Minimizing acquisition-related radiomics variability by image resampling and batch effect correction to allow for large-scale data analysis
| Autor: | K. Bernatowicz, Nahum Calvo, Manuel Escobar, Roser Sala-Llonch, Eric Delgado-Muñoz, Cristina Suarez, Richard Mast, Alonso Garcia-Ruiz, Arturo Navarro-Martin, David Leiva, Marta Ligero, Rodrigo Dienstmann, Raquel Perez-Lopez, Olivia Jordi-Ollero, Guillermo Villacampa |
|---|---|
| Rok vydání: | 2020 |
| Předmět: |
Data Analysis
medicine.medical_specialty Tomografia Normalization (image processing) Image processing computer.software_genre Imaging phantom 030218 nuclear medicine & medical imaging Metastasis 03 medical and health sciences Computed Tomography 0302 clinical medicine Metàstasi Voxel Resampling Image Processing Computer-Assisted Image scaling medicine Humans Radiology Nuclear Medicine and imaging Càncer Tomography Retrospective Studies Cancer X-ray computed tomography Pixel Phantoms Imaging business.industry Radiologic phantom Biochemical markers Pattern recognition General Medicine Imatges mèdiques 030220 oncology & carcinogenesis Marcadors bioquímics Radiology Artificial intelligence Tomography X-Ray Computed business computer Imaging systems in medicine |
| Zdroj: | Dipòsit Digital de la UB Universidad de Barcelona European Radiology |
| Popis: | Objective To identify CT-acquisition parameters accounting for radiomics variability and to develop a post-acquisition CT-image correction method to reduce variability and improve radiomics classification in both phantom and clinical applications. Methods CT-acquisition protocols were prospectively tested in a phantom. The multi-centric retrospective clinical study included CT scans of patients with colorectal/renal cancer liver metastases. Ninety-three radiomics features of first order and texture were extracted. Intraclass correlation coefficients (ICCs) between CT-acquisition protocols were evaluated to define sources of variability. Voxel size, ComBat, and singular value decomposition (SVD) compensation methods were explored for reducing the radiomics variability. The number of robust features was compared before and after correction using two-proportion z test. The radiomics classification accuracy (K-means purity) was assessed before and after ComBat- and SVD-based correction. Results Fifty-three acquisition protocols in 13 tissue densities were analyzed. Ninety-seven liver metastases from 43 patients with CT from two vendors were included. Pixel size, reconstruction slice spacing, convolution kernel, and acquisition slice thickness are relevant sources of radiomics variability with a percentage of robust features lower than 80%. Resampling to isometric voxels increased the number of robust features when images were acquired with different pixel sizes (p < 0.05). SVD-based for thickness correction and ComBat correction for thickness and combined thickness–kernel increased the number of reproducible features (p < 0.05). ComBat showed the highest improvement of radiomics-based classification in both the phantom and clinical applications (K-means purity 65.98 vs 73.20). Conclusion CT-image post-acquisition processing and radiomics normalization by means of batch effect correction allow for standardization of large-scale data analysis and improve the classification accuracy. Key Points • The voxel size (accounting for the pixel size and slice spacing), slice thickness, and convolution kernel are relevant sources of CT-radiomics variability. • Voxel size resampling increased the mean percentage of robust CT-radiomics features from 59.50 to 89.25% when comparing CT scans acquired with different pixel sizes and from 71.62 to 82.58% when the scans were acquired with different slice spacings. • ComBat batch effect correction reduced the CT-radiomics variability secondary to the slice thickness and convolution kernel, improving the capacity of CT-radiomics to differentiate tissues (in the phantom application) and the primary tumor type from liver metastases (in the clinical application). |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|