Background/HypothesisMRI-guided online adaptive radiotherapy (MRI-g-OART) improves target coverage and organs-at-risk (OARs) sparing in radiation therapy (RT). For patients with locally advanced cervical cancer (LACC) undergoing RT, changes in bladder and rectal filling contribute to large inter-fraction target volume motion. We hypothesized that deep learning (DL) convolutional neural networks (CNN) can be trained to accurately segment gross tumor volume (GTV) and OARs both in planning and daily fractions’ MRI scans.Materials/MethodsWe utilized planning and daily treatment fraction setup (RT-Fr) MRIs from LACC patients, treated with stereotactic body RT to a dose of 45-54 Gy in 25 fractions. Nine structures were manually contoured. MASK R-CNN network was trained and tested under three scenarios: (i) Leave-one-out (LOO), using the planning images of N- 1 patients for training; (ii) the same network, tested on the RT-Fr MRIs of the “left-out” patient, (iii) including the planning MRI of the “left-out” patient as an additional training sample, and tested on RT-Fr MRIs. The network performance was evaluated using the Dice Similarity Coefficient (DSC) and Hausdorff distances. The association between the structures’ volume and corresponding DSCs was investigated using Pearson’s Correlation Coefficient, r.ResultsMRIs from fifteen LACC patients were analyzed. In the LOO scenario the DSC for Rectum, Femur, and Bladder was >0.8, followed by the GTV, Uterus, Mesorectum and Parametrium (0.6-0.7). The results for Vagina and Sigmoid were suboptimal. The performance of the network was similar for most organs when tested on RT-Fr MRI. Including the planning MRI in the training did not improve the segmentation of the RT-Fr MRI. There was a significant correlation between the average organ volume and the corresponding DSC (r = 0.759, p = 0.018).ConclusionWe have established a robust workflow for training MASK R-CNN to automatically segment GTV and OARs in MRI-g-OART of LACC. Albeit the small number of patients in this pilot project, the network was trained to successfully identify several structures while challenges remain, especially in relatively small organs. With the increase of the LACC cases, the performance of the network will improve. A robust auto-contouring tool would improve workflow efficiency and patient tolerance of the OART process.

Purpose: Recent integration of open-source data to machine learning models, especially in the medical field, has opened new doors to study disease progression and/or regression. However, the limitation of using medical data for machine learning approaches is the specificity of data to a particular medical condition. In this context, most recent technologies like generative adversarial networks (GAN) could be used to generate high quality synthetic data that preserves the clinical variability. Materials and Methods: In this study, we used 139 T2-weighted prostate magnetic resonant images (MRI) from various sources as training data for Single Natural Image GAN (SinGAN), to make a generative model. A deep learning semantic segmentation pipeline trained the model to segment the prostate boundary on 2D MRI slices. Synthetic images with a high-level segmentation boundary of the prostate were filtered and used in the quality control assessment by participating scientists with varying degree of experience (more than 10 years, 1 year, or no experience) to work with MRI images. Results: The most experienced participating group correctly identified conventional vs synthetic images with 67% accuracy, the group with 1 year of experience correctly identified the images with 58% accuracy, and group with no prior experience reached 50% accuracy. Nearly half (47%) of the synthetic images were mistakenly evaluated as conventional images. Interestingly, a blinded quality assessment by a board-certified radiologist to differentiate conventional and synthetic images was not significantly different in context of the mean quality of synthetic and conventional images. Conclusions: This study shows promise that high quality synthetic images from MRI can be generated using GAN. Such an AI model may contribute significantly to various clinical applications which involves supervised machine learning approaches.

