Stability of Radiomic Features across Different Region of Interest Sizes—A CT and MR Phantom Study

We aimed to evaluate radiomic features’ stability across different region of interest (ROI) sizes in CT and MR images. We chose a phantom with a homogenous internal structure so no differences for a feature extracted from ROIs of different sizes would be expected. For this, we scanned a plastic cup filled with sodium chloride solution ten times in CT and per MR sequence (T1-weighted-gradient-echo and T2-weighted-turbo-inversion-recovery-magnitude). We placed sphere-shaped ROIs of different diameters (4, 8, and 16 mm, and 4, 8, and 16 pixels) into the phantom’s center. Features were extracted using PyRadiomics. We assessed feature stability across ROI sizes with overall concordance correlation coefficients (OCCCs). Differences were tested for significance with the Mann–Whitney U-test. Of 93 features, 87 T1w-derived, 87 TIRM-derived, and 70 CT-derived features were significantly different between ROI sizes. Among MR-derived features, OCCCs showed excellent (>0.90) agreement for mean, median, and root mean squared for ROI sizes between 4 and 16 mm and pixels. We further observed excellent agreement for 10th and 90th percentile in T1w and 10th percentile in T2w TIRM images. There was no excellent agreement among the OCCCs of CT-derived features. In summary, many features indicated significant differences and only few showed excellent agreement across varying ROI sizes, although we examined a homogenous phantom. Since we considered a small phantom in an experimental setting, further studies to investigate this size effect would be necessary for a generalization. Nevertheless, we believe knowledge about this effect is crucial in interpreting radiomics studies, as features that supposedly discriminate disease entities may only indicate a systematic difference in ROI size.

Analisis Variasi Nilai Time Repetition (TR) dan Time Inversion (TI) terhadap Informasi Anatomi Sekuens Turbo Inversion Recovery Magnitude (TIRM) MRI Wrist Joint Dengan Menggunakan MRI 0,3 Tesla

Backgroud: The Turbo Inversion Recovery Magnitude (TIRM) pulse sequence is used to examine wrist joint, especially in the coronal plane. Main parameters of inversion recovery pulse sequence are time repetition (TR), time echo (TE) and time inversion (TI). This study aims to analyze the variation of time repetition (TR) and time inversion (TI) on anatomical information using TIRM pulse sequence on wrist joint MR imaging with 0,3 tesla.Methods: This study was a quantitave experimental study with a linear regression test. This study was conducted in Radiology Department of Banyumas hospital using twenty serial images from only one patient with 10 variation of TR (3000 ms, 3200ms, 3400 ms, 3600 ms, 3800 ms, 4000 ms, 4200 ms, 4400 ms, 4600 ms, 4800 ms) and 10 variation of TI (70 ms, 75 ms, 80 ms, 85 ms, 90 ms, 95 ms, 100 ms, 105 ms, 110 ms, 115 ms). Image assessed by only one respondent.Results: There was no significant influence of variation of TR and TI on anatomical information. Significant number was 0,240 which is bigger than p value (0,05). TR and TI variation affected just only 15,5% to anatomical information, 84,5% was influenced by other variables that unconfirmed in this study.Conclusion: There was differences of anatomical information in MRI wrist joint sequence coronal T2WI-FSE fat suppression between SPIR and SPAIR with a significance level of p value 0.001 (p 0.05). SPAIR is the method which is clearer to show the anatomical information of wrist joint.