Choi, Byong Su

AbstractBackgroundAdaptive radiotherapy (ART) workflows have been increasingly adopted to achieve dose escalation and tissue sparing under shifting anatomic conditions, but the necessity of recontouring and the associated time burden hinders a real‐time or online ART workflow. In response to this challenge, approaches to auto‐segmentation involving deformable image registration, atlas‐based segmentation, and deep learning‐based segmentation (DLS) have been developed. Despite the particular promise shown by DLS methods, implementing these approaches in a clinical setting remains a challenge, namely due to the difficulty of curating a data set of sufficient size and quality so as to achieve generalizability in a trained model.PurposeTo address this challenge, we have developed an intentional deep overfit learning (IDOL) framework tailored to the auto‐segmentation task. However, certain limitations were identified, particularly the insufficiency of the personalized dataset to effectively overfit the model. In this study, we introduce a personalized hyperspace learning (PHL)‐IDOL segmentation framework capable of generating datasets that induce the model to overfit specific patient characteristics for medical image segmentation.MethodsThe PHL‐IDOL model is trained in two stages. In the first, a conventional, general model is trained with a diverse set of patient data (n = 100 patients) consisting of CT images and clinical contours. Following this, the general model is tuned with a data set consisting of two components: (a) selection of a subset of the patient data (m < n) using the similarity metrics (mean square error (MSE), peak signal‐to‐noise ratio (PSNR), structural similarity index (SSIM), and the universal quality image index (UQI) values); (b) adjust the CT and the clinical contours using a deformed vector generated from the reference patient and the selected patients using (a). After training, the general model, the continual model, the conventional IDOL model, and the proposed PHL‐IDOL model were evaluated using the volumetric dice similarity coefficient (VDSC) and the Hausdorff distance 95% (HD95%) computed for 18 structures in 20 test patients.ResultsImplementing the PHL‐IDOL framework resulted in improved segmentation performance for each patient. The Dice scores increased from 0.810.05 with the general model, 0.83 for the continual model, 0.83 for the conventional IDOL model to an average of 0.87 with the PHL‐IDOL model. Similarly, the Hausdorff distance decreased from 3.06 with the general model, 2.84 for the continual model, 2.79 for the conventional IDOL model and 2.36 for the PHL‐IDOL model. All the standard deviations were decreased by nearly half of the values comparing the general model and the PHL‐IDOL model.ConclusionThe PHL‐IDOL framework applied to the auto‐segmentation task achieves improved performance compared to the general DLS approach, demonstrating the promise of leveraging patient‐specific prior information in a task central to online ART workflows.

AbstractBackgroundThe growing adoption of magnetic resonance imaging (MRI)‐guided radiation therapy (RT) platforms and a focus on MRI‐only RT workflows have brought the technical challenge of synthetic computed tomography (sCT) reconstruction to the forefront. Unpaired‐data deep learning‐based approaches to the problem offer the attractive characteristic of not requiring paired training data, but the gap between paired‐ and unpaired‐data results can be limiting.PurposeWe present two distinct approaches aimed at improving unpaired‐data sCT reconstruction results: a cascade ensemble that combines multiple models and a personalized training strategy originally designed for the paired‐data setting.MethodsComparisons are made between the following models: (1) the paired‐data fully convolutional DenseNet (FCDN), (2) the FCDN with the Intentional Deep Overfit Learning (IDOL) personalized training strategy, (3) the unpaired‐data CycleGAN, (4) the CycleGAN with the IDOL training strategy, and (5) the CycleGAN as an intermediate model in a cascade ensemble approach. Evaluation of the various models over 25 total patients is carried out using a five‐fold cross‐validation scheme, with the patient‐specific IDOL models being trained for the five patients of fold 3, chosen at random.ResultsIn both the paired‐ and unpaired‐data settings, adopting the IDOL training strategy led to improvements in the mean absolute error (MAE) between true CT images and sCT outputs within the body contour (mean improvement, paired‐ and unpaired‐data approaches, respectively: 38%, 9%) and in regions of bone (52%, 5%), the peak signal‐to‐noise ratio (PSNR; 15%, 7%), and the structural similarity index (SSIM; 6%, <1%). The ensemble approach offered additional benefits over the IDOL approach in all three metrics (mean improvement over unpaired‐data approach in fold 3; MAE: 20%; bone MAE: 16%; PSNR: 10%; SSIM: 2%), and differences in body MAE between the ensemble approach and the paired‐data approach are statistically insignificant.ConclusionsWe have demonstrated that both a cascade ensemble approach and a personalized training strategy designed initially for the paired‐data setting offer significant improvements in image quality metrics for the unpaired‐data sCT reconstruction task. Closing the gap between paired‐ and unpaired‐data approaches is a step toward fully enabling these powerful and attractive unpaired‐data frameworks.