The recent integration of open-source data with machine learning models, especially in the medical field, has opened new doors to studying disease progression and/or regression. However, the ability to use medical data for machine learning approaches is limited by the specificity of data for a particular medical condition. In this context, the most recent technologies, like generative adversarial networks (GANs), are being looked upon as a potential way to generate high-quality synthetic data that preserve the clinical variability of a condition. However, despite some success, GAN model usage remains largely minimal when depicting the heterogeneity of a disease such as prostate cancer. Previous studies from our group members have focused on automating the quantitative multi-parametric magnetic resonance imaging (mpMRI) using habitat risk scoring (HRS) maps on the prostate cancer patients in the BLaStM trial. In the current study, we aimed to use the images from the BLaStM trial and other sources to train the GAN models, generate synthetic images, and validate their quality. In this context, we used T2-weighted prostate MRI images as training data for Single Natural Image GANs (SinGANs) to make a generative model. A deep learning semantic segmentation pipeline trained the model to segment the prostate boundary on 2D MRI slices. Synthetic images with a high-level segmentation boundary of the prostate were filtered and used in the quality control assessment by participating scientists with varying degrees of experience (more than ten years, one year, or no experience) to work with MRI images. Results showed that the most experienced participating group correctly identified conventional vs. synthetic images with 67% accuracy, the group with one year of experience correctly identified the images with 58% accuracy, and the group with no prior experience reached 50% accuracy. Nearly half (47%) of the synthetic images were mistakenly evaluated as conventional. Interestingly, in a blinded quality assessment, a board-certified radiologist did not significantly differentiate between conventional and synthetic images in the context of the mean quality of synthetic and conventional images. Furthermore, to validate the usability of the generated synthetic images from prostate cancer MRIs, we subjected these to anomaly detection along with the original images. Importantly, the success rate of anomaly detection for quality control-approved synthetic data in phase one corresponded to that of the conventional images. In sum, this study shows promise that high-quality synthetic images from MRIs can be generated using GANs. Such an AI model may contribute significantly to various clinical applications which involve supervised machine-learning approaches.

Simple Summary In this study, we investigated the longitudinal changes and predictive value of multiparametric MRI (mpMRI) features of prostate cancer patients receiving Lattice Extreme Ablative Dose (LEAD) boost radiotherapy (RT). Ninety-five mpMRI from 25 patients, acquired pre-RT and at 3 time points following RT were analyzed. Five regions of interest were analyzed, related to tumor, peritumoral, and normally-appearing tissues. We identified significant changes in the imaging parameters following RT in all regions. By using selected features at the four scan points and their differences (Δ radiomics), we were able to build viable predictive models for endpoint biopsy positivity. Our study demonstrates that RT causes significant changes to quantitative imaging features in both tumorous and normally-appearing tissues. Because of the noninvasive nature of the mpMRI, acquiring multiple exams post-RT is feasible to monitor treatment response. Several quantitative imaging features are promising predictors of treatment failure based on post-treatment positive biopsy, a strong marker for clinically relevant endpoints. Abstract We investigated the longitudinal changes in multiparametric MRI (mpMRI) (T2-weighted, Apparent Diffusion Coefficient (ADC), and Dynamic Contrast Enhanced (DCE-)MRI) of prostate cancer patients receiving Lattice Extreme Ablative Dose (LEAD) radiotherapy (RT) and the capability of their imaging features to predict RT outcome based on endpoint biopsies. Ninety-five mpMRI exams from 25 patients, acquired pre-RT and at 3-, 9-, and 24-months post-RT were analyzed. MRI/Ultrasound-fused biopsies were acquired pre- and at two-years post-RT (endpoint). Five regions of interest (ROIs) were analyzed: Gross tumor volume (GTV), normally-appearing tissue (NAT) and peritumoral volume in both peripheral (PZ) and transition (TZ) zones. Diffusion and perfusion radiomics features were extracted from mpMRI and compared before and after RT using two-tailed Student t-tests. Selected features at the four scan points and their differences (Δ radiomics) were used in multivariate logistic regression models to predict the endpoint biopsy positivity. Baseline ADC values were significantly different between GTV, NAT-PZ, and NAT-TZ ( p -values < 0.005). Pharmaco-kinetic features changed significantly in the GTV at 3-month post-RT compared to baseline. Several radiomics features at baseline and three-months post-RT were significantly associated with endpoint biopsy positivity and were used to build models with high predictive power of this endpoint (AUC = 0.98 and 0.89, respectively). Our study characterized the RT-induced changes in perfusion and diffusion. Quantitative imaging features from mpMRI show promise as being predictive of endpoint biopsy positivity.