The radiomics phantom was developed by our group previously 14 and was used to assess the repeatability of radiomic features for the imaging sequences used in clinical rectal cancer patients. The phantom was imaged twice during each imaging session over a four-month period to measure the temporal stability of radiomic features.
The phantom was positioned on two oil filled containers to ensure adequate signal to trigger a localiser scan (Figure 3-a). A non-slip mat was placed under the phantom base to minimise movement and vibrations caused by image acquisition.
The phantom is comprised of eight test objects of which three were used in this study for radiomics analysis including test objects M1, M2 and M8 (Figure 3-b). Only three test objects were selected for segmentation as these objects have a variation of textures and shapes, including a solid homogenous structure (M1), heterogeneous structure with fine texture details (M2) and a complex shape (M8). The test objects were segmented using a global threshold-based segmentation method described by Rai et al.14. The threshold values are based on the minimum and maximum pixel values. This was performed on one reference scan (test) and then propagated on the second scan (retest) to minimise contour variability. The upper and lower threshold pixel values were based on the histogram of the models.
Retrospective analysis of a test-retest cohort of rectal cancer patients was performed. This study was approved by the South Western Sydney Human Research Ethics Committee (SWSLHD HREC) (HREC Number: HREC/15/LPOOL/555). All patients included in this study provided written informed consent. All experiments were performed in accordance with relevant guidelines and regulations.
Ten patients treated at Liverpool and Macarthur Cancer Therapy Centre between 2015 and 2017 with stage IIIA-IVB rectal adenocarcinoma were recruited. Inclusion criteria included any patient with confirmed rectal adenocarcinoma requiring a simulation MRI for their radiation therapy planning. Exclusion criteria were patients with a contraindication to MRI such as non-safe or non-compatible medical devices.
All imaging in this study was conducted on a radiotherapy dedicated 3 Tesla MRI (MAGNETOM Skyra, Siemens Healthineers, Erlangen, Germany), using an 18-channel receiver only surface coil and 32-channel spine coil integrated into the MRI bed. A flat top radiation therapy table (CIVCO Medical Solutions, Coralville, USA) was used for both phantom and patient imaging to replicate patient treatment conditions (Figure 3-a).
The imaging protocol acquired for both phantom and patients was a T2-weighted (T2-w) turbo spin echo (TSE) sequence. The sequence was acquired with a TE/TR of 96/10000 ms, 3/0 mm slice thickness/spacing, 1 signal average, 320 x 224 matrix, 160° flip angle, 400Hz/Px receiver bandwidth, 220 mm field of view (FOV), and 0.7 x 0.7 mm2 in-plane resolution.
The phantom test objects were placed on a 3D printed horizontal plate in their corresponding position. The horizontal plate was aligned using the external laser bridge system (LAP Laser, Luneburg, Germany) at every scan session to ensure accurate reproducibility of position and to minimise setup errors. The phantom was imaged weekly for a period of 4 months.
All patients in the test-retest cohort were scanned in their radiation therapy (RT) treatment position including a flat table top and radiation therapy immobilisation equipment. The external laser system was used to align the patient to their planning tattoos (given in CT simulation) to assist with reproducing the patient position. After the first sequence was acquired (test) the patient left the MRI room and went for a short walk. They were then repositioned in the same RT planning positioning and the second T2-w TSE scan was acquired (retest). All ten patients received two scans for a total of 20 datasets.
The impact of varied image quality on the reproducibility of radiomic features in the phantom was investigated to assess the impact it may have on radiomic feature stability.
To assess the impact on feature stability, the original phantom images were pre-processed with added noise and variable spatial resolution. To adjust the spatial resolution, the images were resampled to 0.5, 0.8, 1 and 1.2 mm2. To add noise to the original images a Gaussian noise filter was added to the datasets. The standard deviation of the noise levels tested were set to 2, 5, 10 and 20 with the range of image intensities ranging from 0 to 302. For all images (both original and processed), the SNR within the individual images was assessed as the mean signal intensity within one phantom test object (M1) divided by the standard deviation of a nearby air signal. All post-processing was performed in 3D Slicer (Version 4.13.0, available at: http://slicer.org/).
Tumour and Tissue Segmentation
All segmentations were performed in imaging processing software MiM (MiM Maestro, Cleveland, OH, USA).
The rectal tumour volumes were contoured manually by two radiation oncologists (MH & YT) on both repeat T2-w sequences. Observer 2 (YT) performed a copy and adjust contour from the original contour of observer 1 (MH). The rectal tumour volume was defined as a high signal region on T2-w imaging by both observers. Care was taken to ensure only the tumour volumes excluded healthy rectal wall, lumen and faecal matter (Figure 4). This process was completed on both test and retest imaging by both observers.
Normal Tissue Segmentation
The right gluteus maximus was selected as a reference for normal tissue. Radiomic feature stability within a reference muscle was performed to quantify features that are stable in an otherwise normal human tissue.
The gluteus maximus was selected as it is covered in the field of view of all MRI scans across all datasets and was consistently outside the highest planning dose areas (< 20% of Max Dose). A spherical ROI was placed over the middle of the gluteus maximus on axial imaging. The size of the spherical ROI was kept consistent across all scans with an average volume of 4 cc. The reference muscle was contoured manually by a single observer (RR) on T2-w imaging
Both in-vivo and phantom segmentations were analysed using PyRadiomics21 which is available in-house as a plug in within MiM software. 83 radiomic features were calculated including 15 first order statistics, 14 shape, and various textural features including 23 GLCM, 13 GLRLM, 13 GLSZM and 5 from NGTDM. All features were computed with a fixed bin width of 25. A list of all features examined can be found in supplementary material (Table 1).
Statistical Analysis & Feature Selection
For both the original and post-processed phantom imaging, the coefficient of variation (COV) was calculated to assess the degree of variability in features. The COV was calculated as:
where the standard deviation (SD) and the mean is derived from the radiomic features over all time points of imaging for each model.
The features were divided into four groups based on COV as very small (COV ≤ 5%), small (5% < COV ≤ 10%), intermediate (10% < COV ≤ 20%), and large (COV > 20%) ranges of variation 22.
For the test-retest patient cohort, the intraclass correlation coefficient (ICC) test was performed to measure the reproducibility and repeatability of radiomic features between the test and retest scans for both observers for the rectal tumour volumes and normal muscles.
The impact of spatial resolution and Gaussian noise filtering on the reproducibility and repeatability of each radiomic feature were quantified using ICC. Features that returned an ICC of ≥ 0.8 were considered to have an almost perfect strength of agreement. ICC was calculated in R using the DescTools package (Version 3.5.1).