorated instead 0.33 0.44, 0.29 21.9 20.5, 0.10). Conclusion Using improves some, but not did automatically lead improvement overall best model. Level Evidence 3. Technical Efficacy Stage 2.
Language: Английский
Citations
6
Insights into Imaging, Journal Year: 2024, Volume and Issue: 15(1)
Published: June 3, 2024
Abstract Objectives Achieving a consensus on definition for different aspects of radiomics workflows to support their translation into clinical usage. Furthermore, assess the perspective experts important challenges successful workflow implementation. Materials and methods The was achieved by multi-stage process. Stage 1 comprised screening, retrospective analysis with semantic mapping terms found in 22 definitions, compilation an initial baseline definition. Stages 2 3 consisted Delphi process over 45 hailing from sites participating German Research Foundation (DFG) Priority Program 2177. aimed achieve broad proposal, while stage identified importance translational challenges. Results Workflow definitions publications (published 2012–2020) were analyzed. Sixty-nine extracted, mapped, ambiguities (e.g., homonymous synonymous terms) resolved. developed via final comprising seven phases 37 reached high overall (> 89% “agree” or “strongly agree”). Two no strong consensus. In addition, characterized experts’ ten most workflows. Conclusion To overcome inconsistencies between existing offer well-defined, broad, referenceable terminology, radiomics-based setups literature compiled. Moreover, relevant towards application characterized. Critical relevance statement Lack standardization represents one major obstacle radiomics. Here, we report studies highlight advance adoption Key Points Published terminologies are inconsistent, hindering translation. A proposal agreement developed. Publicly available result resources further exploitation scientific community. Graphical
Language: Английский
Citations
6
American Journal of Neuroradiology, Journal Year: 2024, Volume and Issue: 45(2), P. 236 - 243
Published: Jan. 12, 2024
MS is a chronic progressive, idiopathic, demyelinating disorder whose diagnosis contingent on the interpretation of MR imaging. New imaging lesions are an early biomarker disease progression. We aimed to evaluate machine learning model based radiomics features in predicting progression brain individuals with MS.
Language: Английский
Citations
4
European Radiology, Journal Year: 2024, Volume and Issue: 34(10), P. 6527 - 6543
Published: April 16, 2024
Lung cancer, the second most common presents persistently dismal prognoses. Radiomics, a promising field, aims to provide novel imaging biomarkers improve outcomes. However, clinical translation faces reproducibility challenges, despite efforts address them with quality scoring tools.
Language: Английский
Citations
3
Heliyon, Journal Year: 2024, Volume and Issue: 10(13), P. e33702 - e33702
Published: June 26, 2024
Language: Английский
Citations
3