Assessing the reproducibility of CBCT-derived radiomics features using a novel three-dimensional printed phantom.

PURPOSE: Radiomics modeling is an exciting avenue for enhancing clinical decision making and personalized treatment. Radiation oncology patients often undergo routine imaging for position verification, particularly using LINAC-mounted cone beam computed tomography (CBCT). The wealth of imaging data collected in modern radiation therapy presents an ideal use case for radiomics modeling. Despite this, texture feature (TF) calculation can be limited by concerns over feature stability and reproducibility; in theory, this issue is compounded by the relatively poor image quality of CBCT, as well as variation of acquisition and reconstruction parameters. METHODS: In this study, we developed and validated a novel three-dimensional (3D) printed phantom for evaluating CBCT-based TF reliability. The phantom has a cylindrical shape (22 cm diameter and 25.5 cm height) with five inner inserts designed to hold custom-printed rods (1 cm diameter and 10-20 cm height) of various materials, infill shapes, and densities. TF reproducibility was evaluated across and within three LINACs from a single vendor using sets of three consecutive CBCT taken with the head, thorax, and pelvis clinical imaging protocols. PyRadiomics was used to extract a standard set of TFs from regions of interest centered on each rod. Two-way mixed effects absolute agreement intra-class correlation coefficient (ICC) was used to evaluate TF reproducibility, with features showing ICC values above 0.9 considered robust if their Bonferroni-corrected p-value was below 0.05. RESULTS: A total of 63, 87, and 83 features exhibited test-retest reliability for the head, thorax, and pelvis imaging protocols respectively. When assessing stability between discreet imaging sessions on the same LINAC, these numbers were reduced to 5, 63, and 70 features, respectively. The thorax and pelvis protocols maintained a rich candidate feature space in inter-LINAC analysis with 61 and 65 features, respectively, exceeding the ICC criteria. Crucially, no features were deemed reproducible when compared between protocols. CONCLUSIONS: We have developed a 3D phantom for consistent evaluation of TF stability and reproducibility. For LINACs from a single vendor, our study found a substantial number of features available for robust radiomics modeling from CBCT imaging. However, some features showed variations across LINACs. Studies involving CBCT-based radiomics must preselect features prior to their use in clinical-based models.

Task-based assessment of a convolutional neural network for segmenting breast lesions for radiomic analysis.

PURPOSE: Radiomics allows for powerful data-mining and feature extraction techniques to guide clinical decision making. Image segmentation is a necessary step in such pipelines and different techniques can significantly affect results. We demonstrate that a convolutional neural network (CNN) segmentation method performs comparably to expert manual segmentations in an established radiomics pipeline. METHODS: Using the manual regions of interest (ROIs) of an expert radiologist (R1), a CNN was trained to segment breast lesions from dynamic contrast-enhanced MRI (DCE-MRI). Following network training, we segmented lesions for the testing set of a previously established radiomics pipeline for predicting lymph node metastases using DCE-MRI of breast cancer. Prediction accuracy of CNN segmentations relative to manual segmentations by R1 from the original study, a resident (R2), and another expert radiologist (R3) were determined. We then retrained the CNN and radiomics model using R3's manual segmentations to determine the effects of different expert observers on end-to-end prediction. RESULTS: Using R1's ROIs, the CNN achieved a mean Dice coefficient of 0.71 ± 0.16 in the testing set. When input to our previously published radiomics pipeline, these CNN segmentations achieved comparable prediction performance to R1's manual ROIs, and superior performance to those of the other radiologists. Similar results were seen when training the CNN and radiomics model using R3's ROIs. CONCLUSION: A CNN architecture is able to provide DCE-MRI breast lesion segmentations which are suitable for input to our radiomics model. Moreover, the previously established radiomics model and CNN can be accurately trained end-to-end using ground truth data provided by distinct experts.

Synthesis of Patient-Specific Transmission Data for PET Attenuation Correction for PET/MRI Neuroimaging Using a Convolutional Neural Network.

Attenuation correction is a notable challenge associated with simultaneous PET/MRI, particularly in neuroimaging, where sharp boundaries between air and bone volumes exist. This challenge leads to concerns about the visual and, more specifically, quantitative accuracy of PET reconstructions for data obtained with PET/MRI. Recently developed techniques can synthesize attenuation maps using only MRI data and are likely adequate for clinical use; however, little work has been conducted to assess their suitability for the dynamic PET studies frequently used in research to derive physiologic information such as the binding potential of neuroreceptors in a region. At the same time, existing PET/MRI attenuation correction methods are predicated on synthesizing CT data, which is not ideal, as CT data are acquired with much lower-energy photons than PET data and thus do not optimally reflect the PET attenuation map. Methods: We trained a convolutional neural network to generate patient-specific transmission data from T1-weighted MRI. Using the trained network, we generated transmission data for a testing set comprising 11 subjects scanned with 11C-labeled N-[2-]4-(2-methoxyphenyl)-1-piperazinyl]ethyl]-N-(2-pyridinyl)cyclohexanecarboxamide) (11C-WAY-100635) and 10 subjects scanned with 11C-labeled 3-amino-4-(2-dimethylaminomethyl-phenylsulfanyl)benzonitrile (11C-DASB). We assessed both static and dynamic reconstructions. For dynamic PET data, we report differences in both the nondisplaceable and the free binding potential for 11C-WAY-100635 and distribution volume for 11C-DASB. Results: The mean bias for generated transmission data was -1.06% ± 0.81%. Global biases in static PET uptake were -0.49% ± 1.7%, and -1.52% ± 0.73% for 11C-WAY-100635 and 11C-DASB, respectively. Conclusion: Our neural network approach is capable of synthesizing patient-specific transmission data with sufficient accuracy for both static and dynamic PET studies.